2022-05-01 00:46:28 -06:00
|
|
|
|
import base64
|
2021-04-07 05:37:43 -06:00
|
|
|
|
import calendar
|
2022-11-14 16:53:32 -07:00
|
|
|
|
import collections
|
2021-06-29 16:07:49 -06:00
|
|
|
|
import copy
|
2021-07-18 22:55:07 -06:00
|
|
|
|
import datetime
|
2022-09-08 23:16:46 -06:00
|
|
|
|
import enum
|
2021-03-03 03:32:40 -07:00
|
|
|
|
import hashlib
|
2013-09-22 02:37:23 -06:00
|
|
|
|
import itertools
|
2013-06-23 11:58:33 -06:00
|
|
|
|
import json
|
2021-11-16 12:56:23 -07:00
|
|
|
|
import math
|
2013-09-21 16:35:03 -06:00
|
|
|
|
import os.path
|
2016-02-29 12:01:33 -07:00
|
|
|
|
import random
|
2013-06-23 11:58:33 -06:00
|
|
|
|
import re
|
2021-12-14 21:29:48 -07:00
|
|
|
|
import sys
|
2022-04-11 16:32:57 -06:00
|
|
|
|
import threading
|
2021-02-04 07:57:26 -07:00
|
|
|
|
import time
|
2013-09-21 06:19:30 -06:00
|
|
|
|
import traceback
|
2022-06-24 02:10:17 -06:00
|
|
|
|
import urllib.parse
|
2013-06-23 11:58:33 -06:00
|
|
|
|
|
2013-06-23 12:28:15 -06:00
|
|
|
|
from .common import InfoExtractor, SearchInfoExtractor
|
2022-08-18 10:05:18 -06:00
|
|
|
|
from .openload import PhantomJSwrapper
|
2022-06-24 04:54:43 -06:00
|
|
|
|
from ..compat import functools
|
2021-02-04 07:37:17 -07:00
|
|
|
|
from ..jsinterp import JSInterpreter
|
2023-07-09 01:53:02 -06:00
|
|
|
|
from ..networking.exceptions import HTTPError, network_exceptions
|
2014-12-11 02:08:17 -07:00
|
|
|
|
from ..utils import (
|
2022-04-11 16:32:57 -06:00
|
|
|
|
NO_DEFAULT,
|
|
|
|
|
ExtractorError,
|
2022-10-03 20:48:31 -06:00
|
|
|
|
LazyList,
|
2022-07-25 21:53:10 -06:00
|
|
|
|
UserNotLive,
|
2021-11-16 12:56:23 -07:00
|
|
|
|
bug_reports_message,
|
2022-05-11 09:54:44 -06:00
|
|
|
|
classproperty,
|
2013-06-23 11:58:33 -06:00
|
|
|
|
clean_html,
|
2021-04-07 05:37:43 -06:00
|
|
|
|
datetime_from_str,
|
2021-07-20 21:52:34 -06:00
|
|
|
|
dict_get,
|
2022-09-26 21:02:57 -06:00
|
|
|
|
filter_dict,
|
2015-02-11 10:39:31 -07:00
|
|
|
|
float_or_none,
|
2021-07-20 21:52:34 -06:00
|
|
|
|
format_field,
|
2022-03-08 13:54:41 -07:00
|
|
|
|
get_first,
|
2014-01-18 21:47:20 -07:00
|
|
|
|
int_or_none,
|
2021-08-13 00:18:26 -06:00
|
|
|
|
is_html,
|
2021-11-05 19:05:24 -06:00
|
|
|
|
join_nonempty,
|
2022-01-31 19:40:19 -07:00
|
|
|
|
js_to_json,
|
2016-01-24 10:02:19 -07:00
|
|
|
|
mimetype2ext,
|
2021-07-20 21:52:34 -06:00
|
|
|
|
orderedSet,
|
2017-02-12 04:09:53 -07:00
|
|
|
|
parse_codecs,
|
2021-07-14 17:24:42 -06:00
|
|
|
|
parse_count,
|
2015-07-20 13:10:28 -06:00
|
|
|
|
parse_duration,
|
2021-07-21 09:15:45 -06:00
|
|
|
|
parse_iso8601,
|
2021-08-22 13:02:00 -06:00
|
|
|
|
parse_qs,
|
2021-02-18 11:12:56 -07:00
|
|
|
|
qualities,
|
2017-05-06 15:19:11 -06:00
|
|
|
|
remove_start,
|
2015-07-25 09:30:34 -06:00
|
|
|
|
smuggle_url,
|
2018-11-02 17:26:16 -06:00
|
|
|
|
str_or_none,
|
2015-06-28 12:48:06 -06:00
|
|
|
|
str_to_int,
|
2021-12-19 21:47:53 -07:00
|
|
|
|
strftime_or_none,
|
2021-07-19 18:02:41 -06:00
|
|
|
|
traverse_obj,
|
2017-01-26 07:43:14 -07:00
|
|
|
|
try_get,
|
2013-06-23 11:58:33 -06:00
|
|
|
|
unescapeHTML,
|
|
|
|
|
unified_strdate,
|
2022-01-07 04:03:02 -07:00
|
|
|
|
unified_timestamp,
|
2015-07-25 09:30:34 -06:00
|
|
|
|
unsmuggle_url,
|
2020-11-19 12:22:59 -07:00
|
|
|
|
update_url_query,
|
2018-12-16 05:35:48 -07:00
|
|
|
|
url_or_none,
|
2021-07-18 22:55:07 -06:00
|
|
|
|
urljoin,
|
2021-07-19 18:02:41 -06:00
|
|
|
|
variadic,
|
2013-06-23 11:58:33 -06:00
|
|
|
|
)
|
|
|
|
|
|
2023-03-11 10:03:23 -07:00
|
|
|
|
STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
|
2022-06-26 18:50:06 -06:00
|
|
|
|
# any clients starting with _ cannot be explicitly requested by the user
|
2021-07-30 13:45:04 -06:00
|
|
|
|
INNERTUBE_CLIENTS = {
|
|
|
|
|
'web': {
|
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
|
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'WEB',
|
2022-08-02 01:02:05 -06:00
|
|
|
|
'clientVersion': '2.20220801.00.00',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 1
|
|
|
|
|
},
|
|
|
|
|
'web_embedded': {
|
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
|
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'WEB_EMBEDDED_PLAYER',
|
2022-08-02 01:02:05 -06:00
|
|
|
|
'clientVersion': '1.20220731.00.00',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 56
|
|
|
|
|
},
|
|
|
|
|
'web_music': {
|
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
|
|
|
|
|
'INNERTUBE_HOST': 'music.youtube.com',
|
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'WEB_REMIX',
|
2022-08-02 01:02:05 -06:00
|
|
|
|
'clientVersion': '1.20220727.01.00',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
|
|
|
|
|
},
|
2021-08-01 15:13:46 -06:00
|
|
|
|
'web_creator': {
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
|
2021-08-01 15:13:46 -06:00
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'WEB_CREATOR',
|
2022-08-02 01:02:05 -06:00
|
|
|
|
'clientVersion': '1.20220726.00.00',
|
2021-08-01 15:13:46 -06:00
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
|
|
|
|
|
},
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'android': {
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'ANDROID',
|
2022-08-28 16:59:54 -06:00
|
|
|
|
'clientVersion': '17.31.35',
|
|
|
|
|
'androidSdkVersion': 30,
|
|
|
|
|
'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
|
2021-07-30 13:45:04 -06:00
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
|
2021-09-06 01:26:41 -06:00
|
|
|
|
'REQUIRE_JS_PLAYER': False
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
|
|
|
|
'android_embedded': {
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'ANDROID_EMBEDDED_PLAYER',
|
2022-08-28 16:59:54 -06:00
|
|
|
|
'clientVersion': '17.31.35',
|
|
|
|
|
'androidSdkVersion': 30,
|
|
|
|
|
'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
2021-09-06 01:26:41 -06:00
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
|
|
|
|
|
'REQUIRE_JS_PLAYER': False
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
|
|
|
|
'android_music': {
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'ANDROID_MUSIC',
|
2022-08-02 01:02:05 -06:00
|
|
|
|
'clientVersion': '5.16.51',
|
2022-08-28 16:59:54 -06:00
|
|
|
|
'androidSdkVersion': 30,
|
|
|
|
|
'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
|
2021-07-30 13:45:04 -06:00
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
|
2021-09-06 01:26:41 -06:00
|
|
|
|
'REQUIRE_JS_PLAYER': False
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
2021-08-01 15:13:46 -06:00
|
|
|
|
'android_creator': {
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
|
2021-08-01 15:13:46 -06:00
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'ANDROID_CREATOR',
|
2022-08-28 16:59:54 -06:00
|
|
|
|
'clientVersion': '22.30.100',
|
|
|
|
|
'androidSdkVersion': 30,
|
|
|
|
|
'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
|
2021-08-01 15:13:46 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
2021-09-06 01:26:41 -06:00
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
|
|
|
|
|
'REQUIRE_JS_PLAYER': False
|
2021-08-01 15:13:46 -06:00
|
|
|
|
},
|
2022-01-01 22:22:31 -07:00
|
|
|
|
# iOS clients have HLS live streams. Setting device model to get 60fps formats.
|
|
|
|
|
# See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'ios': {
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'IOS',
|
2022-08-28 21:36:55 -06:00
|
|
|
|
'clientVersion': '17.33.2',
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'deviceModel': 'iPhone14,3',
|
2022-08-28 21:36:55 -06:00
|
|
|
|
'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
|
2021-07-30 13:45:04 -06:00
|
|
|
|
}
|
|
|
|
|
},
|
2021-09-06 01:26:41 -06:00
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
|
|
|
|
|
'REQUIRE_JS_PLAYER': False
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
|
|
|
|
'ios_embedded': {
|
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'IOS_MESSAGES_EXTENSION',
|
2022-08-28 21:36:55 -06:00
|
|
|
|
'clientVersion': '17.33.2',
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'deviceModel': 'iPhone14,3',
|
2022-08-28 21:36:55 -06:00
|
|
|
|
'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
2021-09-06 01:26:41 -06:00
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
|
|
|
|
|
'REQUIRE_JS_PLAYER': False
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
|
|
|
|
'ios_music': {
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'IOS_MUSIC',
|
2022-08-28 21:36:55 -06:00
|
|
|
|
'clientVersion': '5.21',
|
|
|
|
|
'deviceModel': 'iPhone14,3',
|
|
|
|
|
'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
2021-09-06 01:26:41 -06:00
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
|
|
|
|
|
'REQUIRE_JS_PLAYER': False
|
2021-07-30 13:45:04 -06:00
|
|
|
|
},
|
2021-08-01 15:13:46 -06:00
|
|
|
|
'ios_creator': {
|
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'IOS_CREATOR',
|
2022-08-28 21:36:55 -06:00
|
|
|
|
'clientVersion': '22.33.101',
|
|
|
|
|
'deviceModel': 'iPhone14,3',
|
|
|
|
|
'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
|
2021-08-01 15:13:46 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
2021-09-06 01:26:41 -06:00
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
|
|
|
|
|
'REQUIRE_JS_PLAYER': False
|
2021-08-01 15:13:46 -06:00
|
|
|
|
},
|
2021-07-30 13:43:26 -06:00
|
|
|
|
# mweb has 'ultralow' formats
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/pull/557
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'mweb': {
|
2022-01-01 22:22:31 -07:00
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'MWEB',
|
2022-08-02 01:02:05 -06:00
|
|
|
|
'clientVersion': '2.20220801.00.00',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 2
|
2022-03-29 04:05:31 -06:00
|
|
|
|
},
|
|
|
|
|
# This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
|
|
|
|
|
# See: https://github.com/zerodytrash/YouTube-Internal-Clients
|
|
|
|
|
'tv_embedded': {
|
|
|
|
|
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
|
|
|
|
|
'INNERTUBE_CONTEXT': {
|
|
|
|
|
'client': {
|
|
|
|
|
'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
|
|
|
|
|
'clientVersion': '2.0',
|
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
'INNERTUBE_CONTEXT_CLIENT_NAME': 85
|
|
|
|
|
},
|
2021-07-30 13:45:04 -06:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
2022-03-29 04:05:31 -06:00
|
|
|
|
def _split_innertube_client(client_name):
|
|
|
|
|
variant, *base = client_name.rsplit('.', 1)
|
|
|
|
|
if base:
|
|
|
|
|
return variant, base[0], variant
|
|
|
|
|
base, *variant = client_name.split('_', 1)
|
|
|
|
|
return client_name, base, variant[0] if variant else None
|
|
|
|
|
|
|
|
|
|
|
2023-03-11 10:03:23 -07:00
|
|
|
|
def short_client_name(client_name):
|
|
|
|
|
main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
|
|
|
|
|
return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
|
|
|
|
|
|
|
|
|
|
|
2021-07-30 13:45:04 -06:00
|
|
|
|
def build_innertube_clients():
|
2022-02-18 04:44:16 -07:00
|
|
|
|
THIRD_PARTY = {
|
2022-03-29 04:05:31 -06:00
|
|
|
|
'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
|
2021-07-27 08:03:59 -06:00
|
|
|
|
}
|
2023-06-21 12:50:04 -06:00
|
|
|
|
BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb')
|
2022-02-18 04:44:16 -07:00
|
|
|
|
priority = qualities(BASE_CLIENTS[::-1])
|
2021-07-30 13:45:04 -06:00
|
|
|
|
|
|
|
|
|
for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
|
2021-08-01 00:12:26 -06:00
|
|
|
|
ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
|
2021-07-30 13:45:04 -06:00
|
|
|
|
ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
|
2021-09-06 01:26:41 -06:00
|
|
|
|
ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
|
2021-07-30 13:45:04 -06:00
|
|
|
|
ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
|
|
|
|
|
|
2022-03-29 04:05:31 -06:00
|
|
|
|
_, base_client, variant = _split_innertube_client(client)
|
2022-02-18 04:44:16 -07:00
|
|
|
|
ytcfg['priority'] = 10 * priority(base_client)
|
|
|
|
|
|
2022-03-04 07:23:18 -07:00
|
|
|
|
if not variant:
|
2022-03-29 04:05:31 -06:00
|
|
|
|
INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
|
|
|
|
|
embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
|
|
|
|
|
embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
|
|
|
|
|
embedscreen['priority'] -= 3
|
|
|
|
|
elif variant == 'embedded':
|
2022-03-04 07:23:18 -07:00
|
|
|
|
ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
|
2021-07-30 13:45:04 -06:00
|
|
|
|
ytcfg['priority'] -= 2
|
2022-03-04 07:23:18 -07:00
|
|
|
|
else:
|
2021-07-30 13:45:04 -06:00
|
|
|
|
ytcfg['priority'] -= 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
build_innertube_clients()
|
|
|
|
|
|
|
|
|
|
|
2022-09-08 23:16:46 -06:00
|
|
|
|
class BadgeType(enum.Enum):
|
|
|
|
|
AVAILABILITY_UNLISTED = enum.auto()
|
|
|
|
|
AVAILABILITY_PRIVATE = enum.auto()
|
|
|
|
|
AVAILABILITY_PUBLIC = enum.auto()
|
|
|
|
|
AVAILABILITY_PREMIUM = enum.auto()
|
|
|
|
|
AVAILABILITY_SUBSCRIPTION = enum.auto()
|
|
|
|
|
LIVE_NOW = enum.auto()
|
2023-06-08 07:28:49 -06:00
|
|
|
|
VERIFIED = enum.auto()
|
2022-09-08 23:16:46 -06:00
|
|
|
|
|
|
|
|
|
|
2013-09-11 07:48:23 -06:00
|
|
|
|
class YoutubeBaseInfoExtractor(InfoExtractor):
|
2013-07-24 12:40:12 -06:00
|
|
|
|
"""Provide base functions for Youtube extractors"""
|
2017-05-06 10:58:47 -06:00
|
|
|
|
|
2020-11-21 15:21:09 -07:00
|
|
|
|
_RESERVED_NAMES = (
|
2023-01-02 07:09:03 -07:00
|
|
|
|
r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
|
2022-02-01 13:43:17 -07:00
|
|
|
|
r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
|
2022-09-26 16:49:12 -06:00
|
|
|
|
r'browse|oembed|get_video_info|iframe_api|s/player|source|'
|
2022-09-26 16:25:58 -06:00
|
|
|
|
r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
|
2020-11-21 15:21:09 -07:00
|
|
|
|
|
2021-07-30 13:43:26 -06:00
|
|
|
|
_PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
|
|
|
|
|
|
2022-03-18 14:53:33 -06:00
|
|
|
|
# _NETRC_MACHINE = 'youtube'
|
2021-07-30 13:43:26 -06:00
|
|
|
|
|
2013-07-24 12:40:12 -06:00
|
|
|
|
# If True it will raise an error if no login info is provided
|
|
|
|
|
_LOGIN_REQUIRED = False
|
|
|
|
|
|
2021-11-05 21:07:34 -06:00
|
|
|
|
_INVIDIOUS_SITES = (
|
|
|
|
|
# invidious-redirect websites
|
|
|
|
|
r'(?:www\.)?redirect\.invidious\.io',
|
|
|
|
|
r'(?:(?:www|dev)\.)?invidio\.us',
|
2022-04-28 19:19:57 -06:00
|
|
|
|
# Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
|
2021-11-05 21:07:34 -06:00
|
|
|
|
r'(?:www\.)?invidious\.pussthecat\.org',
|
|
|
|
|
r'(?:www\.)?invidious\.zee\.li',
|
|
|
|
|
r'(?:www\.)?invidious\.ethibox\.fr',
|
2023-02-12 00:51:15 -07:00
|
|
|
|
r'(?:www\.)?iv\.ggtyler\.dev',
|
|
|
|
|
r'(?:www\.)?inv\.vern\.i2p',
|
|
|
|
|
r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
|
|
|
|
|
r'(?:www\.)?inv\.riverside\.rocks',
|
|
|
|
|
r'(?:www\.)?invidious\.silur\.me',
|
|
|
|
|
r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
|
|
|
|
|
r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
|
|
|
|
|
r'(?:www\.)?invidious\.slipfox\.xyz',
|
|
|
|
|
r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
|
|
|
|
|
r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
|
|
|
|
|
r'(?:www\.)?invidious\.tiekoetter\.com',
|
|
|
|
|
r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
|
|
|
|
|
r'(?:www\.)?invidious\.nerdvpn\.de',
|
|
|
|
|
r'(?:www\.)?invidious\.weblibre\.org',
|
|
|
|
|
r'(?:www\.)?inv\.odyssey346\.dev',
|
|
|
|
|
r'(?:www\.)?invidious\.dhusch\.de',
|
|
|
|
|
r'(?:www\.)?iv\.melmac\.space',
|
|
|
|
|
r'(?:www\.)?watch\.thekitty\.zone',
|
|
|
|
|
r'(?:www\.)?invidious\.privacydev\.net',
|
|
|
|
|
r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
|
|
|
|
|
r'(?:www\.)?invidious\.drivet\.xyz',
|
|
|
|
|
r'(?:www\.)?vid\.priv\.au',
|
|
|
|
|
r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
|
|
|
|
|
r'(?:www\.)?inv\.vern\.cc',
|
|
|
|
|
r'(?:www\.)?invidious\.esmailelbob\.xyz',
|
|
|
|
|
r'(?:www\.)?invidious\.sethforprivacy\.com',
|
|
|
|
|
r'(?:www\.)?yt\.oelrichsgarcia\.de',
|
|
|
|
|
r'(?:www\.)?yt\.artemislena\.eu',
|
|
|
|
|
r'(?:www\.)?invidious\.flokinet\.to',
|
|
|
|
|
r'(?:www\.)?invidious\.baczek\.me',
|
|
|
|
|
r'(?:www\.)?y\.com\.sb',
|
|
|
|
|
r'(?:www\.)?invidious\.epicsite\.xyz',
|
|
|
|
|
r'(?:www\.)?invidious\.lidarshield\.cloud',
|
|
|
|
|
r'(?:www\.)?yt\.funami\.tech',
|
2021-11-05 21:07:34 -06:00
|
|
|
|
r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
|
2022-01-09 07:38:34 -07:00
|
|
|
|
r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
|
|
|
|
|
r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
|
2021-11-05 21:07:34 -06:00
|
|
|
|
# youtube-dl invidious instances list
|
|
|
|
|
r'(?:(?:www|no)\.)?invidiou\.sh',
|
|
|
|
|
r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
|
|
|
|
|
r'(?:www\.)?invidious\.kabi\.tk',
|
|
|
|
|
r'(?:www\.)?invidious\.mastodon\.host',
|
|
|
|
|
r'(?:www\.)?invidious\.zapashcanon\.fr',
|
|
|
|
|
r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
|
|
|
|
|
r'(?:www\.)?invidious\.tinfoil-hat\.net',
|
|
|
|
|
r'(?:www\.)?invidious\.himiko\.cloud',
|
|
|
|
|
r'(?:www\.)?invidious\.reallyancient\.tech',
|
|
|
|
|
r'(?:www\.)?invidious\.tube',
|
|
|
|
|
r'(?:www\.)?invidiou\.site',
|
|
|
|
|
r'(?:www\.)?invidious\.site',
|
|
|
|
|
r'(?:www\.)?invidious\.xyz',
|
|
|
|
|
r'(?:www\.)?invidious\.nixnet\.xyz',
|
|
|
|
|
r'(?:www\.)?invidious\.048596\.xyz',
|
|
|
|
|
r'(?:www\.)?invidious\.drycat\.fr',
|
|
|
|
|
r'(?:www\.)?inv\.skyn3t\.in',
|
|
|
|
|
r'(?:www\.)?tube\.poal\.co',
|
|
|
|
|
r'(?:www\.)?tube\.connect\.cafe',
|
|
|
|
|
r'(?:www\.)?vid\.wxzm\.sx',
|
|
|
|
|
r'(?:www\.)?vid\.mint\.lgbt',
|
|
|
|
|
r'(?:www\.)?vid\.puffyan\.us',
|
|
|
|
|
r'(?:www\.)?yewtu\.be',
|
|
|
|
|
r'(?:www\.)?yt\.elukerio\.org',
|
|
|
|
|
r'(?:www\.)?yt\.lelux\.fi',
|
|
|
|
|
r'(?:www\.)?invidious\.ggc-project\.de',
|
|
|
|
|
r'(?:www\.)?yt\.maisputain\.ovh',
|
|
|
|
|
r'(?:www\.)?ytprivate\.com',
|
|
|
|
|
r'(?:www\.)?invidious\.13ad\.de',
|
|
|
|
|
r'(?:www\.)?invidious\.toot\.koeln',
|
|
|
|
|
r'(?:www\.)?invidious\.fdn\.fr',
|
|
|
|
|
r'(?:www\.)?watch\.nettohikari\.com',
|
|
|
|
|
r'(?:www\.)?invidious\.namazso\.eu',
|
|
|
|
|
r'(?:www\.)?invidious\.silkky\.cloud',
|
|
|
|
|
r'(?:www\.)?invidious\.exonip\.de',
|
|
|
|
|
r'(?:www\.)?invidious\.riverside\.rocks',
|
|
|
|
|
r'(?:www\.)?invidious\.blamefran\.net',
|
|
|
|
|
r'(?:www\.)?invidious\.moomoo\.de',
|
|
|
|
|
r'(?:www\.)?ytb\.trom\.tf',
|
|
|
|
|
r'(?:www\.)?yt\.cyberhost\.uk',
|
|
|
|
|
r'(?:www\.)?kgg2m7yk5aybusll\.onion',
|
|
|
|
|
r'(?:www\.)?qklhadlycap4cnod\.onion',
|
|
|
|
|
r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
|
|
|
|
|
r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
|
|
|
|
|
r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
|
|
|
|
|
r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
|
|
|
|
|
r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
|
|
|
|
|
r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
|
|
|
|
|
r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
|
|
|
|
|
r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
|
|
|
|
|
r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
|
|
|
|
|
r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
|
2022-05-12 14:52:13 -06:00
|
|
|
|
# piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
|
|
|
|
|
r'(?:www\.)?piped\.kavin\.rocks',
|
|
|
|
|
r'(?:www\.)?piped\.tokhmi\.xyz',
|
2022-11-06 10:42:23 -07:00
|
|
|
|
r'(?:www\.)?piped\.syncpundit\.io',
|
2022-05-12 14:52:13 -06:00
|
|
|
|
r'(?:www\.)?piped\.mha\.fi',
|
2022-11-06 10:42:23 -07:00
|
|
|
|
r'(?:www\.)?watch\.whatever\.social',
|
|
|
|
|
r'(?:www\.)?piped\.garudalinux\.org',
|
|
|
|
|
r'(?:www\.)?piped\.rivo\.lol',
|
|
|
|
|
r'(?:www\.)?piped-libre\.kavin\.rocks',
|
|
|
|
|
r'(?:www\.)?yt\.jae\.fi',
|
2022-05-12 14:52:13 -06:00
|
|
|
|
r'(?:www\.)?piped\.mint\.lgbt',
|
2022-11-06 10:42:23 -07:00
|
|
|
|
r'(?:www\.)?il\.ax',
|
|
|
|
|
r'(?:www\.)?piped\.esmailelbob\.xyz',
|
|
|
|
|
r'(?:www\.)?piped\.projectsegfau\.lt',
|
|
|
|
|
r'(?:www\.)?piped\.privacydev\.net',
|
|
|
|
|
r'(?:www\.)?piped\.palveluntarjoaja\.eu',
|
|
|
|
|
r'(?:www\.)?piped\.smnz\.de',
|
|
|
|
|
r'(?:www\.)?piped\.adminforge\.de',
|
|
|
|
|
r'(?:www\.)?watch\.whatevertinfoil\.de',
|
|
|
|
|
r'(?:www\.)?piped\.qdi\.fi',
|
2022-11-17 06:15:38 -07:00
|
|
|
|
r'(?:www\.)?piped\.video',
|
|
|
|
|
r'(?:www\.)?piped\.aeong\.one',
|
2023-02-12 00:51:15 -07:00
|
|
|
|
r'(?:www\.)?piped\.moomoo\.me',
|
|
|
|
|
r'(?:www\.)?piped\.chauvet\.pro',
|
|
|
|
|
r'(?:www\.)?watch\.leptons\.xyz',
|
|
|
|
|
r'(?:www\.)?pd\.vern\.cc',
|
|
|
|
|
r'(?:www\.)?piped\.hostux\.net',
|
|
|
|
|
r'(?:www\.)?piped\.lunar\.icu',
|
2023-02-12 01:33:45 -07:00
|
|
|
|
# Hyperpipe instances from https://hyperpipe.codeberg.page/
|
|
|
|
|
r'(?:www\.)?hyperpipe\.surge\.sh',
|
|
|
|
|
r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
|
|
|
|
|
r'(?:www\.)?listen\.whatever\.social',
|
|
|
|
|
r'(?:www\.)?music\.adminforge\.de',
|
2021-11-05 21:07:34 -06:00
|
|
|
|
)
|
|
|
|
|
|
2022-09-08 23:16:46 -06:00
|
|
|
|
# extracted from account/account_menu ep
|
|
|
|
|
# XXX: These are the supported YouTube UI and API languages,
|
|
|
|
|
# which is slightly different from languages supported for translation in YouTube studio
|
|
|
|
|
_SUPPORTED_LANG_CODES = [
|
|
|
|
|
'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
|
|
|
|
|
'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
|
|
|
|
|
'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
|
|
|
|
|
'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
|
|
|
|
|
'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
|
|
|
|
|
'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
|
|
|
|
|
]
|
|
|
|
|
|
2022-10-03 14:04:04 -06:00
|
|
|
|
_IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
|
|
|
|
|
|
2023-04-14 01:58:36 -06:00
|
|
|
|
_YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en
|
|
|
|
|
_YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'
|
|
|
|
|
|
|
|
|
|
def ucid_or_none(self, ucid):
|
|
|
|
|
return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None)
|
|
|
|
|
|
|
|
|
|
def handle_or_none(self, handle):
|
|
|
|
|
return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None)
|
|
|
|
|
|
|
|
|
|
def handle_from_url(self, url):
|
|
|
|
|
return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})',
|
|
|
|
|
url, 'channel handle', default=None)
|
|
|
|
|
|
|
|
|
|
def ucid_from_url(self, url):
|
|
|
|
|
return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})',
|
|
|
|
|
url, 'channel id', default=None)
|
|
|
|
|
|
2022-09-08 23:16:46 -06:00
|
|
|
|
@functools.cached_property
|
|
|
|
|
def _preferred_lang(self):
|
|
|
|
|
"""
|
|
|
|
|
Returns a language code supported by YouTube for the user preferred language.
|
|
|
|
|
Returns None if no preferred language set.
|
|
|
|
|
"""
|
|
|
|
|
preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
|
|
|
|
|
if not preferred_lang:
|
|
|
|
|
return
|
|
|
|
|
if preferred_lang not in self._SUPPORTED_LANG_CODES:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
|
|
|
|
|
expected=True)
|
|
|
|
|
elif preferred_lang != 'en':
|
|
|
|
|
self.report_warning(
|
|
|
|
|
f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
|
|
|
|
|
return preferred_lang
|
|
|
|
|
|
2021-04-01 02:28:33 -06:00
|
|
|
|
def _initialize_consent(self):
|
|
|
|
|
cookies = self._get_cookies('https://www.youtube.com/')
|
|
|
|
|
if cookies.get('__Secure-3PSID'):
|
|
|
|
|
return
|
2023-08-11 22:26:08 -06:00
|
|
|
|
socs = cookies.get('SOCS')
|
|
|
|
|
if socs and not socs.value.startswith('CAA'): # not consented
|
|
|
|
|
return
|
|
|
|
|
self._set_cookie('.youtube.com', 'SOCS', 'CAI', secure=True) # accept all (required for mixes)
|
2017-09-01 11:57:14 -06:00
|
|
|
|
|
2021-12-19 21:47:53 -07:00
|
|
|
|
def _initialize_pref(self):
|
|
|
|
|
cookies = self._get_cookies('https://www.youtube.com/')
|
|
|
|
|
pref_cookie = cookies.get('PREF')
|
|
|
|
|
pref = {}
|
|
|
|
|
if pref_cookie:
|
|
|
|
|
try:
|
2022-06-24 04:54:43 -06:00
|
|
|
|
pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
|
2021-12-19 21:47:53 -07:00
|
|
|
|
except ValueError:
|
|
|
|
|
self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
|
2022-09-08 23:16:46 -06:00
|
|
|
|
pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
|
2022-06-24 04:54:43 -06:00
|
|
|
|
self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
|
2021-12-19 21:47:53 -07:00
|
|
|
|
|
2013-07-24 12:40:12 -06:00
|
|
|
|
def _real_initialize(self):
|
2021-12-19 21:47:53 -07:00
|
|
|
|
self._initialize_pref()
|
2021-04-01 02:28:33 -06:00
|
|
|
|
self._initialize_consent()
|
2022-04-09 13:30:21 -06:00
|
|
|
|
self._check_login_required()
|
|
|
|
|
|
|
|
|
|
def _check_login_required(self):
|
2022-05-16 08:06:36 -06:00
|
|
|
|
if self._LOGIN_REQUIRED and not self._cookies_passed:
|
2022-03-18 14:53:33 -06:00
|
|
|
|
self.raise_login_required('Login details are needed to download this content', method='cookies')
|
2013-06-23 11:58:33 -06:00
|
|
|
|
|
2022-06-03 09:32:31 -06:00
|
|
|
|
_YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
|
|
|
|
|
_YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
|
2020-11-21 07:50:42 -07:00
|
|
|
|
|
2021-07-30 13:45:04 -06:00
|
|
|
|
def _get_default_ytcfg(self, client='web'):
|
|
|
|
|
return copy.deepcopy(INNERTUBE_CLIENTS[client])
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2021-07-30 13:45:04 -06:00
|
|
|
|
def _get_innertube_host(self, client='web'):
|
|
|
|
|
return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2021-07-30 13:45:04 -06:00
|
|
|
|
def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
|
2021-06-29 16:07:49 -06:00
|
|
|
|
# try_get but with fallback to default ytcfg client values when present
|
|
|
|
|
_func = lambda y: try_get(y, getter, expected_type)
|
|
|
|
|
return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
|
|
|
|
|
|
2021-07-30 13:45:04 -06:00
|
|
|
|
def _extract_client_name(self, ytcfg, default_client='web'):
|
2021-07-30 13:43:26 -06:00
|
|
|
|
return self._ytcfg_get_safe(
|
|
|
|
|
ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
|
2022-06-24 04:54:43 -06:00
|
|
|
|
lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2021-07-30 13:45:04 -06:00
|
|
|
|
def _extract_client_version(self, ytcfg, default_client='web'):
|
2021-07-30 13:43:26 -06:00
|
|
|
|
return self._ytcfg_get_safe(
|
|
|
|
|
ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
|
2022-06-24 04:54:43 -06:00
|
|
|
|
lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2022-06-08 16:18:01 -06:00
|
|
|
|
def _select_api_hostname(self, req_api_hostname, default_client=None):
|
|
|
|
|
return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
|
|
|
|
|
or req_api_hostname or self._get_innertube_host(default_client or 'web'))
|
|
|
|
|
|
2021-07-30 13:45:04 -06:00
|
|
|
|
def _extract_api_key(self, ytcfg=None, default_client='web'):
|
2022-06-24 04:54:43 -06:00
|
|
|
|
return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2021-07-30 13:45:04 -06:00
|
|
|
|
def _extract_context(self, ytcfg=None, default_client='web'):
|
2021-12-19 21:47:53 -07:00
|
|
|
|
context = get_first(
|
|
|
|
|
(ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
|
2022-01-20 08:02:01 -07:00
|
|
|
|
# Enforce language and tz for extraction
|
|
|
|
|
client_context = traverse_obj(context, 'client', expected_type=dict, default={})
|
2022-09-08 23:16:46 -06:00
|
|
|
|
client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
|
2021-06-29 16:07:49 -06:00
|
|
|
|
return context
|
|
|
|
|
|
2021-08-01 20:30:08 -06:00
|
|
|
|
_SAPISID = None
|
|
|
|
|
|
2021-06-29 16:07:49 -06:00
|
|
|
|
def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
|
2021-03-03 03:32:40 -07:00
|
|
|
|
time_now = round(time.time())
|
2021-08-01 20:30:08 -06:00
|
|
|
|
if self._SAPISID is None:
|
|
|
|
|
yt_cookies = self._get_cookies('https://www.youtube.com')
|
|
|
|
|
# Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/393
|
|
|
|
|
sapisid_cookie = dict_get(
|
|
|
|
|
yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
|
|
|
|
|
if sapisid_cookie and sapisid_cookie.value:
|
|
|
|
|
self._SAPISID = sapisid_cookie.value
|
|
|
|
|
self.write_debug('Extracted SAPISID cookie')
|
|
|
|
|
# SAPISID cookie is required if not already present
|
|
|
|
|
if not yt_cookies.get('SAPISID'):
|
|
|
|
|
self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
|
|
|
|
|
self._set_cookie(
|
|
|
|
|
'.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
|
|
|
|
|
else:
|
|
|
|
|
self._SAPISID = False
|
|
|
|
|
if not self._SAPISID:
|
|
|
|
|
return None
|
2021-06-10 15:02:57 -06:00
|
|
|
|
# SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
|
|
|
|
|
sapisidhash = hashlib.sha1(
|
2022-04-11 09:10:28 -06:00
|
|
|
|
f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
|
2021-06-10 15:02:57 -06:00
|
|
|
|
return f'SAPISIDHASH {time_now}_{sapisidhash}'
|
2021-03-03 03:32:40 -07:00
|
|
|
|
|
|
|
|
|
def _call_api(self, ep, query, video_id, fatal=True, headers=None,
|
2021-04-11 14:23:04 -06:00
|
|
|
|
note='Downloading API JSON', errnote='Unable to download API page',
|
2021-07-30 13:45:04 -06:00
|
|
|
|
context=None, api_key=None, api_hostname=None, default_client='web'):
|
2021-04-11 14:23:04 -06:00
|
|
|
|
|
2021-06-29 16:07:49 -06:00
|
|
|
|
data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
|
2020-11-19 12:22:59 -07:00
|
|
|
|
data.update(query)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
real_headers = self.generate_api_headers(default_client=default_client)
|
2021-04-11 14:23:04 -06:00
|
|
|
|
real_headers.update({'content-type': 'application/json'})
|
|
|
|
|
if headers:
|
|
|
|
|
real_headers.update(headers)
|
2022-06-08 16:18:01 -06:00
|
|
|
|
api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
|
|
|
|
|
or api_key or self._extract_api_key(default_client=default_client))
|
2021-02-04 07:37:17 -07:00
|
|
|
|
return self._download_json(
|
2022-06-08 16:18:01 -06:00
|
|
|
|
f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
|
2021-03-03 03:32:40 -07:00
|
|
|
|
video_id=video_id, fatal=fatal, note=note, errnote=errnote,
|
2021-04-11 14:23:04 -06:00
|
|
|
|
data=json.dumps(data).encode('utf8'), headers=real_headers,
|
2022-06-08 16:18:01 -06:00
|
|
|
|
query={'key': api_key, 'prettyPrint': 'false'})
|
2021-04-11 14:23:04 -06:00
|
|
|
|
|
2022-06-06 18:25:37 -06:00
|
|
|
|
def extract_yt_initial_data(self, item_id, webpage, fatal=True):
|
|
|
|
|
return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
|
2022-06-03 09:59:03 -06:00
|
|
|
|
|
2021-09-23 18:52:17 -06:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _extract_session_index(*data):
|
|
|
|
|
"""
|
|
|
|
|
Index of current account in account list.
|
|
|
|
|
See: https://github.com/yt-dlp/yt-dlp/pull/519
|
|
|
|
|
"""
|
|
|
|
|
for ytcfg in data:
|
|
|
|
|
session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
|
|
|
|
|
if session_index is not None:
|
|
|
|
|
return session_index
|
|
|
|
|
|
|
|
|
|
# Deprecated?
|
|
|
|
|
def _extract_identity_token(self, ytcfg=None, webpage=None):
|
2021-03-14 16:41:11 -06:00
|
|
|
|
if ytcfg:
|
2022-06-24 04:54:43 -06:00
|
|
|
|
token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
|
2021-03-14 16:41:11 -06:00
|
|
|
|
if token:
|
|
|
|
|
return token
|
2021-09-23 18:52:17 -06:00
|
|
|
|
if webpage:
|
|
|
|
|
return self._search_regex(
|
|
|
|
|
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
|
|
|
|
|
'identity token', default=None, fatal=False)
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
|
|
|
|
@staticmethod
|
2021-07-18 22:55:07 -06:00
|
|
|
|
def _extract_account_syncid(*args):
|
2021-04-13 23:07:03 -06:00
|
|
|
|
"""
|
|
|
|
|
Extract syncId required to download private playlists of secondary channels
|
2021-07-18 22:55:07 -06:00
|
|
|
|
@params response and/or ytcfg
|
2021-04-13 23:07:03 -06:00
|
|
|
|
"""
|
2021-07-18 22:55:07 -06:00
|
|
|
|
for data in args:
|
|
|
|
|
# ytcfg includes channel_syncid if on secondary channel
|
2022-06-24 04:54:43 -06:00
|
|
|
|
delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
|
2021-07-18 22:55:07 -06:00
|
|
|
|
if delegated_sid:
|
|
|
|
|
return delegated_sid
|
|
|
|
|
sync_ids = (try_get(
|
|
|
|
|
data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
|
2022-06-24 04:54:43 -06:00
|
|
|
|
lambda x: x['DATASYNC_ID']), str) or '').split('||')
|
2021-07-18 22:55:07 -06:00
|
|
|
|
if len(sync_ids) >= 2 and sync_ids[1]:
|
|
|
|
|
# datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
|
|
|
|
|
# and just "user_syncid||" for primary channel. We only want the channel_syncid
|
|
|
|
|
return sync_ids[0]
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2021-10-08 15:19:25 -06:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _extract_visitor_data(*args):
|
|
|
|
|
"""
|
|
|
|
|
Extracts visitorData from an API response or ytcfg
|
|
|
|
|
Appears to be used to track session state
|
|
|
|
|
"""
|
2021-11-18 17:06:28 -07:00
|
|
|
|
return get_first(
|
2022-01-20 23:04:36 -07:00
|
|
|
|
args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
|
2021-11-18 17:06:28 -07:00
|
|
|
|
expected_type=str)
|
2021-10-08 15:19:25 -06:00
|
|
|
|
|
2022-05-20 09:25:21 -06:00
|
|
|
|
@functools.cached_property
|
2021-09-23 18:52:17 -06:00
|
|
|
|
def is_authenticated(self):
|
|
|
|
|
return bool(self._generate_sapisidhash_header())
|
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
def extract_ytcfg(self, video_id, webpage):
|
2021-04-20 23:07:24 -06:00
|
|
|
|
if not webpage:
|
|
|
|
|
return {}
|
2021-01-01 05:26:37 -07:00
|
|
|
|
return self._parse_json(
|
|
|
|
|
self._search_regex(
|
|
|
|
|
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
|
2021-04-11 14:23:04 -06:00
|
|
|
|
default='{}'), video_id, fatal=False) or {}
|
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
def generate_api_headers(
|
2021-09-23 18:52:17 -06:00
|
|
|
|
self, *, ytcfg=None, account_syncid=None, session_index=None,
|
|
|
|
|
visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
|
|
|
|
|
|
2022-06-08 16:18:01 -06:00
|
|
|
|
origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
|
2021-04-11 14:23:04 -06:00
|
|
|
|
headers = {
|
2022-06-24 04:54:43 -06:00
|
|
|
|
'X-YouTube-Client-Name': str(
|
2021-07-20 21:52:34 -06:00
|
|
|
|
self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
|
|
|
|
|
'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
|
2021-09-23 18:52:17 -06:00
|
|
|
|
'Origin': origin,
|
|
|
|
|
'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
|
|
|
|
|
'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
|
2022-08-28 16:59:54 -06:00
|
|
|
|
'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
|
|
|
|
|
'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
|
2021-09-23 18:52:17 -06:00
|
|
|
|
}
|
|
|
|
|
if session_index is None:
|
2021-07-18 00:23:32 -06:00
|
|
|
|
session_index = self._extract_session_index(ytcfg)
|
|
|
|
|
if account_syncid or session_index is not None:
|
|
|
|
|
headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
|
2021-09-23 18:52:17 -06:00
|
|
|
|
|
2021-06-29 16:07:49 -06:00
|
|
|
|
auth = self._generate_sapisidhash_header(origin)
|
2021-04-11 14:23:04 -06:00
|
|
|
|
if auth is not None:
|
|
|
|
|
headers['Authorization'] = auth
|
2021-06-29 16:07:49 -06:00
|
|
|
|
headers['X-Origin'] = origin
|
2022-09-26 21:02:57 -06:00
|
|
|
|
return filter_dict(headers)
|
2021-01-01 05:26:37 -07:00
|
|
|
|
|
2022-04-09 13:30:21 -06:00
|
|
|
|
def _download_ytcfg(self, client, video_id):
|
|
|
|
|
url = {
|
|
|
|
|
'web': 'https://www.youtube.com',
|
|
|
|
|
'web_music': 'https://music.youtube.com',
|
|
|
|
|
'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
|
|
|
|
|
}.get(client)
|
|
|
|
|
if not url:
|
|
|
|
|
return {}
|
|
|
|
|
webpage = self._download_webpage(
|
|
|
|
|
url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
|
|
|
|
|
return self.extract_ytcfg(video_id, webpage) or {}
|
|
|
|
|
|
2021-07-11 17:18:40 -06:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _build_api_continuation_query(continuation, ctp=None):
|
|
|
|
|
query = {
|
|
|
|
|
'continuation': continuation
|
|
|
|
|
}
|
|
|
|
|
# TODO: Inconsistency with clickTrackingParams.
|
|
|
|
|
# Currently we have a fixed ctp contained within context (from ytcfg)
|
|
|
|
|
# and a ctp in root query for continuation.
|
|
|
|
|
if ctp:
|
|
|
|
|
query['clickTracking'] = {'clickTrackingParams': ctp}
|
|
|
|
|
return query
|
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_next_continuation_data(cls, renderer):
|
|
|
|
|
next_continuation = try_get(
|
|
|
|
|
renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
|
|
|
|
|
lambda x: x['continuation']['reloadContinuationData']), dict)
|
|
|
|
|
if not next_continuation:
|
|
|
|
|
return
|
|
|
|
|
continuation = next_continuation.get('continuation')
|
|
|
|
|
if not continuation:
|
|
|
|
|
return
|
|
|
|
|
ctp = next_continuation.get('clickTrackingParams')
|
2021-07-18 22:55:07 -06:00
|
|
|
|
return cls._build_api_continuation_query(continuation, ctp)
|
2021-07-11 17:18:40 -06:00
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_continuation_ep_data(cls, continuation_ep: dict):
|
|
|
|
|
if isinstance(continuation_ep, dict):
|
|
|
|
|
continuation = try_get(
|
2022-06-24 04:54:43 -06:00
|
|
|
|
continuation_ep, lambda x: x['continuationCommand']['token'], str)
|
2021-07-11 17:18:40 -06:00
|
|
|
|
if not continuation:
|
|
|
|
|
return
|
|
|
|
|
ctp = continuation_ep.get('clickTrackingParams')
|
2021-07-18 22:55:07 -06:00
|
|
|
|
return cls._build_api_continuation_query(continuation, ctp)
|
2021-07-11 17:18:40 -06:00
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_continuation(cls, renderer):
|
|
|
|
|
next_continuation = cls._extract_next_continuation_data(renderer)
|
|
|
|
|
if next_continuation:
|
|
|
|
|
return next_continuation
|
2021-07-18 22:55:07 -06:00
|
|
|
|
|
2022-09-26 21:02:57 -06:00
|
|
|
|
return traverse_obj(renderer, (
|
|
|
|
|
('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
|
|
|
|
|
('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
|
|
|
|
|
), get_all=False, expected_type=cls._extract_continuation_ep_data)
|
2021-07-11 17:18:40 -06:00
|
|
|
|
|
2021-07-18 22:55:07 -06:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_alerts(cls, data):
|
2021-06-29 16:07:49 -06:00
|
|
|
|
for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
|
|
|
|
|
if not isinstance(alert_dict, dict):
|
|
|
|
|
continue
|
|
|
|
|
for alert in alert_dict.values():
|
|
|
|
|
alert_type = alert.get('type')
|
|
|
|
|
if not alert_type:
|
|
|
|
|
continue
|
2021-07-23 18:46:46 -06:00
|
|
|
|
message = cls._get_text(alert, 'text')
|
2021-06-29 16:07:49 -06:00
|
|
|
|
if message:
|
|
|
|
|
yield alert_type, message
|
|
|
|
|
|
2021-09-03 20:33:42 -06:00
|
|
|
|
def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
|
2022-10-03 14:04:04 -06:00
|
|
|
|
errors, warnings = [], []
|
2021-06-29 16:07:49 -06:00
|
|
|
|
for alert_type, alert_message in alerts:
|
2021-08-13 00:18:26 -06:00
|
|
|
|
if alert_type.lower() == 'error' and fatal:
|
2021-06-29 16:07:49 -06:00
|
|
|
|
errors.append([alert_type, alert_message])
|
2022-10-03 14:04:04 -06:00
|
|
|
|
elif alert_message not in self._IGNORED_WARNINGS:
|
2021-06-29 16:07:49 -06:00
|
|
|
|
warnings.append([alert_type, alert_message])
|
|
|
|
|
|
|
|
|
|
for alert_type, alert_message in (warnings + errors[:-1]):
|
2022-04-11 09:10:28 -06:00
|
|
|
|
self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
|
2021-06-29 16:07:49 -06:00
|
|
|
|
if errors:
|
|
|
|
|
raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
|
|
|
|
|
|
|
|
|
|
def _extract_and_report_alerts(self, data, *args, **kwargs):
|
|
|
|
|
return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
|
|
|
|
|
|
2023-06-08 07:28:49 -06:00
|
|
|
|
def _extract_badges(self, badge_list: list):
|
|
|
|
|
"""
|
|
|
|
|
Extract known BadgeType's from a list of badge renderers.
|
|
|
|
|
@returns [{'type': BadgeType}]
|
|
|
|
|
"""
|
|
|
|
|
icon_type_map = {
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
|
|
|
|
|
'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC,
|
|
|
|
|
'CHECK_CIRCLE_THICK': BadgeType.VERIFIED,
|
|
|
|
|
'OFFICIAL_ARTIST_BADGE': BadgeType.VERIFIED,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'CHECK': BadgeType.VERIFIED,
|
2022-09-08 23:16:46 -06:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
badge_style_map = {
|
|
|
|
|
'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
|
|
|
|
|
'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'BADGE_STYLE_TYPE_VERIFIED': BadgeType.VERIFIED,
|
2023-06-20 21:51:20 -06:00
|
|
|
|
'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED,
|
2022-09-08 23:16:46 -06:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
label_map = {
|
|
|
|
|
'unlisted': BadgeType.AVAILABILITY_UNLISTED,
|
|
|
|
|
'private': BadgeType.AVAILABILITY_PRIVATE,
|
|
|
|
|
'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
|
|
|
|
|
'live': BadgeType.LIVE_NOW,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'premium': BadgeType.AVAILABILITY_PREMIUM,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'verified': BadgeType.VERIFIED,
|
2023-06-20 21:51:20 -06:00
|
|
|
|
'official artist channel': BadgeType.VERIFIED,
|
2022-09-08 23:16:46 -06:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
badges = []
|
2023-06-08 07:28:49 -06:00
|
|
|
|
for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))):
|
2022-09-08 23:16:46 -06:00
|
|
|
|
badge_type = (
|
2023-06-08 07:28:49 -06:00
|
|
|
|
icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
|
2022-09-08 23:16:46 -06:00
|
|
|
|
or badge_style_map.get(traverse_obj(badge, 'style'))
|
|
|
|
|
)
|
|
|
|
|
if badge_type:
|
|
|
|
|
badges.append({'type': badge_type})
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
# fallback, won't work in some languages
|
2023-06-08 07:28:49 -06:00
|
|
|
|
label = traverse_obj(
|
|
|
|
|
badge, 'label', ('accessibilityData', 'label'), 'tooltip', 'iconTooltip', get_all=False, expected_type=str, default='')
|
2022-09-08 23:16:46 -06:00
|
|
|
|
for match, label_badge_type in label_map.items():
|
|
|
|
|
if match in label.lower():
|
2023-06-08 07:28:49 -06:00
|
|
|
|
badges.append({'type': label_badge_type})
|
|
|
|
|
break
|
2022-09-08 23:16:46 -06:00
|
|
|
|
|
2021-07-14 20:42:30 -06:00
|
|
|
|
return badges
|
|
|
|
|
|
2022-09-08 23:16:46 -06:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _has_badge(badges, badge_type):
|
|
|
|
|
return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
|
|
|
|
|
|
2021-07-14 20:42:30 -06:00
|
|
|
|
@staticmethod
|
2021-07-23 18:46:46 -06:00
|
|
|
|
def _get_text(data, *path_list, max_runs=None):
|
|
|
|
|
for path in path_list or [None]:
|
|
|
|
|
if path is None:
|
|
|
|
|
obj = [data]
|
|
|
|
|
else:
|
|
|
|
|
obj = traverse_obj(data, path, default=[])
|
|
|
|
|
if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
|
|
|
|
|
obj = [obj]
|
|
|
|
|
for item in obj:
|
2022-06-24 04:54:43 -06:00
|
|
|
|
text = try_get(item, lambda x: x['simpleText'], str)
|
2021-07-23 18:46:46 -06:00
|
|
|
|
if text:
|
|
|
|
|
return text
|
|
|
|
|
runs = try_get(item, lambda x: x['runs'], list) or []
|
|
|
|
|
if not runs and isinstance(item, list):
|
|
|
|
|
runs = item
|
|
|
|
|
|
|
|
|
|
runs = runs[:min(len(runs), max_runs or len(runs))]
|
2023-02-09 15:26:26 -07:00
|
|
|
|
text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
|
2021-07-23 18:46:46 -06:00
|
|
|
|
if text:
|
|
|
|
|
return text
|
2021-07-14 20:42:30 -06:00
|
|
|
|
|
2022-01-07 04:03:02 -07:00
|
|
|
|
def _get_count(self, data, *path_list):
|
|
|
|
|
count_text = self._get_text(data, *path_list) or ''
|
|
|
|
|
count = parse_count(count_text)
|
|
|
|
|
if count is None:
|
|
|
|
|
count = str_to_int(
|
|
|
|
|
self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
|
|
|
|
|
return count
|
|
|
|
|
|
2021-12-23 20:42:02 -07:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _extract_thumbnails(data, *path_list):
|
|
|
|
|
"""
|
|
|
|
|
Extract thumbnails from thumbnails dict
|
|
|
|
|
@param path_list: path list to level that contains 'thumbnails' key
|
|
|
|
|
"""
|
|
|
|
|
thumbnails = []
|
|
|
|
|
for path in path_list or [()]:
|
2023-02-09 15:26:26 -07:00
|
|
|
|
for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
|
2021-12-23 20:42:02 -07:00
|
|
|
|
thumbnail_url = url_or_none(thumbnail.get('url'))
|
|
|
|
|
if not thumbnail_url:
|
|
|
|
|
continue
|
|
|
|
|
# Sometimes youtube gives a wrong thumbnail URL. See:
|
|
|
|
|
# https://github.com/yt-dlp/yt-dlp/issues/233
|
|
|
|
|
# https://github.com/ytdl-org/youtube-dl/issues/28023
|
|
|
|
|
if 'maxresdefault' in thumbnail_url:
|
|
|
|
|
thumbnail_url = thumbnail_url.split('?')[0]
|
|
|
|
|
thumbnails.append({
|
|
|
|
|
'url': thumbnail_url,
|
|
|
|
|
'height': int_or_none(thumbnail.get('height')),
|
|
|
|
|
'width': int_or_none(thumbnail.get('width')),
|
|
|
|
|
})
|
|
|
|
|
return thumbnails
|
|
|
|
|
|
2021-12-19 21:47:53 -07:00
|
|
|
|
@staticmethod
|
|
|
|
|
def extract_relative_time(relative_time_text):
|
|
|
|
|
"""
|
|
|
|
|
Extracts a relative time from string and converts to dt object
|
2023-06-03 00:33:51 -06:00
|
|
|
|
e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today', '8 yr ago'
|
2021-12-19 21:47:53 -07:00
|
|
|
|
"""
|
2023-06-03 00:33:51 -06:00
|
|
|
|
|
2023-09-23 14:00:31 -06:00
|
|
|
|
# XXX: this could be moved to a general function in utils/_utils.py
|
2023-06-03 00:33:51 -06:00
|
|
|
|
# The relative time text strings are roughly the same as what
|
|
|
|
|
# Javascript's Intl.RelativeTimeFormat function generates.
|
|
|
|
|
# See: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Intl/RelativeTimeFormat
|
|
|
|
|
mobj = re.search(
|
|
|
|
|
r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>sec(?:ond)?|s|min(?:ute)?|h(?:our|r)?|d(?:ay)?|w(?:eek|k)?|mo(?:nth)?|y(?:ear|r)?)s?\s*ago',
|
|
|
|
|
relative_time_text)
|
2021-12-19 21:47:53 -07:00
|
|
|
|
if mobj:
|
2022-01-07 04:03:02 -07:00
|
|
|
|
start = mobj.group('start')
|
|
|
|
|
if start:
|
|
|
|
|
return datetime_from_str(start)
|
2021-12-19 21:47:53 -07:00
|
|
|
|
try:
|
2022-01-07 04:03:02 -07:00
|
|
|
|
return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
|
2021-12-19 21:47:53 -07:00
|
|
|
|
except ValueError:
|
|
|
|
|
return None
|
|
|
|
|
|
2022-09-08 23:16:46 -06:00
|
|
|
|
def _parse_time_text(self, text):
|
|
|
|
|
if not text:
|
|
|
|
|
return
|
2021-12-19 21:47:53 -07:00
|
|
|
|
dt = self.extract_relative_time(text)
|
|
|
|
|
timestamp = None
|
|
|
|
|
if isinstance(dt, datetime.datetime):
|
|
|
|
|
timestamp = calendar.timegm(dt.timetuple())
|
2022-01-07 04:03:02 -07:00
|
|
|
|
|
|
|
|
|
if timestamp is None:
|
|
|
|
|
timestamp = (
|
|
|
|
|
unified_timestamp(text) or unified_timestamp(
|
|
|
|
|
self._search_regex(
|
2022-03-13 16:02:44 -06:00
|
|
|
|
(r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
|
2022-01-20 08:02:01 -07:00
|
|
|
|
text.lower(), 'time text', default=None)))
|
2022-01-07 04:03:02 -07:00
|
|
|
|
|
2022-09-08 23:16:46 -06:00
|
|
|
|
if text and timestamp is None and self._preferred_lang in (None, 'en'):
|
|
|
|
|
self.report_warning(
|
|
|
|
|
f'Cannot parse localized time text "{text}"', only_once=True)
|
|
|
|
|
return timestamp
|
2021-12-19 21:47:53 -07:00
|
|
|
|
|
2021-06-29 16:07:49 -06:00
|
|
|
|
def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
|
|
|
|
|
ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
|
2021-07-30 13:45:04 -06:00
|
|
|
|
default_client='web'):
|
2023-10-03 00:42:30 -06:00
|
|
|
|
raise_for_incomplete = bool(self._configuration_arg('raise_incomplete_data', ie_key=YoutubeIE))
|
|
|
|
|
# Incomplete Data should be a warning by default when retries are exhausted, while other errors should be fatal.
|
|
|
|
|
icd_retries = iter(self.RetryManager(fatal=raise_for_incomplete))
|
|
|
|
|
icd_rm = next(icd_retries)
|
|
|
|
|
main_retries = iter(self.RetryManager())
|
|
|
|
|
main_rm = next(main_retries)
|
|
|
|
|
for _ in range(main_rm.retries + icd_rm.retries + 1):
|
2021-06-29 16:07:49 -06:00
|
|
|
|
try:
|
|
|
|
|
response = self._call_api(
|
|
|
|
|
ep=ep, fatal=True, headers=headers,
|
2022-08-01 14:13:18 -06:00
|
|
|
|
video_id=item_id, query=query, note=note,
|
2021-06-29 16:07:49 -06:00
|
|
|
|
context=self._extract_context(ytcfg, default_client),
|
|
|
|
|
api_key=self._extract_api_key(ytcfg, default_client),
|
2022-08-01 14:13:18 -06:00
|
|
|
|
api_hostname=api_hostname, default_client=default_client)
|
2021-06-29 16:07:49 -06:00
|
|
|
|
except ExtractorError as e:
|
2022-08-01 14:13:18 -06:00
|
|
|
|
if not isinstance(e.cause, network_exceptions):
|
|
|
|
|
return self._error_or_warning(e, fatal=fatal)
|
2023-07-09 01:53:02 -06:00
|
|
|
|
elif not isinstance(e.cause, HTTPError):
|
2023-10-03 00:42:30 -06:00
|
|
|
|
main_rm.error = e
|
|
|
|
|
next(main_retries)
|
2022-08-01 14:13:18 -06:00
|
|
|
|
continue
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2023-07-09 01:53:02 -06:00
|
|
|
|
first_bytes = e.cause.response.read(512)
|
2022-08-01 14:13:18 -06:00
|
|
|
|
if not is_html(first_bytes):
|
|
|
|
|
yt_error = try_get(
|
|
|
|
|
self._parse_json(
|
2023-07-09 01:53:02 -06:00
|
|
|
|
self._webpage_read_content(e.cause.response, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
|
2022-08-01 14:13:18 -06:00
|
|
|
|
lambda x: x['error']['message'], str)
|
|
|
|
|
if yt_error:
|
|
|
|
|
self._report_alerts([('ERROR', yt_error)], fatal=False)
|
|
|
|
|
# Downloading page may result in intermittent 5xx HTTP error
|
2023-10-03 00:42:30 -06:00
|
|
|
|
# Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
|
2022-08-01 14:13:18 -06:00
|
|
|
|
# We also want to catch all other network exceptions since errors in later pages can be troublesome
|
|
|
|
|
# See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
|
2023-07-09 01:53:02 -06:00
|
|
|
|
if e.cause.status not in (403, 429):
|
2023-10-03 00:42:30 -06:00
|
|
|
|
main_rm.error = e
|
|
|
|
|
next(main_retries)
|
2022-08-01 14:13:18 -06:00
|
|
|
|
continue
|
|
|
|
|
return self._error_or_warning(e, fatal=fatal)
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
self._extract_and_report_alerts(response, only_once=True)
|
|
|
|
|
except ExtractorError as e:
|
2023-10-03 00:42:30 -06:00
|
|
|
|
# YouTube's servers may return errors we want to retry on in a 200 OK response
|
2022-08-01 14:13:18 -06:00
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/839
|
|
|
|
|
if 'unknown error' in e.msg.lower():
|
2023-10-03 00:42:30 -06:00
|
|
|
|
main_rm.error = e
|
|
|
|
|
next(main_retries)
|
2022-08-01 14:13:18 -06:00
|
|
|
|
continue
|
|
|
|
|
return self._error_or_warning(e, fatal=fatal)
|
|
|
|
|
# Youtube sometimes sends incomplete data
|
|
|
|
|
# See: https://github.com/ytdl-org/youtube-dl/issues/28194
|
|
|
|
|
if not traverse_obj(response, *variadic(check_get_keys)):
|
2023-10-03 00:42:30 -06:00
|
|
|
|
icd_rm.error = ExtractorError('Incomplete data received', expected=True)
|
|
|
|
|
should_retry = next(icd_retries, None)
|
|
|
|
|
if not should_retry:
|
|
|
|
|
return None
|
2022-08-01 14:13:18 -06:00
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
return response
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2021-05-15 08:38:47 -06:00
|
|
|
|
@staticmethod
|
|
|
|
|
def is_music_url(url):
|
2023-02-28 11:01:02 -07:00
|
|
|
|
return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
|
2021-05-15 08:38:47 -06:00
|
|
|
|
|
2021-01-16 05:40:15 -07:00
|
|
|
|
def _extract_video(self, renderer):
|
|
|
|
|
video_id = renderer.get('videoId')
|
2022-11-09 19:44:12 -07:00
|
|
|
|
|
|
|
|
|
reel_header_renderer = traverse_obj(renderer, (
|
|
|
|
|
'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
|
|
|
|
|
'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
|
|
|
|
|
|
|
|
|
|
title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
|
2021-07-23 18:46:46 -06:00
|
|
|
|
description = self._get_text(renderer, 'descriptionSnippet')
|
2022-11-05 23:25:31 -06:00
|
|
|
|
|
|
|
|
|
duration = int_or_none(renderer.get('lengthSeconds'))
|
|
|
|
|
if duration is None:
|
|
|
|
|
duration = parse_duration(self._get_text(
|
|
|
|
|
renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
|
2022-03-27 18:49:42 -06:00
|
|
|
|
if duration is None:
|
2022-11-09 19:44:12 -07:00
|
|
|
|
# XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
|
2022-03-27 18:49:42 -06:00
|
|
|
|
duration = parse_duration(self._search_regex(
|
|
|
|
|
r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
|
|
|
|
|
traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
|
|
|
|
|
video_id, default=None, group='duration'))
|
|
|
|
|
|
2021-12-19 21:47:53 -07:00
|
|
|
|
channel_id = traverse_obj(
|
2022-03-26 20:20:43 -06:00
|
|
|
|
renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
|
|
|
|
|
expected_type=str, get_all=False)
|
2022-11-09 19:44:12 -07:00
|
|
|
|
if not channel_id:
|
|
|
|
|
channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
|
|
|
|
|
|
2023-04-14 01:58:36 -06:00
|
|
|
|
channel_id = self.ucid_or_none(channel_id)
|
|
|
|
|
|
2021-12-19 21:47:53 -07:00
|
|
|
|
overlay_style = traverse_obj(
|
2022-03-26 20:20:43 -06:00
|
|
|
|
renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
|
|
|
|
|
get_all=False, expected_type=str)
|
2023-06-08 07:28:49 -06:00
|
|
|
|
badges = self._extract_badges(traverse_obj(renderer, 'badges'))
|
2023-06-08 01:50:05 -06:00
|
|
|
|
owner_badges = self._extract_badges(traverse_obj(renderer, 'ownerBadges'))
|
2022-03-26 23:20:25 -06:00
|
|
|
|
navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
|
2022-03-26 20:20:43 -06:00
|
|
|
|
renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
|
|
|
|
|
expected_type=str)) or ''
|
2022-03-26 23:20:25 -06:00
|
|
|
|
url = f'https://www.youtube.com/watch?v={video_id}'
|
2022-03-26 20:20:43 -06:00
|
|
|
|
if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
|
2022-03-26 23:20:25 -06:00
|
|
|
|
url = f'https://www.youtube.com/shorts/{video_id}'
|
2021-12-23 20:42:02 -07:00
|
|
|
|
|
2022-11-09 19:44:12 -07:00
|
|
|
|
time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
|
|
|
|
|
or self._get_text(reel_header_renderer, 'timestampText') or '')
|
|
|
|
|
scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
|
|
|
|
|
|
2022-10-07 01:00:40 -06:00
|
|
|
|
live_status = (
|
|
|
|
|
'is_upcoming' if scheduled_timestamp is not None
|
|
|
|
|
else 'was_live' if 'streamed' in time_text.lower()
|
|
|
|
|
else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
|
|
|
|
|
else None)
|
|
|
|
|
|
2022-11-09 19:44:12 -07:00
|
|
|
|
# videoInfo is a string like '50K views • 10 years ago'.
|
|
|
|
|
view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
|
|
|
|
|
view_count = (0 if 'no views' in view_count_text.lower()
|
|
|
|
|
else self._get_count({'simpleText': view_count_text}))
|
|
|
|
|
view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
|
|
|
|
|
|
2023-05-27 17:31:45 -06:00
|
|
|
|
channel = (self._get_text(renderer, 'ownerText', 'shortBylineText')
|
|
|
|
|
or self._get_text(reel_header_renderer, 'channelTitleText'))
|
|
|
|
|
|
|
|
|
|
channel_handle = traverse_obj(renderer, (
|
|
|
|
|
'shortBylineText', 'runs', ..., 'navigationEndpoint',
|
|
|
|
|
(('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))),
|
|
|
|
|
expected_type=self.handle_from_url, get_all=False)
|
2021-01-16 05:40:15 -07:00
|
|
|
|
return {
|
2021-04-03 16:05:17 -06:00
|
|
|
|
'_type': 'url',
|
2021-01-16 05:40:15 -07:00
|
|
|
|
'ie_key': YoutubeIE.ie_key(),
|
|
|
|
|
'id': video_id,
|
2022-03-26 23:20:25 -06:00
|
|
|
|
'url': url,
|
2021-01-16 05:40:15 -07:00
|
|
|
|
'title': title,
|
|
|
|
|
'description': description,
|
|
|
|
|
'duration': duration,
|
2021-12-19 21:47:53 -07:00
|
|
|
|
'channel_id': channel_id,
|
2023-05-27 17:31:45 -06:00
|
|
|
|
'channel': channel,
|
2022-11-09 19:44:12 -07:00
|
|
|
|
'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
|
2023-05-27 17:31:45 -06:00
|
|
|
|
'uploader': channel,
|
|
|
|
|
'uploader_id': channel_handle,
|
|
|
|
|
'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
|
2022-11-09 19:44:12 -07:00
|
|
|
|
'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
|
2022-10-12 16:53:39 -06:00
|
|
|
|
'timestamp': (self._parse_time_text(time_text)
|
|
|
|
|
if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
|
|
|
|
|
else None),
|
2021-12-19 21:47:53 -07:00
|
|
|
|
'release_timestamp': scheduled_timestamp,
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability':
|
|
|
|
|
'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
|
|
|
|
|
else self._availability(
|
|
|
|
|
is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
|
|
|
|
|
needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
|
|
|
|
|
needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
|
2022-10-07 01:00:40 -06:00
|
|
|
|
is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
|
2022-11-09 19:44:12 -07:00
|
|
|
|
view_count_field: view_count,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'live_status': live_status,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None
|
2021-01-16 05:40:15 -07:00
|
|
|
|
}
|
|
|
|
|
|
2015-11-21 15:17:07 -07:00
|
|
|
|
|
2015-02-16 13:44:17 -07:00
|
|
|
|
class YoutubeIE(YoutubeBaseInfoExtractor):
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'YouTube'
|
2013-11-18 08:42:35 -07:00
|
|
|
|
_VALID_URL = r"""(?x)^
|
2013-06-23 11:58:33 -06:00
|
|
|
|
(
|
2014-09-11 13:47:25 -06:00
|
|
|
|
(?:https?://|//) # http(s):// or protocol-independent URL
|
2021-02-19 13:44:36 -07:00
|
|
|
|
(?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
|
|
|
|
|
(?:www\.)?deturl\.com/www\.youtube\.com|
|
|
|
|
|
(?:www\.)?pwnyoutube\.com|
|
|
|
|
|
(?:www\.)?hooktube\.com|
|
|
|
|
|
(?:www\.)?yourepeat\.com|
|
|
|
|
|
tube\.majestyc\.net|
|
|
|
|
|
%(invidious)s|
|
|
|
|
|
youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
|
2013-06-23 11:58:33 -06:00
|
|
|
|
(?:.*?\#/)? # handle anchor (#/) redirect urls
|
|
|
|
|
(?: # the various things that can precede the ID:
|
2023-02-03 11:17:13 -07:00
|
|
|
|
(?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
|
2013-06-23 11:58:33 -06:00
|
|
|
|
|(?: # or the v= param in all its forms
|
2014-02-18 12:00:54 -07:00
|
|
|
|
(?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
|
2013-06-23 11:58:33 -06:00
|
|
|
|
(?:\?|\#!?) # the params delimiter ? or # or #!
|
2015-11-29 08:01:59 -07:00
|
|
|
|
(?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
|
2013-06-23 11:58:33 -06:00
|
|
|
|
v=
|
|
|
|
|
)
|
2013-09-05 14:38:23 -06:00
|
|
|
|
))
|
2015-08-16 14:04:13 -06:00
|
|
|
|
|(?:
|
|
|
|
|
youtu\.be| # just youtu.be/xxxx
|
2016-04-03 14:26:20 -06:00
|
|
|
|
vid\.plus| # or vid.plus/xxxx
|
|
|
|
|
zwearz\.com/watch| # or zwearz.com/watch/xxxx
|
2021-02-19 13:44:36 -07:00
|
|
|
|
%(invidious)s
|
2015-08-16 14:04:13 -06:00
|
|
|
|
)/
|
2014-09-11 13:47:25 -06:00
|
|
|
|
|(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
|
2013-09-05 14:38:23 -06:00
|
|
|
|
)
|
2013-06-23 11:58:33 -06:00
|
|
|
|
)? # all until now is optional -> you can pass the naked ID
|
2021-04-16 21:02:33 -06:00
|
|
|
|
(?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
|
2013-06-23 11:58:33 -06:00
|
|
|
|
(?(1).+)? # if we found the ID, everything can follow
|
2021-05-15 08:38:47 -06:00
|
|
|
|
(?:\#|$)""" % {
|
2021-11-05 21:07:34 -06:00
|
|
|
|
'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
|
2021-02-19 13:44:36 -07:00
|
|
|
|
}
|
2022-09-01 13:58:56 -06:00
|
|
|
|
_EMBED_REGEX = [
|
|
|
|
|
r'''(?x)
|
|
|
|
|
(?:
|
2022-09-25 18:58:06 -06:00
|
|
|
|
<(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
|
2022-09-01 13:58:56 -06:00
|
|
|
|
data-video-url=|
|
|
|
|
|
<embed[^>]+?src=|
|
|
|
|
|
embedSWF\(?:\s*|
|
|
|
|
|
<object[^>]+data=|
|
|
|
|
|
new\s+SWFObject\(
|
|
|
|
|
)
|
|
|
|
|
(["\'])
|
|
|
|
|
(?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
|
|
|
|
|
(?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
|
|
|
|
|
\1''',
|
|
|
|
|
# https://wordpress.org/plugins/lazy-load-for-videos/
|
|
|
|
|
r'''(?xs)
|
|
|
|
|
<a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
|
|
|
|
|
\s[^>]*\bclass="[^"]*\blazy-load-youtube''',
|
|
|
|
|
]
|
2022-11-15 17:57:43 -07:00
|
|
|
|
_RETURN_TYPE = 'video' # XXX: How to handle multifeed?
|
2022-09-01 13:58:56 -06:00
|
|
|
|
|
2020-05-01 18:18:08 -06:00
|
|
|
|
_PLAYER_INFO_RE = (
|
2021-02-10 14:22:55 -07:00
|
|
|
|
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
|
|
|
|
|
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
|
2021-02-04 07:37:17 -07:00
|
|
|
|
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
|
2020-05-01 18:18:08 -06:00
|
|
|
|
)
|
2013-12-24 04:34:09 -07:00
|
|
|
|
_formats = {
|
2016-03-02 09:35:04 -07:00
|
|
|
|
'5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
|
|
|
|
|
'6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
|
|
|
|
|
'13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
|
|
|
|
|
'17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
|
|
|
|
|
'18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
|
|
|
|
|
'22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
|
|
|
|
|
'34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
|
|
|
|
|
'35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
|
2016-02-07 12:30:57 -07:00
|
|
|
|
# itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
|
2016-03-02 09:35:04 -07:00
|
|
|
|
'36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
|
|
|
|
|
'37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
|
|
|
|
|
'38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
|
|
|
|
|
'43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
|
|
|
|
|
'44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
|
|
|
|
|
'45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
|
2016-01-02 20:11:19 -07:00
|
|
|
|
'46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
|
2016-03-02 09:35:04 -07:00
|
|
|
|
'59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
|
|
|
|
|
'78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
|
2016-01-02 20:11:19 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# 3D videos
|
2016-03-02 09:35:04 -07:00
|
|
|
|
'82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
|
|
|
|
|
'83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
|
|
|
|
|
'84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
|
|
|
|
|
'85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
|
2016-01-02 20:11:19 -07:00
|
|
|
|
'100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
|
|
|
|
|
'101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
|
|
|
|
|
'102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
|
2013-08-19 19:22:25 -06:00
|
|
|
|
|
2013-09-03 19:49:35 -06:00
|
|
|
|
# Apple HTTP Live Streaming
|
2016-03-17 05:25:37 -06:00
|
|
|
|
'91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
|
2016-03-02 09:35:04 -07:00
|
|
|
|
'92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
|
|
|
|
|
'93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
|
|
|
|
|
'94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
|
|
|
|
|
'95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
|
|
|
|
|
'96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
|
2016-01-02 20:11:19 -07:00
|
|
|
|
'132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
|
|
|
|
|
'151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
|
2013-12-24 04:34:09 -07:00
|
|
|
|
|
|
|
|
|
# DASH mp4 video
|
2017-04-11 09:41:48 -06:00
|
|
|
|
'133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
|
|
|
|
'134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
|
|
|
|
'135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
|
|
|
|
'136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
|
|
|
|
'137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
2019-03-09 05:14:41 -07:00
|
|
|
|
'138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
|
2017-04-11 09:41:48 -06:00
|
|
|
|
'160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
|
|
|
|
'212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
|
|
|
|
'264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
|
|
|
|
'298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
|
|
|
|
|
'299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
|
|
|
|
|
'266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
|
2013-08-19 19:22:25 -06:00
|
|
|
|
|
2013-10-18 15:53:00 -06:00
|
|
|
|
# Dash mp4 audio
|
2017-04-11 09:41:48 -06:00
|
|
|
|
'139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
|
|
|
|
|
'140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
|
|
|
|
|
'141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
|
|
|
|
|
'256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
|
|
|
|
|
'258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
|
|
|
|
|
'325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
|
|
|
|
|
'328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
|
2013-08-19 19:22:25 -06:00
|
|
|
|
|
|
|
|
|
# Dash webm
|
2017-04-11 09:41:48 -06:00
|
|
|
|
'167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
|
|
|
|
|
'168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
|
|
|
|
|
'169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
|
|
|
|
|
'170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
|
|
|
|
|
'218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
|
|
|
|
|
'219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
|
|
|
|
|
'278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
|
|
|
|
|
'242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
2015-11-30 07:42:05 -07:00
|
|
|
|
# itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
|
2017-04-11 09:41:48 -06:00
|
|
|
|
'272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
|
|
|
|
|
'303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
|
|
|
|
|
'308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
|
|
|
|
|
'313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
|
|
|
|
|
'315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
|
2013-12-24 04:34:09 -07:00
|
|
|
|
|
|
|
|
|
# Dash webm audio
|
2017-04-11 09:41:48 -06:00
|
|
|
|
'171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
|
|
|
|
|
'172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
|
2014-01-08 18:38:50 -07:00
|
|
|
|
|
2014-11-18 03:06:09 -07:00
|
|
|
|
# Dash webm audio with opus inside
|
2017-04-11 09:41:48 -06:00
|
|
|
|
'249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
|
|
|
|
|
'250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
|
|
|
|
|
'251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
|
2014-11-18 03:06:09 -07:00
|
|
|
|
|
2014-01-08 18:38:50 -07:00
|
|
|
|
# RTMP (unnamed)
|
|
|
|
|
'_rtmp': {'protocol': 'rtmp'},
|
2019-06-13 12:59:05 -06:00
|
|
|
|
|
|
|
|
|
# av01 video only formats sometimes served with "unknown" codecs
|
2021-08-22 13:59:43 -06:00
|
|
|
|
'394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
|
|
|
|
|
'395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
|
|
|
|
|
'396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
|
|
|
|
|
'397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
|
|
|
|
|
'398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
|
|
|
|
|
'399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
|
|
|
|
|
'400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
|
|
|
|
|
'401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
|
2013-06-23 11:58:33 -06:00
|
|
|
|
}
|
2021-01-01 05:26:37 -07:00
|
|
|
|
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
|
2013-08-19 19:22:25 -06:00
|
|
|
|
|
2017-02-26 02:51:21 -07:00
|
|
|
|
_GEO_BYPASS = False
|
|
|
|
|
|
2014-09-12 23:51:06 -06:00
|
|
|
|
IE_NAME = 'youtube'
|
2013-06-27 11:13:11 -06:00
|
|
|
|
_TESTS = [
|
|
|
|
|
{
|
2016-09-17 08:48:20 -06:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
|
2014-09-24 01:49:53 -06:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'BaW_jenozKc',
|
|
|
|
|
'ext': 'mp4',
|
2020-09-02 14:37:35 -06:00
|
|
|
|
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
|
2021-12-14 15:02:40 -07:00
|
|
|
|
'channel': 'Philipp Hagemeister',
|
2018-09-14 12:24:26 -06:00
|
|
|
|
'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
|
|
|
|
|
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
|
2014-09-24 01:49:53 -06:00
|
|
|
|
'upload_date': '20121002',
|
2021-12-14 15:02:40 -07:00
|
|
|
|
'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
|
2014-09-24 01:49:53 -06:00
|
|
|
|
'categories': ['Science & Technology'],
|
2020-09-02 14:37:35 -06:00
|
|
|
|
'tags': ['youtube-dl'],
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 10,
|
2018-11-02 17:26:16 -06:00
|
|
|
|
'view_count': int,
|
2014-08-31 10:10:05 -06:00
|
|
|
|
'like_count': int,
|
2021-12-14 15:02:40 -07:00
|
|
|
|
'availability': 'public',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'age_limit': 0,
|
2015-07-20 13:10:28 -06:00
|
|
|
|
'start_time': 1,
|
2015-07-23 05:20:21 -06:00
|
|
|
|
'end_time': 9,
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'comment_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Philipp Hagemeister',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
|
|
|
|
|
'uploader_id': '@PhilippHagemeister',
|
2023-05-26 06:24:39 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2013-06-27 11:13:11 -06:00
|
|
|
|
}
|
2013-06-27 11:55:39 -06:00
|
|
|
|
},
|
2013-11-18 05:05:18 -07:00
|
|
|
|
{
|
2014-09-24 01:49:53 -06:00
|
|
|
|
'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
|
|
|
|
|
'note': 'Embed-only video (#1746)',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'yZIXLfi8CZQ',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'upload_date': '20120608',
|
|
|
|
|
'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
|
|
|
|
|
'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
|
2015-11-23 08:35:23 -07:00
|
|
|
|
'age_limit': 18,
|
2021-02-04 07:37:17 -07:00
|
|
|
|
},
|
|
|
|
|
'skip': 'Private video',
|
2013-11-18 05:05:18 -07:00
|
|
|
|
},
|
2015-08-10 12:52:38 -06:00
|
|
|
|
{
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
|
2015-08-10 12:52:38 -06:00
|
|
|
|
'note': 'Use the first video ID in the URL',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'BaW_jenozKc',
|
|
|
|
|
'ext': 'mp4',
|
2020-09-02 14:37:35 -06:00
|
|
|
|
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'Philipp Hagemeister',
|
|
|
|
|
'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
|
|
|
|
|
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
|
2015-08-10 12:52:38 -06:00
|
|
|
|
'upload_date': '20121002',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
|
2015-08-10 12:52:38 -06:00
|
|
|
|
'categories': ['Science & Technology'],
|
2020-09-02 14:37:35 -06:00
|
|
|
|
'tags': ['youtube-dl'],
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 10,
|
2018-11-02 17:26:16 -06:00
|
|
|
|
'view_count': int,
|
2015-08-10 12:52:38 -06:00
|
|
|
|
'like_count': int,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'availability': 'public',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'age_limit': 0,
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'comment_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Philipp Hagemeister',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
|
|
|
|
|
'uploader_id': '@PhilippHagemeister',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2015-08-10 13:22:06 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2015-08-10 12:52:38 -06:00
|
|
|
|
},
|
2014-01-18 21:47:20 -07:00
|
|
|
|
{
|
2016-09-17 08:48:20 -06:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
|
2014-09-24 01:49:53 -06:00
|
|
|
|
'note': '256k DASH audio (format 141) via DASH manifest',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'a9LDPn-MO4I',
|
|
|
|
|
'ext': 'm4a',
|
|
|
|
|
'upload_date': '20121002',
|
|
|
|
|
'description': '',
|
|
|
|
|
'title': 'UHDTV TEST 8K VIDEO.mp4'
|
2014-01-22 13:56:37 -07:00
|
|
|
|
},
|
2014-09-24 01:49:53 -06:00
|
|
|
|
'params': {
|
|
|
|
|
'youtube_include_dash_manifest': True,
|
|
|
|
|
'format': '141',
|
2014-01-22 13:56:37 -07:00
|
|
|
|
},
|
2016-06-24 09:27:55 -06:00
|
|
|
|
'skip': 'format 141 not served anymore',
|
2014-01-18 21:47:20 -07:00
|
|
|
|
},
|
2020-11-19 12:22:59 -07:00
|
|
|
|
# DASH manifest with encrypted signature
|
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'IB3lcPjvWLA',
|
|
|
|
|
'ext': 'm4a',
|
|
|
|
|
'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
|
|
|
|
|
'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
|
|
|
|
|
'duration': 244,
|
|
|
|
|
'upload_date': '20131011',
|
2021-02-10 14:22:55 -07:00
|
|
|
|
'abr': 129.495,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'like_count': int,
|
|
|
|
|
'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'track': 'The Spark',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
|
|
|
|
|
'channel': 'Afrojack',
|
|
|
|
|
'tags': 'count:19',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'categories': ['Music'],
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'alt_title': 'The Spark',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Afrojack',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@Afrojack',
|
|
|
|
|
'uploader_id': '@Afrojack',
|
2020-11-19 12:22:59 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'youtube_include_dash_manifest': True,
|
|
|
|
|
'format': '141/bestaudio[ext=m4a]',
|
|
|
|
|
},
|
|
|
|
|
},
|
2021-07-27 08:03:59 -06:00
|
|
|
|
# Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
|
2014-11-30 13:45:49 -07:00
|
|
|
|
{
|
2021-07-27 08:03:59 -06:00
|
|
|
|
'note': 'Embed allowed age-gate video',
|
2016-09-17 08:48:20 -06:00
|
|
|
|
'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
|
2014-11-30 13:45:49 -07:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'HtVdAasjOgU',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
|
2017-01-02 05:08:07 -07:00
|
|
|
|
'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 142,
|
2014-11-30 13:45:49 -07:00
|
|
|
|
'upload_date': '20140605',
|
2015-08-10 13:24:53 -06:00
|
|
|
|
'age_limit': 18,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'categories': ['Gaming'],
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
|
|
|
|
|
'availability': 'needs_auth',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'channel': 'The Witcher',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'tags': 'count:17',
|
|
|
|
|
'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'view_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'The Witcher',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@thewitcher',
|
|
|
|
|
'uploader_id': '@thewitcher',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2014-11-30 13:45:49 -07:00
|
|
|
|
},
|
|
|
|
|
},
|
2021-07-27 08:03:59 -06:00
|
|
|
|
{
|
|
|
|
|
'note': 'Age-gate video with embed allowed in public site',
|
|
|
|
|
'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'HsUATh_Nc2U',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Godzilla 2 (Official Video)',
|
|
|
|
|
'description': 'md5:bf77e03fcae5529475e500129b05668a',
|
|
|
|
|
'upload_date': '20200408',
|
|
|
|
|
'age_limit': 18,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'availability': 'needs_auth',
|
|
|
|
|
'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
|
|
|
|
|
'channel': 'FlyingKitty',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'tags': ['Flyingkitty', 'godzilla 2'],
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'duration': 177,
|
|
|
|
|
'playable_in_embed': True,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'FlyingKitty',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@FlyingKitty900',
|
|
|
|
|
'uploader_id': '@FlyingKitty900',
|
2023-05-26 06:24:39 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2021-07-27 08:03:59 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
'note': 'Age-gate video embedable only with clientScreen=EMBED',
|
|
|
|
|
'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'Tq92D6wQ1mg',
|
|
|
|
|
'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
|
2021-07-30 13:43:26 -06:00
|
|
|
|
'ext': 'mp4',
|
2022-03-13 16:02:44 -06:00
|
|
|
|
'upload_date': '20191228',
|
2021-07-27 08:03:59 -06:00
|
|
|
|
'description': 'md5:17eccca93a786d51bc67646756894066',
|
|
|
|
|
'age_limit': 18,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'like_count': int,
|
|
|
|
|
'availability': 'needs_auth',
|
|
|
|
|
'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
|
|
|
|
|
'channel': 'Projekt Melody',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'duration': 106,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'comment_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Projekt Melody',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@ProjektMelody',
|
|
|
|
|
'uploader_id': '@ProjektMelody',
|
2021-07-27 08:03:59 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
'note': 'Non-Agegated non-embeddable video',
|
|
|
|
|
'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'MeJVWBSsPAY',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
|
|
|
|
|
'description': 'Fan Video. Music & Lyrics by OOMPH!.',
|
|
|
|
|
'upload_date': '20130730',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'track': 'Such mich find mich',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'playable_in_embed': False,
|
|
|
|
|
'creator': 'OOMPH!',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'alt_title': 'Such mich find mich',
|
|
|
|
|
'duration': 210,
|
|
|
|
|
'channel': 'Herr Lurik',
|
|
|
|
|
'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
|
|
|
|
|
'categories': ['Music'],
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'artist': 'OOMPH!',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Herr Lurik',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@HerrLurik',
|
|
|
|
|
'uploader_id': '@HerrLurik',
|
2021-07-27 08:03:59 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
'note': 'Non-bypassable age-gated video',
|
|
|
|
|
'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2020-11-19 12:22:59 -07:00
|
|
|
|
# video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
|
|
|
|
|
# YouTube Red ad is not captured for creator
|
|
|
|
|
{
|
|
|
|
|
'url': '__2ABJjxzNo',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '__2ABJjxzNo',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'duration': 266,
|
|
|
|
|
'upload_date': '20100430',
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'creator': 'deadmau5',
|
|
|
|
|
'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'title': 'Deadmau5 - Some Chords (HD)',
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'alt_title': 'Some Chords',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'availability': 'public',
|
|
|
|
|
'tags': 'count:14',
|
|
|
|
|
'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'channel': 'deadmau5',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'track': 'Some Chords',
|
|
|
|
|
'artist': 'deadmau5',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
|
|
|
|
|
'categories': ['Music'],
|
|
|
|
|
'album': 'Some Chords',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'deadmau5',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@deadmau5',
|
|
|
|
|
'uploader_id': '@deadmau5',
|
2020-11-19 12:22:59 -07:00
|
|
|
|
},
|
|
|
|
|
'expected_warnings': [
|
|
|
|
|
'DASH manifest missing',
|
|
|
|
|
]
|
|
|
|
|
},
|
2019-03-09 05:14:41 -07:00
|
|
|
|
# Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
|
2014-12-11 08:28:07 -07:00
|
|
|
|
{
|
|
|
|
|
'url': 'lqQg6PlCWgI',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'lqQg6PlCWgI',
|
|
|
|
|
'ext': 'mp4',
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 6085,
|
2015-11-23 08:37:21 -07:00
|
|
|
|
'upload_date': '20150827',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
|
2014-12-11 08:34:37 -07:00
|
|
|
|
'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'like_count': int,
|
|
|
|
|
'release_timestamp': 1343767800,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'categories': ['Sports'],
|
|
|
|
|
'release_date': '20120731',
|
|
|
|
|
'channel': 'Olympics',
|
|
|
|
|
'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
|
|
|
|
|
'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'live_status': 'was_live',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Olympics',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@Olympics',
|
|
|
|
|
'uploader_id': '@Olympics',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2014-12-11 08:34:37 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': 'requires avconv',
|
2014-12-11 08:28:07 -07:00
|
|
|
|
}
|
2014-12-11 08:34:37 -07:00
|
|
|
|
},
|
2015-01-09 21:45:51 -07:00
|
|
|
|
# Non-square pixels
|
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '_b-2C3KPAM0',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'stretched_ratio': 16 / 9.,
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 85,
|
2015-01-09 21:45:51 -07:00
|
|
|
|
'upload_date': '20110310',
|
|
|
|
|
'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
|
|
|
|
|
'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'channel': '孫ᄋᄅ',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'tags': 'count:11',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
|
|
|
|
|
'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'categories': ['People & Blogs'],
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'availability': 'unlisted',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'comment_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': '孫ᄋᄅ',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@AllenMeow',
|
|
|
|
|
'uploader_id': '@AllenMeow',
|
2015-01-09 21:45:51 -07:00
|
|
|
|
},
|
2015-04-05 12:35:55 -06:00
|
|
|
|
},
|
|
|
|
|
# url_encoded_fmt_stream_map is empty string
|
|
|
|
|
{
|
|
|
|
|
'url': 'qEJwOuvDf7I',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'qEJwOuvDf7I',
|
2015-08-12 09:27:58 -06:00
|
|
|
|
'ext': 'webm',
|
2015-04-05 12:35:55 -06:00
|
|
|
|
'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
|
|
|
|
|
'description': '',
|
|
|
|
|
'upload_date': '20150404',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': 'requires avconv',
|
2016-01-19 07:56:04 -07:00
|
|
|
|
},
|
|
|
|
|
'skip': 'This live event has ended.',
|
2015-04-05 12:35:55 -06:00
|
|
|
|
},
|
2019-03-09 05:14:41 -07:00
|
|
|
|
# Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
|
2015-06-27 02:55:46 -06:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'FIl7x6_3R5Y',
|
2018-06-02 13:23:45 -06:00
|
|
|
|
'ext': 'webm',
|
2015-06-27 02:55:46 -06:00
|
|
|
|
'title': 'md5:7b81415841e02ecd4313668cde88737a',
|
|
|
|
|
'description': 'md5:116377fd2963b81ec4ce64b542173306',
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 220,
|
2015-06-27 02:55:46 -06:00
|
|
|
|
'upload_date': '20150625',
|
2018-06-02 13:23:45 -06:00
|
|
|
|
'formats': 'mincount:31',
|
2015-06-27 02:55:46 -06:00
|
|
|
|
},
|
2018-06-02 13:23:45 -06:00
|
|
|
|
'skip': 'not actual anymore',
|
2015-07-20 11:34:24 -06:00
|
|
|
|
},
|
2015-06-10 00:47:02 -06:00
|
|
|
|
# DASH manifest with segment_list
|
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
|
|
|
|
|
'md5': '8ce563a1d667b599d21064e982ab9e31',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'CsmdDsKjzN8',
|
|
|
|
|
'ext': 'mp4',
|
2015-07-20 11:48:50 -06:00
|
|
|
|
'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
|
2015-06-10 00:47:02 -06:00
|
|
|
|
'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
|
|
|
|
|
'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'youtube_include_dash_manifest': True,
|
|
|
|
|
'format': '135', # bestvideo
|
2016-06-24 09:47:19 -06:00
|
|
|
|
},
|
|
|
|
|
'skip': 'This live event has ended.',
|
2015-07-20 11:34:24 -06:00
|
|
|
|
},
|
2015-07-25 09:30:34 -06:00
|
|
|
|
{
|
2022-11-15 17:57:43 -07:00
|
|
|
|
# Multifeed videos (multiple cameras), URL can be of any Camera
|
2023-04-14 01:58:36 -06:00
|
|
|
|
# TODO: fix multifeed titles
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
|
2015-07-25 09:30:34 -06:00
|
|
|
|
'info_dict': {
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'id': 'zaPI8MvL8pg',
|
|
|
|
|
'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
|
|
|
|
|
'description': 'md5:563ccbc698b39298481ca3c571169519',
|
2015-07-25 09:30:34 -06:00
|
|
|
|
},
|
|
|
|
|
'playlist': [{
|
|
|
|
|
'info_dict': {
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'id': 'j5yGuxZ8lLU',
|
2015-07-25 09:30:34 -06:00
|
|
|
|
'ext': 'mp4',
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
|
|
|
|
|
'description': 'md5:563ccbc698b39298481ca3c571169519',
|
|
|
|
|
'duration': 10120,
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'upload_date': '20131105',
|
|
|
|
|
'categories': ['Gaming'],
|
|
|
|
|
'live_status': 'was_live',
|
|
|
|
|
'tags': 'count:24',
|
|
|
|
|
'release_timestamp': 1383701910,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
|
|
|
|
|
'channel': 'WiiLikeToPlay',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'release_date': '20131106',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'WiiLikeToPlay',
|
|
|
|
|
'uploader_id': '@WLTP',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@WLTP',
|
2015-07-25 09:30:34 -06:00
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
'info_dict': {
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'id': 'zaPI8MvL8pg',
|
2015-07-25 09:30:34 -06:00
|
|
|
|
'ext': 'mp4',
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
|
|
|
|
|
'channel': 'WiiLikeToPlay',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'description': 'md5:563ccbc698b39298481ca3c571169519',
|
|
|
|
|
'duration': 10108,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'tags': 'count:24',
|
|
|
|
|
'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
|
|
|
|
|
'release_timestamp': 1383701915,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'upload_date': '20131105',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
|
|
|
|
|
'release_date': '20131106',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'live_status': 'was_live',
|
|
|
|
|
'categories': ['Gaming'],
|
|
|
|
|
'view_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'WiiLikeToPlay',
|
|
|
|
|
'uploader_id': '@WLTP',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@WLTP',
|
2015-07-25 09:30:34 -06:00
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
'info_dict': {
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'id': 'R7r3vfO7Hao',
|
2015-07-25 09:30:34 -06:00
|
|
|
|
'ext': 'mp4',
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
|
|
|
|
|
'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'upload_date': '20131105',
|
|
|
|
|
'description': 'md5:563ccbc698b39298481ca3c571169519',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'tags': 'count:24',
|
|
|
|
|
'release_date': '20131106',
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
|
|
|
|
|
'channel': 'WiiLikeToPlay',
|
|
|
|
|
'categories': ['Gaming'],
|
|
|
|
|
'release_timestamp': 1383701914,
|
|
|
|
|
'live_status': 'was_live',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'duration': 10128,
|
|
|
|
|
'view_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'WiiLikeToPlay',
|
|
|
|
|
'uploader_id': '@WLTP',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@WLTP',
|
2015-07-25 09:30:34 -06:00
|
|
|
|
},
|
|
|
|
|
}],
|
2022-11-15 17:57:43 -07:00
|
|
|
|
'params': {'skip_download': True},
|
2015-08-16 14:04:13 -06:00
|
|
|
|
},
|
2016-02-12 16:18:58 -07:00
|
|
|
|
{
|
2019-03-09 05:14:41 -07:00
|
|
|
|
# Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
|
2016-02-12 16:18:58 -07:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'gVfLd0zydlo',
|
|
|
|
|
'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
|
|
|
|
|
},
|
|
|
|
|
'playlist_count': 2,
|
2016-06-24 09:47:19 -06:00
|
|
|
|
'skip': 'Not multifeed anymore',
|
2016-02-12 16:18:58 -07:00
|
|
|
|
},
|
2015-08-16 14:04:13 -06:00
|
|
|
|
{
|
2016-09-17 08:48:20 -06:00
|
|
|
|
'url': 'https://vid.plus/FlRa-iH7PGw',
|
2015-08-16 14:04:13 -06:00
|
|
|
|
'only_matching': True,
|
2015-11-22 05:49:33 -07:00
|
|
|
|
},
|
2016-04-03 14:26:20 -06:00
|
|
|
|
{
|
2016-09-17 08:48:20 -06:00
|
|
|
|
'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
|
2016-04-03 14:26:20 -06:00
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2015-11-22 05:49:33 -07:00
|
|
|
|
{
|
2019-03-09 05:14:41 -07:00
|
|
|
|
# Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
|
2016-01-18 10:19:38 -07:00
|
|
|
|
# Also tests cut-off URL expansion in video description (see
|
2019-03-09 05:14:41 -07:00
|
|
|
|
# https://github.com/ytdl-org/youtube-dl/issues/1892,
|
|
|
|
|
# https://github.com/ytdl-org/youtube-dl/issues/8164)
|
2015-11-22 05:49:33 -07:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'lsguqyKfVQg',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
|
2021-07-20 21:52:34 -06:00
|
|
|
|
'alt_title': 'Dark Walk',
|
2015-11-22 05:49:33 -07:00
|
|
|
|
'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 133,
|
2015-11-22 05:49:33 -07:00
|
|
|
|
'upload_date': '20151119',
|
2021-07-20 21:52:34 -06:00
|
|
|
|
'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
|
|
|
|
|
'track': 'Dark Walk',
|
|
|
|
|
'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
|
2019-04-28 10:37:46 -06:00
|
|
|
|
'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
|
|
|
|
|
'categories': ['Film & Animation'],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
|
|
|
|
|
'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
|
|
|
|
|
'tags': 'count:13',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel': 'IronSoulElf',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'age_limit': 0,
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2015-11-22 05:49:33 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
},
|
2015-11-23 08:02:37 -07:00
|
|
|
|
{
|
2019-03-09 05:14:41 -07:00
|
|
|
|
# Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
|
2015-11-23 08:02:37 -07:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2015-11-27 17:07:07 -07:00
|
|
|
|
{
|
|
|
|
|
# Video with yt:stretch=17:0
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'Q39EVAstoRM',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
|
|
|
|
|
'description': 'md5:ee18a25c350637c8faff806845bddee9',
|
|
|
|
|
'upload_date': '20151107',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2016-06-24 09:47:19 -06:00
|
|
|
|
'skip': 'This video does not exist.',
|
2015-11-27 17:07:07 -07:00
|
|
|
|
},
|
2021-04-16 21:02:33 -06:00
|
|
|
|
{
|
|
|
|
|
# Video with incomplete 'yt:stretch=16:'
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2016-03-02 10:07:25 -07:00
|
|
|
|
{
|
|
|
|
|
# Video licensed under Creative Commons
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'M4gD1WSo5mA',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'md5:e41008789470fc2533a3252216f1c1d1',
|
|
|
|
|
'description': 'md5:a677553cf0840649b731a3024aeff4cc',
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 721,
|
2022-03-13 16:02:44 -06:00
|
|
|
|
'upload_date': '20150128',
|
2016-03-02 10:07:25 -07:00
|
|
|
|
'license': 'Creative Commons Attribution license (reuse allowed)',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
|
|
|
|
|
'channel': 'The Berkman Klein Center for Internet & Society',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'categories': ['Education'],
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'playable_in_embed': True,
|
2022-10-18 11:58:57 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'chapters': list,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'The Berkman Klein Center for Internet & Society',
|
|
|
|
|
'uploader_id': '@BKCHarvard',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@BKCHarvard',
|
2016-03-02 10:07:25 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
},
|
2016-03-02 10:49:10 -07:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'eQcmzGIKrzg',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 4060,
|
2022-03-13 16:02:44 -06:00
|
|
|
|
'upload_date': '20151120',
|
2016-03-02 10:49:10 -07:00
|
|
|
|
'license': 'Creative Commons Attribution license (reuse allowed)',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'tags': 'count:12',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'categories': ['News & Politics'],
|
|
|
|
|
'channel': 'Bernie Sanders',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'comment_count': int,
|
2022-10-18 11:58:57 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'chapters': list,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'Bernie Sanders',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@BernieSanders',
|
|
|
|
|
'uploader_id': '@BernieSanders',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2016-03-02 10:49:10 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
},
|
2015-11-29 08:01:59 -07:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
|
|
|
|
|
'only_matching': True,
|
2016-07-11 13:10:35 -06:00
|
|
|
|
},
|
|
|
|
|
{
|
2019-03-09 05:14:41 -07:00
|
|
|
|
# YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
|
2016-07-11 13:10:35 -06:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
|
|
|
|
|
'only_matching': True,
|
2016-09-02 12:17:15 -06:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
# Rental video preview
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'uGpuVWrhIzE',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Piku - Trailer',
|
|
|
|
|
'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
|
|
|
|
|
'upload_date': '20150811',
|
|
|
|
|
'license': 'Standard YouTube License',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2018-06-02 13:23:45 -06:00
|
|
|
|
'skip': 'This video is not available.',
|
2017-01-09 08:30:46 -07:00
|
|
|
|
},
|
2017-01-21 04:10:32 -07:00
|
|
|
|
{
|
|
|
|
|
# YouTube Red video with episode data
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'iqKdEhx-dD4',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Isolation - Mind Field (Ep 1)',
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
|
2017-01-26 07:43:14 -07:00
|
|
|
|
'duration': 2085,
|
2017-01-21 04:10:32 -07:00
|
|
|
|
'upload_date': '20170118',
|
|
|
|
|
'series': 'Mind Field',
|
|
|
|
|
'season_number': 1,
|
|
|
|
|
'episode_number': 1,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
|
|
|
|
|
'tags': 'count:12',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'channel': 'Vsauce',
|
|
|
|
|
'episode': 'Episode 1',
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'season': 'Season 1',
|
|
|
|
|
'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'live_status': 'not_live',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Vsauce',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@Vsauce',
|
|
|
|
|
'uploader_id': '@Vsauce',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2017-01-21 04:10:32 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
'expected_warnings': [
|
|
|
|
|
'Skipping DASH manifest',
|
|
|
|
|
],
|
|
|
|
|
},
|
2017-08-26 02:38:38 -06:00
|
|
|
|
{
|
|
|
|
|
# The following content has been identified by the YouTube community
|
|
|
|
|
# as inappropriate or offensive to some audiences.
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '6SJNVb0GnPI',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Race Differences in Intelligence',
|
|
|
|
|
'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
|
|
|
|
|
'duration': 965,
|
|
|
|
|
'upload_date': '20140124',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
|
2017-08-26 02:38:38 -06:00
|
|
|
|
},
|
2017-01-09 08:30:46 -07:00
|
|
|
|
{
|
|
|
|
|
# itag 212
|
|
|
|
|
'url': '1t24XAntNCY',
|
|
|
|
|
'only_matching': True,
|
2017-02-26 02:51:21 -07:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
# geo restricted to JP
|
|
|
|
|
'url': 'sJL6WA-aGkQ',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2018-09-23 11:14:49 -06:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://invidio.us/watch?v=BaW_jenozKc',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2021-02-19 13:44:36 -07:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
# from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
|
|
|
|
|
'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2018-12-26 01:30:48 -07:00
|
|
|
|
{
|
|
|
|
|
# DRM protected
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
|
|
|
|
|
'only_matching': True,
|
2019-01-15 12:18:27 -07:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
# Video with unsupported adaptive stream type formats
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'Z4Vy8R84T1U',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
|
|
|
|
|
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
|
|
|
|
|
'duration': 433,
|
|
|
|
|
'upload_date': '20130923',
|
|
|
|
|
'formats': 'maxcount:10',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
'youtube_include_dash_manifest': False,
|
|
|
|
|
},
|
2020-03-05 10:05:50 -07:00
|
|
|
|
'skip': 'not actual anymore',
|
2019-04-21 22:26:48 -06:00
|
|
|
|
},
|
|
|
|
|
{
|
2019-04-27 02:16:17 -06:00
|
|
|
|
# Youtube Music Auto-generated description
|
2023-04-14 01:58:36 -06:00
|
|
|
|
# TODO: fix metadata extraction
|
2019-04-21 22:26:48 -06:00
|
|
|
|
'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'MgNrAu2pzNs',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Voyeur Girl',
|
|
|
|
|
'description': 'md5:7ae382a65843d6df2685993e90a8628f',
|
|
|
|
|
'upload_date': '20190312',
|
|
|
|
|
'artist': 'Stephen',
|
|
|
|
|
'track': 'Voyeur Girl',
|
|
|
|
|
'album': 'it\'s too much love to know my dear',
|
|
|
|
|
'release_date': '20190313',
|
|
|
|
|
'release_year': 2019,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'alt_title': 'Voyeur Girl',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'categories': ['Music'],
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel': 'Stephen', # TODO: should be "Stephen - Topic"
|
|
|
|
|
'uploader': 'Stephen',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'availability': 'public',
|
|
|
|
|
'creator': 'Stephen',
|
|
|
|
|
'duration': 169,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
|
|
|
|
|
'tags': 'count:11',
|
|
|
|
|
'live_status': 'not_live',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2019-04-21 22:26:48 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
},
|
2019-11-30 09:51:34 -07:00
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2020-04-30 11:40:38 -06:00
|
|
|
|
{
|
|
|
|
|
# invalid -> valid video id redirection
|
|
|
|
|
'url': 'DJztXj2GPfl',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'DJztXj2GPfk',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
|
|
|
|
|
'description': 'md5:bf577a41da97918e94fa9798d9228825',
|
|
|
|
|
'upload_date': '20090125',
|
|
|
|
|
'artist': 'Panjabi MC',
|
|
|
|
|
'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
|
|
|
|
|
'album': 'Beware of the Boys (Mundian To Bach Ke)',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'skip': 'Video unavailable',
|
2020-09-13 08:23:21 -06:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
# empty description results in an empty string
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'x41yOUIvK2k',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'IMG 3456',
|
|
|
|
|
'description': '',
|
|
|
|
|
'upload_date': '20170613',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'view_count': int,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'categories': ['Pets & Animals'],
|
|
|
|
|
'duration': 7,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'live_status': 'not_live',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel': 'l\'Or Vert asbl',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'l\'Or Vert asbl',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
|
|
|
|
|
'uploader_id': '@ElevageOrVert',
|
2020-09-13 08:23:21 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
},
|
2020-11-21 07:50:42 -07:00
|
|
|
|
{
|
2021-01-01 05:26:37 -07:00
|
|
|
|
# with '};' inside yt initial data (see [1])
|
|
|
|
|
# see [2] for an example with '};' inside ytInitialPlayerResponse
|
|
|
|
|
# 1. https://github.com/ytdl-org/youtube-dl/issues/27093
|
|
|
|
|
# 2. https://github.com/ytdl-org/youtube-dl/issues/27216
|
2020-11-21 07:50:42 -07:00
|
|
|
|
'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'CHqg6qOn4no',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Part 77 Sort a list of simple types in c#',
|
|
|
|
|
'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
|
|
|
|
|
'upload_date': '20130831',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'categories': ['Education'],
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
|
|
|
|
|
'tags': 'count:12',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'duration': 522,
|
|
|
|
|
'channel': 'kudvenkat',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'comment_count': int,
|
2022-10-18 11:58:57 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'chapters': list,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'kudvenkat',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
|
|
|
|
|
'uploader_id': '@Csharp-video-tutorialsBlogspot',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2020-11-21 07:50:42 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
},
|
2021-01-01 05:26:37 -07:00
|
|
|
|
{
|
|
|
|
|
# another example of '};' in ytInitialData
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2021-02-04 07:37:17 -07:00
|
|
|
|
{
|
2021-02-10 14:22:55 -07:00
|
|
|
|
# https://github.com/ytdl-org/youtube-dl/pull/28094
|
|
|
|
|
'url': 'OtqTfy26tG0',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'OtqTfy26tG0',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Burn Out',
|
|
|
|
|
'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
|
|
|
|
|
'upload_date': '20141120',
|
|
|
|
|
'artist': 'The Cinematic Orchestra',
|
|
|
|
|
'track': 'Burn Out',
|
|
|
|
|
'album': 'Every Day',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'like_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'alt_title': 'Burn Out',
|
|
|
|
|
'duration': 614,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
|
|
|
|
|
'creator': 'The Cinematic Orchestra',
|
|
|
|
|
'channel': 'The Cinematic Orchestra',
|
|
|
|
|
'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
|
|
|
|
|
'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
|
|
|
|
|
'categories': ['Music'],
|
|
|
|
|
'playable_in_embed': True,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'The Cinematic Orchestra',
|
|
|
|
|
'comment_count': int,
|
2021-02-10 14:22:55 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2021-02-04 07:37:17 -07:00
|
|
|
|
},
|
2021-02-19 13:44:36 -07:00
|
|
|
|
{
|
|
|
|
|
# controversial video, only works with bpctr when authenticated with cookies
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
},
|
2021-07-20 12:01:28 -06:00
|
|
|
|
{
|
|
|
|
|
# controversial video, requires bpctr/contentCheckOk
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'SZJvDhaSDnc',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'San Diego teen commits suicide after bullying over embarrassing video',
|
|
|
|
|
'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
|
|
|
|
|
'upload_date': '20140716',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
|
|
|
|
|
'duration': 170,
|
|
|
|
|
'categories': ['News & Politics'],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel': 'CBS Mornings',
|
|
|
|
|
'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
|
|
|
|
|
'age_limit': 18,
|
|
|
|
|
'availability': 'needs_auth',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'playable_in_embed': True,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'CBS Mornings',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@CBSMornings',
|
|
|
|
|
'uploader_id': '@CBSMornings',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2021-07-20 12:01:28 -06:00
|
|
|
|
}
|
|
|
|
|
},
|
2021-04-10 10:47:11 -06:00
|
|
|
|
{
|
|
|
|
|
# restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
|
|
|
|
|
'url': 'cBvYw8_A0vQ',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'cBvYw8_A0vQ',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
|
|
|
|
|
'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
|
|
|
|
|
'upload_date': '20201120',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'duration': 1456,
|
|
|
|
|
'categories': ['Travel & Events'],
|
|
|
|
|
'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel': 'Walk around Japan',
|
|
|
|
|
'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'playable_in_embed': True,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Walk around Japan',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
|
|
|
|
|
'uploader_id': '@walkaroundjapan7124',
|
2021-04-10 10:47:11 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2021-05-14 01:01:53 -06:00
|
|
|
|
}, {
|
|
|
|
|
# Has multiple audio streams
|
|
|
|
|
'url': 'WaOKSUlf4TM',
|
|
|
|
|
'only_matching': True
|
2021-05-15 08:38:47 -06:00
|
|
|
|
}, {
|
|
|
|
|
# Requires Premium: has format 141 when requested using YTM url
|
|
|
|
|
'url': 'https://music.youtube.com/watch?v=XclachpHxis',
|
|
|
|
|
'only_matching': True
|
|
|
|
|
}, {
|
2021-05-12 13:20:02 -06:00
|
|
|
|
# multiple subtitles with same lang_code
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
|
|
|
|
|
'only_matching': True,
|
2021-06-29 16:07:49 -06:00
|
|
|
|
}, {
|
|
|
|
|
# Force use android client fallback
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'YOelRv7fMxY',
|
2021-07-20 21:52:34 -06:00
|
|
|
|
'title': 'DIGGING A SECRET TUNNEL Part 1',
|
2021-06-29 16:07:49 -06:00
|
|
|
|
'ext': '3gp',
|
|
|
|
|
'upload_date': '20210624',
|
|
|
|
|
'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
|
|
|
|
|
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'description': 'md5:5d5991195d599b56cd0c4148907eec50',
|
|
|
|
|
'duration': 596,
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel': 'colinfurze',
|
|
|
|
|
'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'playable_in_embed': True,
|
2022-10-18 11:58:57 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'chapters': list,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'colinfurze',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@colinfurze',
|
|
|
|
|
'uploader_id': '@colinfurze',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2021-06-29 16:07:49 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'format': '17', # 3gp format available on android
|
|
|
|
|
'extractor_args': {'youtube': {'player_client': ['android']}},
|
|
|
|
|
},
|
2021-05-12 13:20:02 -06:00
|
|
|
|
},
|
2021-06-29 16:07:49 -06:00
|
|
|
|
{
|
|
|
|
|
# Skip download of additional client configs (remix client config in this case)
|
|
|
|
|
'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
'params': {
|
|
|
|
|
'extractor_args': {'youtube': {'player_skip': ['configs']}},
|
|
|
|
|
},
|
2021-08-22 09:04:59 -06:00
|
|
|
|
}, {
|
|
|
|
|
# shorts
|
|
|
|
|
'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
|
|
|
|
|
'only_matching': True,
|
2021-11-18 17:06:28 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'Storyboards',
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '5KLPxDtMqe8',
|
|
|
|
|
'ext': 'mhtml',
|
|
|
|
|
'format_id': 'sb0',
|
|
|
|
|
'title': 'Your Brain is Plastic',
|
|
|
|
|
'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
|
|
|
|
|
'upload_date': '20140324',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'like_count': int,
|
|
|
|
|
'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'tags': 'count:12',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel': 'SciShow',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'duration': 248,
|
|
|
|
|
'categories': ['Education'],
|
|
|
|
|
'age_limit': 0,
|
2022-10-18 11:58:57 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'chapters': list,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'SciShow',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@SciShow',
|
|
|
|
|
'uploader_id': '@SciShow',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2021-11-18 17:06:28 -07:00
|
|
|
|
}, 'params': {'format': 'mhtml', 'skip_download': True}
|
2022-03-08 00:28:00 -07:00
|
|
|
|
}, {
|
|
|
|
|
# Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '2NUZ8W2llS4',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'The NP that test your phone performance 🙂',
|
|
|
|
|
'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
|
|
|
|
|
'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
|
|
|
|
|
'duration': 21,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'categories': ['Gaming'],
|
|
|
|
|
'tags': 'count:23',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'upload_date': '20220103',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel': 'Leon Nguyen',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'comment_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Leon Nguyen',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@LeonNguyen',
|
|
|
|
|
'uploader_id': '@LeonNguyen',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2022-03-08 00:28:00 -07:00
|
|
|
|
}
|
2022-09-01 04:02:28 -06:00
|
|
|
|
}, {
|
|
|
|
|
# Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '2NUZ8W2llS4',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'The NP that test your phone performance 🙂',
|
|
|
|
|
'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
|
|
|
|
|
'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
|
|
|
|
|
'duration': 21,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'categories': ['Gaming'],
|
|
|
|
|
'tags': 'count:23',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'upload_date': '20220102',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel': 'Leon Nguyen',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
|
|
|
|
|
'comment_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Leon Nguyen',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@LeonNguyen',
|
|
|
|
|
'uploader_id': '@LeonNguyen',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2022-09-01 04:02:28 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
|
2022-03-08 00:28:00 -07:00
|
|
|
|
}, {
|
|
|
|
|
# date text is premiered video, ensure upload date in UTC (published 1641172509)
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'mzZzzBU6lrM',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'I Met GeorgeNotFound In Real Life...',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'description': 'md5:978296ec9783a031738b684d4ebf302d',
|
2022-03-08 00:28:00 -07:00
|
|
|
|
'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
|
|
|
|
|
'duration': 955,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'tags': 'count:26',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'release_timestamp': 1641172509,
|
|
|
|
|
'release_date': '20220103',
|
|
|
|
|
'upload_date': '20220103',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel': 'Quackity',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader': 'Quackity',
|
|
|
|
|
'uploader_id': '@Quackity',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@Quackity',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2022-03-08 00:28:00 -07:00
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
{ # continuous livestream. Microformat upload date should be preferred.
|
|
|
|
|
# Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'kgx4WGK0oNU',
|
|
|
|
|
'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'release_timestamp': 1637975704,
|
|
|
|
|
'upload_date': '20210619',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
|
|
|
|
|
'live_status': 'is_live',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
|
|
|
|
|
'channel': 'Abao in Tokyo',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'release_date': '20211127',
|
|
|
|
|
'tags': 'count:39',
|
|
|
|
|
'categories': ['People & Blogs'],
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'description': 'md5:2ef1d002cad520f65825346e2084e49d',
|
2022-10-07 01:00:40 -06:00
|
|
|
|
'concurrent_view_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'Abao in Tokyo',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@abaointokyo',
|
|
|
|
|
'uploader_id': '@abaointokyo',
|
2022-03-08 00:28:00 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': True}
|
2022-05-29 01:54:22 -06:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'tjjjtzRLHvA',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'ハッシュタグ無し };if window.ytcsi',
|
|
|
|
|
'upload_date': '20220323',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'availability': 'unlisted',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel': 'Lesmiscore',
|
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg',
|
2022-05-29 01:54:22 -06:00
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'categories': ['Music'],
|
2022-05-01 00:46:28 -06:00
|
|
|
|
'view_count': int,
|
|
|
|
|
'description': '',
|
2022-05-29 01:54:22 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
|
|
|
|
|
'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'duration': 6,
|
|
|
|
|
'tags': [],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@lesmiscore',
|
|
|
|
|
'uploader': 'Lesmiscore',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@lesmiscore',
|
2022-05-01 00:46:28 -06:00
|
|
|
|
}
|
2022-09-08 23:16:46 -06:00
|
|
|
|
}, {
|
|
|
|
|
# Prefer primary title+description language metadata by default
|
|
|
|
|
# Do not prefer translated description if primary is empty
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'el3E4MbxRqQ',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'dlp test video 2 - primary sv no desc',
|
|
|
|
|
'description': '',
|
|
|
|
|
'channel': 'cole-dlp-test-acc',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'availability': 'unlisted',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'duration': 5,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'upload_date': '20220908',
|
|
|
|
|
'categories': ['People & Blogs'],
|
|
|
|
|
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@coletdjnz',
|
|
|
|
|
'uploader_id': '@coletdjnz',
|
|
|
|
|
'uploader': 'cole-dlp-test-acc',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': True}
|
|
|
|
|
}, {
|
|
|
|
|
# Extractor argument: prefer translated title+description
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'gHKT4uU8Zng',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'channel': 'cole-dlp-test-acc',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'duration': 5,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'upload_date': '20220728',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'categories': ['People & Blogs'],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'thumbnail': r're:^https?://.*\.jpg',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'title': 'dlp test video title translated (fr)',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'description': 'dlp test video description translated (fr)',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@coletdjnz',
|
|
|
|
|
'uploader_id': '@coletdjnz',
|
|
|
|
|
'uploader': 'cole-dlp-test-acc',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
|
|
|
|
|
'expected_warnings': [r'Preferring "fr" translated fields'],
|
2022-08-07 14:06:11 -06:00
|
|
|
|
}, {
|
|
|
|
|
'note': '6 channel audio',
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
|
|
|
|
|
'only_matching': True,
|
2022-11-14 16:53:32 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'Multiple HLS formats with same itag',
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'kX3nB4PpJko',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'duration': 937,
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
|
|
|
|
|
'title': 'Last To Take Hand Off Jet, Keeps It!',
|
|
|
|
|
'channel': 'MrBeast',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'upload_date': '20221112',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'tags': [],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'MrBeast',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@MrBeast',
|
|
|
|
|
'uploader_id': '@MrBeast',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2022-11-14 16:53:32 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
|
2022-12-30 03:02:33 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'Audio formats with Dynamic Range Compression',
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'Tq92D6wQ1mg',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'ext': 'webm',
|
2022-12-30 03:02:33 -07:00
|
|
|
|
'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
|
|
|
|
|
'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'description': 'md5:17eccca93a786d51bc67646756894066',
|
|
|
|
|
'upload_date': '20191228',
|
|
|
|
|
'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
|
|
|
|
|
'age_limit': 18,
|
|
|
|
|
'channel': 'Projekt Melody',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'availability': 'needs_auth',
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'duration': 106,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'Projekt Melody',
|
|
|
|
|
'uploader_id': '@ProjektMelody',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@ProjektMelody',
|
2022-12-30 03:02:33 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
|
2023-02-03 11:17:13 -07:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
'url': 'https://www.youtube.com/live/qVv6vCqciTM',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'qVv6vCqciTM',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'chapters': 'count:13',
|
|
|
|
|
'upload_date': '20221223',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'release_date': '20221223',
|
|
|
|
|
'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
|
|
|
|
|
'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'duration': 4438,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'live_status': 'was_live',
|
|
|
|
|
'release_timestamp': 1671793345,
|
|
|
|
|
'channel': 'さなちゃんねる',
|
|
|
|
|
'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
|
|
|
|
|
'uploader': 'さなちゃんねる',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@sana_natori',
|
|
|
|
|
'uploader_id': '@sana_natori',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
},
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
# Fallbacks when webpage and web client is unavailable
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'wSSmNUl9Snw',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
# 'categories': ['Science & Technology'],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'chapters': 'count:2',
|
|
|
|
|
'channel': 'Scott Manley',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
# 'availability': 'public',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'upload_date': '20170831',
|
|
|
|
|
'duration': 682,
|
|
|
|
|
'tags': 'count:8',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@scottmanley',
|
|
|
|
|
'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
|
|
|
|
|
'uploader': 'Scott Manley',
|
|
|
|
|
'uploader_id': '@scottmanley',
|
|
|
|
|
'title': 'The Computer Hack That Saved Apollo 14',
|
|
|
|
|
'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
|
|
|
|
|
'thumbnail': r're:^https?://.*\.webp',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
|
|
|
|
|
'playable_in_embed': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
|
2023-02-03 11:17:13 -07:00
|
|
|
|
},
|
|
|
|
|
},
|
2013-06-27 11:13:11 -06:00
|
|
|
|
]
|
|
|
|
|
|
2022-07-08 05:23:05 -06:00
|
|
|
|
_WEBPAGE_TESTS = [
|
|
|
|
|
# YouTube <object> embed
|
|
|
|
|
{
|
|
|
|
|
'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
|
|
|
|
|
'md5': '873c81d308b979f0e23ee7e620b312a3',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'msN87y-iEx0',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
|
|
|
|
|
'upload_date': '20080526',
|
|
|
|
|
'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
|
|
|
|
|
'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'comment_count': int,
|
|
|
|
|
'channel': 'Christopher Sykes',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'duration': 195,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'categories': ['Science & Technology'],
|
|
|
|
|
'channel_follower_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'Christopher Sykes',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
|
|
|
|
|
'uploader_id': '@ChristopherSykesDocumentaries',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2022-07-08 05:23:05 -06:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
]
|
|
|
|
|
|
2021-04-16 21:02:33 -06:00
|
|
|
|
@classmethod
|
|
|
|
|
def suitable(cls, url):
|
2021-08-22 13:02:00 -06:00
|
|
|
|
from ..utils import parse_qs
|
|
|
|
|
|
2021-04-16 21:02:33 -06:00
|
|
|
|
qs = parse_qs(url)
|
|
|
|
|
if qs.get('list', [None])[0]:
|
|
|
|
|
return False
|
2022-04-11 09:10:28 -06:00
|
|
|
|
return super().suitable(url)
|
2021-04-16 21:02:33 -06:00
|
|
|
|
|
2013-09-21 06:19:30 -06:00
|
|
|
|
def __init__(self, *args, **kwargs):
|
2022-04-11 09:10:28 -06:00
|
|
|
|
super().__init__(*args, **kwargs)
|
2021-02-04 07:37:17 -07:00
|
|
|
|
self._code_cache = {}
|
2013-09-21 07:19:48 -06:00
|
|
|
|
self._player_cache = {}
|
2013-09-21 06:19:30 -06:00
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
|
2021-12-19 23:06:46 -07:00
|
|
|
|
lock = threading.Lock()
|
2021-12-26 03:19:35 -07:00
|
|
|
|
start_time = time.time()
|
2021-12-19 23:06:46 -07:00
|
|
|
|
formats = [f for f in formats if f.get('is_from_start')]
|
|
|
|
|
|
2021-12-26 03:19:35 -07:00
|
|
|
|
def refetch_manifest(format_id, delay):
|
|
|
|
|
nonlocal formats, start_time, is_live
|
|
|
|
|
if time.time() <= start_time + delay:
|
2021-12-19 23:06:46 -07:00
|
|
|
|
return
|
|
|
|
|
|
|
|
|
|
_, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
|
2023-02-09 15:26:26 -07:00
|
|
|
|
video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
|
2021-12-19 23:06:46 -07:00
|
|
|
|
microformats = traverse_obj(
|
|
|
|
|
prs, (..., 'microformat', 'playerMicroformatRenderer'),
|
2023-02-09 15:26:26 -07:00
|
|
|
|
expected_type=dict)
|
2022-10-03 20:48:31 -06:00
|
|
|
|
_, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
|
|
|
|
|
is_live = live_status == 'is_live'
|
2021-12-26 03:19:35 -07:00
|
|
|
|
start_time = time.time()
|
2021-12-19 23:06:46 -07:00
|
|
|
|
|
2021-12-26 03:19:35 -07:00
|
|
|
|
def mpd_feed(format_id, delay):
|
2021-12-19 23:06:46 -07:00
|
|
|
|
"""
|
|
|
|
|
@returns (manifest_url, manifest_stream_number, is_live) or None
|
|
|
|
|
"""
|
2023-01-06 12:30:42 -07:00
|
|
|
|
for retry in self.RetryManager(fatal=False):
|
|
|
|
|
with lock:
|
|
|
|
|
refetch_manifest(format_id, delay)
|
|
|
|
|
|
|
|
|
|
f = next((f for f in formats if f['format_id'] == format_id), None)
|
|
|
|
|
if not f:
|
|
|
|
|
if not is_live:
|
|
|
|
|
retry.error = f'{video_id}: Video is no longer live'
|
|
|
|
|
else:
|
|
|
|
|
retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
|
|
|
|
|
continue
|
|
|
|
|
return f['manifest_url'], f['manifest_stream_number'], is_live
|
|
|
|
|
return None
|
2021-12-19 23:06:46 -07:00
|
|
|
|
|
|
|
|
|
for f in formats:
|
2022-10-03 20:48:31 -06:00
|
|
|
|
f['is_live'] = is_live
|
|
|
|
|
gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
|
|
|
|
|
live_start_time, mpd_feed, not is_live and f.copy())
|
|
|
|
|
if is_live:
|
|
|
|
|
f['fragments'] = gen
|
|
|
|
|
f['protocol'] = 'http_dash_segments_generator'
|
|
|
|
|
else:
|
|
|
|
|
f['fragments'] = LazyList(gen({}))
|
|
|
|
|
del f['is_from_start']
|
2021-12-19 23:06:46 -07:00
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
|
2021-12-19 23:06:46 -07:00
|
|
|
|
FETCH_SPAN, MAX_DURATION = 5, 432000
|
|
|
|
|
|
|
|
|
|
mpd_url, stream_number, is_live = None, None, True
|
|
|
|
|
|
|
|
|
|
begin_index = 0
|
|
|
|
|
download_start_time = ctx.get('start') or time.time()
|
|
|
|
|
|
|
|
|
|
lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
|
|
|
|
|
if lack_early_segments:
|
|
|
|
|
self.report_warning(bug_reports_message(
|
|
|
|
|
'Starting download from the last 120 hours of the live stream since '
|
|
|
|
|
'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
|
|
|
|
|
lack_early_segments = True
|
|
|
|
|
|
|
|
|
|
known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
|
|
|
|
|
fragments, fragment_base_url = None, None
|
|
|
|
|
|
2022-02-24 10:00:46 -07:00
|
|
|
|
def _extract_sequence_from_mpd(refresh_sequence, immediate):
|
2021-12-19 23:06:46 -07:00
|
|
|
|
nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
|
|
|
|
|
# Obtain from MPD's maximum seq value
|
|
|
|
|
old_mpd_url = mpd_url
|
2021-12-26 03:19:35 -07:00
|
|
|
|
last_error = ctx.pop('last_error', None)
|
2023-07-09 01:53:02 -06:00
|
|
|
|
expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403
|
2021-12-26 03:19:35 -07:00
|
|
|
|
mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
|
|
|
|
|
or (mpd_url, stream_number, False))
|
|
|
|
|
if not refresh_sequence:
|
|
|
|
|
if expire_fast and not is_live:
|
|
|
|
|
return False, last_seq
|
|
|
|
|
elif old_mpd_url == mpd_url:
|
|
|
|
|
return True, last_seq
|
2022-10-03 20:48:31 -06:00
|
|
|
|
if manifestless_orig_fmt:
|
|
|
|
|
fmt_info = manifestless_orig_fmt
|
|
|
|
|
else:
|
|
|
|
|
try:
|
|
|
|
|
fmts, _ = self._extract_mpd_formats_and_subtitles(
|
|
|
|
|
mpd_url, None, note=False, errnote=False, fatal=False)
|
|
|
|
|
except ExtractorError:
|
|
|
|
|
fmts = None
|
|
|
|
|
if not fmts:
|
|
|
|
|
no_fragment_score += 2
|
|
|
|
|
return False, last_seq
|
|
|
|
|
fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
|
2021-12-19 23:06:46 -07:00
|
|
|
|
fragments = fmt_info['fragments']
|
|
|
|
|
fragment_base_url = fmt_info['fragment_base_url']
|
|
|
|
|
assert fragment_base_url
|
|
|
|
|
|
|
|
|
|
_last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
|
|
|
|
|
return True, _last_seq
|
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
|
2021-12-19 23:06:46 -07:00
|
|
|
|
while is_live:
|
|
|
|
|
fetch_time = time.time()
|
|
|
|
|
if no_fragment_score > 30:
|
|
|
|
|
return
|
|
|
|
|
if last_segment_url:
|
|
|
|
|
# Obtain from "X-Head-Seqnum" header value from each segment
|
|
|
|
|
try:
|
|
|
|
|
urlh = self._request_webpage(
|
|
|
|
|
last_segment_url, None, note=False, errnote=False, fatal=False)
|
|
|
|
|
except ExtractorError:
|
|
|
|
|
urlh = None
|
|
|
|
|
last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
|
|
|
|
|
if last_seq is None:
|
2022-02-24 10:00:46 -07:00
|
|
|
|
no_fragment_score += 2
|
2021-12-19 23:06:46 -07:00
|
|
|
|
last_segment_url = None
|
|
|
|
|
continue
|
|
|
|
|
else:
|
2022-02-24 10:00:46 -07:00
|
|
|
|
should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
|
|
|
|
|
no_fragment_score += 2
|
2021-12-26 03:19:35 -07:00
|
|
|
|
if not should_continue:
|
2021-12-19 23:06:46 -07:00
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
if known_idx > last_seq:
|
|
|
|
|
last_segment_url = None
|
|
|
|
|
continue
|
|
|
|
|
|
|
|
|
|
last_seq += 1
|
|
|
|
|
|
|
|
|
|
if begin_index < 0 and known_idx < 0:
|
|
|
|
|
# skip from the start when it's negative value
|
|
|
|
|
known_idx = last_seq + begin_index
|
|
|
|
|
if lack_early_segments:
|
|
|
|
|
known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
|
|
|
|
|
try:
|
|
|
|
|
for idx in range(known_idx, last_seq):
|
|
|
|
|
# do not update sequence here or you'll get skipped some part of it
|
2022-02-24 10:00:46 -07:00
|
|
|
|
should_continue, _ = _extract_sequence_from_mpd(False, False)
|
2021-12-26 03:19:35 -07:00
|
|
|
|
if not should_continue:
|
2021-12-19 23:06:46 -07:00
|
|
|
|
known_idx = idx - 1
|
|
|
|
|
raise ExtractorError('breaking out of outer loop')
|
|
|
|
|
last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
|
|
|
|
|
yield {
|
|
|
|
|
'url': last_segment_url,
|
2022-06-07 06:44:08 -06:00
|
|
|
|
'fragment_count': last_seq,
|
2021-12-19 23:06:46 -07:00
|
|
|
|
}
|
|
|
|
|
if known_idx == last_seq:
|
|
|
|
|
no_fragment_score += 5
|
|
|
|
|
else:
|
|
|
|
|
no_fragment_score = 0
|
|
|
|
|
known_idx = last_seq
|
|
|
|
|
except ExtractorError:
|
|
|
|
|
continue
|
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
if manifestless_orig_fmt:
|
|
|
|
|
# Stop at the first iteration if running for post-live manifestless;
|
|
|
|
|
# fragment count no longer increase since it starts
|
|
|
|
|
break
|
|
|
|
|
|
2021-12-19 23:06:46 -07:00
|
|
|
|
time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
|
|
|
|
|
|
2021-09-06 01:26:41 -06:00
|
|
|
|
def _extract_player_url(self, *ytcfgs, webpage=None):
|
|
|
|
|
player_url = traverse_obj(
|
|
|
|
|
ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
|
2022-06-24 04:54:43 -06:00
|
|
|
|
get_all=False, expected_type=str)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
if not player_url:
|
2021-09-06 01:26:41 -06:00
|
|
|
|
return
|
2022-02-13 14:36:01 -07:00
|
|
|
|
return urljoin('https://www.youtube.com', player_url)
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2021-09-06 01:26:41 -06:00
|
|
|
|
def _download_player_url(self, video_id, fatal=False):
|
|
|
|
|
res = self._download_webpage(
|
|
|
|
|
'https://www.youtube.com/iframe_api',
|
|
|
|
|
note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
|
|
|
|
|
if res:
|
|
|
|
|
player_version = self._search_regex(
|
|
|
|
|
r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
|
|
|
|
|
if player_version:
|
|
|
|
|
return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
|
|
|
|
|
|
2014-08-02 04:21:53 -06:00
|
|
|
|
def _signature_cache_id(self, example_sig):
|
|
|
|
|
""" Return a string representation of a signature """
|
2022-06-24 04:54:43 -06:00
|
|
|
|
return '.'.join(str(len(part)) for part in example_sig.split('.'))
|
2014-08-02 04:21:53 -06:00
|
|
|
|
|
2020-05-01 18:18:08 -06:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_player_info(cls, player_url):
|
|
|
|
|
for player_re in cls._PLAYER_INFO_RE:
|
|
|
|
|
id_m = re.search(player_re, player_url)
|
|
|
|
|
if id_m:
|
|
|
|
|
break
|
|
|
|
|
else:
|
2014-07-22 18:19:33 -06:00
|
|
|
|
raise ExtractorError('Cannot identify player %r' % player_url)
|
2021-02-04 07:37:17 -07:00
|
|
|
|
return id_m.group('id')
|
2020-05-01 18:18:08 -06:00
|
|
|
|
|
2021-10-30 22:23:58 -06:00
|
|
|
|
def _load_player(self, video_id, player_url, fatal=True):
|
2021-06-29 16:07:49 -06:00
|
|
|
|
player_id = self._extract_player_info(player_url)
|
|
|
|
|
if player_id not in self._code_cache:
|
2021-10-03 15:14:55 -06:00
|
|
|
|
code = self._download_webpage(
|
2021-06-29 16:07:49 -06:00
|
|
|
|
player_url, video_id, fatal=fatal,
|
|
|
|
|
note='Downloading player ' + player_id,
|
|
|
|
|
errnote='Download of %s failed' % player_url)
|
2021-10-03 15:14:55 -06:00
|
|
|
|
if code:
|
|
|
|
|
self._code_cache[player_id] = code
|
2021-10-30 22:23:58 -06:00
|
|
|
|
return self._code_cache.get(player_id)
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2020-05-01 18:18:08 -06:00
|
|
|
|
def _extract_signature_function(self, video_id, player_url, example_sig):
|
2021-02-04 07:37:17 -07:00
|
|
|
|
player_id = self._extract_player_info(player_url)
|
2013-09-21 06:19:30 -06:00
|
|
|
|
|
2013-09-21 16:35:03 -06:00
|
|
|
|
# Read from filesystem cache
|
2022-04-11 09:10:28 -06:00
|
|
|
|
func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
|
2013-09-21 16:35:03 -06:00
|
|
|
|
assert os.path.basename(func_id) == func_id
|
2014-09-03 04:41:05 -06:00
|
|
|
|
|
2022-06-27 23:10:54 -06:00
|
|
|
|
self.write_debug(f'Extracting signature function {func_id}')
|
2022-08-18 09:57:41 -06:00
|
|
|
|
cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
|
2013-09-21 07:19:48 -06:00
|
|
|
|
|
2022-08-18 09:57:41 -06:00
|
|
|
|
if not cache_spec:
|
|
|
|
|
code = self._load_player(video_id, player_url)
|
2021-10-30 22:23:58 -06:00
|
|
|
|
if code:
|
2021-06-29 16:07:49 -06:00
|
|
|
|
res = self._parse_sig_js(code)
|
2022-06-24 02:10:17 -06:00
|
|
|
|
test_string = ''.join(map(chr, range(len(example_sig))))
|
2022-08-18 09:57:41 -06:00
|
|
|
|
cache_spec = [ord(c) for c in res(test_string)]
|
2022-06-22 22:14:22 -06:00
|
|
|
|
self.cache.store('youtube-sigfuncs', func_id, cache_spec)
|
2022-08-18 09:57:41 -06:00
|
|
|
|
|
|
|
|
|
return lambda s: ''.join(s[i] for i in cache_spec)
|
2013-09-21 07:19:48 -06:00
|
|
|
|
|
2014-08-02 04:21:53 -06:00
|
|
|
|
def _print_sig_code(self, func, example_sig):
|
2021-10-30 22:23:58 -06:00
|
|
|
|
if not self.get_param('youtube_print_sig_code'):
|
|
|
|
|
return
|
|
|
|
|
|
2013-09-22 02:30:02 -06:00
|
|
|
|
def gen_sig_code(idxs):
|
|
|
|
|
def _genslice(start, end, step):
|
2014-09-12 23:51:06 -06:00
|
|
|
|
starts = '' if start == 0 else str(start)
|
2014-11-23 13:20:46 -07:00
|
|
|
|
ends = (':%d' % (end + step)) if end + step >= 0 else ':'
|
2014-09-24 01:51:45 -06:00
|
|
|
|
steps = '' if step == 1 else (':%d' % step)
|
2022-04-11 09:10:28 -06:00
|
|
|
|
return f's[{starts}{ends}{steps}]'
|
2013-09-22 02:30:02 -06:00
|
|
|
|
|
|
|
|
|
step = None
|
2014-12-16 16:06:41 -07:00
|
|
|
|
# Quelch pyflakes warnings - start will be set when step is set
|
|
|
|
|
start = '(Never used)'
|
2013-09-22 02:30:02 -06:00
|
|
|
|
for i, prev in zip(idxs[1:], idxs[:-1]):
|
|
|
|
|
if step is not None:
|
|
|
|
|
if i - prev == step:
|
|
|
|
|
continue
|
|
|
|
|
yield _genslice(start, prev, step)
|
|
|
|
|
step = None
|
|
|
|
|
continue
|
|
|
|
|
if i - prev in [-1, 1]:
|
|
|
|
|
step = i - prev
|
|
|
|
|
start = prev
|
|
|
|
|
continue
|
|
|
|
|
else:
|
2014-09-12 23:51:06 -06:00
|
|
|
|
yield 's[%d]' % prev
|
2013-09-22 02:30:02 -06:00
|
|
|
|
if step is None:
|
2014-09-12 23:51:06 -06:00
|
|
|
|
yield 's[%d]' % i
|
2013-09-22 02:30:02 -06:00
|
|
|
|
else:
|
|
|
|
|
yield _genslice(start, i, step)
|
|
|
|
|
|
2022-06-24 02:10:17 -06:00
|
|
|
|
test_string = ''.join(map(chr, range(len(example_sig))))
|
2013-09-22 04:18:16 -06:00
|
|
|
|
cache_res = func(test_string)
|
2013-09-22 02:30:02 -06:00
|
|
|
|
cache_spec = [ord(c) for c in cache_res]
|
2014-09-12 23:51:06 -06:00
|
|
|
|
expr_code = ' + '.join(gen_sig_code(cache_spec))
|
2014-08-02 04:21:53 -06:00
|
|
|
|
signature_id_tuple = '(%s)' % (
|
2022-06-24 04:54:43 -06:00
|
|
|
|
', '.join(str(len(p)) for p in example_sig.split('.')))
|
2014-09-24 01:51:45 -06:00
|
|
|
|
code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
|
2014-09-12 23:51:06 -06:00
|
|
|
|
' return %s\n') % (signature_id_tuple, expr_code)
|
2014-09-24 01:51:45 -06:00
|
|
|
|
self.to_screen('Extracted signature function:\n' + code)
|
2013-09-22 02:30:02 -06:00
|
|
|
|
|
2013-09-21 06:19:30 -06:00
|
|
|
|
def _parse_sig_js(self, jscode):
|
|
|
|
|
funcname = self._search_regex(
|
2019-06-21 09:58:42 -06:00
|
|
|
|
(r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
|
|
|
|
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
2021-08-07 21:54:37 -06:00
|
|
|
|
r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
|
|
|
|
|
r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
|
2023-05-24 12:00:43 -06:00
|
|
|
|
r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\))?',
|
2019-06-21 13:22:07 -06:00
|
|
|
|
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
|
2019-06-21 09:58:42 -06:00
|
|
|
|
# Obsolete patterns
|
2023-05-24 12:00:43 -06:00
|
|
|
|
r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
2018-09-07 14:36:10 -06:00
|
|
|
|
r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
|
2019-06-21 09:58:42 -06:00
|
|
|
|
r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
|
|
|
|
r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
|
|
|
|
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
|
|
|
|
r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
|
2017-01-31 08:19:29 -07:00
|
|
|
|
jscode, 'Initial JS player signature function name', group='sig')
|
2014-03-29 23:02:58 -06:00
|
|
|
|
|
|
|
|
|
jsi = JSInterpreter(jscode)
|
|
|
|
|
initial_function = jsi.extract_function(funcname)
|
2013-09-21 06:19:30 -06:00
|
|
|
|
return lambda s: initial_function([s])
|
|
|
|
|
|
2022-08-18 09:57:41 -06:00
|
|
|
|
def _cached(self, func, *cache_id):
|
|
|
|
|
def inner(*args, **kwargs):
|
|
|
|
|
if cache_id not in self._player_cache:
|
|
|
|
|
try:
|
|
|
|
|
self._player_cache[cache_id] = func(*args, **kwargs)
|
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
self._player_cache[cache_id] = e
|
|
|
|
|
except Exception as e:
|
|
|
|
|
self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
|
|
|
|
|
|
|
|
|
|
ret = self._player_cache[cache_id]
|
|
|
|
|
if isinstance(ret, Exception):
|
|
|
|
|
raise ret
|
|
|
|
|
return ret
|
|
|
|
|
return inner
|
|
|
|
|
|
2021-02-04 07:37:17 -07:00
|
|
|
|
def _decrypt_signature(self, s, video_id, player_url):
|
2013-06-27 14:20:50 -06:00
|
|
|
|
"""Turn the encrypted s field into a working signature"""
|
2022-08-18 09:57:41 -06:00
|
|
|
|
extract_sig = self._cached(
|
|
|
|
|
self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
|
|
|
|
|
func = extract_sig(video_id, player_url, s)
|
|
|
|
|
self._print_sig_code(func, s)
|
|
|
|
|
return func(s)
|
2021-10-30 22:23:58 -06:00
|
|
|
|
|
|
|
|
|
def _decrypt_nsig(self, s, video_id, player_url):
|
|
|
|
|
"""Turn the encrypted n field into a working signature"""
|
|
|
|
|
if player_url is None:
|
|
|
|
|
raise ExtractorError('Cannot decrypt nsig without player_url')
|
2022-02-13 14:36:01 -07:00
|
|
|
|
player_url = urljoin('https://www.youtube.com', player_url)
|
2021-10-30 22:23:58 -06:00
|
|
|
|
|
2022-09-01 02:08:25 -06:00
|
|
|
|
try:
|
|
|
|
|
jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
|
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
raise ExtractorError('Unable to extract nsig function code', cause=e)
|
2022-08-18 09:57:41 -06:00
|
|
|
|
if self.get_param('youtube_print_sig_code'):
|
|
|
|
|
self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
|
2021-10-30 22:23:58 -06:00
|
|
|
|
|
2022-08-18 10:05:18 -06:00
|
|
|
|
try:
|
|
|
|
|
extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
|
|
|
|
|
ret = extract_nsig(jsi, func_code)(s)
|
|
|
|
|
except JSInterpreter.Exception as e:
|
|
|
|
|
try:
|
2022-08-21 18:49:06 -06:00
|
|
|
|
jsi = PhantomJSwrapper(self, timeout=5000)
|
2022-08-18 10:05:18 -06:00
|
|
|
|
except ExtractorError:
|
|
|
|
|
raise e
|
|
|
|
|
self.report_warning(
|
|
|
|
|
f'Native nsig extraction failed: Trying with PhantomJS\n'
|
|
|
|
|
f' n = {s} ; player = {player_url}', video_id)
|
2022-10-10 20:29:27 -06:00
|
|
|
|
self.write_debug(e, only_once=True)
|
2022-08-18 10:05:18 -06:00
|
|
|
|
|
|
|
|
|
args, func_body = func_code
|
|
|
|
|
ret = jsi.execute(
|
|
|
|
|
f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
|
|
|
|
|
video_id=video_id, note='Executing signature code').strip()
|
2022-08-18 09:57:41 -06:00
|
|
|
|
|
|
|
|
|
self.write_debug(f'Decrypted nsig {s} => {ret}')
|
|
|
|
|
return ret
|
|
|
|
|
|
2022-08-20 13:21:03 -06:00
|
|
|
|
def _extract_n_function_name(self, jscode):
|
|
|
|
|
funcname, idx = self._search_regex(
|
|
|
|
|
r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
|
|
|
|
|
jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
|
|
|
|
|
if not idx:
|
|
|
|
|
return funcname
|
|
|
|
|
|
|
|
|
|
return json.loads(js_to_json(self._search_regex(
|
2023-07-06 08:39:42 -06:00
|
|
|
|
rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
|
2022-08-20 13:21:03 -06:00
|
|
|
|
f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
|
|
|
|
|
|
2022-08-18 09:57:41 -06:00
|
|
|
|
def _extract_n_function_code(self, video_id, player_url):
|
2021-10-30 22:23:58 -06:00
|
|
|
|
player_id = self._extract_player_info(player_url)
|
2022-09-01 01:44:04 -06:00
|
|
|
|
func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
|
2022-08-18 09:57:41 -06:00
|
|
|
|
jscode = func_code or self._load_player(video_id, player_url)
|
|
|
|
|
jsi = JSInterpreter(jscode)
|
2021-10-30 22:23:58 -06:00
|
|
|
|
|
|
|
|
|
if func_code:
|
2022-08-18 09:57:41 -06:00
|
|
|
|
return jsi, player_id, func_code
|
2021-10-30 22:23:58 -06:00
|
|
|
|
|
2022-09-01 02:08:25 -06:00
|
|
|
|
func_name = self._extract_n_function_name(jscode)
|
|
|
|
|
|
|
|
|
|
# For redundancy
|
|
|
|
|
func_code = self._search_regex(
|
|
|
|
|
r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
|
|
|
|
|
# NB: The end of the regex is intentionally kept strict
|
|
|
|
|
{(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
|
|
|
|
|
jscode, 'nsig function', group=('var', 'code'), default=None)
|
|
|
|
|
if func_code:
|
|
|
|
|
func_code = ([func_code[0]], func_code[1])
|
|
|
|
|
else:
|
|
|
|
|
self.write_debug('Extracting nsig function with jsinterp')
|
|
|
|
|
func_code = jsi.extract_function_code(func_name)
|
|
|
|
|
|
2022-08-18 09:57:41 -06:00
|
|
|
|
self.cache.store('youtube-nsig', player_id, func_code)
|
|
|
|
|
return jsi, player_id, func_code
|
|
|
|
|
|
|
|
|
|
def _extract_n_function_from_code(self, jsi, func_code):
|
2022-08-13 17:21:54 -06:00
|
|
|
|
func = jsi.extract_function_from_code(*func_code)
|
2022-08-18 05:08:35 -06:00
|
|
|
|
|
2022-08-18 09:57:41 -06:00
|
|
|
|
def extract_nsig(s):
|
2022-08-18 10:05:18 -06:00
|
|
|
|
try:
|
|
|
|
|
ret = func([s])
|
|
|
|
|
except JSInterpreter.Exception:
|
|
|
|
|
raise
|
|
|
|
|
except Exception as e:
|
|
|
|
|
raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
|
|
|
|
|
|
2022-08-18 05:08:35 -06:00
|
|
|
|
if ret.startswith('enhanced_except_'):
|
2022-08-18 10:05:18 -06:00
|
|
|
|
raise JSInterpreter.Exception('Signature function returned an exception')
|
2022-08-18 05:08:35 -06:00
|
|
|
|
return ret
|
2022-08-18 09:57:41 -06:00
|
|
|
|
|
|
|
|
|
return extract_nsig
|
2013-09-21 06:19:30 -06:00
|
|
|
|
|
2021-06-29 16:07:49 -06:00
|
|
|
|
def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
|
|
|
|
|
"""
|
|
|
|
|
Extract signatureTimestamp (sts)
|
|
|
|
|
Required to tell API what sig/player version is in use.
|
|
|
|
|
"""
|
|
|
|
|
sts = None
|
|
|
|
|
if isinstance(ytcfg, dict):
|
|
|
|
|
sts = int_or_none(ytcfg.get('STS'))
|
|
|
|
|
|
|
|
|
|
if not sts:
|
|
|
|
|
# Attempt to extract from player
|
|
|
|
|
if player_url is None:
|
|
|
|
|
error_msg = 'Cannot extract signature timestamp without player_url.'
|
|
|
|
|
if fatal:
|
|
|
|
|
raise ExtractorError(error_msg)
|
|
|
|
|
self.report_warning(error_msg)
|
|
|
|
|
return
|
2021-10-30 22:23:58 -06:00
|
|
|
|
code = self._load_player(video_id, player_url, fatal=fatal)
|
|
|
|
|
if code:
|
2021-06-29 16:07:49 -06:00
|
|
|
|
sts = int_or_none(self._search_regex(
|
|
|
|
|
r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
|
|
|
|
|
'JS player signature timestamp', group='sts', fatal=fatal))
|
|
|
|
|
return sts
|
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
def _mark_watched(self, video_id, player_responses):
|
2022-06-23 17:30:17 -06:00
|
|
|
|
for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
|
|
|
|
|
label = 'fully ' if is_full else ''
|
|
|
|
|
url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
|
|
|
|
|
expected_type=url_or_none)
|
|
|
|
|
if not url:
|
|
|
|
|
self.report_warning(f'Unable to mark {label}watched')
|
|
|
|
|
return
|
2022-06-24 04:54:43 -06:00
|
|
|
|
parsed_url = urllib.parse.urlparse(url)
|
|
|
|
|
qs = urllib.parse.parse_qs(parsed_url.query)
|
2022-06-23 17:30:17 -06:00
|
|
|
|
|
|
|
|
|
# cpn generation algorithm is reverse engineered from base.js.
|
|
|
|
|
# In fact it works even with dummy cpn.
|
|
|
|
|
CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
|
|
|
|
|
cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
|
|
|
|
|
|
|
|
|
|
# # more consistent results setting it to right before the end
|
|
|
|
|
video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
|
|
|
|
|
|
|
|
|
|
qs.update({
|
|
|
|
|
'ver': ['2'],
|
|
|
|
|
'cpn': [cpn],
|
|
|
|
|
'cmt': video_length,
|
|
|
|
|
'el': 'detailpage', # otherwise defaults to "shorts"
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
if is_full:
|
|
|
|
|
# these seem to mark watchtime "history" in the real world
|
|
|
|
|
# they're required, so send in a single value
|
|
|
|
|
qs.update({
|
2022-10-18 12:35:54 -06:00
|
|
|
|
'st': 0,
|
2022-06-23 17:30:17 -06:00
|
|
|
|
'et': video_length,
|
|
|
|
|
})
|
|
|
|
|
|
2022-06-24 04:54:43 -06:00
|
|
|
|
url = urllib.parse.urlunparse(
|
|
|
|
|
parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
|
2022-06-23 17:30:17 -06:00
|
|
|
|
|
|
|
|
|
self._download_webpage(
|
|
|
|
|
url, video_id, f'Marking {label}watched',
|
|
|
|
|
'Unable to mark watched', fatal=False)
|
2016-02-29 12:01:33 -07:00
|
|
|
|
|
2022-07-31 19:23:25 -06:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_from_webpage(cls, url, webpage):
|
|
|
|
|
# Invidious Instances
|
|
|
|
|
# https://github.com/yt-dlp/yt-dlp/issues/195
|
|
|
|
|
# https://github.com/iv-org/invidious/pull/1730
|
|
|
|
|
mobj = re.search(
|
|
|
|
|
r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
|
|
|
|
|
webpage)
|
|
|
|
|
if mobj:
|
|
|
|
|
yield cls.url_result(mobj.group('url'), cls)
|
|
|
|
|
raise cls.StopExtraction()
|
|
|
|
|
|
|
|
|
|
yield from super()._extract_from_webpage(url, webpage)
|
2017-09-05 11:48:37 -06:00
|
|
|
|
|
|
|
|
|
# lazyYT YouTube embed
|
2022-07-31 19:23:25 -06:00
|
|
|
|
for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
|
|
|
|
|
yield cls.url_result(unescapeHTML(id_), cls, id_)
|
2017-09-05 11:48:37 -06:00
|
|
|
|
|
|
|
|
|
# Wordpress "YouTube Video Importer" plugin
|
2022-07-31 19:23:25 -06:00
|
|
|
|
for m in re.findall(r'''(?x)<div[^>]+
|
|
|
|
|
class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
|
|
|
|
|
data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
|
|
|
|
|
yield cls.url_result(m[-1], cls, m[-1])
|
2017-09-05 11:48:37 -06:00
|
|
|
|
|
2014-02-08 11:20:11 -07:00
|
|
|
|
@classmethod
|
|
|
|
|
def extract_id(cls, url):
|
2022-06-27 23:10:54 -06:00
|
|
|
|
video_id = cls.get_temp_id(url)
|
|
|
|
|
if not video_id:
|
|
|
|
|
raise ExtractorError(f'Invalid URL: {url}')
|
|
|
|
|
return video_id
|
2013-06-23 11:58:33 -06:00
|
|
|
|
|
2021-07-19 18:02:41 -06:00
|
|
|
|
def _extract_chapters_from_json(self, data, duration):
|
|
|
|
|
chapter_list = traverse_obj(
|
|
|
|
|
data, (
|
|
|
|
|
'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
|
|
|
|
|
'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
|
|
|
|
|
), expected_type=list)
|
|
|
|
|
|
2023-03-04 06:33:17 -07:00
|
|
|
|
return self._extract_chapters_helper(
|
2021-07-19 18:02:41 -06:00
|
|
|
|
chapter_list,
|
2023-03-04 06:33:17 -07:00
|
|
|
|
start_function=lambda chapter: float_or_none(
|
2021-07-19 18:02:41 -06:00
|
|
|
|
traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
|
2023-03-04 06:33:17 -07:00
|
|
|
|
title_function=lambda chapter: traverse_obj(
|
2021-07-19 18:02:41 -06:00
|
|
|
|
chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
|
|
|
|
|
duration=duration)
|
|
|
|
|
|
|
|
|
|
def _extract_chapters_from_engagement_panel(self, data, duration):
|
|
|
|
|
content_list = traverse_obj(
|
2020-11-19 12:22:59 -07:00
|
|
|
|
data,
|
2021-07-19 18:02:41 -06:00
|
|
|
|
('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
|
2023-02-09 15:26:26 -07:00
|
|
|
|
expected_type=list)
|
2021-07-23 18:46:46 -06:00
|
|
|
|
chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
|
|
|
|
|
chapter_title = lambda chapter: self._get_text(chapter, 'title')
|
2021-07-19 18:02:41 -06:00
|
|
|
|
|
2022-06-03 09:59:03 -06:00
|
|
|
|
return next(filter(None, (
|
2023-03-04 06:33:17 -07:00
|
|
|
|
self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
|
|
|
|
|
chapter_time, chapter_title, duration)
|
2022-06-03 09:59:03 -06:00
|
|
|
|
for contents in content_list)), [])
|
2021-07-19 18:02:41 -06:00
|
|
|
|
|
2023-10-06 19:00:15 -06:00
|
|
|
|
def _extract_heatmap(self, data):
|
|
|
|
|
return traverse_obj(data, (
|
|
|
|
|
'frameworkUpdates', 'entityBatchUpdate', 'mutations',
|
|
|
|
|
lambda _, v: v['payload']['macroMarkersListEntity']['markersList']['markerType'] == 'MARKER_TYPE_HEATMAP',
|
|
|
|
|
'payload', 'macroMarkersListEntity', 'markersList', 'markers', ..., {
|
|
|
|
|
'start_time': ('startMillis', {functools.partial(float_or_none, scale=1000)}),
|
|
|
|
|
'end_time': {lambda x: (int(x['startMillis']) + int(x['durationMillis'])) / 1000},
|
|
|
|
|
'value': ('intensityScoreNormalized', {float_or_none}),
|
|
|
|
|
})) or None
|
2023-05-26 06:24:39 -06:00
|
|
|
|
|
2021-03-14 16:41:11 -06:00
|
|
|
|
def _extract_comment(self, comment_renderer, parent=None):
|
|
|
|
|
comment_id = comment_renderer.get('commentId')
|
|
|
|
|
if not comment_id:
|
|
|
|
|
return
|
2021-07-18 22:55:07 -06:00
|
|
|
|
|
2023-06-01 02:43:32 -06:00
|
|
|
|
info = {
|
|
|
|
|
'id': comment_id,
|
|
|
|
|
'text': self._get_text(comment_renderer, 'contentText'),
|
|
|
|
|
'like_count': self._get_count(comment_renderer, 'voteCount'),
|
|
|
|
|
'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
|
|
|
|
|
'author': self._get_text(comment_renderer, 'authorText'),
|
|
|
|
|
'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
|
|
|
|
|
'parent': parent or 'root',
|
|
|
|
|
}
|
2021-07-18 22:55:07 -06:00
|
|
|
|
|
2022-09-08 23:16:46 -06:00
|
|
|
|
# Timestamp is an estimate calculated from the current time and time_text
|
|
|
|
|
time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
|
|
|
|
|
timestamp = self._parse_time_text(time_text)
|
|
|
|
|
|
2023-06-01 02:43:32 -06:00
|
|
|
|
info.update({
|
|
|
|
|
# FIXME: non-standard, but we need a way of showing that it is an estimate.
|
|
|
|
|
'_time_text': time_text,
|
|
|
|
|
'timestamp': timestamp,
|
|
|
|
|
})
|
2021-07-18 22:55:07 -06:00
|
|
|
|
|
2023-06-01 02:43:32 -06:00
|
|
|
|
info['author_url'] = urljoin(
|
|
|
|
|
'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
|
|
|
|
|
('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
|
|
|
|
|
expected_type=str, get_all=False))
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2023-06-01 02:43:32 -06:00
|
|
|
|
author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
|
|
|
|
|
if author_is_uploader is not None:
|
|
|
|
|
info['author_is_uploader'] = author_is_uploader
|
|
|
|
|
|
|
|
|
|
comment_abr = traverse_obj(
|
2023-06-22 12:08:42 -06:00
|
|
|
|
comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
|
2023-06-01 02:43:32 -06:00
|
|
|
|
if comment_abr is not None:
|
|
|
|
|
info['is_favorited'] = 'creatorHeart' in comment_abr
|
|
|
|
|
|
2023-06-08 07:28:49 -06:00
|
|
|
|
badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')])
|
|
|
|
|
if self._has_badge(badges, BadgeType.VERIFIED):
|
|
|
|
|
info['author_is_verified'] = True
|
2023-06-01 02:43:32 -06:00
|
|
|
|
|
|
|
|
|
is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
|
|
|
|
|
if is_pinned:
|
|
|
|
|
info['is_pinned'] = True
|
|
|
|
|
|
|
|
|
|
return info
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2021-12-14 21:29:48 -07:00
|
|
|
|
def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
|
|
|
|
|
|
|
|
|
|
get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
|
2021-07-11 17:18:40 -06:00
|
|
|
|
|
|
|
|
|
def extract_header(contents):
|
|
|
|
|
_continuation = None
|
|
|
|
|
for content in contents:
|
2021-12-14 21:29:48 -07:00
|
|
|
|
comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
|
2022-01-07 04:03:02 -07:00
|
|
|
|
expected_comment_count = self._get_count(
|
|
|
|
|
comments_header_renderer, 'countText', 'commentsCount')
|
2021-07-18 22:55:07 -06:00
|
|
|
|
|
2023-05-31 01:08:28 -06:00
|
|
|
|
if expected_comment_count is not None:
|
2021-12-14 21:29:48 -07:00
|
|
|
|
tracker['est_total'] = expected_comment_count
|
|
|
|
|
self.to_screen(f'Downloading ~{expected_comment_count} comments')
|
|
|
|
|
comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
|
2021-07-11 17:18:40 -06:00
|
|
|
|
|
|
|
|
|
sort_menu_item = try_get(
|
|
|
|
|
comments_header_renderer,
|
|
|
|
|
lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
|
|
|
|
|
sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
|
|
|
|
|
|
|
|
|
|
_continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
|
|
|
|
|
if not _continuation:
|
|
|
|
|
continue
|
|
|
|
|
|
2021-12-14 21:29:48 -07:00
|
|
|
|
sort_text = str_or_none(sort_menu_item.get('title'))
|
|
|
|
|
if not sort_text:
|
2021-07-11 17:18:40 -06:00
|
|
|
|
sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
|
2021-12-14 21:29:48 -07:00
|
|
|
|
self.to_screen('Sorting comments by %s' % sort_text.lower())
|
2021-07-11 17:18:40 -06:00
|
|
|
|
break
|
2021-10-12 03:50:50 -06:00
|
|
|
|
return _continuation
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2021-07-11 17:18:40 -06:00
|
|
|
|
def extract_thread(contents):
|
2021-03-14 16:41:11 -06:00
|
|
|
|
if not parent:
|
2021-12-14 21:29:48 -07:00
|
|
|
|
tracker['current_page_thread'] = 0
|
2021-03-14 16:41:11 -06:00
|
|
|
|
for content in contents:
|
2021-12-14 21:29:48 -07:00
|
|
|
|
if not parent and tracker['total_parent_comments'] >= max_parents:
|
|
|
|
|
yield
|
2021-03-14 16:41:11 -06:00
|
|
|
|
comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
|
2021-12-14 21:29:48 -07:00
|
|
|
|
comment_renderer = get_first(
|
|
|
|
|
(comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
|
|
|
|
|
expected_type=dict, default={})
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
|
|
|
|
comment = self._extract_comment(comment_renderer, parent)
|
|
|
|
|
if not comment:
|
|
|
|
|
continue
|
2023-04-06 01:44:22 -06:00
|
|
|
|
comment_id = comment['id']
|
2023-06-01 02:43:32 -06:00
|
|
|
|
if comment.get('is_pinned'):
|
2023-04-06 01:44:22 -06:00
|
|
|
|
tracker['pinned_comment_ids'].add(comment_id)
|
2023-03-01 00:56:53 -07:00
|
|
|
|
# Sometimes YouTube may break and give us infinite looping comments.
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/6290
|
2023-04-06 01:44:22 -06:00
|
|
|
|
if comment_id in tracker['seen_comment_ids']:
|
2023-06-01 02:43:32 -06:00
|
|
|
|
if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
|
2023-04-06 01:44:22 -06:00
|
|
|
|
# Pinned comments may appear a second time in newest first sort
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/6712
|
|
|
|
|
continue
|
2023-07-03 04:47:10 -06:00
|
|
|
|
self.report_warning(
|
|
|
|
|
'Detected YouTube comments looping. Stopping comment extraction '
|
|
|
|
|
f'{"for this thread" if parent else ""} as we probably cannot get any more.')
|
2023-03-01 00:56:53 -07:00
|
|
|
|
yield
|
|
|
|
|
else:
|
|
|
|
|
tracker['seen_comment_ids'].add(comment['id'])
|
2021-12-14 21:29:48 -07:00
|
|
|
|
|
|
|
|
|
tracker['running_total'] += 1
|
|
|
|
|
tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
|
2021-03-14 16:41:11 -06:00
|
|
|
|
yield comment
|
2021-12-14 21:29:48 -07:00
|
|
|
|
|
2021-03-14 16:41:11 -06:00
|
|
|
|
# Attempt to get the replies
|
|
|
|
|
comment_replies_renderer = try_get(
|
|
|
|
|
comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
|
|
|
|
|
|
|
|
|
|
if comment_replies_renderer:
|
2021-12-14 21:29:48 -07:00
|
|
|
|
tracker['current_page_thread'] += 1
|
2021-03-14 16:41:11 -06:00
|
|
|
|
comment_entries_iter = self._comment_entries(
|
2021-09-23 18:52:17 -06:00
|
|
|
|
comment_replies_renderer, ytcfg, video_id,
|
2021-12-14 21:29:48 -07:00
|
|
|
|
parent=comment.get('id'), tracker=tracker)
|
2022-04-11 09:10:28 -06:00
|
|
|
|
yield from itertools.islice(comment_entries_iter, min(
|
|
|
|
|
max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2021-12-14 21:29:48 -07:00
|
|
|
|
# Keeps track of counts across recursive calls
|
|
|
|
|
if not tracker:
|
|
|
|
|
tracker = dict(
|
|
|
|
|
running_total=0,
|
2023-05-31 01:08:28 -06:00
|
|
|
|
est_total=None,
|
2021-12-14 21:29:48 -07:00
|
|
|
|
current_page_thread=0,
|
|
|
|
|
total_parent_comments=0,
|
2023-03-01 00:56:53 -07:00
|
|
|
|
total_reply_comments=0,
|
2023-04-06 01:44:22 -06:00
|
|
|
|
seen_comment_ids=set(),
|
|
|
|
|
pinned_comment_ids=set()
|
|
|
|
|
)
|
2021-12-14 21:29:48 -07:00
|
|
|
|
|
|
|
|
|
# TODO: Deprecated
|
2021-07-11 17:18:40 -06:00
|
|
|
|
# YouTube comments have a max depth of 2
|
2021-12-14 21:29:48 -07:00
|
|
|
|
max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
|
|
|
|
|
if max_depth:
|
2022-08-30 09:28:28 -06:00
|
|
|
|
self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
|
|
|
|
|
'Set max replies in the max-comments extractor argument instead')
|
2021-07-11 17:18:40 -06:00
|
|
|
|
if max_depth == 1 and parent:
|
|
|
|
|
return
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2021-12-14 21:29:48 -07:00
|
|
|
|
max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
|
|
|
|
|
lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
|
2021-07-11 17:18:40 -06:00
|
|
|
|
|
2021-12-14 21:29:48 -07:00
|
|
|
|
continuation = self._extract_continuation(root_continuation_data)
|
2021-10-17 20:58:42 -06:00
|
|
|
|
|
2021-12-14 21:29:48 -07:00
|
|
|
|
response = None
|
2022-05-01 00:46:28 -06:00
|
|
|
|
is_forced_continuation = False
|
2021-07-11 17:18:40 -06:00
|
|
|
|
is_first_continuation = parent is None
|
2022-05-01 00:46:28 -06:00
|
|
|
|
if is_first_continuation and not continuation:
|
|
|
|
|
# Sometimes you can get comments by generating the continuation yourself,
|
|
|
|
|
# even if YouTube initially reports them being disabled - e.g. stories comments.
|
|
|
|
|
# Note: if the comment section is actually disabled, YouTube may return a response with
|
|
|
|
|
# required check_get_keys missing. So we will disable that check initially in this case.
|
|
|
|
|
continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
|
|
|
|
|
is_forced_continuation = True
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2023-05-31 01:08:28 -06:00
|
|
|
|
continuation_items_path = (
|
|
|
|
|
'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
|
2021-03-14 16:41:11 -06:00
|
|
|
|
for page_num in itertools.count(0):
|
|
|
|
|
if not continuation:
|
|
|
|
|
break
|
2021-12-14 21:29:48 -07:00
|
|
|
|
headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
|
2023-05-31 01:08:28 -06:00
|
|
|
|
comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
|
2021-07-11 17:18:40 -06:00
|
|
|
|
if page_num == 0:
|
|
|
|
|
if is_first_continuation:
|
|
|
|
|
note_prefix = 'Downloading comment section API JSON'
|
2021-03-14 16:41:11 -06:00
|
|
|
|
else:
|
2021-07-11 17:18:40 -06:00
|
|
|
|
note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
|
2021-12-14 21:29:48 -07:00
|
|
|
|
tracker['current_page_thread'], comment_prog_str)
|
2021-07-11 17:18:40 -06:00
|
|
|
|
else:
|
|
|
|
|
note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
|
|
|
|
|
' ' if parent else '', ' replies' if parent else '',
|
|
|
|
|
page_num, comment_prog_str)
|
2023-05-31 01:08:28 -06:00
|
|
|
|
|
|
|
|
|
# Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
|
|
|
|
|
# Ignore check if YouTube says the comment count is 0.
|
|
|
|
|
check_get_keys = None
|
|
|
|
|
if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
|
|
|
|
|
check_get_keys = [[*continuation_items_path, ..., (
|
|
|
|
|
'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
|
2022-11-09 23:35:22 -07:00
|
|
|
|
try:
|
|
|
|
|
response = self._extract_response(
|
|
|
|
|
item_id=None, query=continuation,
|
|
|
|
|
ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
|
2023-05-31 01:08:28 -06:00
|
|
|
|
check_get_keys=check_get_keys)
|
2022-11-09 23:35:22 -07:00
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
# Ignore incomplete data error for replies if retries didn't work.
|
|
|
|
|
# This is to allow any other parent comments and comment threads to be downloaded.
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/4669
|
2023-07-03 04:47:10 -06:00
|
|
|
|
if 'incomplete data' in str(e).lower() and parent:
|
|
|
|
|
if self.get_param('ignoreerrors') in (True, 'only_download'):
|
|
|
|
|
self.report_warning(
|
|
|
|
|
'Received incomplete data for a comment reply thread and retrying did not help. '
|
|
|
|
|
'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
|
|
|
|
|
return
|
|
|
|
|
else:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
'Incomplete data received for comment reply thread. '
|
|
|
|
|
'Pass --ignore-errors to ignore and allow rest of comments to download.',
|
|
|
|
|
expected=True)
|
|
|
|
|
raise
|
2022-05-01 00:46:28 -06:00
|
|
|
|
is_forced_continuation = False
|
2021-07-11 17:18:40 -06:00
|
|
|
|
continuation = None
|
2023-05-31 01:08:28 -06:00
|
|
|
|
for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
|
2021-12-14 21:29:48 -07:00
|
|
|
|
if is_first_continuation:
|
|
|
|
|
continuation = extract_header(continuation_items)
|
|
|
|
|
is_first_continuation = False
|
2021-07-11 17:18:40 -06:00
|
|
|
|
if continuation:
|
2021-03-14 16:41:11 -06:00
|
|
|
|
break
|
2021-12-14 21:29:48 -07:00
|
|
|
|
continue
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2021-12-14 21:29:48 -07:00
|
|
|
|
for entry in extract_thread(continuation_items):
|
|
|
|
|
if not entry:
|
|
|
|
|
return
|
|
|
|
|
yield entry
|
|
|
|
|
continuation = self._extract_continuation({'contents': continuation_items})
|
|
|
|
|
if continuation:
|
2021-07-11 17:18:40 -06:00
|
|
|
|
break
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2022-05-01 00:46:28 -06:00
|
|
|
|
message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
|
|
|
|
|
if message and not parent and tracker['running_total'] == 0:
|
|
|
|
|
self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
|
2022-11-09 20:33:03 -07:00
|
|
|
|
raise self.CommentsDisabled
|
2022-05-01 00:46:28 -06:00
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _generate_comment_continuation(video_id):
|
|
|
|
|
"""
|
|
|
|
|
Generates initial comment section continuation token from given video id
|
|
|
|
|
"""
|
|
|
|
|
token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
|
|
|
|
|
return base64.b64encode(token.encode()).decode()
|
|
|
|
|
|
2021-10-12 03:50:50 -06:00
|
|
|
|
def _get_comments(self, ytcfg, video_id, contents, webpage):
|
2021-03-14 16:41:11 -06:00
|
|
|
|
"""Entry for comment extraction"""
|
2021-07-11 17:18:40 -06:00
|
|
|
|
def _real_comment_extract(contents):
|
2021-10-17 20:58:42 -06:00
|
|
|
|
renderer = next((
|
|
|
|
|
item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
|
|
|
|
|
if item.get('sectionIdentifier') == 'comment-item-section'), None)
|
|
|
|
|
yield from self._comment_entries(renderer, ytcfg, video_id)
|
2021-09-23 18:52:17 -06:00
|
|
|
|
|
2021-10-12 03:50:50 -06:00
|
|
|
|
max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
|
|
|
|
|
return itertools.islice(_real_comment_extract(contents), 0, max_comments)
|
2021-03-14 16:41:11 -06:00
|
|
|
|
|
2021-06-29 16:07:49 -06:00
|
|
|
|
@staticmethod
|
2021-09-23 18:52:17 -06:00
|
|
|
|
def _get_checkok_params():
|
|
|
|
|
return {'contentCheckOk': True, 'racyCheckOk': True}
|
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def _generate_player_context(cls, sts=None):
|
2021-06-29 16:07:49 -06:00
|
|
|
|
context = {
|
|
|
|
|
'html5Preference': 'HTML5_PREF_WANTS',
|
|
|
|
|
}
|
|
|
|
|
if sts is not None:
|
|
|
|
|
context['signatureTimestamp'] = sts
|
|
|
|
|
return {
|
|
|
|
|
'playbackContext': {
|
|
|
|
|
'contentPlaybackContext': context
|
2021-07-20 12:01:28 -06:00
|
|
|
|
},
|
2021-09-23 18:52:17 -06:00
|
|
|
|
**cls._get_checkok_params()
|
2021-06-29 16:07:49 -06:00
|
|
|
|
}
|
|
|
|
|
|
2021-08-01 15:13:46 -06:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _is_agegated(player_response):
|
|
|
|
|
if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
|
2021-07-28 23:23:56 -06:00
|
|
|
|
return True
|
2021-08-01 15:13:46 -06:00
|
|
|
|
|
2023-02-09 15:26:26 -07:00
|
|
|
|
reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
|
2021-08-01 15:13:46 -06:00
|
|
|
|
AGE_GATE_REASONS = (
|
|
|
|
|
'confirm your age', 'age-restricted', 'inappropriate', # reason
|
|
|
|
|
'age_verification_required', 'age_check_required', # status
|
|
|
|
|
)
|
|
|
|
|
return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _is_unplayable(player_response):
|
|
|
|
|
return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
|
2021-07-28 23:23:56 -06:00
|
|
|
|
|
2022-08-28 16:59:54 -06:00
|
|
|
|
def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
|
2021-06-29 16:07:49 -06:00
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
|
|
|
|
|
syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
|
2021-09-06 01:26:41 -06:00
|
|
|
|
sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
|
2021-07-20 21:52:34 -06:00
|
|
|
|
headers = self.generate_api_headers(
|
2021-09-23 18:52:17 -06:00
|
|
|
|
ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
|
2021-05-15 08:38:47 -06:00
|
|
|
|
|
2022-05-01 00:46:28 -06:00
|
|
|
|
yt_query = {
|
|
|
|
|
'videoId': video_id,
|
|
|
|
|
}
|
2023-07-06 07:32:41 -06:00
|
|
|
|
if _split_innertube_client(client)[0] == 'android':
|
2023-07-29 00:20:42 -06:00
|
|
|
|
yt_query['params'] = 'CgIQBg=='
|
|
|
|
|
|
2023-07-29 16:50:25 -06:00
|
|
|
|
pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
|
2023-07-29 00:20:42 -06:00
|
|
|
|
if pp_arg:
|
|
|
|
|
yt_query['params'] = pp_arg
|
2022-08-28 16:59:54 -06:00
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
yt_query.update(self._generate_player_context(sts))
|
|
|
|
|
return self._extract_response(
|
|
|
|
|
item_id=video_id, ep='player', query=yt_query,
|
2021-08-07 00:45:58 -06:00
|
|
|
|
ytcfg=player_ytcfg, headers=headers, fatal=True,
|
2021-07-30 13:45:04 -06:00
|
|
|
|
default_client=client,
|
2021-07-20 21:52:34 -06:00
|
|
|
|
note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
|
|
|
|
|
) or None
|
|
|
|
|
|
|
|
|
|
def _get_requested_clients(self, url, smuggled_data):
|
2021-07-25 15:55:53 -06:00
|
|
|
|
requested_clients = []
|
2023-06-21 12:50:04 -06:00
|
|
|
|
default = ['ios', 'android', 'web']
|
2021-07-30 13:45:04 -06:00
|
|
|
|
allowed_clients = sorted(
|
2022-04-11 09:10:28 -06:00
|
|
|
|
(client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
|
2021-07-30 13:45:04 -06:00
|
|
|
|
key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
|
2021-07-25 15:55:53 -06:00
|
|
|
|
for client in self._configuration_arg('player_client'):
|
|
|
|
|
if client in allowed_clients:
|
|
|
|
|
requested_clients.append(client)
|
2021-11-15 18:22:01 -07:00
|
|
|
|
elif client == 'default':
|
|
|
|
|
requested_clients.extend(default)
|
2021-07-25 15:55:53 -06:00
|
|
|
|
elif client == 'all':
|
|
|
|
|
requested_clients.extend(allowed_clients)
|
|
|
|
|
else:
|
|
|
|
|
self.report_warning(f'Skipping unsupported client {client}')
|
2021-07-20 21:52:34 -06:00
|
|
|
|
if not requested_clients:
|
2021-11-15 18:22:01 -07:00
|
|
|
|
requested_clients = default
|
2015-07-25 09:30:34 -06:00
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
if smuggled_data.get('is_music_url') or self.is_music_url(url):
|
|
|
|
|
requested_clients.extend(
|
2021-08-01 15:13:46 -06:00
|
|
|
|
f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
|
2018-11-02 17:26:16 -06:00
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
return orderedSet(requested_clients)
|
2015-07-25 09:30:34 -06:00
|
|
|
|
|
2022-08-28 16:59:54 -06:00
|
|
|
|
def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
|
2021-07-20 21:52:34 -06:00
|
|
|
|
initial_pr = None
|
|
|
|
|
if webpage:
|
2022-06-03 09:32:31 -06:00
|
|
|
|
initial_pr = self._search_json(
|
|
|
|
|
self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
|
2020-04-09 09:42:43 -06:00
|
|
|
|
|
2022-03-24 17:30:41 -06:00
|
|
|
|
all_clients = set(clients)
|
2021-07-27 03:40:44 -06:00
|
|
|
|
clients = clients[::-1]
|
2021-09-06 01:26:41 -06:00
|
|
|
|
prs = []
|
2021-08-01 15:13:46 -06:00
|
|
|
|
|
2022-03-24 17:30:41 -06:00
|
|
|
|
def append_client(*client_names):
|
2022-03-29 04:05:31 -06:00
|
|
|
|
""" Append the first client name that exists but not already used """
|
2022-03-24 17:30:41 -06:00
|
|
|
|
for client_name in client_names:
|
2022-03-29 04:05:31 -06:00
|
|
|
|
actual_client = _split_innertube_client(client_name)[0]
|
|
|
|
|
if actual_client in INNERTUBE_CLIENTS:
|
|
|
|
|
if actual_client not in all_clients:
|
2022-03-24 17:30:41 -06:00
|
|
|
|
clients.append(client_name)
|
2022-03-29 04:05:31 -06:00
|
|
|
|
all_clients.add(actual_client)
|
|
|
|
|
return
|
2021-08-01 15:13:46 -06:00
|
|
|
|
|
2021-08-07 00:45:58 -06:00
|
|
|
|
# Android player_response does not have microFormats which are needed for
|
|
|
|
|
# extraction of some data. So we return the initial_pr with formats
|
|
|
|
|
# stripped out even if not requested by the user
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/501
|
|
|
|
|
if initial_pr:
|
|
|
|
|
pr = dict(initial_pr)
|
|
|
|
|
pr['streamingData'] = None
|
2021-09-06 01:26:41 -06:00
|
|
|
|
prs.append(pr)
|
2021-08-07 00:45:58 -06:00
|
|
|
|
|
|
|
|
|
last_error = None
|
2021-09-06 01:26:41 -06:00
|
|
|
|
tried_iframe_fallback = False
|
|
|
|
|
player_url = None
|
2021-07-27 03:40:44 -06:00
|
|
|
|
while clients:
|
2022-03-29 04:05:31 -06:00
|
|
|
|
client, base_client, variant = _split_innertube_client(clients.pop())
|
2021-07-20 21:52:34 -06:00
|
|
|
|
player_ytcfg = master_ytcfg if client == 'web' else {}
|
2022-04-09 13:30:21 -06:00
|
|
|
|
if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
|
|
|
|
|
player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
|
2021-07-27 03:40:44 -06:00
|
|
|
|
|
2021-09-06 01:26:41 -06:00
|
|
|
|
player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
|
|
|
|
|
require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
|
|
|
|
|
if 'js' in self._configuration_arg('player_skip'):
|
|
|
|
|
require_js_player = False
|
|
|
|
|
player_url = None
|
|
|
|
|
|
|
|
|
|
if not player_url and not tried_iframe_fallback and require_js_player:
|
|
|
|
|
player_url = self._download_player_url(video_id)
|
|
|
|
|
tried_iframe_fallback = True
|
|
|
|
|
|
2021-08-07 00:45:58 -06:00
|
|
|
|
try:
|
|
|
|
|
pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
|
2022-08-28 16:59:54 -06:00
|
|
|
|
client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
|
2021-08-07 00:45:58 -06:00
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
if last_error:
|
|
|
|
|
self.report_warning(last_error)
|
|
|
|
|
last_error = e
|
|
|
|
|
continue
|
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
if pr:
|
2022-08-07 07:43:20 -06:00
|
|
|
|
# YouTube may return a different video player response than expected.
|
|
|
|
|
# See: https://github.com/TeamNewPipe/NewPipe/issues/8713
|
|
|
|
|
pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
|
|
|
|
|
if pr_video_id and pr_video_id != video_id:
|
|
|
|
|
self.report_warning(
|
2022-08-07 18:01:57 -06:00
|
|
|
|
f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
|
2022-08-07 07:43:20 -06:00
|
|
|
|
else:
|
2023-03-11 10:03:23 -07:00
|
|
|
|
# Save client name for introspection later
|
|
|
|
|
name = short_client_name(client)
|
|
|
|
|
sd = traverse_obj(pr, ('streamingData', {dict})) or {}
|
|
|
|
|
sd[STREAMING_DATA_CLIENT_NAME] = name
|
|
|
|
|
for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
|
|
|
|
|
f[STREAMING_DATA_CLIENT_NAME] = name
|
2022-08-07 07:43:20 -06:00
|
|
|
|
prs.append(pr)
|
2021-07-27 03:40:44 -06:00
|
|
|
|
|
2021-08-01 15:13:46 -06:00
|
|
|
|
# creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
|
2022-03-29 04:05:31 -06:00
|
|
|
|
if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
|
|
|
|
|
append_client(f'{base_client}_creator')
|
2021-08-01 15:13:46 -06:00
|
|
|
|
elif self._is_agegated(pr):
|
2022-03-29 04:05:31 -06:00
|
|
|
|
if variant == 'tv_embedded':
|
|
|
|
|
append_client(f'{base_client}_embedded')
|
|
|
|
|
elif not variant:
|
|
|
|
|
append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
|
2021-07-27 03:40:44 -06:00
|
|
|
|
|
2021-08-07 00:45:58 -06:00
|
|
|
|
if last_error:
|
2021-09-06 01:26:41 -06:00
|
|
|
|
if not len(prs):
|
2021-08-07 00:45:58 -06:00
|
|
|
|
raise last_error
|
|
|
|
|
self.report_warning(last_error)
|
2021-09-06 01:26:41 -06:00
|
|
|
|
return prs, player_url
|
2021-07-20 21:52:34 -06:00
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
def _needs_live_processing(self, live_status, duration):
|
|
|
|
|
if (live_status == 'is_live' and self.get_param('live_from_start')
|
2023-06-25 19:55:47 -06:00
|
|
|
|
or live_status == 'post_live' and (duration or 0) > 2 * 3600):
|
2022-10-03 20:48:31 -06:00
|
|
|
|
return live_status
|
|
|
|
|
|
|
|
|
|
def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
|
2023-03-12 03:16:09 -06:00
|
|
|
|
CHUNK_SIZE = 10 << 20
|
2022-11-14 16:53:32 -07:00
|
|
|
|
itags, stream_ids = collections.defaultdict(set), []
|
2022-08-20 13:26:27 -06:00
|
|
|
|
itag_qualities, res_qualities = {}, {0: None}
|
2021-05-17 13:41:57 -06:00
|
|
|
|
q = qualities([
|
2021-07-25 16:03:42 -06:00
|
|
|
|
# Normally tiny is the smallest video-only formats. But
|
|
|
|
|
# audio-only formats with unknown quality may get tagged as tiny
|
|
|
|
|
'tiny',
|
|
|
|
|
'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
|
2021-05-17 13:41:57 -06:00
|
|
|
|
'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
|
|
|
|
|
])
|
2023-02-09 15:26:26 -07:00
|
|
|
|
streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
|
2023-06-25 08:40:00 -06:00
|
|
|
|
format_types = self._configuration_arg('formats')
|
|
|
|
|
all_formats = 'duplicate' in format_types
|
|
|
|
|
if self._configuration_arg('include_duplicate_formats'):
|
|
|
|
|
all_formats = True
|
|
|
|
|
self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
|
|
|
|
|
'Use formats=duplicate extractor argument instead')
|
2021-05-15 08:38:47 -06:00
|
|
|
|
|
2023-03-12 03:16:09 -06:00
|
|
|
|
def build_fragments(f):
|
|
|
|
|
return LazyList({
|
|
|
|
|
'url': update_url_query(f['url'], {
|
|
|
|
|
'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
|
|
|
|
|
})
|
|
|
|
|
} for range_start in range(0, f['filesize'], CHUNK_SIZE))
|
|
|
|
|
|
2021-02-04 07:37:17 -07:00
|
|
|
|
for fmt in streaming_formats:
|
2022-03-26 23:28:26 -06:00
|
|
|
|
if fmt.get('targetDurationSec'):
|
2021-02-04 07:37:17 -07:00
|
|
|
|
continue
|
2020-08-04 18:30:10 -06:00
|
|
|
|
|
2021-02-10 14:22:55 -07:00
|
|
|
|
itag = str_or_none(fmt.get('itag'))
|
2021-05-15 08:38:47 -06:00
|
|
|
|
audio_track = fmt.get('audioTrack') or {}
|
2022-12-30 03:02:33 -07:00
|
|
|
|
stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
|
2023-03-09 10:43:02 -07:00
|
|
|
|
if not all_formats:
|
|
|
|
|
if stream_id in stream_ids:
|
|
|
|
|
continue
|
2021-05-15 08:38:47 -06:00
|
|
|
|
|
2021-02-10 14:22:55 -07:00
|
|
|
|
quality = fmt.get('quality')
|
2021-07-25 16:03:42 -06:00
|
|
|
|
height = int_or_none(fmt.get('height'))
|
2021-05-17 13:41:57 -06:00
|
|
|
|
if quality == 'tiny' or not quality:
|
|
|
|
|
quality = fmt.get('audioQuality', '').lower() or quality
|
2021-07-25 16:03:42 -06:00
|
|
|
|
# The 3gp format (17) in android client has a quality of "small",
|
|
|
|
|
# but is actually worse than other formats
|
|
|
|
|
if itag == '17':
|
|
|
|
|
quality = 'tiny'
|
|
|
|
|
if quality:
|
|
|
|
|
if itag:
|
|
|
|
|
itag_qualities[itag] = quality
|
|
|
|
|
if height:
|
|
|
|
|
res_qualities[height] = quality
|
2021-02-10 14:22:55 -07:00
|
|
|
|
# FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
|
|
|
|
|
# (adding `&sq=0` to the URL) and parsing emsg box to determine the
|
|
|
|
|
# number of fragment that would subsequently requested with (`&sq=N`)
|
|
|
|
|
if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
|
|
|
|
|
continue
|
|
|
|
|
|
2021-02-04 07:37:17 -07:00
|
|
|
|
fmt_url = fmt.get('url')
|
|
|
|
|
if not fmt_url:
|
2022-06-24 04:54:43 -06:00
|
|
|
|
sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
|
2021-02-04 07:37:17 -07:00
|
|
|
|
fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
|
|
|
|
|
encrypted_sig = try_get(sc, lambda x: x['s'][0])
|
2022-05-28 12:14:36 -06:00
|
|
|
|
if not all((sc, fmt_url, player_url, encrypted_sig)):
|
2021-02-04 07:37:17 -07:00
|
|
|
|
continue
|
2022-05-28 12:14:36 -06:00
|
|
|
|
try:
|
|
|
|
|
fmt_url += '&%s=%s' % (
|
|
|
|
|
traverse_obj(sc, ('sp', -1)) or 'signature',
|
|
|
|
|
self._decrypt_signature(encrypted_sig, video_id, player_url)
|
|
|
|
|
)
|
|
|
|
|
except ExtractorError as e:
|
2022-08-18 09:57:41 -06:00
|
|
|
|
self.report_warning('Signature extraction failed: Some formats may be missing',
|
|
|
|
|
video_id=video_id, only_once=True)
|
2022-05-28 12:14:36 -06:00
|
|
|
|
self.write_debug(e, only_once=True)
|
2014-08-01 22:35:18 -06:00
|
|
|
|
continue
|
2021-02-04 07:37:17 -07:00
|
|
|
|
|
2021-10-30 22:23:58 -06:00
|
|
|
|
query = parse_qs(fmt_url)
|
|
|
|
|
throttled = False
|
2021-11-28 05:31:46 -07:00
|
|
|
|
if query.get('n'):
|
2021-10-30 22:23:58 -06:00
|
|
|
|
try:
|
2022-08-18 09:57:41 -06:00
|
|
|
|
decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
|
2021-10-30 22:23:58 -06:00
|
|
|
|
fmt_url = update_url_query(fmt_url, {
|
2022-08-18 09:57:41 -06:00
|
|
|
|
'n': decrypt_nsig(query['n'][0], video_id, player_url)
|
|
|
|
|
})
|
2021-10-30 22:23:58 -06:00
|
|
|
|
except ExtractorError as e:
|
2022-08-18 10:05:18 -06:00
|
|
|
|
phantomjs_hint = ''
|
|
|
|
|
if isinstance(e, JSInterpreter.Exception):
|
2022-08-30 05:53:59 -06:00
|
|
|
|
phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
|
|
|
|
|
f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
|
2022-09-07 06:05:45 -06:00
|
|
|
|
if player_url:
|
|
|
|
|
self.report_warning(
|
|
|
|
|
f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
|
|
|
|
|
f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
|
|
|
|
|
self.write_debug(e, only_once=True)
|
|
|
|
|
else:
|
|
|
|
|
self.report_warning(
|
|
|
|
|
'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
|
|
|
|
|
video_id=video_id, only_once=True)
|
2021-10-30 22:23:58 -06:00
|
|
|
|
throttled = True
|
|
|
|
|
|
2022-02-18 07:11:37 -07:00
|
|
|
|
tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
|
2022-02-11 13:43:17 -07:00
|
|
|
|
language_preference = (
|
|
|
|
|
10 if audio_track.get('audioIsDefault') and 10
|
|
|
|
|
else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
|
|
|
|
|
else -1)
|
2022-02-18 07:11:37 -07:00
|
|
|
|
# Some formats may have much smaller duration than others (possibly damaged during encoding)
|
2022-08-14 06:04:13 -06:00
|
|
|
|
# E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
|
2022-03-16 08:16:19 -06:00
|
|
|
|
# Make sure to avoid false positives with small duration differences.
|
2022-08-14 06:04:13 -06:00
|
|
|
|
# E.g. __2ABJjxzNo, ySuUZEjARPY
|
2022-03-16 08:16:19 -06:00
|
|
|
|
is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
|
2022-03-04 07:08:55 -07:00
|
|
|
|
if is_damaged:
|
2022-05-09 05:54:28 -06:00
|
|
|
|
self.report_warning(
|
|
|
|
|
f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
|
2023-03-11 10:03:23 -07:00
|
|
|
|
|
|
|
|
|
client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
|
2023-06-19 02:39:26 -06:00
|
|
|
|
name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
|
2023-06-20 17:41:14 -06:00
|
|
|
|
fps = int_or_none(fmt.get('fps')) or 0
|
2021-02-04 07:37:17 -07:00
|
|
|
|
dct = {
|
|
|
|
|
'asr': int_or_none(fmt.get('audioSampleRate')),
|
|
|
|
|
'filesize': int_or_none(fmt.get('contentLength')),
|
2022-12-30 03:02:33 -07:00
|
|
|
|
'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
|
2021-11-05 19:05:24 -06:00
|
|
|
|
'format_note': join_nonempty(
|
2023-03-04 10:10:08 -07:00
|
|
|
|
join_nonempty(audio_track.get('displayName'),
|
|
|
|
|
language_preference > 0 and ' (default)', delim=''),
|
2023-06-19 02:39:26 -06:00
|
|
|
|
name, fmt.get('isDrc') and 'DRC',
|
2022-08-07 14:06:11 -06:00
|
|
|
|
try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
|
|
|
|
|
try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
|
2023-03-11 10:03:23 -07:00
|
|
|
|
throttled and 'THROTTLED', is_damaged and 'DAMAGED',
|
2023-03-09 10:43:02 -07:00
|
|
|
|
(self.get_param('verbose') or all_formats) and client_name,
|
2023-03-11 10:03:23 -07:00
|
|
|
|
delim=', '),
|
2022-05-06 20:33:41 -06:00
|
|
|
|
# Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
|
2023-06-19 02:39:26 -06:00
|
|
|
|
'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
|
|
|
|
|
+ (100 if 'Premium' in name else 0)),
|
2023-06-20 17:41:14 -06:00
|
|
|
|
'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
|
2022-08-07 14:06:11 -06:00
|
|
|
|
'audio_channels': fmt.get('audioChannels'),
|
2021-07-25 16:03:42 -06:00
|
|
|
|
'height': height,
|
2022-12-30 03:02:33 -07:00
|
|
|
|
'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
|
2022-03-26 23:28:26 -06:00
|
|
|
|
'has_drm': bool(fmt.get('drmFamilies')),
|
2021-02-10 14:22:55 -07:00
|
|
|
|
'tbr': tbr,
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'url': fmt_url,
|
2021-07-25 16:03:42 -06:00
|
|
|
|
'width': int_or_none(fmt.get('width')),
|
2022-02-11 13:43:17 -07:00
|
|
|
|
'language': join_nonempty(audio_track.get('id', '').split('.')[0],
|
2023-01-02 07:09:03 -07:00
|
|
|
|
'desc' if language_preference < -1 else '') or None,
|
2022-02-11 13:43:17 -07:00
|
|
|
|
'language_preference': language_preference,
|
2022-03-08 10:32:25 -07:00
|
|
|
|
# Strictly de-prioritize damaged and 3gp formats
|
|
|
|
|
'preference': -10 if is_damaged else -2 if itag == '17' else None,
|
2021-02-04 07:37:17 -07:00
|
|
|
|
}
|
2021-07-08 10:11:08 -06:00
|
|
|
|
mime_mobj = re.match(
|
|
|
|
|
r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
|
|
|
|
|
if mime_mobj:
|
|
|
|
|
dct['ext'] = mimetype2ext(mime_mobj.group(1))
|
|
|
|
|
dct.update(parse_codecs(mime_mobj.group(2)))
|
2023-03-09 10:43:02 -07:00
|
|
|
|
if itag:
|
|
|
|
|
itags[itag].add(('https', dct.get('language')))
|
|
|
|
|
stream_ids.append(stream_id)
|
2023-03-09 09:39:23 -07:00
|
|
|
|
single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
|
|
|
|
|
if single_stream and dct.get('ext'):
|
|
|
|
|
dct['container'] = dct['ext'] + '_dash'
|
2023-03-09 10:43:02 -07:00
|
|
|
|
|
2023-06-25 08:40:00 -06:00
|
|
|
|
if (all_formats or 'dashy' in format_types) and dct['filesize']:
|
2023-03-09 10:43:02 -07:00
|
|
|
|
yield {
|
|
|
|
|
**dct,
|
|
|
|
|
'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
|
2023-02-28 10:33:44 -07:00
|
|
|
|
'protocol': 'http_dash_segments',
|
2023-03-12 03:16:09 -06:00
|
|
|
|
'fragments': build_fragments(dct),
|
2023-03-09 10:43:02 -07:00
|
|
|
|
}
|
2023-06-25 08:40:00 -06:00
|
|
|
|
if all_formats or 'dashy' not in format_types:
|
|
|
|
|
dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
|
|
|
|
|
yield dct
|
2021-02-04 07:37:17 -07:00
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
needs_live_processing = self._needs_live_processing(live_status, duration)
|
2023-06-25 08:40:00 -06:00
|
|
|
|
skip_bad_formats = 'incomplete' not in format_types
|
|
|
|
|
if self._configuration_arg('include_incomplete_formats'):
|
|
|
|
|
skip_bad_formats = False
|
|
|
|
|
self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
|
|
|
|
|
'Use formats=incomplete extractor argument instead')
|
2022-10-03 20:48:31 -06:00
|
|
|
|
|
|
|
|
|
skip_manifests = set(self._configuration_arg('skip'))
|
|
|
|
|
if (not self.get_param('youtube_include_hls_manifest', True)
|
|
|
|
|
or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
|
|
|
|
|
or needs_live_processing and skip_bad_formats):
|
|
|
|
|
skip_manifests.add('hls')
|
|
|
|
|
|
2022-05-09 05:54:28 -06:00
|
|
|
|
if not self.get_param('youtube_include_dash_manifest', True):
|
2022-10-03 20:48:31 -06:00
|
|
|
|
skip_manifests.add('dash')
|
|
|
|
|
if self._configuration_arg('include_live_dash'):
|
|
|
|
|
self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
|
2023-06-25 08:40:00 -06:00
|
|
|
|
'Use formats=incomplete extractor argument instead')
|
2022-10-03 20:48:31 -06:00
|
|
|
|
elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
|
|
|
|
|
skip_manifests.add('dash')
|
2021-06-25 08:05:41 -06:00
|
|
|
|
|
2023-03-11 10:03:23 -07:00
|
|
|
|
def process_manifest_format(f, proto, client_name, itag):
|
2022-11-14 16:53:32 -07:00
|
|
|
|
key = (proto, f.get('language'))
|
2023-03-09 10:43:02 -07:00
|
|
|
|
if not all_formats and key in itags[itag]:
|
2022-11-14 16:53:32 -07:00
|
|
|
|
return False
|
|
|
|
|
itags[itag].add(key)
|
|
|
|
|
|
2023-03-09 10:43:02 -07:00
|
|
|
|
if itag and all_formats:
|
|
|
|
|
f['format_id'] = f'{itag}-{proto}'
|
|
|
|
|
elif any(p != proto for p, _ in itags[itag]):
|
2022-11-14 16:53:32 -07:00
|
|
|
|
f['format_id'] = f'{itag}-{proto}'
|
|
|
|
|
elif itag:
|
2021-10-31 01:56:44 -06:00
|
|
|
|
f['format_id'] = itag
|
|
|
|
|
|
2023-06-23 06:46:07 -06:00
|
|
|
|
if f.get('source_preference') is None:
|
|
|
|
|
f['source_preference'] = -1
|
|
|
|
|
|
2023-06-21 12:50:04 -06:00
|
|
|
|
if itag in ('616', '235'):
|
|
|
|
|
f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
|
2023-06-23 06:46:07 -06:00
|
|
|
|
f['source_preference'] += 100
|
2023-06-21 12:50:04 -06:00
|
|
|
|
|
2022-08-20 13:26:27 -06:00
|
|
|
|
f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
|
2022-08-15 02:28:39 -06:00
|
|
|
|
if f['quality'] == -1 and f.get('height'):
|
|
|
|
|
f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
|
2023-06-20 21:51:20 -06:00
|
|
|
|
if self.get_param('verbose') or all_formats:
|
2023-03-11 10:03:23 -07:00
|
|
|
|
f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
|
2023-06-20 17:41:14 -06:00
|
|
|
|
if f.get('fps') and f['fps'] <= 1:
|
|
|
|
|
del f['fps']
|
2023-06-23 06:46:07 -06:00
|
|
|
|
|
|
|
|
|
if proto == 'hls' and f.get('has_drm'):
|
|
|
|
|
f['has_drm'] = 'maybe'
|
|
|
|
|
f['source_preference'] -= 5
|
2021-10-31 01:56:44 -06:00
|
|
|
|
return True
|
2021-07-25 16:03:42 -06:00
|
|
|
|
|
2022-06-21 16:16:54 -06:00
|
|
|
|
subtitles = {}
|
2021-07-20 21:52:34 -06:00
|
|
|
|
for sd in streaming_data:
|
2023-03-11 10:03:23 -07:00
|
|
|
|
client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
|
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
|
2021-05-15 08:38:47 -06:00
|
|
|
|
if hls_manifest_url:
|
2022-10-03 20:48:31 -06:00
|
|
|
|
fmts, subs = self._extract_m3u8_formats_and_subtitles(
|
|
|
|
|
hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
|
2022-06-21 16:16:54 -06:00
|
|
|
|
subtitles = self._merge_subtitles(subs, subtitles)
|
|
|
|
|
for f in fmts:
|
2023-03-11 10:03:23 -07:00
|
|
|
|
if process_manifest_format(f, 'hls', client_name, self._search_regex(
|
2021-10-31 01:56:44 -06:00
|
|
|
|
r'/itag/(\d+)', f['url'], 'itag', default=None)):
|
|
|
|
|
yield f
|
2021-02-04 07:37:17 -07:00
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
|
2021-06-25 08:05:41 -06:00
|
|
|
|
if dash_manifest_url:
|
2022-06-21 16:16:54 -06:00
|
|
|
|
formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
|
|
|
|
|
subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
|
|
|
|
|
for f in formats:
|
2023-03-11 10:03:23 -07:00
|
|
|
|
if process_manifest_format(f, 'dash', client_name, f['format_id']):
|
2021-10-31 01:56:44 -06:00
|
|
|
|
f['filesize'] = int_or_none(self._search_regex(
|
|
|
|
|
r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
|
2022-10-03 20:48:31 -06:00
|
|
|
|
if needs_live_processing:
|
2021-12-19 23:06:46 -07:00
|
|
|
|
f['is_from_start'] = True
|
|
|
|
|
|
2021-10-31 01:56:44 -06:00
|
|
|
|
yield f
|
2022-06-21 16:16:54 -06:00
|
|
|
|
yield subtitles
|
2021-07-20 21:52:34 -06:00
|
|
|
|
|
2021-11-16 12:56:23 -07:00
|
|
|
|
def _extract_storyboard(self, player_responses, duration):
|
|
|
|
|
spec = get_first(
|
|
|
|
|
player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
|
2022-01-19 05:39:52 -07:00
|
|
|
|
base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
|
|
|
|
|
if not base_url:
|
2021-11-16 12:56:23 -07:00
|
|
|
|
return
|
|
|
|
|
L = len(spec) - 1
|
|
|
|
|
for i, args in enumerate(spec):
|
|
|
|
|
args = args.split('#')
|
|
|
|
|
counts = list(map(int_or_none, args[:5]))
|
|
|
|
|
if len(args) != 8 or not all(counts):
|
|
|
|
|
self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
|
|
|
|
|
continue
|
|
|
|
|
width, height, frame_count, cols, rows = counts
|
|
|
|
|
N, sigh = args[6:]
|
|
|
|
|
|
|
|
|
|
url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
|
|
|
|
|
fragment_count = frame_count / (cols * rows)
|
|
|
|
|
fragment_duration = duration / fragment_count
|
|
|
|
|
yield {
|
|
|
|
|
'format_id': f'sb{i}',
|
|
|
|
|
'format_note': 'storyboard',
|
|
|
|
|
'ext': 'mhtml',
|
|
|
|
|
'protocol': 'mhtml',
|
|
|
|
|
'acodec': 'none',
|
|
|
|
|
'vcodec': 'none',
|
|
|
|
|
'url': url,
|
|
|
|
|
'width': width,
|
|
|
|
|
'height': height,
|
2022-07-12 09:16:45 -06:00
|
|
|
|
'fps': frame_count / duration,
|
|
|
|
|
'rows': rows,
|
|
|
|
|
'columns': cols,
|
2021-11-16 12:56:23 -07:00
|
|
|
|
'fragments': [{
|
2022-03-13 16:03:40 -06:00
|
|
|
|
'url': url.replace('$M', str(j)),
|
2021-11-16 12:56:23 -07:00
|
|
|
|
'duration': min(fragment_duration, duration - (j * fragment_duration)),
|
|
|
|
|
} for j in range(math.ceil(fragment_count))],
|
|
|
|
|
}
|
|
|
|
|
|
2021-12-19 23:06:46 -07:00
|
|
|
|
def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
|
2021-09-06 01:26:41 -06:00
|
|
|
|
webpage = None
|
|
|
|
|
if 'webpage' not in self._configuration_arg('player_skip'):
|
2022-08-28 16:59:54 -06:00
|
|
|
|
query = {'bpctr': '9999999999', 'has_verified': '1'}
|
2023-07-29 16:50:25 -06:00
|
|
|
|
pp = self._configuration_arg('player_params', [None], casesense=True)[0]
|
2023-07-29 00:20:42 -06:00
|
|
|
|
if pp:
|
|
|
|
|
query['pp'] = pp
|
2021-09-06 01:26:41 -06:00
|
|
|
|
webpage = self._download_webpage(
|
2022-08-28 16:59:54 -06:00
|
|
|
|
webpage_url, video_id, fatal=False, query=query)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
|
|
|
|
|
master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
|
|
|
|
|
|
2021-09-06 01:26:41 -06:00
|
|
|
|
player_responses, player_url = self._extract_player_responses(
|
2021-07-20 21:52:34 -06:00
|
|
|
|
self._get_requested_clients(url, smuggled_data),
|
2022-08-28 16:59:54 -06:00
|
|
|
|
video_id, webpage, master_ytcfg, smuggled_data)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
|
2021-12-19 23:06:46 -07:00
|
|
|
|
return webpage, master_ytcfg, player_responses, player_url
|
|
|
|
|
|
2022-03-16 08:16:19 -06:00
|
|
|
|
def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
|
2021-12-19 23:06:46 -07:00
|
|
|
|
live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
|
|
|
|
|
is_live = get_first(video_details, 'isLive')
|
|
|
|
|
if is_live is None:
|
|
|
|
|
is_live = get_first(live_broadcast_details, 'isLiveNow')
|
2022-10-03 20:48:31 -06:00
|
|
|
|
live_content = get_first(video_details, 'isLiveContent')
|
|
|
|
|
is_upcoming = get_first(video_details, 'isUpcoming')
|
|
|
|
|
post_live = get_first(video_details, 'isPostLiveDvr')
|
|
|
|
|
live_status = ('post_live' if post_live
|
|
|
|
|
else 'is_live' if is_live
|
|
|
|
|
else 'is_upcoming' if is_upcoming
|
2022-10-13 20:11:53 -06:00
|
|
|
|
else 'was_live' if live_content
|
|
|
|
|
else 'not_live' if False in (is_live, live_content)
|
|
|
|
|
else None)
|
2023-02-09 15:26:26 -07:00
|
|
|
|
streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
|
2022-10-03 20:48:31 -06:00
|
|
|
|
*formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
|
2023-06-23 06:46:07 -06:00
|
|
|
|
if all(f.get('has_drm') for f in formats):
|
|
|
|
|
# If there are no formats that definitely don't have DRM, all have DRM
|
|
|
|
|
for f in formats:
|
|
|
|
|
f['has_drm'] = True
|
2021-12-19 23:06:46 -07:00
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
return live_broadcast_details, live_status, streaming_data, formats, subtitles
|
2021-12-19 23:06:46 -07:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
url, smuggled_data = unsmuggle_url(url, {})
|
|
|
|
|
video_id = self._match_id(url)
|
|
|
|
|
|
|
|
|
|
base_url = self.http_scheme() + '//www.youtube.com/'
|
|
|
|
|
webpage_url = base_url + 'watch?v=' + video_id
|
|
|
|
|
|
|
|
|
|
webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
|
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
playability_statuses = traverse_obj(
|
2023-02-09 15:26:26 -07:00
|
|
|
|
player_responses, (..., 'playabilityStatus'), expected_type=dict)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
|
|
|
|
|
trailer_video_id = get_first(
|
|
|
|
|
playability_statuses,
|
|
|
|
|
('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
|
|
|
|
|
expected_type=str)
|
|
|
|
|
if trailer_video_id:
|
|
|
|
|
return self.url_result(
|
|
|
|
|
trailer_video_id, self.ie_key(), trailer_video_id)
|
|
|
|
|
|
|
|
|
|
search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
|
|
|
|
|
if webpage else (lambda x: None))
|
|
|
|
|
|
2023-02-09 15:26:26 -07:00
|
|
|
|
video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
microformats = traverse_obj(
|
|
|
|
|
player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
|
2023-02-09 15:26:26 -07:00
|
|
|
|
expected_type=dict)
|
2022-09-08 23:16:46 -06:00
|
|
|
|
|
|
|
|
|
translated_title = self._get_text(microformats, (..., 'title'))
|
|
|
|
|
video_title = (self._preferred_lang and translated_title
|
|
|
|
|
or get_first(video_details, 'title') # primary
|
|
|
|
|
or translated_title
|
|
|
|
|
or search_meta(['og:title', 'twitter:title', 'title']))
|
|
|
|
|
translated_description = self._get_text(microformats, (..., 'description'))
|
|
|
|
|
original_description = get_first(video_details, 'shortDescription')
|
|
|
|
|
video_description = (
|
|
|
|
|
self._preferred_lang and translated_description
|
|
|
|
|
# If original description is blank, it will be an empty string.
|
|
|
|
|
# Do not prefer translated description in this case.
|
|
|
|
|
or original_description if original_description is not None else translated_description)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
|
2021-11-03 04:57:34 -06:00
|
|
|
|
multifeed_metadata_list = get_first(
|
|
|
|
|
player_responses,
|
|
|
|
|
('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
|
|
|
|
|
expected_type=str)
|
|
|
|
|
if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
|
|
|
|
|
if self.get_param('noplaylist'):
|
2021-07-20 21:52:34 -06:00
|
|
|
|
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
|
2021-11-03 04:57:34 -06:00
|
|
|
|
else:
|
|
|
|
|
entries = []
|
|
|
|
|
feed_ids = []
|
|
|
|
|
for feed in multifeed_metadata_list.split(','):
|
|
|
|
|
# Unquote should take place before split on comma (,) since textual
|
|
|
|
|
# fields may contain comma as well (see
|
|
|
|
|
# https://github.com/ytdl-org/youtube-dl/issues/8536)
|
2022-06-24 04:54:43 -06:00
|
|
|
|
feed_data = urllib.parse.parse_qs(
|
2022-06-24 02:10:17 -06:00
|
|
|
|
urllib.parse.unquote_plus(feed))
|
2021-11-03 04:57:34 -06:00
|
|
|
|
|
|
|
|
|
def feed_entry(name):
|
|
|
|
|
return try_get(
|
2022-06-24 04:54:43 -06:00
|
|
|
|
feed_data, lambda x: x[name][0], str)
|
2021-11-03 04:57:34 -06:00
|
|
|
|
|
|
|
|
|
feed_id = feed_entry('id')
|
|
|
|
|
if not feed_id:
|
|
|
|
|
continue
|
|
|
|
|
feed_title = feed_entry('title')
|
|
|
|
|
title = video_title
|
|
|
|
|
if feed_title:
|
|
|
|
|
title += ' (%s)' % feed_title
|
|
|
|
|
entries.append({
|
|
|
|
|
'_type': 'url_transparent',
|
|
|
|
|
'ie_key': 'Youtube',
|
|
|
|
|
'url': smuggle_url(
|
|
|
|
|
'%swatch?v=%s' % (base_url, feed_data['id'][0]),
|
|
|
|
|
{'force_singlefeed': True}),
|
|
|
|
|
'title': title,
|
|
|
|
|
})
|
|
|
|
|
feed_ids.append(feed_id)
|
|
|
|
|
self.to_screen(
|
|
|
|
|
'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
|
|
|
|
|
% (', '.join(feed_ids), video_id))
|
|
|
|
|
return self.playlist_result(
|
|
|
|
|
entries, video_id, video_title, video_description)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
|
2022-10-28 12:30:33 -06:00
|
|
|
|
duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
|
|
|
|
|
or int_or_none(get_first(microformats, 'lengthSeconds'))
|
|
|
|
|
or parse_duration(search_meta('duration')) or None)
|
2022-03-16 08:16:19 -06:00
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
|
|
|
|
|
self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
|
|
|
|
|
if live_status == 'post_live':
|
|
|
|
|
self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
|
2019-09-11 09:44:47 -06:00
|
|
|
|
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if not formats:
|
2021-07-20 21:52:34 -06:00
|
|
|
|
if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
|
2021-08-22 14:08:38 -06:00
|
|
|
|
self.report_drm(video_id)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
pemr = get_first(
|
|
|
|
|
playability_statuses,
|
|
|
|
|
('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
|
|
|
|
|
reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
|
|
|
|
|
subreason = clean_html(self._get_text(pemr, 'subreason') or '')
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if subreason:
|
|
|
|
|
if subreason == 'The uploader has not made this video available in your country.':
|
2021-07-20 21:52:34 -06:00
|
|
|
|
countries = get_first(microformats, 'availableCountries')
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if not countries:
|
|
|
|
|
regions_allowed = search_meta('regionsAllowed')
|
|
|
|
|
countries = regions_allowed.split(',') if regions_allowed else None
|
2021-04-16 18:09:58 -06:00
|
|
|
|
self.raise_geo_restricted(subreason, countries, metadata_available=True)
|
2021-07-20 21:52:34 -06:00
|
|
|
|
reason += f'. {subreason}'
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if reason:
|
2021-04-16 18:09:58 -06:00
|
|
|
|
self.raise_no_formats(reason, expected=True)
|
2019-09-11 09:44:47 -06:00
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
keywords = get_first(video_details, 'keywords', expected_type=list) or []
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if not keywords and webpage:
|
|
|
|
|
keywords = [
|
|
|
|
|
unescapeHTML(m.group('content'))
|
|
|
|
|
for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
|
|
|
|
|
for keyword in keywords:
|
|
|
|
|
if keyword.startswith('yt:stretch='):
|
2021-04-16 21:02:33 -06:00
|
|
|
|
mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
|
|
|
|
|
if mobj:
|
|
|
|
|
# NB: float is intentional for forcing float division
|
|
|
|
|
w, h = (float(v) for v in mobj.groups())
|
|
|
|
|
if w > 0 and h > 0:
|
|
|
|
|
ratio = w / h
|
|
|
|
|
for f in formats:
|
|
|
|
|
if f.get('vcodec') != 'none':
|
|
|
|
|
f['stretched_ratio'] = ratio
|
|
|
|
|
break
|
2021-12-23 20:42:02 -07:00
|
|
|
|
thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
|
2021-05-18 07:45:11 -06:00
|
|
|
|
thumbnail_url = search_meta(['og:image', 'twitter:image'])
|
|
|
|
|
if thumbnail_url:
|
|
|
|
|
thumbnails.append({
|
|
|
|
|
'url': thumbnail_url,
|
|
|
|
|
})
|
2021-10-24 03:25:28 -06:00
|
|
|
|
original_thumbnails = thumbnails.copy()
|
|
|
|
|
|
2021-07-15 11:19:59 -06:00
|
|
|
|
# The best resolution thumbnails sometimes does not appear in the webpage
|
2022-04-28 13:01:34 -06:00
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/340
|
2021-07-19 16:10:35 -06:00
|
|
|
|
# List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
|
2021-10-18 03:53:42 -06:00
|
|
|
|
thumbnail_names = [
|
2022-06-26 18:50:06 -06:00
|
|
|
|
# While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
|
2022-04-28 13:01:34 -06:00
|
|
|
|
# in resolution, these are not the custom thumbnail. So de-prioritize them
|
|
|
|
|
'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
|
|
|
|
|
'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
|
2021-07-19 16:10:35 -06:00
|
|
|
|
]
|
|
|
|
|
n_thumbnail_names = len(thumbnail_names)
|
2021-07-15 11:19:59 -06:00
|
|
|
|
thumbnails.extend({
|
|
|
|
|
'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
|
|
|
|
|
video_id=video_id, name=name, ext=ext,
|
2022-10-03 20:48:31 -06:00
|
|
|
|
webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
|
2021-07-19 16:10:35 -06:00
|
|
|
|
} for name in thumbnail_names for ext in ('webp', 'jpg'))
|
2021-07-15 11:19:59 -06:00
|
|
|
|
for thumb in thumbnails:
|
2021-07-19 16:10:35 -06:00
|
|
|
|
i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
|
2021-07-15 11:19:59 -06:00
|
|
|
|
thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
|
2021-05-18 07:45:11 -06:00
|
|
|
|
self._remove_duplicate_formats(thumbnails)
|
2021-10-24 03:25:28 -06:00
|
|
|
|
self._downloader._sort_thumbnails(original_thumbnails)
|
2021-02-04 07:37:17 -07:00
|
|
|
|
|
2021-07-21 09:15:45 -06:00
|
|
|
|
category = get_first(microformats, 'category') or search_meta('genre')
|
2023-04-14 01:58:36 -06:00
|
|
|
|
channel_id = self.ucid_or_none(str_or_none(
|
2021-07-21 09:15:45 -06:00
|
|
|
|
get_first(video_details, 'channelId')
|
|
|
|
|
or get_first(microformats, 'externalChannelId')
|
2023-04-14 01:58:36 -06:00
|
|
|
|
or search_meta('channelId')))
|
2021-07-21 09:15:45 -06:00
|
|
|
|
owner_profile_url = get_first(microformats, 'ownerProfileUrl')
|
|
|
|
|
|
2021-12-19 23:06:46 -07:00
|
|
|
|
live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
|
|
|
|
|
live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
|
|
|
|
|
if not duration and live_end_time and live_start_time:
|
|
|
|
|
duration = live_end_time - live_start_time
|
|
|
|
|
|
2022-10-03 20:48:31 -06:00
|
|
|
|
needs_live_processing = self._needs_live_processing(live_status, duration)
|
|
|
|
|
|
|
|
|
|
def is_bad_format(fmt):
|
|
|
|
|
if needs_live_processing and not fmt.get('is_from_start'):
|
|
|
|
|
return True
|
|
|
|
|
elif (live_status == 'is_live' and needs_live_processing != 'is_live'
|
|
|
|
|
and fmt.get('protocol') == 'http_dash_segments'):
|
|
|
|
|
return True
|
|
|
|
|
|
|
|
|
|
for fmt in filter(is_bad_format, formats):
|
|
|
|
|
fmt['preference'] = (fmt.get('preference') or -1) - 10
|
2023-06-25 19:55:47 -06:00
|
|
|
|
fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
|
2022-10-03 20:48:31 -06:00
|
|
|
|
|
|
|
|
|
if needs_live_processing:
|
|
|
|
|
self._prepare_live_from_start_formats(
|
|
|
|
|
formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
|
2021-07-21 09:15:45 -06:00
|
|
|
|
|
2021-11-16 12:56:23 -07:00
|
|
|
|
formats.extend(self._extract_storyboard(player_responses, duration))
|
|
|
|
|
|
2023-04-14 01:58:36 -06:00
|
|
|
|
channel_handle = self.handle_from_url(owner_profile_url)
|
|
|
|
|
|
2021-02-04 07:37:17 -07:00
|
|
|
|
info = {
|
|
|
|
|
'id': video_id,
|
2021-12-15 09:00:46 -07:00
|
|
|
|
'title': video_title,
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'formats': formats,
|
|
|
|
|
'thumbnails': thumbnails,
|
2021-10-24 03:25:28 -06:00
|
|
|
|
# The best thumbnail that we are sure exists. Prevents unnecessary
|
|
|
|
|
# URL checking if user don't care about getting the best possible thumbnail
|
|
|
|
|
'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'description': video_description,
|
|
|
|
|
'channel_id': channel_id,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'duration': duration,
|
|
|
|
|
'view_count': int_or_none(
|
2021-07-20 21:52:34 -06:00
|
|
|
|
get_first((video_details, microformats), (..., 'viewCount'))
|
2021-02-04 07:37:17 -07:00
|
|
|
|
or search_meta('interactionCount')),
|
2021-07-20 21:52:34 -06:00
|
|
|
|
'average_rating': float_or_none(get_first(video_details, 'averageRating')),
|
2021-02-04 07:37:17 -07:00
|
|
|
|
'age_limit': 18 if (
|
2021-07-20 21:52:34 -06:00
|
|
|
|
get_first(microformats, 'isFamilySafe') is False
|
2021-02-04 07:37:17 -07:00
|
|
|
|
or search_meta('isFamilyFriendly') == 'false'
|
|
|
|
|
or search_meta('og:restrictions:age') == '18+') else 0,
|
|
|
|
|
'webpage_url': webpage_url,
|
|
|
|
|
'categories': [category] if category else None,
|
|
|
|
|
'tags': keywords,
|
2021-07-20 21:52:34 -06:00
|
|
|
|
'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
|
2022-10-03 20:48:31 -06:00
|
|
|
|
'live_status': live_status,
|
2021-12-19 23:06:46 -07:00
|
|
|
|
'release_timestamp': live_start_time,
|
2022-11-16 22:10:03 -07:00
|
|
|
|
'_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
|
|
|
|
|
'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
|
2021-02-04 07:37:17 -07:00
|
|
|
|
}
|
2020-06-15 13:29:04 -06:00
|
|
|
|
|
2022-06-21 16:16:54 -06:00
|
|
|
|
subtitles = {}
|
2021-07-22 22:07:15 -06:00
|
|
|
|
pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if pctr:
|
2021-10-12 00:33:56 -06:00
|
|
|
|
def get_lang_code(track):
|
|
|
|
|
return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
|
|
|
|
|
or track.get('languageCode'))
|
|
|
|
|
|
|
|
|
|
# Converted into dicts to remove duplicates
|
|
|
|
|
captions = {
|
|
|
|
|
get_lang_code(sub): sub
|
2023-02-09 15:26:26 -07:00
|
|
|
|
for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
|
2021-10-12 00:33:56 -06:00
|
|
|
|
translation_languages = {
|
|
|
|
|
lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
|
2023-02-09 15:26:26 -07:00
|
|
|
|
for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
|
2021-10-12 00:33:56 -06:00
|
|
|
|
|
2021-05-13 05:19:40 -06:00
|
|
|
|
def process_language(container, base_url, lang_code, sub_name, query):
|
2021-05-12 13:20:02 -06:00
|
|
|
|
lang_subs = container.setdefault(lang_code, [])
|
2021-02-04 07:37:17 -07:00
|
|
|
|
for fmt in self._SUBTITLE_FORMATS:
|
|
|
|
|
query.update({
|
|
|
|
|
'fmt': fmt,
|
|
|
|
|
})
|
|
|
|
|
lang_subs.append({
|
|
|
|
|
'ext': fmt,
|
2022-02-13 14:36:01 -07:00
|
|
|
|
'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
|
2021-05-13 05:19:40 -06:00
|
|
|
|
'name': sub_name,
|
2021-02-04 07:37:17 -07:00
|
|
|
|
})
|
2018-06-02 13:08:38 -06:00
|
|
|
|
|
2022-07-17 16:49:43 -06:00
|
|
|
|
# NB: Constructing the full subtitle dictionary is slow
|
|
|
|
|
get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
|
|
|
|
|
self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
|
2021-10-12 00:33:56 -06:00
|
|
|
|
for lang_code, caption_track in captions.items():
|
|
|
|
|
base_url = caption_track.get('baseUrl')
|
2022-03-27 02:36:26 -06:00
|
|
|
|
orig_lang = parse_qs(base_url).get('lang', [None])[-1]
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if not base_url:
|
|
|
|
|
continue
|
2021-10-12 00:33:56 -06:00
|
|
|
|
lang_name = self._get_text(caption_track, 'name', max_runs=1)
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if caption_track.get('kind') != 'asr':
|
|
|
|
|
if not lang_code:
|
|
|
|
|
continue
|
|
|
|
|
process_language(
|
2021-10-12 00:33:56 -06:00
|
|
|
|
subtitles, base_url, lang_code, lang_name, {})
|
|
|
|
|
if not caption_track.get('isTranslatable'):
|
|
|
|
|
continue
|
2021-07-22 22:07:15 -06:00
|
|
|
|
for trans_code, trans_name in translation_languages.items():
|
|
|
|
|
if not trans_code:
|
2021-02-04 07:37:17 -07:00
|
|
|
|
continue
|
2022-03-27 02:36:26 -06:00
|
|
|
|
orig_trans_code = trans_code
|
2022-11-29 16:47:45 -07:00
|
|
|
|
if caption_track.get('kind') != 'asr' and trans_code != 'und':
|
2022-07-17 16:49:43 -06:00
|
|
|
|
if not get_translated_subs:
|
2022-03-27 02:34:20 -06:00
|
|
|
|
continue
|
2021-10-12 00:33:56 -06:00
|
|
|
|
trans_code += f'-{lang_code}'
|
2022-06-17 20:00:12 -06:00
|
|
|
|
trans_name += format_field(lang_name, None, ' from %s')
|
2022-03-27 02:36:26 -06:00
|
|
|
|
if lang_code == f'a-{orig_trans_code}':
|
2023-06-14 07:38:46 -06:00
|
|
|
|
# Set audio language based on original subtitles
|
|
|
|
|
for f in formats:
|
|
|
|
|
if f.get('acodec') != 'none' and not f.get('language'):
|
|
|
|
|
f['language'] = orig_trans_code
|
|
|
|
|
# Add an "-orig" label to the original language so that it can be distinguished.
|
|
|
|
|
# The subs are returned without "-orig" as well for compatibility
|
2022-02-11 13:20:25 -07:00
|
|
|
|
process_language(
|
2022-03-04 21:08:03 -07:00
|
|
|
|
automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
|
|
|
|
|
# Setting tlang=lang returns damaged subtitles.
|
|
|
|
|
process_language(automatic_captions, base_url, trans_code, trans_name,
|
2022-03-27 02:36:26 -06:00
|
|
|
|
{} if orig_lang == orig_trans_code else {'tlang': trans_code})
|
2022-06-21 16:16:54 -06:00
|
|
|
|
|
|
|
|
|
info['automatic_captions'] = automatic_captions
|
|
|
|
|
info['subtitles'] = subtitles
|
2018-06-02 13:08:38 -06:00
|
|
|
|
|
2022-06-24 04:54:43 -06:00
|
|
|
|
parsed_url = urllib.parse.urlparse(url)
|
2021-02-04 07:37:17 -07:00
|
|
|
|
for component in [parsed_url.fragment, parsed_url.query]:
|
2022-06-24 04:54:43 -06:00
|
|
|
|
query = urllib.parse.parse_qs(component)
|
2021-02-04 07:37:17 -07:00
|
|
|
|
for k, v in query.items():
|
|
|
|
|
for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
|
|
|
|
|
d_k += '_time'
|
|
|
|
|
if d_k not in info and k in s_ks:
|
|
|
|
|
info[d_k] = parse_duration(query[k][0])
|
2019-04-27 02:16:17 -06:00
|
|
|
|
|
|
|
|
|
# Youtube Music Auto-generated description
|
2023-06-22 01:27:54 -06:00
|
|
|
|
if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
|
|
|
|
|
# XXX: Causes catastrophic backtracking if description has "·"
|
|
|
|
|
# E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
|
|
|
|
|
# Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
|
|
|
|
|
# reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
|
2022-06-03 09:59:03 -06:00
|
|
|
|
mobj = re.search(
|
|
|
|
|
r'''(?xs)
|
2023-06-22 01:27:54 -06:00
|
|
|
|
(?=(?P<track>[^\n·]+))(?P=track)·
|
|
|
|
|
(?=(?P<artist>[^\n]+))(?P=artist)\n+
|
|
|
|
|
(?=(?P<album>[^\n]+))(?P=album)\n
|
2022-06-03 09:59:03 -06:00
|
|
|
|
(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
|
|
|
|
|
(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
|
2023-06-22 01:27:54 -06:00
|
|
|
|
(.+?\nArtist\s*:\s*
|
|
|
|
|
(?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
|
|
|
|
|
)?.+\nAuto-generated\ by\ YouTube\.\s*$
|
2022-06-03 09:59:03 -06:00
|
|
|
|
''', video_description)
|
2019-04-27 02:16:17 -06:00
|
|
|
|
if mobj:
|
|
|
|
|
release_year = mobj.group('release_year')
|
|
|
|
|
release_date = mobj.group('release_date')
|
|
|
|
|
if release_date:
|
|
|
|
|
release_date = release_date.replace('-', '')
|
|
|
|
|
if not release_year:
|
2021-02-04 07:37:17 -07:00
|
|
|
|
release_year = release_date[:4]
|
|
|
|
|
info.update({
|
|
|
|
|
'album': mobj.group('album'.strip()),
|
|
|
|
|
'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
|
|
|
|
|
'track': mobj.group('track').strip(),
|
|
|
|
|
'release_date': release_date,
|
2021-02-10 14:22:55 -07:00
|
|
|
|
'release_year': int_or_none(release_year),
|
2021-02-04 07:37:17 -07:00
|
|
|
|
})
|
2018-06-02 13:08:38 -06:00
|
|
|
|
|
2021-02-04 07:37:17 -07:00
|
|
|
|
initial_data = None
|
|
|
|
|
if webpage:
|
2022-06-10 13:03:54 -06:00
|
|
|
|
initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
|
2023-03-12 19:43:37 -06:00
|
|
|
|
if not traverse_obj(initial_data, 'contents'):
|
|
|
|
|
self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
|
|
|
|
|
initial_data = None
|
2021-02-04 07:37:17 -07:00
|
|
|
|
if not initial_data:
|
2021-09-23 18:52:17 -06:00
|
|
|
|
query = {'videoId': video_id}
|
|
|
|
|
query.update(self._get_checkok_params())
|
2021-06-29 16:07:49 -06:00
|
|
|
|
initial_data = self._extract_response(
|
|
|
|
|
item_id=video_id, ep='next', fatal=False,
|
2023-03-12 19:43:37 -06:00
|
|
|
|
ytcfg=master_ytcfg, query=query, check_get_keys='contents',
|
2021-09-23 18:52:17 -06:00
|
|
|
|
headers=self.generate_api_headers(ytcfg=master_ytcfg),
|
2021-06-29 16:07:49 -06:00
|
|
|
|
note='Downloading initial data API JSON')
|
2021-02-04 07:37:17 -07:00
|
|
|
|
|
2022-06-17 00:30:55 -06:00
|
|
|
|
info['comment_count'] = traverse_obj(initial_data, (
|
|
|
|
|
'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
|
2023-03-14 17:21:14 -06:00
|
|
|
|
'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
|
2022-06-17 00:30:55 -06:00
|
|
|
|
), (
|
|
|
|
|
'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
|
2023-03-14 17:21:14 -06:00
|
|
|
|
'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
|
|
|
|
|
), expected_type=self._get_count, get_all=False)
|
2022-06-17 00:30:55 -06:00
|
|
|
|
|
2022-04-17 14:58:28 -06:00
|
|
|
|
try: # This will error if there is no livechat
|
2021-06-22 18:12:39 -06:00
|
|
|
|
initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
|
2022-04-17 14:58:28 -06:00
|
|
|
|
except (KeyError, IndexError, TypeError):
|
|
|
|
|
pass
|
|
|
|
|
else:
|
2021-10-12 00:33:56 -06:00
|
|
|
|
info.setdefault('subtitles', {})['live_chat'] = [{
|
2022-06-11 23:56:50 -06:00
|
|
|
|
# url is needed to set cookies
|
|
|
|
|
'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
|
2021-06-22 18:12:39 -06:00
|
|
|
|
'video_id': video_id,
|
|
|
|
|
'ext': 'json',
|
2022-10-03 20:48:31 -06:00
|
|
|
|
'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
|
|
|
|
|
else 'youtube_live_chat_replay'),
|
2021-06-22 18:12:39 -06:00
|
|
|
|
}]
|
2021-02-04 07:37:17 -07:00
|
|
|
|
|
|
|
|
|
if initial_data:
|
2021-07-19 18:02:41 -06:00
|
|
|
|
info['chapters'] = (
|
|
|
|
|
self._extract_chapters_from_json(initial_data, duration)
|
|
|
|
|
or self._extract_chapters_from_engagement_panel(initial_data, duration)
|
2022-05-28 13:30:41 -06:00
|
|
|
|
or self._extract_chapters_from_description(video_description, duration)
|
2021-07-19 18:02:41 -06:00
|
|
|
|
or None)
|
2021-02-04 07:37:17 -07:00
|
|
|
|
|
2023-10-06 19:00:15 -06:00
|
|
|
|
info['heatmap'] = self._extract_heatmap(initial_data)
|
2023-05-26 06:24:39 -06:00
|
|
|
|
|
2022-03-13 16:02:44 -06:00
|
|
|
|
contents = traverse_obj(
|
|
|
|
|
initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
|
|
|
|
|
expected_type=list, default=[])
|
|
|
|
|
|
|
|
|
|
vpir = get_first(contents, 'videoPrimaryInfoRenderer')
|
|
|
|
|
if vpir:
|
|
|
|
|
stl = vpir.get('superTitleLink')
|
|
|
|
|
if stl:
|
|
|
|
|
stl = self._get_text(stl)
|
|
|
|
|
if try_get(
|
|
|
|
|
vpir,
|
|
|
|
|
lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
|
|
|
|
|
info['location'] = stl
|
|
|
|
|
else:
|
2022-04-14 22:22:03 -06:00
|
|
|
|
mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
|
2022-03-13 16:02:44 -06:00
|
|
|
|
if mobj:
|
2021-02-04 07:37:17 -07:00
|
|
|
|
info.update({
|
2022-03-13 16:02:44 -06:00
|
|
|
|
'series': mobj.group(1),
|
|
|
|
|
'season_number': int(mobj.group(2)),
|
|
|
|
|
'episode_number': int(mobj.group(3)),
|
2021-02-04 07:37:17 -07:00
|
|
|
|
})
|
2022-03-13 16:02:44 -06:00
|
|
|
|
for tlb in (try_get(
|
|
|
|
|
vpir,
|
|
|
|
|
lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
|
|
|
|
|
list) or []):
|
2022-09-08 18:34:39 -06:00
|
|
|
|
tbrs = variadic(
|
|
|
|
|
traverse_obj(
|
2023-02-09 15:26:26 -07:00
|
|
|
|
tlb, ('toggleButtonRenderer', ...),
|
|
|
|
|
('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
|
2022-09-08 18:34:39 -06:00
|
|
|
|
for tbr in tbrs:
|
|
|
|
|
for getter, regex in [(
|
|
|
|
|
lambda x: x['defaultText']['accessibility']['accessibilityData'],
|
|
|
|
|
r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
|
|
|
|
|
lambda x: x['accessibility'],
|
|
|
|
|
lambda x: x['accessibilityData']['accessibilityData'],
|
|
|
|
|
], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
|
|
|
|
|
label = (try_get(tbr, getter, dict) or {}).get('label')
|
|
|
|
|
if label:
|
|
|
|
|
mobj = re.match(regex, label)
|
|
|
|
|
if mobj:
|
|
|
|
|
info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
|
|
|
|
|
break
|
2022-03-13 16:02:44 -06:00
|
|
|
|
sbr_tooltip = try_get(
|
|
|
|
|
vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
|
|
|
|
|
if sbr_tooltip:
|
|
|
|
|
like_count, dislike_count = sbr_tooltip.split(' / ')
|
|
|
|
|
info.update({
|
|
|
|
|
'like_count': str_to_int(like_count),
|
|
|
|
|
'dislike_count': str_to_int(dislike_count),
|
|
|
|
|
})
|
2022-10-07 01:00:40 -06:00
|
|
|
|
vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
|
|
|
|
|
if vcr:
|
|
|
|
|
vc = self._get_count(vcr, 'viewCount')
|
|
|
|
|
# Upcoming premieres with waiting count are treated as live here
|
|
|
|
|
if vcr.get('isLive'):
|
|
|
|
|
info['concurrent_view_count'] = vc
|
|
|
|
|
elif info.get('view_count') is None:
|
|
|
|
|
info['view_count'] = vc
|
|
|
|
|
|
2022-03-13 16:02:44 -06:00
|
|
|
|
vsir = get_first(contents, 'videoSecondaryInfoRenderer')
|
|
|
|
|
if vsir:
|
|
|
|
|
vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
|
|
|
|
|
info.update({
|
|
|
|
|
'channel': self._get_text(vor, 'title'),
|
|
|
|
|
'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
|
|
|
|
|
|
2023-04-14 01:58:36 -06:00
|
|
|
|
if not channel_handle:
|
|
|
|
|
channel_handle = self.handle_from_url(
|
|
|
|
|
traverse_obj(vor, (
|
|
|
|
|
('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
|
|
|
|
|
(('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
|
|
|
|
|
{str}), get_all=False))
|
|
|
|
|
|
2022-03-13 16:02:44 -06:00
|
|
|
|
rows = try_get(
|
|
|
|
|
vsir,
|
|
|
|
|
lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
|
|
|
|
|
list) or []
|
|
|
|
|
multiple_songs = False
|
|
|
|
|
for row in rows:
|
|
|
|
|
if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
|
|
|
|
|
multiple_songs = True
|
|
|
|
|
break
|
|
|
|
|
for row in rows:
|
|
|
|
|
mrr = row.get('metadataRowRenderer') or {}
|
|
|
|
|
mrr_title = mrr.get('title')
|
|
|
|
|
if not mrr_title:
|
|
|
|
|
continue
|
|
|
|
|
mrr_title = self._get_text(mrr, 'title')
|
|
|
|
|
mrr_contents_text = self._get_text(mrr, ('contents', 0))
|
|
|
|
|
if mrr_title == 'License':
|
|
|
|
|
info['license'] = mrr_contents_text
|
|
|
|
|
elif not multiple_songs:
|
|
|
|
|
if mrr_title == 'Album':
|
|
|
|
|
info['album'] = mrr_contents_text
|
|
|
|
|
elif mrr_title == 'Artist':
|
|
|
|
|
info['artist'] = mrr_contents_text
|
|
|
|
|
elif mrr_title == 'Song':
|
|
|
|
|
info['track'] = mrr_contents_text
|
2023-06-08 01:50:05 -06:00
|
|
|
|
owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges')))
|
|
|
|
|
if self._has_badge(owner_badges, BadgeType.VERIFIED):
|
|
|
|
|
info['channel_is_verified'] = True
|
2021-02-04 07:37:17 -07:00
|
|
|
|
|
2023-04-14 01:58:36 -06:00
|
|
|
|
info.update({
|
|
|
|
|
'uploader': info.get('channel'),
|
|
|
|
|
'uploader_id': channel_handle,
|
|
|
|
|
'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
|
|
|
|
|
})
|
2022-03-13 16:02:44 -06:00
|
|
|
|
# The upload date for scheduled, live and past live streams / premieres in microformats
|
|
|
|
|
# may be different from the stream date. Although not in UTC, we will prefer it in this case.
|
2022-03-08 00:28:00 -07:00
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
|
2022-03-13 16:02:44 -06:00
|
|
|
|
upload_date = (
|
|
|
|
|
unified_strdate(get_first(microformats, 'uploadDate'))
|
|
|
|
|
or unified_strdate(search_meta('uploadDate')))
|
2022-09-01 04:02:28 -06:00
|
|
|
|
if not upload_date or (
|
2022-10-03 20:48:31 -06:00
|
|
|
|
live_status in ('not_live', None)
|
2022-09-01 04:02:28 -06:00
|
|
|
|
and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
|
|
|
|
|
):
|
2022-09-08 23:16:46 -06:00
|
|
|
|
upload_date = strftime_or_none(
|
2023-06-20 21:51:20 -06:00
|
|
|
|
self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
|
2022-03-13 16:02:44 -06:00
|
|
|
|
info['upload_date'] = upload_date
|
2022-03-08 00:28:00 -07:00
|
|
|
|
|
2021-02-04 07:37:17 -07:00
|
|
|
|
for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
|
|
|
|
|
v = info.get(s_k)
|
|
|
|
|
if v:
|
|
|
|
|
info[d_k] = v
|
2020-09-15 09:16:58 -06:00
|
|
|
|
|
2023-06-08 07:28:49 -06:00
|
|
|
|
badges = self._extract_badges(traverse_obj(vpir, 'badges'))
|
2022-09-08 23:16:46 -06:00
|
|
|
|
|
|
|
|
|
is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
|
|
|
|
|
or get_first(video_details, 'isPrivate', expected_type=bool))
|
|
|
|
|
|
|
|
|
|
info['availability'] = (
|
|
|
|
|
'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
|
|
|
|
|
else self._availability(
|
|
|
|
|
is_private=is_private,
|
|
|
|
|
needs_premium=(
|
|
|
|
|
self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
|
|
|
|
|
or False if initial_data and is_private is not None else None),
|
|
|
|
|
needs_subscription=(
|
|
|
|
|
self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
|
|
|
|
|
or False if initial_data and is_private is not None else None),
|
|
|
|
|
needs_auth=info['age_limit'] >= 18,
|
|
|
|
|
is_unlisted=None if is_private is None else (
|
|
|
|
|
self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
|
|
|
|
|
or get_first(microformats, 'isUnlisted', expected_type=bool))))
|
2021-03-21 15:23:34 -06:00
|
|
|
|
|
2021-10-12 03:50:50 -06:00
|
|
|
|
info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
|
2013-12-17 19:30:55 -07:00
|
|
|
|
|
2021-07-20 21:52:34 -06:00
|
|
|
|
self.mark_watched(video_id, player_responses)
|
2016-02-29 12:01:33 -07:00
|
|
|
|
|
2021-02-04 07:37:17 -07:00
|
|
|
|
return info
|
2013-06-23 11:58:33 -06:00
|
|
|
|
|
2021-11-23 20:57:59 -07:00
|
|
|
|
|
2021-11-23 20:01:52 -07:00
|
|
|
|
class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
|
2022-02-01 13:43:17 -07:00
|
|
|
|
@staticmethod
|
|
|
|
|
def passthrough_smuggled_data(func):
|
2022-11-11 01:22:40 -07:00
|
|
|
|
def _smuggle(info, smuggled_data):
|
|
|
|
|
if info.get('_type') not in ('url', 'url_transparent'):
|
|
|
|
|
return info
|
|
|
|
|
if smuggled_data.get('is_music_url'):
|
|
|
|
|
parsed_url = urllib.parse.urlparse(info['url'])
|
|
|
|
|
if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
|
|
|
|
|
smuggled_data.pop('is_music_url')
|
|
|
|
|
info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
|
|
|
|
|
if smuggled_data:
|
|
|
|
|
info['url'] = smuggle_url(info['url'], smuggled_data)
|
|
|
|
|
return info
|
2022-02-01 13:43:17 -07:00
|
|
|
|
|
|
|
|
|
@functools.wraps(func)
|
|
|
|
|
def wrapper(self, url):
|
|
|
|
|
url, smuggled_data = unsmuggle_url(url, {})
|
|
|
|
|
if self.is_music_url(url):
|
|
|
|
|
smuggled_data['is_music_url'] = True
|
|
|
|
|
info_dict = func(self, url, smuggled_data)
|
2022-11-11 01:22:40 -07:00
|
|
|
|
if smuggled_data:
|
|
|
|
|
_smuggle(info_dict, smuggled_data)
|
|
|
|
|
if info_dict.get('entries'):
|
2022-11-11 11:32:07 -07:00
|
|
|
|
info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
|
2022-02-01 13:43:17 -07:00
|
|
|
|
return info_dict
|
|
|
|
|
return wrapper
|
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
@staticmethod
|
2021-03-04 11:05:26 -07:00
|
|
|
|
def _extract_basic_item_renderer(item):
|
|
|
|
|
# Modified from _extract_grid_item_renderer
|
2021-04-16 21:02:33 -06:00
|
|
|
|
known_basic_renderers = (
|
2022-04-03 07:31:03 -06:00
|
|
|
|
'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
|
2021-03-04 11:05:26 -07:00
|
|
|
|
)
|
|
|
|
|
for key, renderer in item.items():
|
2021-04-16 21:02:33 -06:00
|
|
|
|
if not isinstance(renderer, dict):
|
2021-03-04 11:05:26 -07:00
|
|
|
|
continue
|
2021-04-16 21:02:33 -06:00
|
|
|
|
elif key in known_basic_renderers:
|
|
|
|
|
return renderer
|
|
|
|
|
elif key.startswith('grid') and key.endswith('Renderer'):
|
|
|
|
|
return renderer
|
2020-11-19 12:22:59 -07:00
|
|
|
|
|
2022-12-12 16:08:14 -07:00
|
|
|
|
def _extract_channel_renderer(self, renderer):
|
2023-04-14 01:58:36 -06:00
|
|
|
|
channel_id = self.ucid_or_none(renderer['channelId'])
|
2022-12-12 16:08:14 -07:00
|
|
|
|
title = self._get_text(renderer, 'title')
|
2023-04-14 01:58:36 -06:00
|
|
|
|
channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
|
|
|
|
|
channel_handle = self.handle_from_url(
|
|
|
|
|
traverse_obj(renderer, (
|
|
|
|
|
'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
|
|
|
|
|
('browseEndpoint', 'canonicalBaseUrl')),
|
|
|
|
|
{str}), get_all=False))
|
2023-06-08 07:28:49 -06:00
|
|
|
|
if not channel_handle:
|
|
|
|
|
# As of 2023-06-01, YouTube sets subscriberCountText to the handle in search
|
|
|
|
|
channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText'))
|
2022-12-12 16:08:14 -07:00
|
|
|
|
return {
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'url': channel_url,
|
|
|
|
|
'id': channel_id,
|
|
|
|
|
'ie_key': YoutubeTabIE.ie_key(),
|
|
|
|
|
'channel': title,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': title,
|
2022-12-12 16:08:14 -07:00
|
|
|
|
'channel_id': channel_id,
|
|
|
|
|
'channel_url': channel_url,
|
|
|
|
|
'title': title,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': channel_handle,
|
|
|
|
|
'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
|
2023-06-08 07:28:49 -06:00
|
|
|
|
# See above. YouTube sets videoCountText to the subscriber text in search channel renderers.
|
|
|
|
|
# However, in feed/channels this is set correctly to the subscriber count
|
|
|
|
|
'channel_follower_count': traverse_obj(
|
|
|
|
|
renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count),
|
2022-12-12 16:08:14 -07:00
|
|
|
|
'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'playlist_count': (
|
|
|
|
|
# videoCountText may be the subscriber count
|
|
|
|
|
self._get_count(renderer, 'videoCountText')
|
|
|
|
|
if self._get_count(renderer, 'subscriberCountText') is not None else None),
|
2022-12-12 16:08:14 -07:00
|
|
|
|
'description': self._get_text(renderer, 'descriptionSnippet'),
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True if self._has_badge(
|
|
|
|
|
self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None,
|
2022-12-12 16:08:14 -07:00
|
|
|
|
}
|
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
def _grid_entries(self, grid_renderer):
|
|
|
|
|
for item in grid_renderer['items']:
|
|
|
|
|
if not isinstance(item, dict):
|
2015-04-28 09:07:56 -06:00
|
|
|
|
continue
|
2021-03-04 11:05:26 -07:00
|
|
|
|
renderer = self._extract_basic_item_renderer(item)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
if not isinstance(renderer, dict):
|
|
|
|
|
continue
|
2021-07-23 18:46:46 -06:00
|
|
|
|
title = self._get_text(renderer, 'title')
|
2021-07-18 22:55:07 -06:00
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
# playlist
|
|
|
|
|
playlist_id = renderer.get('playlistId')
|
|
|
|
|
if playlist_id:
|
|
|
|
|
yield self.url_result(
|
|
|
|
|
'https://www.youtube.com/playlist?list=%s' % playlist_id,
|
|
|
|
|
ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
|
|
|
|
|
video_title=title)
|
2021-04-16 21:02:33 -06:00
|
|
|
|
continue
|
2020-11-19 12:22:59 -07:00
|
|
|
|
# video
|
|
|
|
|
video_id = renderer.get('videoId')
|
|
|
|
|
if video_id:
|
|
|
|
|
yield self._extract_video(renderer)
|
2021-04-16 21:02:33 -06:00
|
|
|
|
continue
|
2020-11-19 12:22:59 -07:00
|
|
|
|
# channel
|
|
|
|
|
channel_id = renderer.get('channelId')
|
|
|
|
|
if channel_id:
|
2022-12-12 16:08:14 -07:00
|
|
|
|
yield self._extract_channel_renderer(renderer)
|
2021-04-16 21:02:33 -06:00
|
|
|
|
continue
|
|
|
|
|
# generic endpoint URL support
|
|
|
|
|
ep_url = urljoin('https://www.youtube.com/', try_get(
|
|
|
|
|
renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
|
2022-06-24 04:54:43 -06:00
|
|
|
|
str))
|
2021-04-16 21:02:33 -06:00
|
|
|
|
if ep_url:
|
|
|
|
|
for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
|
|
|
|
|
if ie.suitable(ep_url):
|
|
|
|
|
yield self.url_result(
|
|
|
|
|
ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
|
|
|
|
|
break
|
2020-11-19 12:22:59 -07:00
|
|
|
|
|
2022-02-01 11:24:00 -07:00
|
|
|
|
def _music_reponsive_list_entry(self, renderer):
|
|
|
|
|
video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
|
|
|
|
|
if video_id:
|
2023-05-22 05:47:06 -06:00
|
|
|
|
title = traverse_obj(renderer, (
|
|
|
|
|
'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
|
|
|
|
|
'text', 'runs', 0, 'text'))
|
2022-02-01 11:24:00 -07:00
|
|
|
|
return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
|
2023-05-22 05:47:06 -06:00
|
|
|
|
ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
|
2022-02-01 11:24:00 -07:00
|
|
|
|
playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
|
|
|
|
|
if playlist_id:
|
|
|
|
|
video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
|
|
|
|
|
if video_id:
|
|
|
|
|
return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
|
|
|
|
|
ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
|
|
|
|
|
return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
|
|
|
|
|
ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
|
|
|
|
|
browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
|
|
|
|
|
if browse_id:
|
|
|
|
|
return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
|
|
|
|
|
ie=YoutubeTabIE.ie_key(), video_id=browse_id)
|
|
|
|
|
|
2020-11-23 14:59:10 -07:00
|
|
|
|
def _shelf_entries_from_content(self, shelf_renderer):
|
|
|
|
|
content = shelf_renderer.get('content')
|
|
|
|
|
if not isinstance(content, dict):
|
2020-11-19 12:22:59 -07:00
|
|
|
|
return
|
2021-03-04 11:05:26 -07:00
|
|
|
|
renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
|
2020-11-23 14:59:10 -07:00
|
|
|
|
if renderer:
|
|
|
|
|
# TODO: add support for nested playlists so each shelf is processed
|
|
|
|
|
# as separate playlist
|
|
|
|
|
# TODO: this includes only first N items
|
2022-04-11 09:10:28 -06:00
|
|
|
|
yield from self._grid_entries(renderer)
|
2020-11-23 14:59:10 -07:00
|
|
|
|
renderer = content.get('horizontalListRenderer')
|
|
|
|
|
if renderer:
|
|
|
|
|
# TODO
|
|
|
|
|
pass
|
2020-11-19 12:22:59 -07:00
|
|
|
|
|
2021-01-01 05:26:37 -07:00
|
|
|
|
def _shelf_entries(self, shelf_renderer, skip_channels=False):
|
2020-11-19 12:22:59 -07:00
|
|
|
|
ep = try_get(
|
|
|
|
|
shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
|
2022-06-24 04:54:43 -06:00
|
|
|
|
str)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
shelf_url = urljoin('https://www.youtube.com', ep)
|
2020-11-23 14:59:10 -07:00
|
|
|
|
if shelf_url:
|
2021-01-01 05:26:37 -07:00
|
|
|
|
# Skipping links to another channels, note that checking for
|
|
|
|
|
# endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
|
|
|
|
|
# will not work
|
|
|
|
|
if skip_channels and '/channels?' in shelf_url:
|
|
|
|
|
return
|
2021-07-23 18:46:46 -06:00
|
|
|
|
title = self._get_text(shelf_renderer, 'title')
|
2020-11-23 14:59:10 -07:00
|
|
|
|
yield self.url_result(shelf_url, video_title=title)
|
|
|
|
|
# Shelf may not contain shelf URL, fallback to extraction from content
|
2022-04-11 09:10:28 -06:00
|
|
|
|
yield from self._shelf_entries_from_content(shelf_renderer)
|
2013-06-23 11:58:33 -06:00
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
def _playlist_entries(self, video_list_renderer):
|
|
|
|
|
for content in video_list_renderer['contents']:
|
|
|
|
|
if not isinstance(content, dict):
|
|
|
|
|
continue
|
|
|
|
|
renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
|
|
|
|
|
if not isinstance(renderer, dict):
|
|
|
|
|
continue
|
|
|
|
|
video_id = renderer.get('videoId')
|
|
|
|
|
if not video_id:
|
|
|
|
|
continue
|
|
|
|
|
yield self._extract_video(renderer)
|
2017-12-18 13:51:28 -07:00
|
|
|
|
|
2020-11-21 15:21:09 -07:00
|
|
|
|
def _rich_entries(self, rich_grid_renderer):
|
2022-09-21 23:39:02 -06:00
|
|
|
|
renderer = traverse_obj(
|
2023-05-20 01:11:03 -06:00
|
|
|
|
rich_grid_renderer,
|
|
|
|
|
('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
|
2020-11-21 15:21:09 -07:00
|
|
|
|
video_id = renderer.get('videoId')
|
2023-05-20 01:11:03 -06:00
|
|
|
|
if video_id:
|
|
|
|
|
yield self._extract_video(renderer)
|
|
|
|
|
return
|
|
|
|
|
playlist_id = renderer.get('playlistId')
|
|
|
|
|
if playlist_id:
|
|
|
|
|
yield self.url_result(
|
|
|
|
|
f'https://www.youtube.com/playlist?list={playlist_id}',
|
|
|
|
|
ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
|
|
|
|
|
video_title=self._get_text(renderer, 'title'))
|
2020-11-21 15:21:09 -07:00
|
|
|
|
return
|
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
def _video_entry(self, video_renderer):
|
|
|
|
|
video_id = video_renderer.get('videoId')
|
|
|
|
|
if video_id:
|
|
|
|
|
return self._extract_video(video_renderer)
|
2016-09-02 10:43:20 -06:00
|
|
|
|
|
2022-04-02 00:11:14 -06:00
|
|
|
|
def _hashtag_tile_entry(self, hashtag_tile_renderer):
|
|
|
|
|
url = urljoin('https://youtube.com', traverse_obj(
|
|
|
|
|
hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
|
|
|
|
|
if url:
|
|
|
|
|
return self.url_result(
|
|
|
|
|
url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
|
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
def _post_thread_entries(self, post_thread_renderer):
|
|
|
|
|
post_renderer = try_get(
|
|
|
|
|
post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
|
|
|
|
|
if not post_renderer:
|
|
|
|
|
return
|
|
|
|
|
# video attachment
|
|
|
|
|
video_renderer = try_get(
|
2021-04-27 00:03:58 -06:00
|
|
|
|
post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
|
|
|
|
|
video_id = video_renderer.get('videoId')
|
|
|
|
|
if video_id:
|
|
|
|
|
entry = self._extract_video(video_renderer)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
if entry:
|
|
|
|
|
yield entry
|
2021-04-27 00:03:58 -06:00
|
|
|
|
# playlist attachment
|
|
|
|
|
playlist_id = try_get(
|
2022-06-24 04:54:43 -06:00
|
|
|
|
post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
|
2021-04-27 00:03:58 -06:00
|
|
|
|
if playlist_id:
|
|
|
|
|
yield self.url_result(
|
2021-04-28 08:29:40 -06:00
|
|
|
|
'https://www.youtube.com/playlist?list=%s' % playlist_id,
|
|
|
|
|
ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
# inline video links
|
|
|
|
|
runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
|
|
|
|
|
for run in runs:
|
|
|
|
|
if not isinstance(run, dict):
|
|
|
|
|
continue
|
|
|
|
|
ep_url = try_get(
|
2022-06-24 04:54:43 -06:00
|
|
|
|
run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
if not ep_url:
|
|
|
|
|
continue
|
|
|
|
|
if not YoutubeIE.suitable(ep_url):
|
|
|
|
|
continue
|
|
|
|
|
ep_video_id = YoutubeIE._match_id(ep_url)
|
|
|
|
|
if video_id == ep_video_id:
|
|
|
|
|
continue
|
2021-04-27 00:03:58 -06:00
|
|
|
|
yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
|
2016-09-02 10:43:20 -06:00
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
def _post_thread_continuation_entries(self, post_thread_continuation):
|
|
|
|
|
contents = post_thread_continuation.get('contents')
|
|
|
|
|
if not isinstance(contents, list):
|
|
|
|
|
return
|
|
|
|
|
for content in contents:
|
|
|
|
|
renderer = content.get('backstagePostThreadRenderer')
|
2022-05-31 11:40:45 -06:00
|
|
|
|
if isinstance(renderer, dict):
|
|
|
|
|
yield from self._post_thread_entries(renderer)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
continue
|
2022-05-31 11:40:45 -06:00
|
|
|
|
renderer = content.get('videoRenderer')
|
|
|
|
|
if isinstance(renderer, dict):
|
|
|
|
|
yield self._video_entry(renderer)
|
2017-12-18 13:51:28 -07:00
|
|
|
|
|
2021-04-03 16:05:17 -06:00
|
|
|
|
r''' # unused
|
|
|
|
|
def _rich_grid_entries(self, contents):
|
|
|
|
|
for content in contents:
|
|
|
|
|
video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
|
|
|
|
|
if video_renderer:
|
|
|
|
|
entry = self._video_entry(video_renderer)
|
|
|
|
|
if entry:
|
|
|
|
|
yield entry
|
|
|
|
|
'''
|
2022-03-18 14:53:33 -06:00
|
|
|
|
|
2022-09-26 16:25:58 -06:00
|
|
|
|
def _report_history_entries(self, renderer):
|
|
|
|
|
for url in traverse_obj(renderer, (
|
2022-09-26 21:02:57 -06:00
|
|
|
|
'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
|
|
|
|
|
'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
|
2022-09-26 16:25:58 -06:00
|
|
|
|
'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
|
|
|
|
|
yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
|
|
|
|
|
|
2021-11-23 20:01:52 -07:00
|
|
|
|
def _extract_entries(self, parent_renderer, continuation_list):
|
|
|
|
|
# continuation_list is modified in-place with continuation_list = [continuation_token]
|
|
|
|
|
continuation_list[:] = [None]
|
|
|
|
|
contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
|
|
|
|
|
for content in contents:
|
|
|
|
|
if not isinstance(content, dict):
|
|
|
|
|
continue
|
2022-02-01 11:24:00 -07:00
|
|
|
|
is_renderer = traverse_obj(
|
|
|
|
|
content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
|
|
|
|
|
expected_type=dict)
|
2021-11-23 20:01:52 -07:00
|
|
|
|
if not is_renderer:
|
2022-09-26 16:25:58 -06:00
|
|
|
|
if content.get('richItemRenderer'):
|
|
|
|
|
for entry in self._rich_entries(content['richItemRenderer']):
|
2021-11-23 20:01:52 -07:00
|
|
|
|
yield entry
|
|
|
|
|
continuation_list[0] = self._extract_continuation(parent_renderer)
|
2022-09-26 16:25:58 -06:00
|
|
|
|
elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
|
|
|
|
|
table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
|
|
|
|
|
yield from self._report_history_entries(table)
|
|
|
|
|
continuation_list[0] = self._extract_continuation(table)
|
2021-11-23 20:01:52 -07:00
|
|
|
|
continue
|
2022-09-26 16:25:58 -06:00
|
|
|
|
|
2021-11-23 20:01:52 -07:00
|
|
|
|
isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
|
|
|
|
|
for isr_content in isr_contents:
|
|
|
|
|
if not isinstance(isr_content, dict):
|
2020-11-19 12:22:59 -07:00
|
|
|
|
continue
|
2021-02-09 09:07:59 -07:00
|
|
|
|
|
2021-11-23 20:01:52 -07:00
|
|
|
|
known_renderers = {
|
|
|
|
|
'playlistVideoListRenderer': self._playlist_entries,
|
|
|
|
|
'gridRenderer': self._grid_entries,
|
2022-04-03 07:31:03 -06:00
|
|
|
|
'reelShelfRenderer': self._grid_entries,
|
|
|
|
|
'shelfRenderer': self._shelf_entries,
|
2022-02-01 11:24:00 -07:00
|
|
|
|
'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'backstagePostThreadRenderer': self._post_thread_entries,
|
|
|
|
|
'videoRenderer': lambda x: [self._video_entry(x)],
|
2021-11-23 20:57:59 -07:00
|
|
|
|
'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
|
|
|
|
|
'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
|
2023-06-29 17:26:27 -06:00
|
|
|
|
'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
|
|
|
|
|
'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}
|
|
|
|
|
for key, renderer in isr_content.items():
|
|
|
|
|
if key not in known_renderers:
|
|
|
|
|
continue
|
|
|
|
|
for entry in known_renderers[key](renderer):
|
|
|
|
|
if entry:
|
|
|
|
|
yield entry
|
|
|
|
|
continuation_list[0] = self._extract_continuation(renderer)
|
|
|
|
|
break
|
2020-11-23 14:47:42 -07:00
|
|
|
|
|
|
|
|
|
if not continuation_list[0]:
|
2021-11-23 20:01:52 -07:00
|
|
|
|
continuation_list[0] = self._extract_continuation(is_renderer)
|
2020-11-21 15:21:09 -07:00
|
|
|
|
|
2021-11-23 20:01:52 -07:00
|
|
|
|
if not continuation_list[0]:
|
|
|
|
|
continuation_list[0] = self._extract_continuation(parent_renderer)
|
|
|
|
|
|
|
|
|
|
def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
|
|
|
|
|
continuation_list = [None]
|
|
|
|
|
extract_entries = lambda x: self._extract_entries(x, continuation_list)
|
2021-01-01 05:26:37 -07:00
|
|
|
|
tab_content = try_get(tab, lambda x: x['content'], dict)
|
|
|
|
|
if not tab_content:
|
|
|
|
|
return
|
2020-11-21 15:21:09 -07:00
|
|
|
|
parent_renderer = (
|
2021-01-01 05:26:37 -07:00
|
|
|
|
try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
|
|
|
|
|
or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
|
2022-04-11 09:10:28 -06:00
|
|
|
|
yield from extract_entries(parent_renderer)
|
2020-11-21 15:21:09 -07:00
|
|
|
|
continuation = continuation_list[0]
|
2023-07-14 21:20:24 -06:00
|
|
|
|
seen_continuations = set()
|
2020-11-19 12:22:59 -07:00
|
|
|
|
for page_num in itertools.count(1):
|
|
|
|
|
if not continuation:
|
|
|
|
|
break
|
2023-07-14 21:20:24 -06:00
|
|
|
|
continuation_token = continuation.get('continuation')
|
|
|
|
|
if continuation_token is not None and continuation_token in seen_continuations:
|
|
|
|
|
self.write_debug('Detected YouTube feed looping - assuming end of feed.')
|
|
|
|
|
break
|
|
|
|
|
seen_continuations.add(continuation_token)
|
2021-09-23 18:52:17 -06:00
|
|
|
|
headers = self.generate_api_headers(
|
|
|
|
|
ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
|
2021-04-15 05:22:59 -06:00
|
|
|
|
response = self._extract_response(
|
2022-04-11 09:10:28 -06:00
|
|
|
|
item_id=f'{item_id} page {page_num}',
|
2021-07-18 22:55:07 -06:00
|
|
|
|
query=continuation, headers=headers, ytcfg=ytcfg,
|
2021-04-15 05:22:59 -06:00
|
|
|
|
check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
|
2021-03-03 03:32:40 -07:00
|
|
|
|
|
|
|
|
|
if not response:
|
2020-11-19 12:22:59 -07:00
|
|
|
|
break
|
2021-10-08 15:19:25 -06:00
|
|
|
|
# Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
|
|
|
|
|
# See: https://github.com/ytdl-org/youtube-dl/issues/28702
|
|
|
|
|
visitor_data = self._extract_visitor_data(response) or visitor_data
|
2016-02-18 09:03:46 -07:00
|
|
|
|
|
2021-02-09 08:02:12 -07:00
|
|
|
|
known_renderers = {
|
2022-03-17 17:53:51 -06:00
|
|
|
|
'videoRenderer': (self._grid_entries, 'items'), # for membership tab
|
2021-02-09 08:02:12 -07:00
|
|
|
|
'gridPlaylistRenderer': (self._grid_entries, 'items'),
|
|
|
|
|
'gridVideoRenderer': (self._grid_entries, 'items'),
|
2021-07-20 11:51:04 -06:00
|
|
|
|
'gridChannelRenderer': (self._grid_entries, 'items'),
|
2021-02-09 08:02:12 -07:00
|
|
|
|
'playlistVideoRenderer': (self._playlist_entries, 'contents'),
|
2021-03-04 11:05:26 -07:00
|
|
|
|
'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
|
2021-02-18 01:24:06 -07:00
|
|
|
|
'richItemRenderer': (extract_entries, 'contents'), # for hashtag
|
2022-09-26 16:25:58 -06:00
|
|
|
|
'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
|
|
|
|
|
'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
|
2022-09-26 17:14:54 -06:00
|
|
|
|
'playlistVideoListContinuation': (self._playlist_entries, None),
|
|
|
|
|
'gridContinuation': (self._grid_entries, None),
|
|
|
|
|
'itemSectionContinuation': (self._post_thread_continuation_entries, None),
|
|
|
|
|
'sectionListContinuation': (extract_entries, None), # for feeds
|
2021-02-09 08:02:12 -07:00
|
|
|
|
}
|
2022-09-26 17:14:54 -06:00
|
|
|
|
|
|
|
|
|
continuation_items = traverse_obj(response, (
|
|
|
|
|
('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
|
|
|
|
|
'appendContinuationItemsAction', 'continuationItems'
|
|
|
|
|
), 'continuationContents', get_all=False)
|
|
|
|
|
continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
|
|
|
|
|
|
2021-02-09 08:02:12 -07:00
|
|
|
|
video_items_renderer = None
|
2022-09-26 17:14:54 -06:00
|
|
|
|
for key in continuation_item.keys():
|
2021-02-09 08:02:12 -07:00
|
|
|
|
if key not in known_renderers:
|
2020-11-19 12:22:59 -07:00
|
|
|
|
continue
|
2022-09-26 17:14:54 -06:00
|
|
|
|
func, parent_key = known_renderers[key]
|
|
|
|
|
video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
|
2021-02-18 01:24:06 -07:00
|
|
|
|
continuation_list = [None]
|
2022-09-26 17:14:54 -06:00
|
|
|
|
yield from func(video_items_renderer)
|
2021-02-18 01:24:06 -07:00
|
|
|
|
continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
|
2022-09-26 17:14:54 -06:00
|
|
|
|
|
|
|
|
|
if not video_items_renderer:
|
2021-02-09 08:02:12 -07:00
|
|
|
|
break
|
2016-07-08 19:37:02 -06:00
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
@staticmethod
|
2022-02-28 22:08:19 -07:00
|
|
|
|
def _extract_selected_tab(tabs, fatal=True):
|
2022-11-09 01:58:44 -07:00
|
|
|
|
for tab_renderer in tabs:
|
|
|
|
|
if tab_renderer.get('selected'):
|
|
|
|
|
return tab_renderer
|
|
|
|
|
if fatal:
|
|
|
|
|
raise ExtractorError('Unable to find selected tab')
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _extract_tab_renderers(response):
|
|
|
|
|
return traverse_obj(
|
|
|
|
|
response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
|
2014-12-06 06:02:19 -07:00
|
|
|
|
|
2021-10-08 15:19:25 -06:00
|
|
|
|
def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
|
2022-11-11 01:22:40 -07:00
|
|
|
|
metadata = self._extract_metadata_from_tabs(item_id, data)
|
2021-02-02 09:21:32 -07:00
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
selected_tab = self._extract_selected_tab(tabs)
|
2022-11-11 01:22:40 -07:00
|
|
|
|
metadata['title'] += format_field(selected_tab, 'title', ' - %s')
|
|
|
|
|
metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
|
|
|
|
|
|
|
|
|
|
return self.playlist_result(
|
|
|
|
|
self._entries(
|
|
|
|
|
selected_tab, metadata['id'], ytcfg,
|
|
|
|
|
self._extract_account_syncid(ytcfg, data),
|
|
|
|
|
self._extract_visitor_data(data, ytcfg)),
|
|
|
|
|
**metadata)
|
2021-04-03 16:05:17 -06:00
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
def _extract_metadata_from_tabs(self, item_id, data):
|
|
|
|
|
info = {'id': item_id}
|
|
|
|
|
|
|
|
|
|
metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
|
2022-11-05 23:25:31 -06:00
|
|
|
|
if metadata_renderer:
|
2023-04-14 01:58:36 -06:00
|
|
|
|
channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
|
2023-05-24 12:00:43 -06:00
|
|
|
|
('channelUrl', {self.ucid_from_url}))
|
2022-11-11 01:22:40 -07:00
|
|
|
|
info.update({
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel': metadata_renderer.get('title'),
|
|
|
|
|
'channel_id': channel_id,
|
2022-11-11 01:22:40 -07:00
|
|
|
|
})
|
2023-04-14 01:58:36 -06:00
|
|
|
|
if info['channel_id']:
|
|
|
|
|
info['id'] = info['channel_id']
|
2022-11-11 01:22:40 -07:00
|
|
|
|
else:
|
|
|
|
|
metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
|
2021-02-02 09:21:32 -07:00
|
|
|
|
|
2022-01-20 07:59:09 -07:00
|
|
|
|
# We can get the uncropped banner/avatar by replacing the crop params with '=s0'
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
|
|
|
|
|
def _get_uncropped(url):
|
|
|
|
|
return url_or_none((url or '').split('=')[0] + '=s0')
|
|
|
|
|
|
2022-11-05 23:25:31 -06:00
|
|
|
|
avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
|
2022-01-20 07:59:09 -07:00
|
|
|
|
if avatar_thumbnails:
|
|
|
|
|
uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
|
|
|
|
|
if uncropped_avatar:
|
|
|
|
|
avatar_thumbnails.append({
|
|
|
|
|
'url': uncropped_avatar,
|
|
|
|
|
'id': 'avatar_uncropped',
|
|
|
|
|
'preference': 1
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
channel_banners = self._extract_thumbnails(
|
2022-11-11 01:22:40 -07:00
|
|
|
|
data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
|
2022-01-20 07:59:09 -07:00
|
|
|
|
for banner in channel_banners:
|
|
|
|
|
banner['preference'] = -10
|
|
|
|
|
|
|
|
|
|
if channel_banners:
|
|
|
|
|
uncropped_banner = _get_uncropped(channel_banners[0]['url'])
|
|
|
|
|
if uncropped_banner:
|
|
|
|
|
channel_banners.append({
|
|
|
|
|
'url': uncropped_banner,
|
|
|
|
|
'id': 'banner_uncropped',
|
|
|
|
|
'preference': -5
|
|
|
|
|
})
|
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
# Deprecated - remove primary_sidebar_renderer when layout discontinued
|
|
|
|
|
primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
|
|
|
|
|
playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
|
|
|
|
|
|
2022-01-20 07:59:09 -07:00
|
|
|
|
primary_thumbnails = self._extract_thumbnails(
|
2022-04-03 07:31:03 -06:00
|
|
|
|
primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
|
2022-11-05 23:25:31 -06:00
|
|
|
|
playlist_thumbnails = self._extract_thumbnails(
|
|
|
|
|
playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
|
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
info.update({
|
|
|
|
|
'title': (traverse_obj(metadata_renderer, 'title')
|
|
|
|
|
or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
|
|
|
|
|
or info['id']),
|
|
|
|
|
'availability': self._extract_availability(data),
|
|
|
|
|
'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
|
|
|
|
|
'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
|
|
|
|
|
'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
|
|
|
|
|
'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
|
|
|
|
|
})
|
2022-01-07 04:03:02 -07:00
|
|
|
|
|
2023-04-14 01:58:36 -06:00
|
|
|
|
channel_handle = (
|
|
|
|
|
traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
|
|
|
|
|
or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
|
|
|
|
|
|
|
|
|
|
if channel_handle:
|
|
|
|
|
info.update({
|
|
|
|
|
'uploader_id': channel_handle,
|
|
|
|
|
'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
|
|
|
|
|
})
|
2023-06-08 01:50:05 -06:00
|
|
|
|
|
|
|
|
|
channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False))
|
|
|
|
|
if self._has_badge(channel_badges, BadgeType.VERIFIED):
|
|
|
|
|
info['channel_is_verified'] = True
|
2022-11-05 23:25:31 -06:00
|
|
|
|
# Playlist stats is a text runs array containing [video count, view count, last updated].
|
|
|
|
|
# last updated or (view count and last updated) may be missing.
|
|
|
|
|
playlist_stats = get_first(
|
2022-11-11 01:22:40 -07:00
|
|
|
|
(primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
|
|
|
|
|
|
2022-11-05 23:25:31 -06:00
|
|
|
|
last_updated_unix = self._parse_time_text(
|
|
|
|
|
self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
|
|
|
|
|
or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
|
2023-06-20 21:51:20 -06:00
|
|
|
|
info['modified_date'] = strftime_or_none(last_updated_unix)
|
2022-11-05 23:25:31 -06:00
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
info['view_count'] = self._get_count(playlist_stats, 1)
|
|
|
|
|
if info['view_count'] is None: # 0 is allowed
|
|
|
|
|
info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
|
2023-02-28 11:20:34 -07:00
|
|
|
|
if info['view_count'] is None:
|
|
|
|
|
info['view_count'] = self._get_count(data, (
|
|
|
|
|
'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
|
|
|
|
|
'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
|
2022-11-11 01:22:40 -07:00
|
|
|
|
|
|
|
|
|
info['playlist_count'] = self._get_count(playlist_stats, 0)
|
|
|
|
|
if info['playlist_count'] is None: # 0 is allowed
|
|
|
|
|
info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
|
|
|
|
|
|
2023-04-14 01:58:36 -06:00
|
|
|
|
if not info.get('channel_id'):
|
2022-11-05 23:25:31 -06:00
|
|
|
|
owner = traverse_obj(playlist_header_renderer, 'ownerText')
|
2022-11-11 01:22:40 -07:00
|
|
|
|
if not owner: # Deprecated
|
2022-11-05 23:25:31 -06:00
|
|
|
|
owner = traverse_obj(
|
|
|
|
|
self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
|
|
|
|
|
('videoOwner', 'videoOwnerRenderer', 'title'))
|
|
|
|
|
owner_text = self._get_text(owner)
|
|
|
|
|
browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
|
2022-11-11 01:22:40 -07:00
|
|
|
|
info.update({
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
|
|
|
|
|
'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
|
|
|
|
|
'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
|
2022-11-11 01:22:40 -07:00
|
|
|
|
})
|
2022-11-05 23:25:31 -06:00
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
info.update({
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': info['channel'],
|
|
|
|
|
'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
|
|
|
|
|
'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
|
2022-11-11 01:22:40 -07:00
|
|
|
|
})
|
2023-04-14 01:58:36 -06:00
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
return info
|
2016-07-05 10:30:44 -06:00
|
|
|
|
|
2022-05-01 00:46:28 -06:00
|
|
|
|
def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
|
2021-10-08 15:19:25 -06:00
|
|
|
|
first_id = last_id = response = None
|
2021-03-06 22:24:54 -07:00
|
|
|
|
for page_num in itertools.count(1):
|
2021-03-04 11:05:26 -07:00
|
|
|
|
videos = list(self._playlist_entries(playlist))
|
|
|
|
|
if not videos:
|
|
|
|
|
return
|
2021-03-06 22:24:54 -07:00
|
|
|
|
start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
|
|
|
|
|
if start >= len(videos):
|
|
|
|
|
return
|
2022-05-16 08:06:36 -06:00
|
|
|
|
yield from videos[start:]
|
2021-03-06 22:24:54 -07:00
|
|
|
|
first_id = first_id or videos[0]['id']
|
|
|
|
|
last_id = videos[-1]['id']
|
2021-04-15 05:22:59 -06:00
|
|
|
|
watch_endpoint = try_get(
|
|
|
|
|
playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
|
2021-10-08 15:19:25 -06:00
|
|
|
|
headers = self.generate_api_headers(
|
|
|
|
|
ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
|
|
|
|
|
visitor_data=self._extract_visitor_data(response, data, ytcfg))
|
2021-04-15 05:22:59 -06:00
|
|
|
|
query = {
|
|
|
|
|
'playlistId': playlist_id,
|
|
|
|
|
'videoId': watch_endpoint.get('videoId') or last_id,
|
|
|
|
|
'index': watch_endpoint.get('index') or len(videos),
|
|
|
|
|
'params': watch_endpoint.get('params') or 'OAE%3D'
|
|
|
|
|
}
|
|
|
|
|
response = self._extract_response(
|
|
|
|
|
item_id='%s page %d' % (playlist_id, page_num),
|
2021-07-18 22:55:07 -06:00
|
|
|
|
query=query, ep='next', headers=headers, ytcfg=ytcfg,
|
2021-04-15 05:22:59 -06:00
|
|
|
|
check_get_keys='contents'
|
|
|
|
|
)
|
2021-03-04 11:05:26 -07:00
|
|
|
|
playlist = try_get(
|
2021-04-15 05:22:59 -06:00
|
|
|
|
response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
2021-10-08 15:19:25 -06:00
|
|
|
|
def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
|
2020-11-19 12:22:59 -07:00
|
|
|
|
title = playlist.get('title') or try_get(
|
2022-06-24 04:54:43 -06:00
|
|
|
|
data, lambda x: x['titleText']['simpleText'], str)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
playlist_id = playlist.get('playlistId') or item_id
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
|
|
|
|
# Delegating everything except mix playlists to regular tab-based playlist URL
|
2021-01-01 05:26:37 -07:00
|
|
|
|
playlist_url = urljoin(url, try_get(
|
|
|
|
|
playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
|
2022-06-24 04:54:43 -06:00
|
|
|
|
str))
|
2022-05-01 00:46:28 -06:00
|
|
|
|
|
|
|
|
|
# Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
|
|
|
|
|
# [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
|
|
|
|
|
is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
|
|
|
|
|
|
|
|
|
|
if playlist_url and playlist_url != url and not is_known_unviewable:
|
2021-01-01 05:26:37 -07:00
|
|
|
|
return self.url_result(
|
|
|
|
|
playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
|
|
|
|
|
video_title=title)
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
return self.playlist_result(
|
2022-05-01 00:46:28 -06:00
|
|
|
|
self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
|
2021-03-04 11:05:26 -07:00
|
|
|
|
playlist_id=playlist_id, playlist_title=title)
|
2013-06-23 11:58:33 -06:00
|
|
|
|
|
2021-07-14 20:42:30 -06:00
|
|
|
|
def _extract_availability(self, data):
|
|
|
|
|
"""
|
|
|
|
|
Gets the availability of a given playlist/tab.
|
|
|
|
|
Note: Unless YouTube tells us explicitly, we do not assume it is public
|
|
|
|
|
@param data: response
|
|
|
|
|
"""
|
2022-11-05 23:25:31 -06:00
|
|
|
|
sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
|
|
|
|
|
playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
|
|
|
|
|
player_header_privacy = playlist_header_renderer.get('privacy')
|
2022-09-08 23:16:46 -06:00
|
|
|
|
|
2023-06-08 07:28:49 -06:00
|
|
|
|
badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges'))
|
2021-07-14 20:42:30 -06:00
|
|
|
|
|
|
|
|
|
# Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
|
2022-11-05 23:25:31 -06:00
|
|
|
|
privacy_setting_icon = get_first(
|
|
|
|
|
(playlist_header_renderer, sidebar_renderer),
|
|
|
|
|
('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
|
|
|
|
|
lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
|
|
|
|
|
expected_type=str)
|
|
|
|
|
|
|
|
|
|
microformats_is_unlisted = traverse_obj(
|
|
|
|
|
data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
|
2021-07-14 20:42:30 -06:00
|
|
|
|
|
2022-09-08 23:16:46 -06:00
|
|
|
|
return (
|
|
|
|
|
'public' if (
|
|
|
|
|
self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
|
|
|
|
|
or player_header_privacy == 'PUBLIC'
|
|
|
|
|
or privacy_setting_icon == 'PRIVACY_PUBLIC')
|
|
|
|
|
else self._availability(
|
|
|
|
|
is_private=(
|
|
|
|
|
self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
|
|
|
|
|
or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
|
|
|
|
|
else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
|
|
|
|
|
is_unlisted=(
|
|
|
|
|
self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
|
|
|
|
|
or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
|
2022-11-05 23:25:31 -06:00
|
|
|
|
else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
|
|
|
|
|
else microformats_is_unlisted if microformats_is_unlisted is not None else None),
|
2022-09-08 23:16:46 -06:00
|
|
|
|
needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
|
|
|
|
|
needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
|
|
|
|
|
needs_auth=False))
|
2021-07-14 20:42:30 -06:00
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
|
|
|
|
|
sidebar_renderer = try_get(
|
|
|
|
|
data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
|
|
|
|
|
for item in sidebar_renderer:
|
|
|
|
|
renderer = try_get(item, lambda x: x[info_renderer], expected_type)
|
|
|
|
|
if renderer:
|
|
|
|
|
return renderer
|
|
|
|
|
|
2021-10-08 15:19:25 -06:00
|
|
|
|
def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
|
2021-04-16 16:39:08 -06:00
|
|
|
|
"""
|
2022-11-05 23:25:31 -06:00
|
|
|
|
Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
|
2021-04-16 16:39:08 -06:00
|
|
|
|
"""
|
2022-11-05 23:25:31 -06:00
|
|
|
|
is_playlist = bool(traverse_obj(
|
|
|
|
|
data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
|
|
|
|
|
if not is_playlist:
|
2021-07-14 20:42:30 -06:00
|
|
|
|
return
|
2021-07-20 21:52:34 -06:00
|
|
|
|
headers = self.generate_api_headers(
|
2021-09-23 18:52:17 -06:00
|
|
|
|
ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
|
2021-10-08 15:19:25 -06:00
|
|
|
|
visitor_data=self._extract_visitor_data(data, ytcfg))
|
2021-07-14 20:42:30 -06:00
|
|
|
|
query = {
|
2022-11-05 23:25:31 -06:00
|
|
|
|
'params': 'wgYCCAA=',
|
|
|
|
|
'browseId': f'VL{item_id}'
|
2021-07-14 20:42:30 -06:00
|
|
|
|
}
|
|
|
|
|
return self._extract_response(
|
|
|
|
|
item_id=item_id, headers=headers, query=query,
|
2021-07-18 22:55:07 -06:00
|
|
|
|
check_get_keys='contents', fatal=False, ytcfg=ytcfg,
|
2022-11-05 23:25:31 -06:00
|
|
|
|
note='Redownloading playlist API JSON with unavailable videos')
|
2021-04-16 16:39:08 -06:00
|
|
|
|
|
2022-05-20 09:25:21 -06:00
|
|
|
|
@functools.cached_property
|
2022-04-09 13:30:21 -06:00
|
|
|
|
def skip_webpage(self):
|
|
|
|
|
return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
|
|
|
|
|
|
2021-10-08 15:19:25 -06:00
|
|
|
|
def _extract_webpage(self, url, item_id, fatal=True):
|
2022-08-01 14:13:18 -06:00
|
|
|
|
webpage, data = None, None
|
|
|
|
|
for retry in self.RetryManager(fatal=fatal):
|
2021-10-08 15:19:25 -06:00
|
|
|
|
try:
|
2022-08-01 14:13:18 -06:00
|
|
|
|
webpage = self._download_webpage(url, item_id, note='Downloading webpage')
|
2021-10-08 15:19:25 -06:00
|
|
|
|
data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
|
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
if isinstance(e.cause, network_exceptions):
|
2023-07-09 01:53:02 -06:00
|
|
|
|
if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429):
|
2022-08-01 14:13:18 -06:00
|
|
|
|
retry.error = e
|
|
|
|
|
continue
|
|
|
|
|
self._error_or_warning(e, fatal=fatal)
|
2021-02-25 14:52:44 -07:00
|
|
|
|
break
|
2021-10-08 15:19:25 -06:00
|
|
|
|
|
2022-08-01 14:13:18 -06:00
|
|
|
|
try:
|
|
|
|
|
self._extract_and_report_alerts(data)
|
|
|
|
|
except ExtractorError as e:
|
|
|
|
|
self._error_or_warning(e, fatal=fatal)
|
|
|
|
|
break
|
2021-10-08 15:19:25 -06:00
|
|
|
|
|
2022-08-01 14:13:18 -06:00
|
|
|
|
# Sometimes youtube returns a webpage with incomplete ytInitialData
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/116
|
|
|
|
|
if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
|
|
|
|
|
retry.error = ExtractorError('Incomplete yt initial data received')
|
|
|
|
|
continue
|
2021-10-08 15:19:25 -06:00
|
|
|
|
|
2021-03-04 11:05:26 -07:00
|
|
|
|
return webpage, data
|
|
|
|
|
|
2022-04-09 13:30:21 -06:00
|
|
|
|
def _report_playlist_authcheck(self, ytcfg, fatal=True):
|
|
|
|
|
"""Use if failed to extract ytcfg (and data) from initial webpage"""
|
|
|
|
|
if not ytcfg and self.is_authenticated:
|
|
|
|
|
msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
|
|
|
|
|
if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
|
|
|
|
|
raise ExtractorError(
|
|
|
|
|
f'{msg}. If you are not downloading private content, or '
|
|
|
|
|
'your cookies are only for the first account and channel,'
|
|
|
|
|
' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
|
|
|
|
|
expected=True)
|
|
|
|
|
self.report_warning(msg, only_once=True)
|
|
|
|
|
|
2021-10-08 15:19:25 -06:00
|
|
|
|
def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
|
|
|
|
|
data = None
|
2022-04-09 13:30:21 -06:00
|
|
|
|
if not self.skip_webpage:
|
2021-10-08 15:19:25 -06:00
|
|
|
|
webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
|
|
|
|
|
ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
|
2022-02-22 14:37:47 -07:00
|
|
|
|
# Reject webpage data if redirected to home page without explicitly requesting
|
2022-11-09 01:58:44 -07:00
|
|
|
|
selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
|
2022-02-22 14:37:47 -07:00
|
|
|
|
if (url != 'https://www.youtube.com/feed/recommended'
|
|
|
|
|
and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
|
|
|
|
|
and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
|
|
|
|
|
msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
|
|
|
|
|
if fatal:
|
|
|
|
|
raise ExtractorError(msg, expected=True)
|
|
|
|
|
self.report_warning(msg, only_once=True)
|
2021-10-08 15:19:25 -06:00
|
|
|
|
if not data:
|
2022-04-09 13:30:21 -06:00
|
|
|
|
self._report_playlist_authcheck(ytcfg, fatal=fatal)
|
2021-10-08 15:19:25 -06:00
|
|
|
|
data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
|
|
|
|
|
return data, ytcfg
|
|
|
|
|
|
|
|
|
|
def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
|
|
|
|
|
headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
|
|
|
|
|
resolve_response = self._extract_response(
|
|
|
|
|
item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
|
|
|
|
|
ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
|
|
|
|
|
endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
|
|
|
|
|
for ep_key, ep in endpoints.items():
|
|
|
|
|
params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
|
|
|
|
|
if params:
|
|
|
|
|
return self._extract_response(
|
|
|
|
|
item_id=item_id, query=params, ep=ep, headers=headers,
|
|
|
|
|
ytcfg=ytcfg, fatal=fatal, default_client=default_client,
|
2022-02-28 22:08:19 -07:00
|
|
|
|
check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
|
2021-10-08 15:19:25 -06:00
|
|
|
|
err_note = 'Failed to resolve url (does the playlist exist?)'
|
|
|
|
|
if fatal:
|
|
|
|
|
raise ExtractorError(err_note, expected=True)
|
|
|
|
|
self.report_warning(err_note, item_id)
|
|
|
|
|
|
2021-11-23 20:01:52 -07:00
|
|
|
|
_SEARCH_PARAMS = None
|
|
|
|
|
|
2022-02-03 14:25:38 -07:00
|
|
|
|
def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
|
2021-11-23 20:01:52 -07:00
|
|
|
|
data = {'query': query}
|
|
|
|
|
if params is NO_DEFAULT:
|
|
|
|
|
params = self._SEARCH_PARAMS
|
|
|
|
|
if params:
|
|
|
|
|
data['params'] = params
|
2022-02-01 11:24:00 -07:00
|
|
|
|
|
|
|
|
|
content_keys = (
|
|
|
|
|
('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
|
|
|
|
|
('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
|
|
|
|
|
# ytmusic search
|
|
|
|
|
('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
|
|
|
|
|
('continuationContents', ),
|
|
|
|
|
)
|
2022-04-09 13:30:21 -06:00
|
|
|
|
display_id = f'query "{query}"'
|
2022-04-11 09:10:28 -06:00
|
|
|
|
check_get_keys = tuple({keys[0] for keys in content_keys})
|
2022-04-09 13:30:21 -06:00
|
|
|
|
ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
|
|
|
|
|
self._report_playlist_authcheck(ytcfg, fatal=False)
|
2022-02-01 11:24:00 -07:00
|
|
|
|
|
2021-11-23 20:57:59 -07:00
|
|
|
|
continuation_list = [None]
|
2022-04-09 13:30:21 -06:00
|
|
|
|
search = None
|
2021-11-23 20:01:52 -07:00
|
|
|
|
for page_num in itertools.count(1):
|
2021-11-23 20:57:59 -07:00
|
|
|
|
data.update(continuation_list[0] or {})
|
2022-04-09 13:30:21 -06:00
|
|
|
|
headers = self.generate_api_headers(
|
|
|
|
|
ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
|
2021-11-23 20:01:52 -07:00
|
|
|
|
search = self._extract_response(
|
2022-04-09 13:30:21 -06:00
|
|
|
|
item_id=f'{display_id} page {page_num}', ep='search', query=data,
|
|
|
|
|
default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
|
2022-02-01 11:24:00 -07:00
|
|
|
|
slr_contents = traverse_obj(search, *content_keys)
|
|
|
|
|
yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
|
2021-11-23 20:57:59 -07:00
|
|
|
|
if not continuation_list[0]:
|
2021-11-23 20:01:52 -07:00
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
|
|
|
|
|
IE_DESC = 'YouTube Tabs'
|
|
|
|
|
_VALID_URL = r'''(?x:
|
|
|
|
|
https?://
|
2023-02-03 11:23:35 -07:00
|
|
|
|
(?!consent\.)(?:\w+\.)?
|
2021-11-23 20:01:52 -07:00
|
|
|
|
(?:
|
|
|
|
|
youtube(?:kids)?\.com|
|
|
|
|
|
%(invidious)s
|
|
|
|
|
)/
|
|
|
|
|
(?:
|
|
|
|
|
(?P<channel_type>channel|c|user|browse)/|
|
|
|
|
|
(?P<not_channel>
|
|
|
|
|
feed/|hashtag/|
|
|
|
|
|
(?:playlist|watch)\?.*?\blist=
|
|
|
|
|
)|
|
|
|
|
|
(?!(?:%(reserved_names)s)\b) # Direct URLs
|
|
|
|
|
)
|
|
|
|
|
(?P<id>[^/?\#&]+)
|
|
|
|
|
)''' % {
|
|
|
|
|
'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
|
|
|
|
|
'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
|
|
|
|
|
}
|
|
|
|
|
IE_NAME = 'youtube:tab'
|
|
|
|
|
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'note': 'playlists, multipage',
|
|
|
|
|
'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
|
|
|
|
|
'playlist_mincount': 94,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCqj7Cz7revf5maW9g5pgNcg',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'title': 'Igor Kleiner - Playlists',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'uploader': 'Igor Kleiner',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@IgorDataScience',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@IgorDataScience',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'Igor Kleiner',
|
|
|
|
|
'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
|
|
|
|
|
'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'playlists, multipage, different order',
|
|
|
|
|
'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
|
|
|
|
|
'playlist_mincount': 94,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCqj7Cz7revf5maW9g5pgNcg',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'title': 'Igor Kleiner - Playlists',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'uploader': 'Igor Kleiner',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@IgorDataScience',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@IgorDataScience',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
|
|
|
|
|
'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
|
|
|
|
|
'channel': 'Igor Kleiner',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'playlists, series',
|
|
|
|
|
'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
|
|
|
|
|
'playlist_mincount': 5,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCYO_jab_esuFRV4b17AJtAw',
|
|
|
|
|
'title': '3Blue1Brown - Playlists',
|
|
|
|
|
'description': 'md5:e1384e8a133307dd10edee76e875d62f',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
|
|
|
|
|
'channel': '3Blue1Brown',
|
|
|
|
|
'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@3blue1brown',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@3blue1brown',
|
|
|
|
|
'uploader': '3Blue1Brown',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': ['Mathematics'],
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'channel_follower_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'playlists, singlepage',
|
|
|
|
|
'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
|
|
|
|
|
'playlist_mincount': 4,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
|
|
|
|
|
'title': 'ThirstForScience - Playlists',
|
|
|
|
|
'description': 'md5:609399d937ea957b0f53cbffb747a14c',
|
|
|
|
|
'uploader': 'ThirstForScience',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@ThirstForScience',
|
|
|
|
|
'uploader_id': '@ThirstForScience',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': 'count:13',
|
|
|
|
|
'channel': 'ThirstForScience',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'basic, single video playlist',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
|
|
|
|
|
'title': 'youtube-dl public playlist',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'description': '',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'modified_date': '20201130',
|
|
|
|
|
'channel': 'Sergey M.',
|
|
|
|
|
'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'Sergey M.',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@sergeym.6173',
|
|
|
|
|
'uploader_id': '@sergeym.6173',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_count': 1,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'empty playlist',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
|
|
|
|
|
'title': 'youtube-dl empty playlist',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
|
|
|
|
'channel': 'Sergey M.',
|
|
|
|
|
'description': '',
|
|
|
|
|
'modified_date': '20160902',
|
|
|
|
|
'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@sergeym.6173',
|
|
|
|
|
'uploader_id': '@sergeym.6173',
|
|
|
|
|
'uploader': 'Sergey M.',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_count': 0,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Home tab',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'title': 'lex will - Home',
|
|
|
|
|
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
|
|
|
|
|
'uploader': 'lex will',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@lexwill718',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'lex will',
|
|
|
|
|
'tags': ['bible', 'history', 'prophesy'],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@lexwill718',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 2,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Videos tab',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'title': 'lex will - Videos',
|
|
|
|
|
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
|
|
|
|
|
'uploader': 'lex will',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@lexwill718',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': ['bible', 'history', 'prophesy'],
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@lexwill718',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'lex will',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 975,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Videos tab, sorted by popular',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'title': 'lex will - Videos',
|
|
|
|
|
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
|
|
|
|
|
'uploader': 'lex will',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@lexwill718',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@lexwill718',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'lex will',
|
|
|
|
|
'tags': ['bible', 'history', 'prophesy'],
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 199,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Playlists tab',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'title': 'lex will - Playlists',
|
|
|
|
|
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
|
|
|
|
|
'uploader': 'lex will',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@lexwill718',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@lexwill718',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'lex will',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'tags': ['bible', 'history', 'prophesy'],
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 17,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Community tab',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'title': 'lex will - Community',
|
|
|
|
|
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'lex will',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'tags': ['bible', 'history', 'prophesy'],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@lexwill718',
|
|
|
|
|
'uploader_id': '@lexwill718',
|
|
|
|
|
'uploader': 'lex will',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 18,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Channels tab',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'title': 'lex will - Channels',
|
|
|
|
|
'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'lex will',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
|
|
|
|
|
'tags': ['bible', 'history', 'prophesy'],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@lexwill718',
|
|
|
|
|
'uploader_id': '@lexwill718',
|
|
|
|
|
'uploader': 'lex will',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 12,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Search tab',
|
|
|
|
|
'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
|
|
|
|
|
'playlist_mincount': 40,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCYO_jab_esuFRV4b17AJtAw',
|
|
|
|
|
'title': '3Blue1Brown - Search - linear algebra',
|
|
|
|
|
'description': 'md5:e1384e8a133307dd10edee76e875d62f',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
|
|
|
|
|
'tags': ['Mathematics'],
|
|
|
|
|
'channel': '3Blue1Brown',
|
|
|
|
|
'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@3blue1brown',
|
|
|
|
|
'uploader_id': '@3blue1brown',
|
|
|
|
|
'uploader': '3Blue1Brown',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': '29C3: Not my department',
|
|
|
|
|
'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
|
|
|
|
|
'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'modified_date': '20150605',
|
|
|
|
|
'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'Christiaan008',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@ChRiStIaAn008',
|
|
|
|
|
'uploader': 'Christiaan008',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_count': 96,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Large playlist',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'Uploads from Cauchemar',
|
|
|
|
|
'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
|
|
|
|
'modified_date': r're:\d{8}',
|
|
|
|
|
'channel': 'Cauchemar',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'description': '',
|
|
|
|
|
'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@Cauchemar89',
|
|
|
|
|
'uploader': 'Cauchemar',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@Cauchemar89',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 1123,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'even larger playlist, 8832 videos',
|
|
|
|
|
'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'Uploads from Interstellar Movie',
|
|
|
|
|
'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'Interstellar Movie',
|
|
|
|
|
'description': '',
|
|
|
|
|
'modified_date': r're:\d{8}',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@InterstellarMovie',
|
|
|
|
|
'uploader': 'Interstellar Movie',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 21,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Playlist with "show unavailable videos" button',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
|
|
|
|
|
'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel': 'Phim Siêu Nhân Nhật Bản',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'description': '',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
|
|
|
|
|
'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
|
|
|
|
|
'modified_date': r're:\d{8}',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
|
|
|
|
|
'uploader_id': '@phimsieunhannhatban',
|
|
|
|
|
'uploader': 'Phim Siêu Nhân Nhật Bản',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 200,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'Playlist with unavailable videos in page 7',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'Uploads from BlankTV',
|
|
|
|
|
'id': 'UU8l9frL61Yl5KFOl87nIm2w',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'BlankTV',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'tags': [],
|
|
|
|
|
'modified_date': r're:\d{8}',
|
|
|
|
|
'description': '',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@blanktv',
|
|
|
|
|
'uploader': 'BlankTV',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@blanktv',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 1000,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'Data Analysis with Dr Mike Pound',
|
|
|
|
|
'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
|
|
|
|
|
'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'Computerphile',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2022-11-05 23:25:31 -06:00
|
|
|
|
'modified_date': '20190712',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@Computerphile',
|
|
|
|
|
'uploader': 'Computerphile',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@Computerphile',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 11,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Playlist URL that does not actually serve a playlist',
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'FqZTN594JQw',
|
|
|
|
|
'ext': 'webm',
|
|
|
|
|
'title': "Smiley's People 01 detective, Adventure Series, Action",
|
|
|
|
|
'upload_date': '20150526',
|
|
|
|
|
'license': 'Standard YouTube License',
|
|
|
|
|
'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
|
|
|
|
|
'categories': ['People & Blogs'],
|
|
|
|
|
'tags': list,
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'like_count': int,
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
'skip': 'This video is not available.',
|
|
|
|
|
'add_ie': [YoutubeIE.ie_key()],
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
|
|
|
|
|
'info_dict': {
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'id': 'hGkQjiJLjWQ', # This will keep changing
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'ext': 'mp4',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'title': str,
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'upload_date': r're:\d{8}',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'description': str,
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'categories': ['News & Politics'],
|
|
|
|
|
'tags': list,
|
|
|
|
|
'like_count': int,
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'release_timestamp': int,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'Sky News',
|
|
|
|
|
'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
|
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'view_count': int,
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'playable_in_embed': True,
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'release_date': r're:\d+',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'availability': 'public',
|
|
|
|
|
'live_status': 'is_live',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'concurrent_view_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@SkyNews',
|
|
|
|
|
'uploader_id': '@SkyNews',
|
|
|
|
|
'uploader': 'Sky News',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'expected_warnings': ['Ignoring subtitle tracks found in '],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/user/TheYoungTurks/live',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'a48o2S1cPoo',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'The Young Turks - Live Main Show',
|
|
|
|
|
'upload_date': '20150715',
|
|
|
|
|
'license': 'Standard YouTube License',
|
|
|
|
|
'description': 'md5:438179573adcdff3c97ebb1ee632b891',
|
|
|
|
|
'categories': ['News & Politics'],
|
|
|
|
|
'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
|
|
|
|
|
'like_count': int,
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'A channel that is not live. Should raise error',
|
|
|
|
|
'url': 'https://www.youtube.com/user/numberphile/live',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/feed/trending',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/feed/library',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/feed/history',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/feed/subscriptions',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/feed/watch_later',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Recommended - redirects to home page.',
|
|
|
|
|
'url': 'https://www.youtube.com/feed/recommended',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'inline playlist with not always working continuations',
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/course',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/zsecurity',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.youtube.com/NASAgovVideo/videos',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/TheYoungTurks/live',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/hashtag/cctv9',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'cctv9',
|
|
|
|
|
'title': '#cctv9',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
2022-11-09 19:44:12 -07:00
|
|
|
|
'playlist_mincount': 300, # not consistent but should be over 300
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
|
|
|
|
|
'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
|
|
|
|
|
'only_matching': True
|
|
|
|
|
}, {
|
|
|
|
|
'note': '/browse/ should redirect to /channel/',
|
|
|
|
|
'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
|
|
|
|
|
'only_matching': True
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'VLPL, should redirect to playlist?list=PL...',
|
|
|
|
|
'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
|
|
|
|
|
'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'title': 'NCS : All Releases 💿',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'modified_date': r're:\d{8}',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'channel': 'NoCopyrightSounds',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
|
|
|
|
|
'uploader': 'NoCopyrightSounds',
|
|
|
|
|
'uploader_id': '@NoCopyrightSounds',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 166,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
2023-04-14 01:58:36 -06:00
|
|
|
|
# TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'note': 'Topic, should redirect to playlist?list=UU...',
|
|
|
|
|
'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
|
|
|
|
|
'title': 'Uploads from Royalty Free Music - Topic',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
|
|
|
|
'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
|
|
|
|
|
'channel': 'Royalty Free Music - Topic',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
|
|
|
|
|
'modified_date': r're:\d{8}',
|
|
|
|
|
'description': '',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'Royalty Free Music - Topic',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 101,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
2022-11-09 01:58:44 -07:00
|
|
|
|
# Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
|
|
|
|
|
# Treat as a general feed
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
|
|
|
|
|
'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 9,
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'Youtube music Album',
|
|
|
|
|
'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
|
|
|
|
|
'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'description': '',
|
|
|
|
|
'availability': 'unlisted',
|
|
|
|
|
'modified_date': r're:\d{8}',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_count': 50,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'expected_warnings': ['YouTube Music is not directly supported'],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'unlisted single video playlist',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
|
|
|
|
|
'title': 'yt-dlp unlisted playlist test',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'availability': 'unlisted',
|
|
|
|
|
'tags': [],
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'modified_date': '20220418',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'colethedj',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'description': '',
|
|
|
|
|
'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@colethedj1894',
|
|
|
|
|
'uploader_id': '@colethedj1894',
|
|
|
|
|
'uploader': 'colethedj',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
2023-05-27 17:31:45 -06:00
|
|
|
|
'playlist': [{
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
|
|
|
|
|
'id': 'BaW_jenozKc',
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'ie_key': 'Youtube',
|
|
|
|
|
'duration': 10,
|
|
|
|
|
'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
|
|
|
|
|
'channel': 'Philipp Hagemeister',
|
|
|
|
|
'uploader_id': '@PhilippHagemeister',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
|
|
|
|
|
'uploader': 'Philipp Hagemeister',
|
|
|
|
|
}
|
|
|
|
|
}],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
'playlist_count': 1,
|
2023-05-27 17:31:45 -06:00
|
|
|
|
'params': {'extract_flat': True},
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
|
|
|
|
|
'url': 'https://www.youtube.com/feed/recommended',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'recommended',
|
|
|
|
|
'title': 'recommended',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'tags': [],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 50,
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
'extractor_args': {'youtubetab': {'skip': ['webpage']}}
|
|
|
|
|
},
|
|
|
|
|
}, {
|
|
|
|
|
'note': 'API Fallback: /videos tab, sorted by oldest first',
|
|
|
|
|
'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
|
|
|
|
|
'title': 'Cody\'sLab - Videos',
|
|
|
|
|
'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'Cody\'sLab',
|
|
|
|
|
'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
|
2022-01-20 23:04:36 -07:00
|
|
|
|
'channel_follower_count': int
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 650,
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
'extractor_args': {'youtubetab': {'skip': ['webpage']}}
|
|
|
|
|
},
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'skip': 'Query for sorting no longer works',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
|
|
|
|
|
'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
|
|
|
|
|
'title': 'Uploads from Royalty Free Music - Topic',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'modified_date': r're:\d{8}',
|
|
|
|
|
'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
|
|
|
|
|
'description': '',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'channel': 'Royalty Free Music - Topic',
|
|
|
|
|
'view_count': int,
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': 'Royalty Free Music - Topic',
|
2021-11-23 20:01:52 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 101,
|
|
|
|
|
'params': {
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
'extractor_args': {'youtubetab': {'skip': ['webpage']}}
|
|
|
|
|
},
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
|
2022-02-28 22:08:19 -07:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'non-standard redirect to regional channel',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
|
|
|
|
|
'only_matching': True
|
2022-04-07 02:11:16 -06:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
|
|
|
|
|
'modified_date': '20220407',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'availability': 'unlisted',
|
|
|
|
|
'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
|
|
|
|
|
'channel': 'pukkandan',
|
|
|
|
|
'description': 'Test for collaborative playlist',
|
|
|
|
|
'title': 'yt-dlp test - collaborative playlist',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'view_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@pukkandan',
|
|
|
|
|
'uploader_id': '@pukkandan',
|
|
|
|
|
'uploader': 'pukkandan',
|
2022-04-07 02:11:16 -06:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 2
|
2022-09-08 23:16:46 -06:00
|
|
|
|
}, {
|
|
|
|
|
'note': 'translated tab name',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
|
2022-11-09 19:44:12 -07:00
|
|
|
|
'description': 'test description',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'title': 'cole-dlp-test-acc - 再生リスト',
|
|
|
|
|
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'channel': 'cole-dlp-test-acc',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@coletdjnz',
|
|
|
|
|
'uploader_id': '@coletdjnz',
|
|
|
|
|
'uploader': 'cole-dlp-test-acc',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 1,
|
|
|
|
|
'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
|
|
|
|
|
'expected_warnings': ['Preferring "ja"'],
|
|
|
|
|
}, {
|
|
|
|
|
# XXX: this should really check flat playlist entries, but the test suite doesn't support that
|
|
|
|
|
'note': 'preferred lang set with playlist with translated video titles',
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'channel': 'cole-dlp-test-acc',
|
|
|
|
|
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'description': 'test',
|
|
|
|
|
'title': 'dlp test playlist',
|
|
|
|
|
'availability': 'public',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@coletdjnz',
|
|
|
|
|
'uploader_id': '@coletdjnz',
|
|
|
|
|
'uploader': 'cole-dlp-test-acc',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 1,
|
|
|
|
|
'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
|
|
|
|
|
'expected_warnings': ['Preferring "ja"'],
|
2022-09-21 23:39:02 -06:00
|
|
|
|
}, {
|
|
|
|
|
# shorts audio pivot for 2GtVksBMYFM.
|
|
|
|
|
'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'sfv_audio_pivot',
|
|
|
|
|
'title': 'sfv_audio_pivot',
|
|
|
|
|
'tags': [],
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 50,
|
|
|
|
|
|
2022-11-09 01:58:44 -07:00
|
|
|
|
}, {
|
|
|
|
|
# Channel with a real live tab (not to be mistaken with streams tab)
|
|
|
|
|
# Do not treat like it should redirect to live stream
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
|
|
|
|
|
'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
|
|
|
|
|
'tags': [],
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 20,
|
|
|
|
|
}, {
|
|
|
|
|
# Tab name is not the same as tab id
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCQvWX73GQygcwXOTSf_VDVg',
|
|
|
|
|
'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
|
|
|
|
|
'tags': [],
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 8,
|
|
|
|
|
}, {
|
|
|
|
|
# Home tab id is literally home. Not to get mistaken with featured
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCQvWX73GQygcwXOTSf_VDVg',
|
|
|
|
|
'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
|
|
|
|
|
'tags': [],
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 8,
|
|
|
|
|
}, {
|
|
|
|
|
# Should get three playlists for videos, shorts and streams tabs
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
|
2022-11-11 01:22:40 -07:00
|
|
|
|
'title': 'Polka Ch. 尾丸ポルカ',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'description': 'md5:e56b74b5bb7e9c701522162e9abfb822',
|
2022-11-11 01:22:40 -07:00
|
|
|
|
'channel': 'Polka Ch. 尾丸ポルカ',
|
|
|
|
|
'tags': 'count:35',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@OmaruPolka',
|
|
|
|
|
'uploader': 'Polka Ch. 尾丸ポルカ',
|
|
|
|
|
'uploader_id': '@OmaruPolka',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_count': 3,
|
|
|
|
|
}, {
|
|
|
|
|
# Shorts tab with channel with handle
|
2023-04-14 01:58:36 -06:00
|
|
|
|
# TODO: fix channel description
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'url': 'https://www.youtube.com/@NotJustBikes/shorts',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UC0intLFzLaudFG-xAvUEO-A',
|
|
|
|
|
'title': 'Not Just Bikes - Shorts',
|
|
|
|
|
'tags': 'count:12',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'description': 'md5:26bc55af26855a608a5cf89dfa595c8d',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
|
|
|
|
|
'channel': 'Not Just Bikes',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@NotJustBikes',
|
|
|
|
|
'uploader': 'Not Just Bikes',
|
|
|
|
|
'uploader_id': '@NotJustBikes',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 10,
|
|
|
|
|
}, {
|
|
|
|
|
# Streams tab
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
|
|
|
|
|
'title': '中村悠一 - Live',
|
|
|
|
|
'tags': 'count:7',
|
|
|
|
|
'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
|
|
|
|
|
'channel': '中村悠一',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
|
|
|
|
|
'uploader_id': '@Yuichi-Nakamura',
|
|
|
|
|
'uploader': '中村悠一',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 60,
|
|
|
|
|
}, {
|
|
|
|
|
# Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
|
|
|
|
|
# See test_youtube_lists
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
# No uploads and no UCID given. Should fail with no uploads error
|
|
|
|
|
# See test_youtube_lists
|
|
|
|
|
'url': 'https://www.youtube.com/news',
|
|
|
|
|
'only_matching': True
|
|
|
|
|
}, {
|
|
|
|
|
# No videos tab but has a shorts tab
|
|
|
|
|
'url': 'https://www.youtube.com/c/TKFShorts',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
|
|
|
|
|
'title': 'Shorts Break - Shorts',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'tags': 'count:48',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
|
|
|
|
|
'channel': 'Shorts Break',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
|
|
|
|
|
'uploader': 'Shorts Break',
|
|
|
|
|
'uploader_id': '@ShortsBreak_Official',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 30,
|
|
|
|
|
}, {
|
|
|
|
|
# Trending Now Tab. tab id is empty
|
|
|
|
|
'url': 'https://www.youtube.com/feed/trending',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'trending',
|
|
|
|
|
'title': 'trending - Now',
|
|
|
|
|
'tags': [],
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 30,
|
|
|
|
|
}, {
|
|
|
|
|
# Trending Gaming Tab. tab id is empty
|
|
|
|
|
'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'trending',
|
|
|
|
|
'title': 'trending - Gaming',
|
|
|
|
|
'tags': [],
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 30,
|
2022-11-09 19:44:12 -07:00
|
|
|
|
}, {
|
|
|
|
|
# Shorts url result in shorts tab
|
2023-04-14 01:58:36 -06:00
|
|
|
|
# TODO: Fix channel id extraction
|
2022-11-09 19:44:12 -07:00
|
|
|
|
'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'title': 'cole-dlp-test-acc - Shorts',
|
|
|
|
|
'channel': 'cole-dlp-test-acc',
|
|
|
|
|
'description': 'test description',
|
|
|
|
|
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'tags': [],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@coletdjnz',
|
|
|
|
|
'uploader_id': '@coletdjnz',
|
2022-11-09 19:44:12 -07:00
|
|
|
|
'uploader': 'cole-dlp-test-acc',
|
|
|
|
|
},
|
|
|
|
|
'playlist': [{
|
|
|
|
|
'info_dict': {
|
2023-04-14 01:58:36 -06:00
|
|
|
|
# Channel data is not currently available for short renderers (as of 2023-03-01)
|
2022-11-09 19:44:12 -07:00
|
|
|
|
'_type': 'url',
|
|
|
|
|
'ie_key': 'Youtube',
|
|
|
|
|
'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
|
|
|
|
|
'id': 'sSM9J5YH_60',
|
|
|
|
|
'title': 'SHORT short',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'thumbnails': list,
|
|
|
|
|
}
|
|
|
|
|
}],
|
|
|
|
|
'params': {'extract_flat': True},
|
|
|
|
|
}, {
|
|
|
|
|
# Live video status should be extracted
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCQvWX73GQygcwXOTSf_VDVg',
|
|
|
|
|
'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
|
|
|
|
|
'tags': []
|
|
|
|
|
},
|
|
|
|
|
'playlist': [{
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'ie_key': 'Youtube',
|
|
|
|
|
'url': 'startswith:https://www.youtube.com/watch?v=',
|
|
|
|
|
'id': str,
|
|
|
|
|
'title': str,
|
|
|
|
|
'live_status': 'is_live',
|
|
|
|
|
'channel_id': str,
|
|
|
|
|
'channel_url': str,
|
|
|
|
|
'concurrent_view_count': int,
|
|
|
|
|
'channel': str,
|
2023-05-27 17:31:45 -06:00
|
|
|
|
'uploader': str,
|
|
|
|
|
'uploader_url': str,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'uploader_id': str,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': bool, # this will keep changing
|
2022-11-09 19:44:12 -07:00
|
|
|
|
}
|
|
|
|
|
}],
|
2022-12-12 16:08:14 -07:00
|
|
|
|
'params': {'extract_flat': True, 'playlist_items': '1'},
|
2022-11-09 19:44:12 -07:00
|
|
|
|
'playlist_mincount': 1
|
2022-12-12 16:08:14 -07:00
|
|
|
|
}, {
|
|
|
|
|
# Channel renderer metadata. Contains number of videos on the channel
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'title': 'cole-dlp-test-acc - Channels',
|
|
|
|
|
'channel': 'cole-dlp-test-acc',
|
|
|
|
|
'description': 'test description',
|
|
|
|
|
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
|
|
|
|
|
'tags': [],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@coletdjnz',
|
|
|
|
|
'uploader_id': '@coletdjnz',
|
2022-12-12 16:08:14 -07:00
|
|
|
|
'uploader': 'cole-dlp-test-acc',
|
|
|
|
|
},
|
|
|
|
|
'playlist': [{
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'ie_key': 'YoutubeTab',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
|
|
|
|
|
'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
|
|
|
|
|
'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
|
|
|
|
|
'title': 'PewDiePie',
|
|
|
|
|
'channel': 'PewDiePie',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
|
|
|
|
|
'thumbnails': list,
|
|
|
|
|
'channel_follower_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'playlist_count': int,
|
|
|
|
|
'uploader': 'PewDiePie',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@PewDiePie',
|
|
|
|
|
'uploader_id': '@PewDiePie',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2022-12-12 16:08:14 -07:00
|
|
|
|
}
|
|
|
|
|
}],
|
|
|
|
|
'params': {'extract_flat': True},
|
2023-02-28 11:20:34 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/@3blue1brown/about',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCYO_jab_esuFRV4b17AJtAw',
|
|
|
|
|
'tags': ['Mathematics'],
|
|
|
|
|
'title': '3Blue1Brown - About',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
|
|
|
|
|
'channel': '3Blue1Brown',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
|
|
|
|
|
'description': 'md5:e1384e8a133307dd10edee76e875d62f',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@3blue1brown',
|
|
|
|
|
'uploader_id': '@3blue1brown',
|
|
|
|
|
'uploader': '3Blue1Brown',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-02-28 11:20:34 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_count': 0,
|
2023-05-20 01:11:03 -06:00
|
|
|
|
}, {
|
|
|
|
|
# Podcasts tab, with rich entry playlistRenderers
|
|
|
|
|
'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
|
|
|
|
|
'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
|
|
|
|
|
'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
|
|
|
|
|
'title': '99 Percent Invisible - Podcasts',
|
|
|
|
|
'uploader': '99 Percent Invisible',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'channel': '99 Percent Invisible',
|
|
|
|
|
'uploader_id': '@99percentinvisiblepodcast',
|
|
|
|
|
},
|
|
|
|
|
'playlist_count': 1,
|
|
|
|
|
}, {
|
|
|
|
|
# Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
|
|
|
|
|
'url': 'https://www.youtube.com/@AHimitsu/releases',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
|
|
|
|
|
'channel': 'A Himitsu',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@AHimitsu',
|
|
|
|
|
'title': 'A Himitsu - Releases',
|
|
|
|
|
'uploader_id': '@AHimitsu',
|
|
|
|
|
'uploader': 'A Himitsu',
|
|
|
|
|
'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
|
|
|
|
|
'tags': 'count:16',
|
|
|
|
|
'description': 'I make music',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
|
|
|
|
|
'channel_follower_count': int,
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-05-20 01:11:03 -06:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 10,
|
2023-06-29 17:26:27 -06:00
|
|
|
|
}, {
|
|
|
|
|
# Playlist with only shorts, shown as reel renderers
|
|
|
|
|
# FIXME: future: YouTube currently doesn't give continuation for this,
|
|
|
|
|
# may do in future.
|
|
|
|
|
'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'uploader_id': '@BangyShorts',
|
|
|
|
|
'description': '',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@BangyShorts',
|
|
|
|
|
'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
|
|
|
|
|
'channel': 'Bangy Shorts',
|
|
|
|
|
'uploader': 'Bangy Shorts',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'modified_date': '20230626',
|
|
|
|
|
'title': 'Uploads from Bangy Shorts',
|
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 100,
|
|
|
|
|
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
|
2021-11-23 20:01:52 -07:00
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def suitable(cls, url):
|
2022-04-11 09:10:28 -06:00
|
|
|
|
return False if YoutubeIE.suitable(url) else super().suitable(url)
|
2021-05-15 08:38:47 -06:00
|
|
|
|
|
2022-11-09 01:58:44 -07:00
|
|
|
|
_URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
|
|
|
|
|
|
|
|
|
|
def _get_url_mobj(self, url):
|
|
|
|
|
mobj = self._URL_RE.match(url).groupdict()
|
|
|
|
|
mobj.update((k, '') for k, v in mobj.items() if v is None)
|
|
|
|
|
return mobj
|
|
|
|
|
|
|
|
|
|
def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
|
|
|
|
|
tab_name = (tab.get('title') or '').lower()
|
|
|
|
|
tab_url = urljoin(base_url, traverse_obj(
|
|
|
|
|
tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
|
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
|
|
|
|
|
or traverse_obj(tab, 'tabIdentifier', expected_type=str))
|
2022-11-09 01:58:44 -07:00
|
|
|
|
if tab_id:
|
2022-11-11 01:22:40 -07:00
|
|
|
|
return {
|
|
|
|
|
'TAB_ID_SPONSORSHIPS': 'membership',
|
|
|
|
|
}.get(tab_id, tab_id), tab_name
|
2022-11-09 01:58:44 -07:00
|
|
|
|
|
|
|
|
|
# Fallback to tab name if we cannot get the tab id.
|
|
|
|
|
# XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
|
|
|
|
|
# Note that in the case of translated tab name this may result in an empty string, which we don't want.
|
2022-11-11 01:22:40 -07:00
|
|
|
|
if tab_name:
|
|
|
|
|
self.write_debug(f'Falling back to selected tab name: {tab_name}')
|
2022-11-09 01:58:44 -07:00
|
|
|
|
return {
|
|
|
|
|
'home': 'featured',
|
|
|
|
|
'live': 'streams',
|
|
|
|
|
}.get(tab_name, tab_name), tab_name
|
|
|
|
|
|
|
|
|
|
def _has_tab(self, tabs, tab_id):
|
|
|
|
|
return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
|
2021-05-18 08:01:06 -06:00
|
|
|
|
|
2022-02-01 13:43:17 -07:00
|
|
|
|
@YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
|
|
|
|
|
def _real_extract(self, url, smuggled_data):
|
2021-03-04 11:05:26 -07:00
|
|
|
|
item_id = self._match_id(url)
|
2022-06-24 04:54:43 -06:00
|
|
|
|
url = urllib.parse.urlunparse(
|
|
|
|
|
urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
|
2021-05-17 06:23:08 -06:00
|
|
|
|
compat_opts = self.get_param('compat_opts', [])
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
2022-11-09 01:58:44 -07:00
|
|
|
|
mobj = self._get_url_mobj(url)
|
|
|
|
|
pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
|
2022-11-11 01:22:40 -07:00
|
|
|
|
if is_channel and smuggled_data.get('is_music_url'):
|
|
|
|
|
if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
|
|
|
|
|
return self.url_result(
|
|
|
|
|
f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
|
|
|
|
|
elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
|
|
|
|
|
mdata = self._extract_tab_endpoint(
|
|
|
|
|
f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
|
|
|
|
|
murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
|
|
|
|
|
get_all=False, expected_type=str)
|
|
|
|
|
if not murl:
|
|
|
|
|
raise ExtractorError('Failed to resolve album to playlist')
|
|
|
|
|
return self.url_result(murl, YoutubeTabIE)
|
|
|
|
|
elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
|
|
|
|
|
return self.url_result(
|
|
|
|
|
f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
|
|
|
|
|
|
|
|
|
|
original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
|
2021-05-18 08:01:06 -06:00
|
|
|
|
if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
|
2022-11-11 01:22:40 -07:00
|
|
|
|
url = f'{pre}/videos{post}'
|
2023-02-28 11:01:02 -07:00
|
|
|
|
if smuggled_data.get('is_music_url'):
|
|
|
|
|
self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
|
|
|
|
# Handle both video/playlist URLs
|
2021-04-16 21:02:33 -06:00
|
|
|
|
qs = parse_qs(url)
|
2022-11-11 01:22:40 -07:00
|
|
|
|
video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
|
2021-05-18 08:01:06 -06:00
|
|
|
|
if not video_id and mobj['not_channel'].startswith('watch'):
|
2021-03-04 11:05:26 -07:00
|
|
|
|
if not playlist_id:
|
2021-05-18 08:01:06 -06:00
|
|
|
|
# If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
|
2022-11-11 01:22:40 -07:00
|
|
|
|
raise ExtractorError('A video URL was given without video ID', expected=True)
|
2021-05-18 08:01:06 -06:00
|
|
|
|
# Common mistake: https://www.youtube.com/watch?list=playlist_id
|
2021-12-18 20:05:59 -07:00
|
|
|
|
self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
|
2022-11-11 01:22:40 -07:00
|
|
|
|
return self.url_result(
|
|
|
|
|
f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
2022-11-09 01:58:44 -07:00
|
|
|
|
if not self._yes_playlist(playlist_id, video_id):
|
|
|
|
|
return self.url_result(
|
|
|
|
|
f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
data, ytcfg = self._extract_data(url, display_id)
|
2021-02-25 14:52:44 -07:00
|
|
|
|
|
2022-02-28 22:08:19 -07:00
|
|
|
|
# YouTube may provide a non-standard redirect to the regional channel
|
|
|
|
|
# See: https://github.com/yt-dlp/yt-dlp/issues/2694
|
2022-11-09 01:58:44 -07:00
|
|
|
|
# https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
|
2022-02-28 22:08:19 -07:00
|
|
|
|
redirect_url = traverse_obj(
|
|
|
|
|
data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
|
|
|
|
|
if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
|
2022-11-11 01:22:40 -07:00
|
|
|
|
redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
|
2022-11-09 01:58:44 -07:00
|
|
|
|
self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
|
|
|
|
|
return self.url_result(redirect_url, YoutubeTabIE)
|
2022-02-28 22:08:19 -07:00
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
tabs, extra_tabs = self._extract_tab_renderers(data), []
|
2022-11-09 01:58:44 -07:00
|
|
|
|
if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
|
2021-05-18 07:02:46 -06:00
|
|
|
|
selected_tab = self._extract_selected_tab(tabs)
|
2022-11-09 01:58:44 -07:00
|
|
|
|
selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
|
|
|
|
|
self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
|
|
|
|
|
|
|
|
|
|
if not original_tab_id and selected_tab_name:
|
2022-11-11 01:22:40 -07:00
|
|
|
|
self.to_screen('Downloading all uploads of the channel. '
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'To download only the videos in a specific tab, pass the tab\'s URL')
|
|
|
|
|
if self._has_tab(tabs, 'streams'):
|
2022-11-11 01:22:40 -07:00
|
|
|
|
extra_tabs.append(''.join((pre, '/streams', post)))
|
2022-11-09 01:58:44 -07:00
|
|
|
|
if self._has_tab(tabs, 'shorts'):
|
2022-11-11 01:22:40 -07:00
|
|
|
|
extra_tabs.append(''.join((pre, '/shorts', post)))
|
2022-11-09 01:58:44 -07:00
|
|
|
|
# XXX: Members-only tab should also be extracted
|
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
if not extra_tabs and selected_tab_id != 'videos':
|
2022-11-09 01:58:44 -07:00
|
|
|
|
# Channel does not have streams, shorts or videos tabs
|
|
|
|
|
if item_id[:2] != 'UC':
|
|
|
|
|
raise ExtractorError('This channel has no uploads', expected=True)
|
|
|
|
|
|
|
|
|
|
# Topic channels don't have /videos. Use the equivalent playlist instead
|
|
|
|
|
pl_id = f'UU{item_id[2:]}'
|
|
|
|
|
pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
|
|
|
|
|
try:
|
|
|
|
|
data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
|
|
|
|
|
except ExtractorError:
|
|
|
|
|
raise ExtractorError('This channel has no uploads', expected=True)
|
2022-01-19 14:31:57 -07:00
|
|
|
|
else:
|
2022-11-09 01:58:44 -07:00
|
|
|
|
item_id, url = pl_id, pl_url
|
|
|
|
|
self.to_screen(
|
|
|
|
|
f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
|
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
elif extra_tabs and selected_tab_id != 'videos':
|
2022-11-09 01:58:44 -07:00
|
|
|
|
# When there are shorts/live tabs but not videos tab
|
2022-11-11 01:22:40 -07:00
|
|
|
|
url, data = f'{pre}{post}', None
|
2022-11-09 01:58:44 -07:00
|
|
|
|
|
|
|
|
|
elif (original_tab_id or 'videos') != selected_tab_id:
|
|
|
|
|
if original_tab_id == 'live':
|
|
|
|
|
# Live tab should have redirected to the video
|
|
|
|
|
# Except in the case the channel has an actual live tab
|
|
|
|
|
# Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
|
2022-11-11 01:22:40 -07:00
|
|
|
|
raise UserNotLive(video_id=item_id)
|
2022-11-09 01:58:44 -07:00
|
|
|
|
elif selected_tab_name:
|
|
|
|
|
raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
|
|
|
|
|
|
|
|
|
|
# For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
|
|
|
|
|
url = f'{pre}{post}'
|
2021-05-18 07:02:46 -06:00
|
|
|
|
|
2021-04-16 16:39:08 -06:00
|
|
|
|
# YouTube sometimes provides a button to reload playlist with unavailable videos.
|
2021-05-11 02:00:48 -06:00
|
|
|
|
if 'no-youtube-unavailable-videos' not in compat_opts:
|
2022-11-11 01:22:40 -07:00
|
|
|
|
data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
|
2021-09-03 20:33:42 -06:00
|
|
|
|
self._extract_and_report_alerts(data, only_once=True)
|
2022-11-09 01:58:44 -07:00
|
|
|
|
|
2022-11-11 01:22:40 -07:00
|
|
|
|
tabs, entries = self._extract_tab_renderers(data), []
|
2020-11-19 12:22:59 -07:00
|
|
|
|
if tabs:
|
2022-11-11 01:22:40 -07:00
|
|
|
|
entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
|
|
|
|
|
entries[0].update({
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'extractor_key': YoutubeTabIE.ie_key(),
|
|
|
|
|
'extractor': YoutubeTabIE.IE_NAME,
|
|
|
|
|
'webpage_url': url,
|
|
|
|
|
})
|
2022-11-11 01:22:40 -07:00
|
|
|
|
if self.get_param('playlist_items') == '0':
|
|
|
|
|
entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
|
|
|
|
|
else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
|
|
|
|
|
entries.extend(map(self._real_extract, extra_tabs))
|
|
|
|
|
|
|
|
|
|
if len(entries) == 1:
|
|
|
|
|
return entries[0]
|
|
|
|
|
elif entries:
|
|
|
|
|
metadata = self._extract_metadata_from_tabs(item_id, data)
|
|
|
|
|
uploads_url = 'the Uploads (UU) playlist URL'
|
|
|
|
|
if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
|
|
|
|
|
uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
|
|
|
|
|
self.to_screen(
|
|
|
|
|
'Downloading as multiple playlists, separated by tabs. '
|
|
|
|
|
f'To download as a single playlist instead, pass {uploads_url}')
|
|
|
|
|
return self.playlist_result(entries, item_id, **metadata)
|
|
|
|
|
|
|
|
|
|
# Inline playlist
|
2021-12-18 20:05:59 -07:00
|
|
|
|
playlist = traverse_obj(
|
|
|
|
|
data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
if playlist:
|
2021-10-08 15:19:25 -06:00
|
|
|
|
return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
2021-12-18 20:05:59 -07:00
|
|
|
|
video_id = traverse_obj(
|
|
|
|
|
data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
|
2020-11-19 12:22:59 -07:00
|
|
|
|
if video_id:
|
2022-11-11 01:22:40 -07:00
|
|
|
|
if tab != '/live': # live tab is expected to redirect to video
|
2021-12-18 20:05:59 -07:00
|
|
|
|
self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
|
2022-11-09 01:58:44 -07:00
|
|
|
|
return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
|
2021-03-04 11:05:26 -07:00
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
raise ExtractorError('Unable to recognize tab page')
|
2013-06-23 11:58:33 -06:00
|
|
|
|
|
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
class YoutubePlaylistIE(InfoExtractor):
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'YouTube playlists'
|
2020-11-19 12:22:59 -07:00
|
|
|
|
_VALID_URL = r'''(?x)(?:
|
|
|
|
|
(?:https?://)?
|
|
|
|
|
(?:\w+\.)?
|
|
|
|
|
(?:
|
|
|
|
|
(?:
|
|
|
|
|
youtube(?:kids)?\.com|
|
2021-11-05 21:07:34 -06:00
|
|
|
|
%(invidious)s
|
2020-11-19 12:22:59 -07:00
|
|
|
|
)
|
|
|
|
|
/.*?\?.*?\blist=
|
|
|
|
|
)?
|
|
|
|
|
(?P<id>%(playlist_id)s)
|
2021-11-05 21:07:34 -06:00
|
|
|
|
)''' % {
|
|
|
|
|
'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
|
|
|
|
|
'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
|
|
|
|
|
}
|
2020-11-19 12:22:59 -07:00
|
|
|
|
IE_NAME = 'youtube:playlist'
|
2014-09-24 02:25:47 -06:00
|
|
|
|
_TESTS = [{
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'note': 'issue #673',
|
|
|
|
|
'url': 'PLBB231211A4F62143',
|
2014-09-24 02:25:47 -06:00
|
|
|
|
'info_dict': {
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'title': '[OLD]Team Fortress 2 (Class-based LP)',
|
|
|
|
|
'id': 'PLBB231211A4F62143',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'uploader': 'Wickman',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@WickmanVT',
|
2021-07-20 21:52:34 -06:00
|
|
|
|
'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'view_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@WickmanVT',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'modified_date': r're:\d{8}',
|
|
|
|
|
'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
|
|
|
|
|
'channel': 'Wickman',
|
|
|
|
|
'tags': [],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'availability': 'public',
|
2020-11-19 12:22:59 -07:00
|
|
|
|
},
|
|
|
|
|
'playlist_mincount': 29,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': 'YDL_safe_search',
|
|
|
|
|
'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
|
|
|
|
|
},
|
|
|
|
|
'playlist_count': 2,
|
|
|
|
|
'skip': 'This playlist is private',
|
2016-07-08 19:37:02 -06:00
|
|
|
|
}, {
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'note': 'embedded',
|
|
|
|
|
'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
|
|
|
|
|
'playlist_count': 4,
|
2016-07-08 19:37:02 -06:00
|
|
|
|
'info_dict': {
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'title': 'JODA15',
|
|
|
|
|
'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
|
|
|
|
|
'uploader': 'milan',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@milan5503',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'description': '',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
|
|
|
|
|
'tags': [],
|
|
|
|
|
'modified_date': '20140919',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel': 'milan',
|
|
|
|
|
'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@milan5503',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
},
|
2022-11-09 01:58:44 -07:00
|
|
|
|
'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
|
2014-09-24 02:25:47 -06:00
|
|
|
|
}, {
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'playlist_mincount': 455,
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'title': '2018 Chinese New Singles (11/6 updated)',
|
|
|
|
|
'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
|
|
|
|
|
'uploader': 'LBK',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@music_king',
|
2021-07-20 21:52:34 -06:00
|
|
|
|
'description': 'md5:da521864744d60a198e3a88af4db0d9d',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'LBK',
|
|
|
|
|
'view_count': int,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'tags': [],
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@music_king',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
|
|
|
|
|
'modified_date': r're:\d{8}',
|
2022-09-08 23:16:46 -06:00
|
|
|
|
'availability': 'public',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
},
|
|
|
|
|
'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
|
2016-06-10 02:37:12 -06:00
|
|
|
|
}, {
|
2021-01-01 05:26:37 -07:00
|
|
|
|
'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
# music album playlist
|
|
|
|
|
'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
def suitable(cls, url):
|
2021-04-16 21:02:33 -06:00
|
|
|
|
if YoutubeTabIE.suitable(url):
|
|
|
|
|
return False
|
2021-10-22 14:37:20 -06:00
|
|
|
|
from ..utils import parse_qs
|
2021-04-16 21:02:33 -06:00
|
|
|
|
qs = parse_qs(url)
|
|
|
|
|
if qs.get('v', [None])[0]:
|
|
|
|
|
return False
|
2022-04-11 09:10:28 -06:00
|
|
|
|
return super().suitable(url)
|
2021-01-01 05:26:37 -07:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
playlist_id = self._match_id(url)
|
2021-05-28 12:19:26 -06:00
|
|
|
|
is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
|
2021-05-15 08:38:47 -06:00
|
|
|
|
url = update_url_query(
|
|
|
|
|
'https://www.youtube.com/playlist',
|
|
|
|
|
parse_qs(url) or {'list': playlist_id})
|
|
|
|
|
if is_music_url:
|
|
|
|
|
url = smuggle_url(url, {'is_music_url': True})
|
|
|
|
|
return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
|
2021-01-01 05:26:37 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class YoutubeYtBeIE(InfoExtractor):
|
2021-01-06 23:41:05 -07:00
|
|
|
|
IE_DESC = 'youtu.be'
|
2021-01-01 05:26:37 -07:00
|
|
|
|
_VALID_URL = r'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{11})/*?.*?\blist=(?P<playlist_id>%(playlist_id)s)' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
|
|
|
|
|
_TESTS = [{
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'yeWKywCrFtk',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'Small Scale Baler and Braiding Rugs',
|
|
|
|
|
'uploader': 'Backus-Page House Museum',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@backuspagemuseum',
|
|
|
|
|
'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'upload_date': '20161008',
|
|
|
|
|
'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
|
|
|
|
|
'categories': ['Nonprofits & Activism'],
|
|
|
|
|
'tags': list,
|
|
|
|
|
'like_count': int,
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'playable_in_embed': True,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'thumbnail': r're:^https?://.*\.webp',
|
2022-01-07 04:54:57 -07:00
|
|
|
|
'channel': 'Backus-Page House Museum',
|
|
|
|
|
'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
|
|
|
|
|
'live_status': 'not_live',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'duration': 59,
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'comment_count': int,
|
|
|
|
|
'channel_follower_count': int
|
2020-11-19 12:22:59 -07:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
'noplaylist': True,
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
2020-09-11 21:08:57 -06:00
|
|
|
|
}, {
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
|
2020-09-11 21:08:57 -06:00
|
|
|
|
'only_matching': True,
|
2014-09-24 02:25:47 -06:00
|
|
|
|
}]
|
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
def _real_extract(self, url):
|
2021-08-18 19:41:24 -06:00
|
|
|
|
mobj = self._match_valid_url(url)
|
2021-01-01 05:26:37 -07:00
|
|
|
|
video_id = mobj.group('id')
|
|
|
|
|
playlist_id = mobj.group('playlist_id')
|
2020-11-19 12:22:59 -07:00
|
|
|
|
return self.url_result(
|
2021-01-01 05:26:37 -07:00
|
|
|
|
update_url_query('https://www.youtube.com/watch', {
|
|
|
|
|
'v': video_id,
|
|
|
|
|
'list': playlist_id,
|
|
|
|
|
'feature': 'youtu.be',
|
|
|
|
|
}), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
|
2020-11-19 12:22:59 -07:00
|
|
|
|
|
|
|
|
|
|
2022-01-19 06:24:17 -07:00
|
|
|
|
class YoutubeLivestreamEmbedIE(InfoExtractor):
|
|
|
|
|
IE_DESC = 'YouTube livestream embeds'
|
|
|
|
|
_VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
channel_id = self._match_id(url)
|
|
|
|
|
return self.url_result(
|
|
|
|
|
f'https://www.youtube.com/channel/{channel_id}/live',
|
|
|
|
|
ie=YoutubeTabIE.ie_key(), video_id=channel_id)
|
|
|
|
|
|
|
|
|
|
|
2020-11-19 12:22:59 -07:00
|
|
|
|
class YoutubeYtUserIE(InfoExtractor):
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'YouTube user videos; "ytuser:" prefix'
|
2022-01-19 06:24:17 -07:00
|
|
|
|
IE_NAME = 'youtube:user'
|
2020-11-19 12:22:59 -07:00
|
|
|
|
_VALID_URL = r'ytuser:(?P<id>.+)'
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'ytuser:phihag',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
user_id = self._match_id(url)
|
2022-11-11 03:59:29 -07:00
|
|
|
|
return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
|
2016-07-08 19:37:02 -06:00
|
|
|
|
|
2013-06-23 12:28:15 -06:00
|
|
|
|
|
2020-11-23 14:59:10 -07:00
|
|
|
|
class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
|
2020-11-23 14:47:42 -07:00
|
|
|
|
IE_NAME = 'youtube:favorites'
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
|
2020-11-23 14:47:42 -07:00
|
|
|
|
_VALID_URL = r':ytfav(?:ou?rite)?s?'
|
|
|
|
|
_LOGIN_REQUIRED = True
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': ':ytfav',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': ':ytfavorites',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
return self.url_result(
|
|
|
|
|
'https://www.youtube.com/playlist?list=LL',
|
|
|
|
|
ie=YoutubeTabIE.ie_key())
|
|
|
|
|
|
|
|
|
|
|
2022-04-09 13:55:24 -06:00
|
|
|
|
class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
|
|
|
|
|
IE_NAME = 'youtube:notif'
|
|
|
|
|
IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
|
|
|
|
|
_VALID_URL = r':ytnotif(?:ication)?s?'
|
|
|
|
|
_LOGIN_REQUIRED = True
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': ':ytnotif',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': ':ytnotifications',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _extract_notification_menu(self, response, continuation_list):
|
|
|
|
|
notification_list = traverse_obj(
|
|
|
|
|
response,
|
|
|
|
|
('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
|
|
|
|
|
('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
|
|
|
|
|
expected_type=list) or []
|
|
|
|
|
continuation_list[0] = None
|
|
|
|
|
for item in notification_list:
|
|
|
|
|
entry = self._extract_notification_renderer(item.get('notificationRenderer'))
|
|
|
|
|
if entry:
|
|
|
|
|
yield entry
|
|
|
|
|
continuation = item.get('continuationItemRenderer')
|
|
|
|
|
if continuation:
|
|
|
|
|
continuation_list[0] = continuation
|
|
|
|
|
|
|
|
|
|
def _extract_notification_renderer(self, notification):
|
|
|
|
|
video_id = traverse_obj(
|
|
|
|
|
notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
|
|
|
|
|
url = f'https://www.youtube.com/watch?v={video_id}'
|
|
|
|
|
channel_id = None
|
|
|
|
|
if not video_id:
|
|
|
|
|
browse_ep = traverse_obj(
|
|
|
|
|
notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
|
2023-04-14 01:58:36 -06:00
|
|
|
|
channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
|
2022-04-09 13:55:24 -06:00
|
|
|
|
post_id = self._search_regex(
|
|
|
|
|
r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
|
|
|
|
|
'post id', default=None)
|
|
|
|
|
if not channel_id or not post_id:
|
|
|
|
|
return
|
|
|
|
|
# The direct /post url redirects to this in the browser
|
|
|
|
|
url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
|
|
|
|
|
|
|
|
|
|
channel = traverse_obj(
|
|
|
|
|
notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
|
|
|
|
|
expected_type=str)
|
2022-06-03 01:04:39 -06:00
|
|
|
|
notification_title = self._get_text(notification, 'shortMessage')
|
|
|
|
|
if notification_title:
|
|
|
|
|
notification_title = notification_title.replace('\xad', '') # remove soft hyphens
|
|
|
|
|
# TODO: handle recommended videos
|
2022-04-09 13:55:24 -06:00
|
|
|
|
title = self._search_regex(
|
2022-06-03 01:04:39 -06:00
|
|
|
|
rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
|
2022-04-09 13:55:24 -06:00
|
|
|
|
'video title', default=None)
|
2022-10-12 16:53:39 -06:00
|
|
|
|
timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
|
|
|
|
|
if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
|
|
|
|
|
else None)
|
2022-04-09 13:55:24 -06:00
|
|
|
|
return {
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'url': url,
|
|
|
|
|
'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
|
|
|
|
|
'video_id': video_id,
|
|
|
|
|
'title': title,
|
|
|
|
|
'channel_id': channel_id,
|
|
|
|
|
'channel': channel,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader': channel,
|
2022-04-09 13:55:24 -06:00
|
|
|
|
'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
|
2022-10-12 16:53:39 -06:00
|
|
|
|
'timestamp': timestamp,
|
2022-04-09 13:55:24 -06:00
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
def _notification_menu_entries(self, ytcfg):
|
|
|
|
|
continuation_list = [None]
|
|
|
|
|
response = None
|
|
|
|
|
for page in itertools.count(1):
|
|
|
|
|
ctoken = traverse_obj(
|
|
|
|
|
continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
|
|
|
|
|
response = self._extract_response(
|
|
|
|
|
item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
|
|
|
|
|
ep='notification/get_notification_menu', check_get_keys='actions',
|
|
|
|
|
headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
|
|
|
|
|
yield from self._extract_notification_menu(response, continuation_list)
|
|
|
|
|
if not continuation_list[0]:
|
|
|
|
|
break
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
display_id = 'notifications'
|
|
|
|
|
ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
|
|
|
|
|
self._report_playlist_authcheck(ytcfg)
|
|
|
|
|
return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
|
|
|
|
|
|
|
|
|
|
|
2021-11-23 20:01:52 -07:00
|
|
|
|
class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
|
|
|
|
|
IE_DESC = 'YouTube search'
|
2014-09-12 23:51:06 -06:00
|
|
|
|
IE_NAME = 'youtube:search'
|
2013-06-23 12:28:15 -06:00
|
|
|
|
_SEARCH_KEY = 'ytsearch'
|
2021-11-23 20:57:59 -07:00
|
|
|
|
_SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
|
2022-02-03 23:31:13 -07:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'ytsearch5:youtube-dl test video',
|
|
|
|
|
'playlist_count': 5,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'youtube-dl test video',
|
|
|
|
|
'title': 'youtube-dl test video',
|
|
|
|
|
}
|
|
|
|
|
}]
|
2013-06-23 12:28:15 -06:00
|
|
|
|
|
2021-11-23 20:57:59 -07:00
|
|
|
|
|
2021-12-01 10:50:38 -07:00
|
|
|
|
class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
|
2013-12-03 05:55:25 -07:00
|
|
|
|
IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
|
2013-11-02 20:40:48 -06:00
|
|
|
|
_SEARCH_KEY = 'ytsearchdate'
|
2021-11-23 20:01:52 -07:00
|
|
|
|
IE_DESC = 'YouTube search, newest videos first'
|
2021-11-23 20:57:59 -07:00
|
|
|
|
_SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
|
2022-02-03 23:31:13 -07:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'ytsearchdate5:youtube-dl test video',
|
|
|
|
|
'playlist_count': 5,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'youtube-dl test video',
|
|
|
|
|
'title': 'youtube-dl test video',
|
|
|
|
|
}
|
|
|
|
|
}]
|
2013-07-01 09:59:28 -06:00
|
|
|
|
|
2014-03-03 19:32:28 -07:00
|
|
|
|
|
2021-11-23 20:01:52 -07:00
|
|
|
|
class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'YouTube search URLs with sorting and filter support'
|
2020-11-22 06:09:09 -07:00
|
|
|
|
IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
|
2022-02-01 13:43:17 -07:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
|
2020-11-21 15:21:09 -07:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
|
|
|
|
|
'playlist_mincount': 5,
|
|
|
|
|
'info_dict': {
|
2021-07-20 21:52:34 -06:00
|
|
|
|
'id': 'youtube-dl test video',
|
2020-11-21 15:21:09 -07:00
|
|
|
|
'title': 'youtube-dl test video',
|
|
|
|
|
}
|
2021-11-23 20:57:59 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
|
|
|
|
|
'playlist_mincount': 5,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'python',
|
|
|
|
|
'title': 'python',
|
|
|
|
|
}
|
2022-04-02 00:11:14 -06:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/results?search_query=%23cats',
|
|
|
|
|
'playlist_mincount': 1,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '#cats',
|
|
|
|
|
'title': '#cats',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
# The test suite does not have support for nested playlists
|
|
|
|
|
# 'entries': [{
|
|
|
|
|
# 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
|
|
|
|
|
# 'title': '#cats',
|
|
|
|
|
# }],
|
2022-04-02 00:11:14 -06:00
|
|
|
|
},
|
2022-12-12 16:08:14 -07:00
|
|
|
|
}, {
|
|
|
|
|
# Channel results
|
|
|
|
|
'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'kurzgesagt',
|
|
|
|
|
'title': 'kurzgesagt',
|
|
|
|
|
},
|
|
|
|
|
'playlist': [{
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'_type': 'url',
|
|
|
|
|
'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
|
|
|
|
|
'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
|
|
|
|
|
'ie_key': 'YoutubeTab',
|
|
|
|
|
'channel': 'Kurzgesagt – In a Nutshell',
|
|
|
|
|
'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
|
|
|
|
|
'title': 'Kurzgesagt – In a Nutshell',
|
|
|
|
|
'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
# No longer available for search as it is set to the handle.
|
|
|
|
|
# 'playlist_count': int,
|
2022-12-12 16:08:14 -07:00
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'thumbnails': list,
|
|
|
|
|
'uploader_id': '@kurzgesagt',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@kurzgesagt',
|
|
|
|
|
'uploader': 'Kurzgesagt – In a Nutshell',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'channel_follower_count': int,
|
2022-12-12 16:08:14 -07:00
|
|
|
|
}
|
|
|
|
|
}],
|
|
|
|
|
'params': {'extract_flat': True, 'playlist_items': '1'},
|
|
|
|
|
'playlist_mincount': 1,
|
2020-11-21 15:21:09 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2021-08-22 13:02:00 -06:00
|
|
|
|
qs = parse_qs(url)
|
2020-11-22 06:09:09 -07:00
|
|
|
|
query = (qs.get('search_query') or qs.get('q'))[0]
|
2021-11-23 20:01:52 -07:00
|
|
|
|
return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
|
2020-11-21 15:21:09 -07:00
|
|
|
|
|
|
|
|
|
|
2022-02-01 11:24:00 -07:00
|
|
|
|
class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
|
2022-08-14 06:04:13 -06:00
|
|
|
|
IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
|
2022-02-01 11:24:00 -07:00
|
|
|
|
IE_NAME = 'youtube:music:search_url'
|
|
|
|
|
_VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'https://music.youtube.com/search?q=royalty+free+music',
|
|
|
|
|
'playlist_count': 16,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'royalty free music',
|
|
|
|
|
'title': 'royalty free music',
|
|
|
|
|
}
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
|
|
|
|
|
'playlist_mincount': 30,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'royalty free music - songs',
|
|
|
|
|
'title': 'royalty free music - songs',
|
|
|
|
|
},
|
|
|
|
|
'params': {'extract_flat': 'in_playlist'}
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
|
|
|
|
|
'playlist_mincount': 30,
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'royalty free music - community playlists',
|
|
|
|
|
'title': 'royalty free music - community playlists',
|
|
|
|
|
},
|
|
|
|
|
'params': {'extract_flat': 'in_playlist'}
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
_SECTIONS = {
|
|
|
|
|
'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
|
|
|
|
|
'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
|
|
|
|
|
'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
|
|
|
|
|
'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
|
|
|
|
|
'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
|
|
|
|
|
'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
qs = parse_qs(url)
|
|
|
|
|
query = (qs.get('search_query') or qs.get('q'))[0]
|
|
|
|
|
params = qs.get('sp', (None,))[0]
|
|
|
|
|
if params:
|
|
|
|
|
section = next((k for k, v in self._SECTIONS.items() if v == params), params)
|
|
|
|
|
else:
|
2022-06-24 02:10:17 -06:00
|
|
|
|
section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
|
2022-02-01 11:24:00 -07:00
|
|
|
|
params = self._SECTIONS.get(section)
|
|
|
|
|
if not params:
|
|
|
|
|
section = None
|
|
|
|
|
title = join_nonempty(query, section, delim=' - ')
|
2022-02-03 14:25:38 -07:00
|
|
|
|
return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
|
2022-02-01 11:24:00 -07:00
|
|
|
|
|
|
|
|
|
|
2022-02-01 13:43:17 -07:00
|
|
|
|
class YoutubeFeedsInfoExtractor(InfoExtractor):
|
2013-07-20 11:33:40 -06:00
|
|
|
|
"""
|
2015-05-15 09:06:59 -06:00
|
|
|
|
Base class for feed extractors
|
2022-05-11 09:54:44 -06:00
|
|
|
|
Subclasses must re-define the _FEED_NAME property.
|
2013-07-20 11:33:40 -06:00
|
|
|
|
"""
|
2013-07-24 12:40:12 -06:00
|
|
|
|
_LOGIN_REQUIRED = True
|
2022-05-11 09:54:44 -06:00
|
|
|
|
_FEED_NAME = 'feeds'
|
2022-04-09 13:30:21 -06:00
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
|
YoutubeBaseInfoExtractor._check_login_required(self)
|
2013-07-20 11:33:40 -06:00
|
|
|
|
|
2022-05-11 09:54:44 -06:00
|
|
|
|
@classproperty
|
2013-07-20 11:33:40 -06:00
|
|
|
|
def IE_NAME(self):
|
2022-05-11 09:54:44 -06:00
|
|
|
|
return f'youtube:{self._FEED_NAME}'
|
2013-07-07 05:58:23 -06:00
|
|
|
|
|
2018-04-21 17:07:32 -06:00
|
|
|
|
def _real_extract(self, url):
|
2020-11-23 14:59:10 -07:00
|
|
|
|
return self.url_result(
|
2022-02-01 13:43:17 -07:00
|
|
|
|
f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
|
2015-05-15 09:06:59 -06:00
|
|
|
|
|
|
|
|
|
|
2020-11-21 15:46:05 -07:00
|
|
|
|
class YoutubeWatchLaterIE(InfoExtractor):
|
|
|
|
|
IE_NAME = 'youtube:watchlater'
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
|
2020-11-23 14:59:10 -07:00
|
|
|
|
_VALID_URL = r':ytwatchlater'
|
2016-02-18 08:50:21 -07:00
|
|
|
|
_TESTS = [{
|
2020-11-19 12:22:59 -07:00
|
|
|
|
'url': ':ytwatchlater',
|
2016-02-18 08:50:21 -07:00
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2015-05-15 09:06:59 -06:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2020-11-21 15:46:05 -07:00
|
|
|
|
return self.url_result(
|
|
|
|
|
'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
|
2020-11-21 15:21:09 -07:00
|
|
|
|
|
|
|
|
|
|
2015-05-15 09:06:59 -06:00
|
|
|
|
class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
|
2020-11-23 14:59:10 -07:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
|
2015-05-15 09:06:59 -06:00
|
|
|
|
_FEED_NAME = 'recommended'
|
2021-06-12 09:15:08 -06:00
|
|
|
|
_LOGIN_REQUIRED = False
|
2020-11-23 14:59:10 -07:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': ':ytrec',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': ':ytrecommended',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://youtube.com',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2014-08-31 15:44:43 -06:00
|
|
|
|
|
|
|
|
|
|
2015-05-15 09:06:59 -06:00
|
|
|
|
class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
|
2020-11-23 14:59:10 -07:00
|
|
|
|
_VALID_URL = r':ytsub(?:scription)?s?'
|
2015-05-15 09:06:59 -06:00
|
|
|
|
_FEED_NAME = 'subscriptions'
|
2020-11-23 14:59:10 -07:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': ':ytsubs',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': ':ytsubscriptions',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2014-08-31 15:44:43 -06:00
|
|
|
|
|
|
|
|
|
|
2015-05-15 09:06:59 -06:00
|
|
|
|
class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
|
2021-10-23 08:29:52 -06:00
|
|
|
|
IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
|
2021-03-03 03:32:40 -07:00
|
|
|
|
_VALID_URL = r':ythis(?:tory)?'
|
2015-05-15 09:06:59 -06:00
|
|
|
|
_FEED_NAME = 'history'
|
2020-11-23 14:59:10 -07:00
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': ':ythistory',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2014-08-31 15:44:43 -06:00
|
|
|
|
|
|
|
|
|
|
2022-09-21 23:39:02 -06:00
|
|
|
|
class YoutubeShortsAudioPivotIE(InfoExtractor):
|
2022-09-26 16:49:12 -06:00
|
|
|
|
IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
|
2022-09-21 23:39:02 -06:00
|
|
|
|
IE_NAME = 'youtube:shorts:pivot:audio'
|
2022-09-26 16:49:12 -06:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
|
2022-09-21 23:39:02 -06:00
|
|
|
|
_TESTS = [{
|
2022-09-26 16:49:12 -06:00
|
|
|
|
'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
|
2022-09-21 23:39:02 -06:00
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
|
def _generate_audio_pivot_params(video_id):
|
|
|
|
|
"""
|
|
|
|
|
Generates sfv_audio_pivot browse params for this video id
|
|
|
|
|
"""
|
|
|
|
|
pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
|
|
|
|
|
return urllib.parse.quote(base64.b64encode(pb_params).decode())
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
video_id = self._match_id(url)
|
|
|
|
|
return self.url_result(
|
|
|
|
|
f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
|
|
|
|
|
ie=YoutubeTabIE)
|
|
|
|
|
|
|
|
|
|
|
2013-10-07 04:21:24 -06:00
|
|
|
|
class YoutubeTruncatedURLIE(InfoExtractor):
|
|
|
|
|
IE_NAME = 'youtube:truncated_url'
|
|
|
|
|
IE_DESC = False # Do not list
|
2014-01-23 08:14:54 -07:00
|
|
|
|
_VALID_URL = r'''(?x)
|
2015-01-24 03:42:20 -07:00
|
|
|
|
(?:https?://)?
|
|
|
|
|
(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
|
|
|
|
|
(?:watch\?(?:
|
2014-07-01 07:48:18 -06:00
|
|
|
|
feature=[a-z_]+|
|
2015-01-24 03:42:20 -07:00
|
|
|
|
annotation_id=annotation_[^&]+|
|
|
|
|
|
x-yt-cl=[0-9]+|
|
2015-01-29 19:45:29 -07:00
|
|
|
|
hl=[^&]*|
|
2015-09-13 16:26:12 -06:00
|
|
|
|
t=[0-9]+
|
2015-01-24 03:42:20 -07:00
|
|
|
|
)?
|
|
|
|
|
|
|
|
|
|
|
attribution_link\?a=[^&]+
|
|
|
|
|
)
|
|
|
|
|
$
|
2014-01-23 08:14:54 -07:00
|
|
|
|
'''
|
2013-10-07 04:21:24 -06:00
|
|
|
|
|
2014-07-01 07:48:18 -06:00
|
|
|
|
_TESTS = [{
|
2016-09-17 08:48:20 -06:00
|
|
|
|
'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
|
2014-07-01 07:48:18 -06:00
|
|
|
|
'only_matching': True,
|
2014-07-01 07:49:34 -06:00
|
|
|
|
}, {
|
2016-09-17 08:48:20 -06:00
|
|
|
|
'url': 'https://www.youtube.com/watch?',
|
2014-07-01 07:49:34 -06:00
|
|
|
|
'only_matching': True,
|
2015-01-24 03:42:20 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/watch?feature=foo',
|
|
|
|
|
'only_matching': True,
|
2015-01-29 19:45:29 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/watch?hl=en-GB',
|
|
|
|
|
'only_matching': True,
|
2015-09-13 16:26:12 -06:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://www.youtube.com/watch?t=2372',
|
|
|
|
|
'only_matching': True,
|
2014-07-01 07:48:18 -06:00
|
|
|
|
}]
|
|
|
|
|
|
2013-10-07 04:21:24 -06:00
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
raise ExtractorError(
|
2014-09-12 23:51:06 -06:00
|
|
|
|
'Did you forget to quote the URL? Remember that & is a meta '
|
|
|
|
|
'character in most shells, so you want to put the URL in quotes, '
|
2020-09-02 14:37:35 -06:00
|
|
|
|
'like youtube-dl '
|
2016-09-17 08:48:20 -06:00
|
|
|
|
'"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
|
2020-09-02 14:37:35 -06:00
|
|
|
|
' or simply youtube-dl BaW_jenozKc .',
|
2013-10-07 04:21:24 -06:00
|
|
|
|
expected=True)
|
2015-01-01 15:44:39 -07:00
|
|
|
|
|
|
|
|
|
|
2022-06-21 15:15:05 -06:00
|
|
|
|
class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
|
2021-09-19 08:07:47 -06:00
|
|
|
|
IE_NAME = 'youtube:clip'
|
2022-06-21 15:15:05 -06:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
# FIXME: Other metadata should be extracted from the clip, not from the base video
|
|
|
|
|
'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'section_start': 29.0,
|
|
|
|
|
'section_end': 39.7,
|
|
|
|
|
'duration': 10.7,
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'age_limit': 0,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'categories': ['Gaming'],
|
|
|
|
|
'channel': 'Scott The Woz',
|
|
|
|
|
'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
|
|
|
|
|
'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
|
|
|
|
|
'like_count': int,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'tags': 'count:17',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
|
|
|
|
|
'title': 'Mobile Games on Console - Scott The Woz',
|
|
|
|
|
'upload_date': '20210920',
|
|
|
|
|
'uploader': 'Scott The Woz',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@ScottTheWoz',
|
|
|
|
|
'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
|
2022-07-07 15:20:02 -06:00
|
|
|
|
'view_count': int,
|
|
|
|
|
'live_status': 'not_live',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'chapters': 'count:20',
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'comment_count': int,
|
|
|
|
|
'heatmap': 'count:100',
|
2022-06-21 15:15:05 -06:00
|
|
|
|
}
|
|
|
|
|
}]
|
2021-09-19 08:07:47 -06:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2022-06-21 15:15:05 -06:00
|
|
|
|
clip_id = self._match_id(url)
|
|
|
|
|
_, data = self._extract_webpage(url, clip_id)
|
|
|
|
|
|
|
|
|
|
video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
|
|
|
|
|
if not video_id:
|
|
|
|
|
raise ExtractorError('Unable to find video ID')
|
|
|
|
|
|
|
|
|
|
clip_data = traverse_obj(data, (
|
|
|
|
|
'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
|
|
|
|
|
'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
|
|
|
|
|
'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
|
|
|
|
|
'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
'_type': 'url_transparent',
|
|
|
|
|
'url': f'https://www.youtube.com/watch?v={video_id}',
|
|
|
|
|
'ie_key': YoutubeIE.ie_key(),
|
|
|
|
|
'id': clip_id,
|
|
|
|
|
'section_start': int(clip_data['startTimeMs']) / 1000,
|
|
|
|
|
'section_end': int(clip_data['endTimeMs']) / 1000,
|
|
|
|
|
}
|
2021-09-19 08:07:47 -06:00
|
|
|
|
|
|
|
|
|
|
2023-02-03 11:23:35 -07:00
|
|
|
|
class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
|
|
|
|
|
IE_NAME = 'youtube:consent'
|
|
|
|
|
IE_DESC = False # Do not list
|
|
|
|
|
_VALID_URL = r'https?://consent\.youtube\.com/m\?'
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'https://consent.youtube.com/m?continue=https%3A%2F%2Fwww.youtube.com%2Flive%2FqVv6vCqciTM%3Fcbrd%3D1&gl=NL&m=0&pc=yt&hl=en&src=1',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'qVv6vCqciTM',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'age_limit': 0,
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_id': '@sana_natori',
|
2023-02-03 11:23:35 -07:00
|
|
|
|
'comment_count': int,
|
|
|
|
|
'chapters': 'count:13',
|
|
|
|
|
'upload_date': '20221223',
|
|
|
|
|
'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
|
|
|
|
|
'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
|
2023-04-14 01:58:36 -06:00
|
|
|
|
'uploader_url': 'https://www.youtube.com/@sana_natori',
|
2023-02-03 11:23:35 -07:00
|
|
|
|
'like_count': int,
|
|
|
|
|
'release_date': '20221223',
|
|
|
|
|
'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
|
|
|
|
|
'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
|
|
|
|
|
'view_count': int,
|
|
|
|
|
'playable_in_embed': True,
|
|
|
|
|
'duration': 4438,
|
|
|
|
|
'availability': 'public',
|
|
|
|
|
'channel_follower_count': int,
|
|
|
|
|
'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
|
|
|
|
|
'categories': ['Entertainment'],
|
|
|
|
|
'live_status': 'was_live',
|
|
|
|
|
'release_timestamp': 1671793345,
|
|
|
|
|
'channel': 'さなちゃんねる',
|
|
|
|
|
'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
|
|
|
|
|
'uploader': 'さなちゃんねる',
|
2023-06-08 01:50:05 -06:00
|
|
|
|
'channel_is_verified': True,
|
2023-06-08 07:28:49 -06:00
|
|
|
|
'heatmap': 'count:100',
|
2023-02-03 11:23:35 -07:00
|
|
|
|
},
|
|
|
|
|
'add_ie': ['Youtube'],
|
|
|
|
|
'params': {'skip_download': 'Youtube'},
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
|
|
|
|
|
if not redirect_url:
|
|
|
|
|
raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
|
|
|
|
|
return self.url_result(redirect_url)
|
|
|
|
|
|
|
|
|
|
|
2015-01-01 15:44:39 -07:00
|
|
|
|
class YoutubeTruncatedIDIE(InfoExtractor):
|
|
|
|
|
IE_NAME = 'youtube:truncated_id'
|
|
|
|
|
IE_DESC = False # Do not list
|
2015-01-24 03:42:20 -07:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
|
2015-01-01 15:44:39 -07:00
|
|
|
|
|
|
|
|
|
_TESTS = [{
|
|
|
|
|
'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
video_id = self._match_id(url)
|
|
|
|
|
raise ExtractorError(
|
2022-04-11 09:10:28 -06:00
|
|
|
|
f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
|
2015-01-01 15:44:39 -07:00
|
|
|
|
expected=True)
|