Mirrors
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into master

This commit is contained in:
DEVENU 2024-08-05 16:11:10 +05:30 committed by GitHub
parent b3dbc3deec e7d73bc453
commit ce502038fb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
26 changed files with 1147 additions and 382 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
CONTRIBUTORS
View File

@ -653,3 +653,5 @@ LeSuisse
DunnesH
iancmy
mokrueger
luvyana
szantnerb

39
Changelog.md
View File

@ -4,6 +4,45 @@
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2024.08.01
#### Core changes
- **utils**: `unified_timestamp`: [Recognize Sunday](https://github.com/yt-dlp/yt-dlp/commit/6daf2c27c0464fba98337be30de0b66d520d0db1) ([#10589](https://github.com/yt-dlp/yt-dlp/issues/10589)) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **abematv**: [Fix availability extraction](https://github.com/yt-dlp/yt-dlp/commit/ef36d517f9b05785d61abca7691d9ab7d63cc75c) ([#10569](https://github.com/yt-dlp/yt-dlp/issues/10569)) by [middlingphys](https://github.com/middlingphys)
- **cbc.ca**: player: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/94a1c5e642e468cebeb51f74c6c220434cb47d96) ([#10302](https://github.com/yt-dlp/yt-dlp/issues/10302)) by [bashonly](https://github.com/bashonly), [trainman261](https://github.com/trainman261)
- **discoveryplus**: [Support olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/0b7728618417e1aa382722a4d29b916b594d4459) ([#10566](https://github.com/yt-dlp/yt-dlp/issues/10566)) by [bashonly](https://github.com/bashonly)
- **kick**: clips: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/bb3936ae2b3ce96d0b53f9e17cad1082058f032b) ([#10572](https://github.com/yt-dlp/yt-dlp/issues/10572)) by [luvyana](https://github.com/luvyana)
- **learningonscreen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/fe15d3178e242803ae7a934b90137f13598eba2e) ([#10590](https://github.com/yt-dlp/yt-dlp/issues/10590)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7e3e4779ad13e4511c9ba3869879e53f0267bd7a) ([#10605](https://github.com/yt-dlp/yt-dlp/issues/10605)) by [szantnerb](https://github.com/szantnerb)
- **mlbtv**: [Fix makeup game extraction](https://github.com/yt-dlp/yt-dlp/commit/4b69e1b53ea21e631cd5dd68ff531e2f1671ec17) ([#10607](https://github.com/yt-dlp/yt-dlp/issues/10607)) by [bashonly](https://github.com/bashonly)
- **olympics**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2f1ddfe12a2c174bc777264c5c8ffe7ca0922d94) ([#10604](https://github.com/yt-dlp/yt-dlp/issues/10604)) by [bashonly](https://github.com/bashonly)
- **tva**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/28d485714fef88937c82635438afba5db81f9089) ([#10567](https://github.com/yt-dlp/yt-dlp/issues/10567)) by [bashonly](https://github.com/bashonly)
- **tver**: [Support olympic URLs](https://github.com/yt-dlp/yt-dlp/commit/5260696b1cba77161828941fdb38f09f14ac6c60) ([#10600](https://github.com/yt-dlp/yt-dlp/issues/10600)) by [vvto33](https://github.com/vvto33)
- **vimeo**: review: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/2b6df93a243bdfb9d6bb5c1e18020625cd02d465) ([#10598](https://github.com/yt-dlp/yt-dlp/issues/10598)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Change default player clients to `ios,tv`](https://github.com/yt-dlp/yt-dlp/commit/efb42763dec23ccf6a2e3bac3afbfefce8efd012) ([#10457](https://github.com/yt-dlp/yt-dlp/issues/10457)) by [seproDev](https://github.com/seproDev)
- [Fix `n` function name extraction for player `20dfca59`](https://github.com/yt-dlp/yt-dlp/commit/011b4a04db2a636c3ef0a0ad4e2d3ae482c9fd76) ([#10611](https://github.com/yt-dlp/yt-dlp/issues/10611)) by [bashonly](https://github.com/bashonly)
- [Fix age-verification workaround](https://github.com/yt-dlp/yt-dlp/commit/d19fcb934269465fd707e68a87f735ec6983e93d) ([#10610](https://github.com/yt-dlp/yt-dlp/issues/10610)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
- [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/0e539617a41913c7da1edd74fb6543c10ad727b3) ([#10573](https://github.com/yt-dlp/yt-dlp/issues/10573)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **cleanup**: Miscellaneous: [ffd7781](https://github.com/yt-dlp/yt-dlp/commit/ffd7781d6588926f820b44a34b9e6e3068fb9f97) by [bashonly](https://github.com/bashonly)
### 2024.07.25
#### Extractor changes
- **abematv**: [Adapt key retrieval to request handler framework](https://github.com/yt-dlp/yt-dlp/commit/a3bab4752a2b3d56e5a59b4e0411bb8f695c010b) ([#10491](https://github.com/yt-dlp/yt-dlp/issues/10491)) by [bashonly](https://github.com/bashonly)
- **facebook**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1a34a802f44a1dab8f642c79c3cc810e21541d3b) ([#10531](https://github.com/yt-dlp/yt-dlp/issues/10531)) by [bashonly](https://github.com/bashonly)
- **mlbtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/f0993391e6052ec8f7aacc286609564f226943b9) ([#10515](https://github.com/yt-dlp/yt-dlp/issues/10515)) by [bashonly](https://github.com/bashonly)
- **tiktok**: [Fix and deprioritize JSON subtitles](https://github.com/yt-dlp/yt-dlp/commit/2f97779f335ac069ecccd9c7bf81abf4a83cfe7a) ([#10516](https://github.com/yt-dlp/yt-dlp/issues/10516)) by [bashonly](https://github.com/bashonly)
- **vimeo**: [Fix chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a0a1bc3d8d8e3bb9a48a06e835815a0460e90e77) ([#10544](https://github.com/yt-dlp/yt-dlp/issues/10544)) by [bashonly](https://github.com/bashonly)
- **youtube**: [Fix `n` function name extraction for player `3400486c`](https://github.com/yt-dlp/yt-dlp/commit/713b4cd18f00556771af8cfdd9cea6cc1a09e948) ([#10542](https://github.com/yt-dlp/yt-dlp/issues/10542)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **build**: [Pin `setuptools` version](https://github.com/yt-dlp/yt-dlp/commit/e046db8a116b1c320d4785daadd48ea0b22a3987) ([#10493](https://github.com/yt-dlp/yt-dlp/issues/10493)) by [bashonly](https://github.com/bashonly)
### 2024.07.16
#### Core changes

6
README.md
View File

@ -1758,7 +1758,7 @@ $ yt-dlp --replace-in-metadata "title,uploader" "[ _]" "-"
# EXTRACTOR ARGUMENTS
Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=android_embedded,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=mediaconnect,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"`
@ -1767,7 +1767,7 @@ The following extractors use this feature:
#### youtube
* `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
* `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mediaconnect`, `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. The `android` clients will always be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,tv` is used, but `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
* `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
@ -1775,7 +1775,7 @@ The following extractors use this feature:
* E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total
* `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8)
* `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
* `innertube_key`: Innertube API key to use for all API requests
* `innertube_key`: Innertube API key to use for all API requests. By default, no API key is used
* `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
#### youtubetab (YouTube playlists, channels, feeds, etc.)

9
supportedsites.md
View File

@ -655,10 +655,11 @@
- **Ketnet**
- **khanacademy**
- **khanacademy:unit**
- **Kick**
- **kick:clips**
- **kick:live**
- **kick:vod**
- **Kicker**
- **KickStarter**
- **KickVOD**
- **kinja:embed**
- **KinoPoisk**
- **Kommunetv**
@ -690,6 +691,7 @@
- **Lcp**
- **LcpPlay**
- **Le**: 乐视网
- **LearningOnScreen**
- **Lecture2Go**: (**Currently broken**)
- **Lecturio**: [*lecturio*](## "netrc machine")
- **LecturioCourse**: [*lecturio*](## "netrc machine")
@ -1140,7 +1142,6 @@
- **QuantumTV**: [*quantumtv*](## "netrc machine")
- **QuantumTVLive**: [*quantumtv*](## "netrc machine")
- **QuantumTVRecordings**: [*quantumtv*](## "netrc machine")
- **Qub**
- **R7**: (**Currently broken**)
- **R7Article**: (**Currently broken**)
- **Radiko**
@ -1517,9 +1518,9 @@
- **tv5unis**
- **tv5unis:video**
- **tv8.it**
- **TVA**
- **TVANouvelles**
- **TVANouvellesArticle**
- **tvaplus**: TVA+
- **TVC**
- **TVCArticle**
- **TVer**

2
test/test_utils.py
View File

@ -444,6 +444,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
self.assertEqual(unified_timestamp('Sunday, 26 Nov 2006, 19:00'), 1164567600)
self.assertEqual(unified_timestamp('wed, aug 16, 2008, 12:00pm'), 1218931200)
self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)

8
test/test_youtube_signature.py
View File

@ -171,6 +171,14 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js',
'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A',
),
(
'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js',
'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl',
),
(
'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
'-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
),
]

7
yt_dlp/extractor/_extractors.py
View File

@ -938,6 +938,7 @@ from .khanacademy import (
KhanAcademyUnitIE,
)
from .kick import (
KickClipIE,
KickIE,
KickVODIE,
)
@ -985,6 +986,7 @@ from .lcp import (
LcpIE,
LcpPlayIE,
)
from .learningonscreen import LearningOnScreenIE
from .lecture2go import Lecture2GoIE
from .lecturio import (
LecturioCourseIE,
@ -2168,10 +2170,7 @@ from .tv5unis import (
TV5UnisVideoIE,
)
from .tv24ua import TV24UAVideoIE
from .tva import (
TVAIE,
QubIE,
)
from .tva import TVAIE
from .tvanouvelles import (
TVANouvellesArticleIE,
TVANouvellesIE,

3
yt_dlp/extractor/abematv.py
View File

@ -377,8 +377,7 @@ class AbemaTVIE(AbemaTVBaseIE):
f'https://api.abema.io/v1/video/programs/{video_id}', video_id,
note='Checking playability',
headers=headers)
ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType'))
if 3 not in ondemand_types:
if not traverse_obj(api_response, ('label', 'free', {bool})):
# cannot acquire decryption key for these streams
self.report_warning('This is a premium-only stream')
availability = 'premium_only'

269
yt_dlp/extractor/cbc.py
View File

@ -1,4 +1,5 @@
import base64
import functools
import json
import re
import time
@ -6,17 +7,24 @@ import urllib.parse
import xml.etree.ElementTree
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
join_nonempty,
js_to_json,
mimetype2ext,
orderedSet,
parse_iso8601,
replace_extension,
smuggle_url,
strip_or_none,
traverse_obj,
try_get,
update_url,
url_basename,
url_or_none,
)
@ -149,6 +157,7 @@ class CBCIE(InfoExtractor):
class CBCPlayerIE(InfoExtractor):
IE_NAME = 'cbc.ca:player'
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/(?:video/)?|i/caffeine/syndicate/\?mediaId=))(?P<id>(?:\d\.)?\d+)'
_GEO_COUNTRIES = ['CA']
_TESTS = [{
'url': 'http://www.cbc.ca/player/play/2683190193',
'md5': '64d25f841ddf4ddb28a235338af32e2c',
@ -172,21 +181,20 @@ class CBCPlayerIE(InfoExtractor):
'description': 'md5:dd3b692f0a139b0369943150bd1c46a9',
'timestamp': 1425704400,
'upload_date': '20150307',
'uploader': 'CBCC-NEW',
'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg',
'chapters': [],
'duration': 494.811,
'categories': ['AudioMobile/All in a Weekend Montreal'],
'tags': 'count:8',
'categories': ['All in a Weekend Montreal'],
'tags': 'count:11',
'location': 'Quebec',
'series': 'All in a Weekend Montreal',
'season': 'Season 2015',
'season_number': 2015,
'media_type': 'Excerpt',
'genres': ['Other'],
},
}, {
'url': 'http://www.cbc.ca/i/caffeine/syndicate/?mediaId=2164402062',
'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
'info_dict': {
'id': '2164402062',
'ext': 'mp4',
@ -194,107 +202,168 @@ class CBCPlayerIE(InfoExtractor):
'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
'timestamp': 1320410746,
'upload_date': '20111104',
'uploader': 'CBCC-NEW',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg',
'chapters': [],
'duration': 186.867,
'series': 'CBC News: Windsor at 6:00',
'categories': ['News/Canada/Windsor'],
'categories': ['Windsor'],
'location': 'Windsor',
'tags': ['cancer'],
'creators': ['Allison Johnson'],
'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'],
'media_type': 'Excerpt',
'genres': ['News'],
},
'params': {'skip_download': 'm3u8'},
}, {
# Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
'url': 'https://www.cbc.ca/player/play/1.2985700',
'md5': 'e5e708c34ae6fca156aafe17c43e8b75',
'info_dict': {
'id': '2657631896',
'id': '1.2985700',
'ext': 'mp3',
'title': 'CBC Montreal is organizing its first ever community hackathon!',
'description': 'The modern technology we tend to depend on so heavily, is never without it\'s share of hiccups and headaches. Next weekend - CBC Montreal will be getting members of the public for its first Hackathon.',
'timestamp': 1425704400,
'upload_date': '20150307',
'uploader': 'CBCC-NEW',
'thumbnail': 'http://thumbnails.cbc.ca/maven_legacy/thumbnails/sonali-karnick-220.jpg',
'thumbnail': 'https://i.cbc.ca/ais/1.2985700,1717262248558/full/max/0/default.jpg',
'chapters': [],
'duration': 494.811,
'categories': ['AudioMobile/All in a Weekend Montreal'],
'tags': 'count:8',
'categories': ['All in a Weekend Montreal'],
'tags': 'count:11',
'location': 'Quebec',
'series': 'All in a Weekend Montreal',
'season': 'Season 2015',
'season_number': 2015,
'media_type': 'Excerpt',
'genres': ['Other'],
},
}, {
'url': 'https://www.cbc.ca/player/play/1.1711287',
'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
'info_dict': {
'id': '2164402062',
'id': '1.1711287',
'ext': 'mp4',
'title': 'Cancer survivor four times over',
'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
'timestamp': 1320410746,
'upload_date': '20111104',
'uploader': 'CBCC-NEW',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/277/67/cancer_852x480_2164412612.jpg',
'thumbnail': 'https://i.cbc.ca/ais/1.1711287,1717139372111/full/max/0/default.jpg',
'chapters': [],
'duration': 186.867,
'series': 'CBC News: Windsor at 6:00',
'categories': ['News/Canada/Windsor'],
'categories': ['Windsor'],
'location': 'Windsor',
'tags': ['cancer'],
'creators': ['Allison Johnson'],
'tags': ['Cancer', 'News/Canada/Windsor', 'Windsor'],
'media_type': 'Excerpt',
'genres': ['News'],
},
'params': {'skip_download': 'm3u8'},
}, {
# Has subtitles
# These broadcasts expire after ~1 month, can find new test URL here:
# https://www.cbc.ca/player/news/TV%20Shows/The%20National/Latest%20Broadcast
'url': 'https://www.cbc.ca/player/play/1.7159484',
'md5': '6ed6cd0fc2ef568d2297ba68a763d455',
'url': 'https://www.cbc.ca/player/play/video/9.6424403',
'md5': '8025909eaffcf0adf59922904def9a5e',
'info_dict': {
'id': '2324213316001',
'id': '9.6424403',
'ext': 'mp4',
'title': 'The National | School boards sue social media giants',
'description': 'md5:4b4db69322fa32186c3ce426da07402c',
'timestamp': 1711681200,
'duration': 2743.400,
'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/607/559/thumbnail.jpeg',
'uploader': 'CBCC-NEW',
'title': 'The National | N.W.T. wildfire emergency',
'description': 'md5:ada33d36d1df69347ed575905bfd496c',
'timestamp': 1718589600,
'duration': 2692.833,
'subtitles': {
'en-US': [{
'name': 'English Captions',
'url': 'https://cbchls.akamaized.net/delivery/news-shows/2024/06/17/NAT_JUN16-00-55-00/NAT_JUN16_cc.vtt',
}],
},
'thumbnail': 'https://i.cbc.ca/ais/6272b5c6-5e78-4c05-915d-0e36672e33d1,1714756287822/full/max/0/default.jpg',
'chapters': 'count:5',
'upload_date': '20240329',
'categories': 'count:4',
'upload_date': '20240617',
'categories': ['News', 'The National', 'The National Latest Broadcasts'],
'series': 'The National - Full Show',
'tags': 'count:1',
'creators': ['News'],
'tags': ['The National'],
'location': 'Canada',
'media_type': 'Full Program',
'genres': ['News'],
},
}, {
'url': 'https://www.cbc.ca/player/play/video/1.7194274',
'md5': '188b96cf6bdcb2540e178a6caa957128',
'info_dict': {
'id': '2334524995812',
'id': '1.7194274',
'ext': 'mp4',
'title': '#TheMoment a rare white spirit moose was spotted in Alberta',
'description': 'md5:18ae269a2d0265c5b0bbe4b2e1ac61a3',
'timestamp': 1714788791,
'duration': 77.678,
'subtitles': {'eng': [{'ext': 'vtt', 'protocol': 'm3u8_native'}]},
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/201/543/THE_MOMENT.jpg',
'uploader': 'CBCC-NEW',
'chapters': 'count:0',
'upload_date': '20240504',
'thumbnail': 'https://i.cbc.ca/ais/1.7194274,1717224990425/full/max/0/default.jpg',
'chapters': [],
'categories': 'count:3',
'series': 'The National',
'tags': 'count:15',
'creators': ['encoder'],
'tags': 'count:17',
'location': 'Canada',
'media_type': 'Excerpt',
'upload_date': '20240504',
'genres': ['News'],
},
}, {
'url': 'https://www.cbc.ca/player/play/video/9.6427282',
'info_dict': {
'id': '9.6427282',
'ext': 'mp4',
'title': 'Men\'s Soccer - Argentina vs Morocco',
'description': 'Argentina faces Morocco on the football pitch at Saint Etienne Stadium.',
'series': 'CBC Sports',
'media_type': 'Event Coverage',
'thumbnail': 'https://i.cbc.ca/ais/a4c5c0c2-99fa-4bd3-8061-5a63879c1b33,1718828053500/full/max/0/default.jpg',
'timestamp': 1721825400.0,
'upload_date': '20240724',
'duration': 10568.0,
'chapters': [],
'genres': [],
'tags': ['2024 Paris Olympic Games'],
'categories': ['Olympics Summer Soccer', 'Summer Olympics Replays', 'Summer Olympics Soccer Replays'],
'location': 'Canada',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.cbc.ca/player/play/video/9.6459530',
'md5': '6c1bb76693ab321a2e99c347a1d5ecbc',
'info_dict': {
'id': '9.6459530',
'ext': 'mp4',
'title': 'Parts of Jasper incinerated as wildfire rages',
'description': 'md5:6f1caa8d128ad3f629257ef5fecf0962',
'series': 'The National',
'media_type': 'Excerpt',
'thumbnail': 'https://i.cbc.ca/ais/507c0086-31a2-494d-96e4-bffb1048d045,1721953984375/full/max/0/default.jpg',
'timestamp': 1721964091.012,
'upload_date': '20240726',
'duration': 952.285,
'chapters': [],
'genres': [],
'tags': 'count:23',
'categories': ['News (FAST)', 'News', 'The National', 'TV News Shows', 'The National '],
},
}, {
'url': 'https://www.cbc.ca/player/play/video/9.6420651',
'md5': '71a850c2c6ee5e912de169f5311bb533',
'info_dict': {
'id': '9.6420651',
'ext': 'mp4',
'title': 'Is it a breath of fresh air? Measuring air quality in Edmonton',
'description': 'md5:3922b92cc8b69212d739bd9dd095b1c3',
'series': 'CBC News Edmonton',
'media_type': 'Excerpt',
'thumbnail': 'https://i.cbc.ca/ais/73c4ab9c-7ad4-46ee-bb9b-020fdc01c745,1718214547576/full/max/0/default.jpg',
'timestamp': 1718220065.768,
'upload_date': '20240612',
'duration': 286.086,
'chapters': [],
'genres': ['News'],
'categories': ['News', 'Edmonton'],
'tags': 'count:7',
'location': 'Edmonton',
},
}, {
'url': 'cbcplayer:1.7159484',
@ -307,23 +376,113 @@ class CBCPlayerIE(InfoExtractor):
'only_matching': True,
}]
def _parse_param(self, asset_data, name):
return traverse_obj(asset_data, ('params', lambda _, v: v['name'] == name, 'value', {str}, any))
def _real_extract(self, url):
video_id = self._match_id(url)
if '.' in video_id:
webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
video_id = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage,
'initial state', video_id)['video']['currentClip']['mediaId']
webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
data = self._search_json(
r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)['video']['currentClip']
assets = traverse_obj(
data, ('media', 'assets', lambda _, v: url_or_none(v['key']) and v['type']))
if not assets and (media_id := traverse_obj(data, ('mediaId', {str}))):
# XXX: Deprecated; CBC is migrating off of ThePlatform
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(
f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{media_id}?mbr=true&formats=MPEG4,FLV,MP3', {
'force_smil_url': True,
}),
'id': media_id,
'_format_sort_fields': ('res', 'proto'), # Prioritize direct http formats over HLS
}
is_live = traverse_obj(data, ('media', 'streamType', {str})) == 'Live'
formats, subtitles = [], {}
for sub in traverse_obj(data, ('media', 'textTracks', lambda _, v: url_or_none(v['src']))):
subtitles.setdefault(sub.get('language') or 'und', []).append({
'url': sub['src'],
'name': sub.get('label'),
})
for asset in assets:
asset_key = asset['key']
asset_type = asset['type']
if asset_type != 'medianet':
self.report_warning(f'Skipping unsupported asset type "{asset_type}": {asset_key}')
continue
asset_data = self._download_json(asset_key, video_id, f'Downloading {asset_type} JSON')
ext = mimetype2ext(self._parse_param(asset_data, 'contentType'))
if ext == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
asset_data['url'], video_id, 'mp4', m3u8_id='hls', live=is_live)
formats.extend(fmts)
# Avoid slow/error-prone webvtt-over-m3u8 if direct https vtt is available
if not subtitles:
self._merge_subtitles(subs, target=subtitles)
if is_live or not fmts:
continue
# Check for direct https mp4 format
best_video_fmt = traverse_obj(fmts, (
lambda _, v: v.get('vcodec') != 'none' and v['tbr'], all,
{functools.partial(sorted, key=lambda x: x['tbr'])}, -1, {dict})) or {}
base_url = self._search_regex(
r'(https?://[^?#]+?/)hdntl=', best_video_fmt.get('url'), 'base url', default=None)
if not base_url or '/live/' in base_url:
continue
mp4_url = base_url + replace_extension(url_basename(best_video_fmt['url']), 'mp4')
if self._request_webpage(
HEADRequest(mp4_url), video_id, 'Checking for https format',
errnote=False, fatal=False):
formats.append({
**best_video_fmt,
'url': mp4_url,
'format_id': 'https-mp4',
'protocol': 'https',
'manifest_url': None,
'acodec': None,
})
else:
formats.append({
'url': asset_data['url'],
'ext': ext,
'vcodec': 'none' if self._parse_param(asset_data, 'mediaType') == 'audio' else None,
})
chapters = traverse_obj(data, (
'media', 'chapters', lambda _, v: float(v['startTime']) is not None, {
'start_time': ('startTime', {functools.partial(float_or_none, scale=1000)}),
'end_time': ('endTime', {functools.partial(float_or_none, scale=1000)}),
'title': ('name', {str}),
}))
# Filter out pointless single chapters with start_time==0 and no end_time
if len(chapters) == 1 and not (chapters[0].get('start_time') or chapters[0].get('end_time')):
chapters = []
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(
f'http://link.theplatform.com/s/ExhSPC/media/guid/2655402169/{video_id}?mbr=true&formats=MPEG4,FLV,MP3', {
'force_smil_url': True,
}),
**traverse_obj(data, {
'title': ('title', {str}),
'description': ('description', {str.strip}),
'thumbnail': ('image', 'url', {url_or_none}, {functools.partial(update_url, query=None)}),
'timestamp': ('publishedAt', {functools.partial(float_or_none, scale=1000)}),
'media_type': ('media', 'clipType', {str}),
'series': ('showName', {str}),
'season_number': ('media', 'season', {int_or_none}),
'duration': ('media', 'duration', {float_or_none}, {lambda x: None if is_live else x}),
'location': ('media', 'region', {str}),
'tags': ('tags', ..., 'name', {str}),
'genres': ('media', 'genre', all),
'categories': ('categories', ..., 'name', {str}),
}),
'id': video_id,
'_format_sort_fields': ('res', 'proto'), # Prioritize direct http formats over HLS
'formats': formats,
'subtitles': subtitles,
'chapters': chapters,
'is_live': is_live,
}

8
yt_dlp/extractor/common.py
View File

@ -3150,7 +3150,7 @@ class InfoExtractor:
})
return formats, subtitles
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None):
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None, _headers=None):
def absolute_url(item_url):
return urljoin(base_url, item_url)
@ -3174,11 +3174,11 @@ class InfoExtractor:
formats = self._extract_m3u8_formats(
full_url, video_id, ext='mp4',
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id,
preference=preference, quality=quality, fatal=False)
preference=preference, quality=quality, fatal=False, headers=_headers)
elif ext == 'mpd':
is_plain_url = False
formats = self._extract_mpd_formats(
full_url, video_id, mpd_id=mpd_id, fatal=False)
full_url, video_id, mpd_id=mpd_id, fatal=False, headers=_headers)
else:
is_plain_url = True
formats = [{
@ -3272,6 +3272,8 @@ class InfoExtractor:
})
for f in media_info['formats']:
f.setdefault('http_headers', {})['Referer'] = base_url
if _headers:
f['http_headers'].update(_headers)
if media_info['formats'] or media_info['subtitles']:
entries.append(media_info)
return entries

13
yt_dlp/extractor/dplay.py
View File

@ -934,7 +934,7 @@ class TLCIE(DiscoveryPlusBaseIE):
class DiscoveryPlusIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P<country>[a-z]{2})/)?video(?:/sport)?' + DPlayBaseIE._PATH_REGEX
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:(?P<country>[a-z]{2})/)?video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
'info_dict': {
@ -958,6 +958,9 @@ class DiscoveryPlusIE(DiscoveryPlusBaseIE):
}, {
'url': 'https://www.discoveryplus.com/gb/video/sport/eurosport-1-british-eurosport-1-british-sport/6-hours-of-spa-review',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/gb/video/olympics/dplus-sport-dplus-sport-sport/rugby-sevens-australia-samoa',
'only_matching': True,
}]
_PRODUCT = None
@ -1144,13 +1147,19 @@ class DiscoveryPlusShowBaseIE(DPlayBaseIE):
class DiscoveryPlusItalyIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video' + DPlayBaseIE._PATH_REGEX
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/it/video(?:/sport|/olympics)?' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.discoveryplus.com/it/video/i-signori-della-neve/stagione-2-episodio-1-i-preparativi',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/it/video/super-benny/trailer',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/it/video/olympics/dplus-sport-dplus-sport-sport/water-polo-greece-italy',
'only_matching': True,
}, {
'url': 'https://www.discoveryplus.com/it/video/sport/dplus-sport-dplus-sport-sport/lisa-vittozzi-allinferno-e-ritorno',
'only_matching': True,
}]
_PRODUCT = 'dplus_it'

24
yt_dlp/extractor/facebook.py
View File

@ -571,16 +571,21 @@ class FacebookIE(InfoExtractor):
# Formats larger than ~500MB will return error 403 unless chunk size is regulated
f.setdefault('downloader_options', {})['http_chunk_size'] = 250 << 20
def extract_relay_data(_filter):
return self._parse_json(self._search_regex(
rf'data-sjs>({{.*?{_filter}.*?}})</script>',
webpage, 'replay data', default='{}'), video_id, fatal=False) or {}
def yield_all_relay_data(_filter):
for relay_data in re.findall(rf'data-sjs>({{.*?{_filter}.*?}})</script>', webpage):
yield self._parse_json(relay_data, video_id, fatal=False) or {}
def extract_relay_prefetched_data(_filter):
return traverse_obj(extract_relay_data(_filter), (
'require', (None, (..., ..., ..., '__bbox', 'require')),
def extract_relay_data(_filter):
return next(filter(None, yield_all_relay_data(_filter)), {})
def extract_relay_prefetched_data(_filter, target_keys=None):
path = 'data'
if target_keys is not None:
path = lambda k, v: k == 'data' and any(target in v for target in variadic(target_keys))
return traverse_obj(yield_all_relay_data(_filter), (
..., 'require', (None, (..., ..., ..., '__bbox', 'require')),
lambda _, v: any(key.startswith('RelayPrefetchedStreamCache') for key in v),
..., ..., '__bbox', 'result', 'data', {dict}), get_all=False) or {}
..., ..., '__bbox', 'result', path, {dict}), get_all=False) or {}
if not video_data:
server_js_data = self._parse_json(self._search_regex([
@ -591,7 +596,8 @@ class FacebookIE(InfoExtractor):
if not video_data:
data = extract_relay_prefetched_data(
r'"(?:dash_manifest|playable_url(?:_quality_hd)?)')
r'"(?:dash_manifest|playable_url(?:_quality_hd)?)',
target_keys=('video', 'event', 'nodes', 'node', 'mediaset'))
if data:
entries = []

205
yt_dlp/extractor/kick.py
View File

@ -1,9 +1,14 @@
import functools
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
UserNotLive,
determine_ext,
float_or_none,
int_or_none,
merge_dicts,
parse_iso8601,
str_or_none,
traverse_obj,
unified_timestamp,
@ -25,104 +30,192 @@ class KickBaseIE(InfoExtractor):
def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
return self._download_json(
f'https://kick.com/api/v1/{path}', display_id, note=note,
f'https://kick.com/api/{path}', display_id, note=note,
headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
class KickIE(KickBaseIE):
IE_NAME = 'kick:live'
_VALID_URL = r'https?://(?:www\.)?kick\.com/(?!(?:video|categories|search|auth)(?:[/?#]|$))(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://kick.com/yuppy',
'url': 'https://kick.com/buddha',
'info_dict': {
'id': '6cde1-kickrp-joe-flemmingskick-info-heremust-knowmust-see21',
'id': '92722911-nopixel-40',
'ext': 'mp4',
'title': str,
'description': str,
'channel': 'yuppy',
'channel_id': '33538',
'uploader': 'Yuppy',
'uploader_id': '33793',
'upload_date': str,
'live_status': 'is_live',
'timestamp': int,
'thumbnail': r're:^https?://.*\.jpg',
'thumbnail': r're:https?://.+\.jpg',
'categories': list,
'upload_date': str,
'channel': 'buddha',
'channel_id': '32807',
'uploader': 'Buddha',
'uploader_id': '33057',
'live_status': 'is_live',
'concurrent_view_count': int,
'release_timestamp': int,
'age_limit': 18,
'release_date': str,
},
'skip': 'livestream',
'params': {'skip_download': 'livestream'},
# 'skip': 'livestream',
}, {
'url': 'https://kick.com/kmack710',
'url': 'https://kick.com/xqc',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if KickClipIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
channel = self._match_id(url)
response = self._call_api(f'channels/{channel}', channel)
response = self._call_api(f'v2/channels/{channel}', channel)
if not traverse_obj(response, 'livestream', expected_type=dict):
raise UserNotLive(video_id=channel)
return {
'id': str(traverse_obj(
response, ('livestream', ('slug', 'id')), get_all=False, default=channel)),
'formats': self._extract_m3u8_formats(
response['playback_url'], channel, 'mp4', live=True),
'title': traverse_obj(
response, ('livestream', ('session_title', 'slug')), get_all=False, default=''),
'description': traverse_obj(response, ('user', 'bio')),
'channel': channel,
'channel_id': str_or_none(traverse_obj(response, 'id', ('livestream', 'channel_id'))),
'uploader': traverse_obj(response, 'name', ('user', 'username')),
'uploader_id': str_or_none(traverse_obj(response, 'user_id', ('user', 'id'))),
'is_live': True,
'timestamp': unified_timestamp(traverse_obj(response, ('livestream', 'created_at'))),
'thumbnail': traverse_obj(
response, ('livestream', 'thumbnail', 'url'), expected_type=url_or_none),
'categories': traverse_obj(response, ('recent_categories', ..., 'name')),
'formats': self._extract_m3u8_formats(response['playback_url'], channel, 'mp4', live=True),
**traverse_obj(response, {
'id': ('livestream', 'slug', {str}),
'title': ('livestream', 'session_title', {str}),
'description': ('user', 'bio', {str}),
'channel_id': (('id', ('livestream', 'channel_id')), {int}, {str_or_none}, any),
'uploader': (('name', ('user', 'username')), {str}, any),
'uploader_id': (('user_id', ('user', 'id')), {int}, {str_or_none}, any),
'timestamp': ('livestream', 'created_at', {unified_timestamp}),
'release_timestamp': ('livestream', 'start_time', {unified_timestamp}),
'thumbnail': ('livestream', 'thumbnail', 'url', {url_or_none}),
'categories': ('recent_categories', ..., 'name', {str}),
'concurrent_view_count': ('livestream', 'viewer_count', {int_or_none}),
'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
}),
}
class KickVODIE(KickBaseIE):
IE_NAME = 'kick:vod'
_VALID_URL = r'https?://(?:www\.)?kick\.com/video/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_TESTS = [{
'url': 'https://kick.com/video/58bac65b-e641-4476-a7ba-3707a35e60e3',
'url': 'https://kick.com/video/e74614f4-5270-4319-90ad-32179f19a45c',
'md5': '3870f94153e40e7121a6e46c068b70cb',
'info_dict': {
'id': '58bac65b-e641-4476-a7ba-3707a35e60e3',
'id': 'e74614f4-5270-4319-90ad-32179f19a45c',
'ext': 'mp4',
'title': '🤠REBIRTH IS BACK!!!!🤠!stake CODE JAREDFPS 🤠',
'description': 'md5:02b0c46f9b4197fb545ab09dddb85b1d',
'channel': 'jaredfps',
'channel_id': '26608',
'uploader': 'JaredFPS',
'uploader_id': '26799',
'upload_date': '20240402',
'timestamp': 1712097108,
'duration': 33859.0,
'title': r're:❎ MEGA DRAMA ❎ LIVE ❎ CLICK ❎ ULTIMATE SKILLS .+',
'description': 'THE BEST AT ABSOLUTELY EVERYTHING. THE JUICER. LEADER OF THE JUICERS.',
'channel': 'xqc',
'channel_id': '668',
'uploader': 'xQc',
'uploader_id': '676',
'upload_date': '20240724',
'timestamp': 1721796562,
'duration': 18566.0,
'thumbnail': r're:^https?://.*\.jpg',
'categories': ['Call of Duty: Warzone'],
'view_count': int,
'categories': ['VALORANT'],
'age_limit': 0,
},
'params': {
'skip_download': 'm3u8',
},
'expected_warnings': [r'impersonation'],
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
response = self._call_api(f'video/{video_id}', video_id)
response = self._call_api(f'v1/video/{video_id}', video_id)
return {
'id': video_id,
'formats': self._extract_m3u8_formats(response['source'], video_id, 'mp4'),
'title': traverse_obj(
response, ('livestream', ('session_title', 'slug')), get_all=False, default=''),
'description': traverse_obj(response, ('livestream', 'channel', 'user', 'bio')),
'channel': traverse_obj(response, ('livestream', 'channel', 'slug')),
'channel_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'id'))),
'uploader': traverse_obj(response, ('livestream', 'channel', 'user', 'username')),
'uploader_id': str_or_none(traverse_obj(response, ('livestream', 'channel', 'user_id'))),
'timestamp': unified_timestamp(response.get('created_at')),
'duration': float_or_none(traverse_obj(response, ('livestream', 'duration')), scale=1000),
'thumbnail': traverse_obj(
response, ('livestream', 'thumbnail'), expected_type=url_or_none),
'categories': traverse_obj(response, ('livestream', 'categories', ..., 'name')),
**traverse_obj(response, {
'title': ('livestream', ('session_title', 'slug'), {str}, any),
'description': ('livestream', 'channel', 'user', 'bio', {str}),
'channel': ('livestream', 'channel', 'slug', {str}),
'channel_id': ('livestream', 'channel', 'id', {int}, {str_or_none}),
'uploader': ('livestream', 'channel', 'user', 'username', {str}),
'uploader_id': ('livestream', 'channel', 'user_id', {int}, {str_or_none}),
'timestamp': ('created_at', {parse_iso8601}),
'duration': ('livestream', 'duration', {functools.partial(float_or_none, scale=1000)}),
'thumbnail': ('livestream', 'thumbnail', {url_or_none}),
'categories': ('livestream', 'categories', ..., 'name', {str}),
'view_count': ('views', {int_or_none}),
'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
}),
}
class KickClipIE(KickBaseIE):
IE_NAME = 'kick:clips'
_VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/?\?(?:[^#]+&)?clip=(?P<id>clip_[\w-]+)'
_TESTS = [{
'url': 'https://kick.com/mxddy?clip=clip_01GYXVB5Y8PWAPWCWMSBCFB05X',
'info_dict': {
'id': 'clip_01GYXVB5Y8PWAPWCWMSBCFB05X',
'ext': 'mp4',
'title': 'Maddy detains Abd D:',
'channel': 'mxddy',
'channel_id': '133789',
'uploader': 'AbdCreates',
'uploader_id': '3309077',
'thumbnail': r're:^https?://.*\.jpeg',
'duration': 35,
'timestamp': 1682481453,
'upload_date': '20230426',
'view_count': int,
'like_count': int,
'categories': ['VALORANT'],
'age_limit': 18,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://kick.com/destiny?clip=clip_01H9SKET879NE7N9RJRRDS98J3',
'info_dict': {
'id': 'clip_01H9SKET879NE7N9RJRRDS98J3',
'title': 'W jews',
'ext': 'mp4',
'channel': 'destiny',
'channel_id': '1772249',
'uploader': 'punished_furry',
'uploader_id': '2027722',
'duration': 49.0,
'upload_date': '20230908',
'timestamp': 1694150180,
'thumbnail': 'https://clips.kick.com/clips/j3/clip_01H9SKET879NE7N9RJRRDS98J3/thumbnail.png',
'view_count': int,
'like_count': int,
'categories': ['Just Chatting'],
'age_limit': 0,
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
clip_id = self._match_id(url)
clip = self._call_api(f'v2/clips/{clip_id}/play', clip_id)['clip']
clip_url = clip['clip_url']
if determine_ext(clip_url) == 'm3u8':
formats = self._extract_m3u8_formats(clip_url, clip_id, 'mp4')
else:
formats = [{'url': clip_url}]
return {
'id': clip_id,
'formats': formats,
**traverse_obj(clip, {
'title': ('title', {str}),
'channel': ('channel', 'slug', {str}),
'channel_id': ('channel', 'id', {int}, {str_or_none}),
'uploader': ('creator', 'username', {str}),
'uploader_id': ('creator', 'id', {int}, {str_or_none}),
'thumbnail': ('thumbnail_url', {url_or_none}),
'duration': ('duration', {float_or_none}),
'categories': ('category', 'name', {str}, all),
'timestamp': ('created_at', {parse_iso8601}),
'view_count': ('views', {int_or_none}),
'like_count': ('likes', {int_or_none}),
'age_limit': ('is_mature', {bool}, {lambda x: 18 if x else 0}),
}),
}

78
yt_dlp/extractor/learningonscreen.py Normal file
View File

@ -0,0 +1,78 @@
import functools
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
extract_attributes,
get_element_by_class,
get_element_html_by_id,
join_nonempty,
parse_duration,
unified_timestamp,
)
from ..utils.traversal import traverse_obj
class LearningOnScreenIE(InfoExtractor):
_VALID_URL = r'https?://learningonscreen\.ac\.uk/ondemand/index\.php/prog/(?P<id>\w+)'
_TESTS = [{
'url': 'https://learningonscreen.ac.uk/ondemand/index.php/prog/005D81B2?bcast=22757013',
'info_dict': {
'id': '005D81B2',
'ext': 'mp4',
'title': 'Planet Earth',
'duration': 3600.0,
'timestamp': 1164567600.0,
'upload_date': '20061126',
'thumbnail': 'https://stream.learningonscreen.ac.uk/trilt-cover-images/005D81B2-Planet-Earth-2006-11-26T190000Z-BBC4.jpg',
},
}]
def _real_initialize(self):
if not self._get_cookies('https://learningonscreen.ac.uk/').get('PHPSESSID-BOB-LIVE'):
self.raise_login_required(
'Use --cookies for authentication. See '
' https://github.com/yt-dlp/yt-dlp/wiki/FAQ#how-do-i-pass-cookies-to-yt-dlp '
'for how to manually pass cookies', method=None)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
details = traverse_obj(webpage, (
{functools.partial(get_element_html_by_id, 'programme-details')}, {
'title': ({functools.partial(re.search, r'<h2>([^<]+)</h2>')}, 1, {clean_html}),
'timestamp': (
{functools.partial(get_element_by_class, 'broadcast-date')},
{functools.partial(re.match, r'([^<]+)')}, 1, {unified_timestamp}),
'duration': (
{functools.partial(get_element_by_class, 'prog-running-time')},
{clean_html}, {parse_duration}),
}))
title = details.pop('title', None) or traverse_obj(webpage, (
{functools.partial(get_element_html_by_id, 'add-to-existing-playlist')},
{extract_attributes}, 'data-record-title', {clean_html}))
entries = self._parse_html5_media_entries(
'https://stream.learningonscreen.ac.uk', webpage, video_id, m3u8_id='hls', mpd_id='dash',
_headers={'Origin': 'https://learningonscreen.ac.uk', 'Referer': 'https://learningonscreen.ac.uk/'})
if not entries:
raise ExtractorError('No video found')
if len(entries) > 1:
duration = details.pop('duration', None)
for idx, entry in enumerate(entries, start=1):
entry.update(details)
entry['id'] = join_nonempty(video_id, idx)
entry['title'] = join_nonempty(title, idx)
return self.playlist_result(entries, video_id, title, duration=duration)
return {
**entries[0],
**details,
'id': video_id,
'title': title,
}

4
yt_dlp/extractor/mediaklikk.py
View File

@ -133,7 +133,9 @@ class MediaKlikkIE(InfoExtractor):
r'<p+\b[^>]+\bclass="article_date">([^<]+)<', webpage, 'upload date', default=None))
player_data['video'] = player_data.pop('token')
player_page = self._download_webpage('https://player.mediaklikk.hu/playernew/player.php', video_id, query=player_data)
player_page = self._download_webpage(
'https://player.mediaklikk.hu/playernew/player.php', video_id,
query=player_data, headers={'Referer': url})
player_json = self._search_json(
r'\bpl\.setup\s*\(', player_page, 'player json', video_id, end_pattern=r'\);')
playlist_url = traverse_obj(

239
yt_dlp/extractor/mlb.py
View File

@ -1,16 +1,21 @@
import json
import re
import urllib.parse
import time
import uuid
from .common import InfoExtractor
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
join_nonempty,
jwt_decode_hs256,
parse_duration,
parse_iso8601,
try_get,
url_or_none,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
@ -276,81 +281,225 @@ class MLBVideoIE(MLBBaseIE):
class MLBTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mlb\.com/tv/g(?P<id>\d{6})'
_NETRC_MACHINE = 'mlb'
_TESTS = [{
'url': 'https://www.mlb.com/tv/g661581/vee2eff5f-a7df-4c20-bdb4-7b926fa12638',
'info_dict': {
'id': '661581',
'ext': 'mp4',
'title': '2022-07-02 - St. Louis Cardinals @ Philadelphia Phillies',
'release_date': '20220702',
'release_timestamp': 1656792300,
},
'params': {
'skip_download': True,
'params': {'skip_download': 'm3u8'},
}, {
# makeup game: has multiple dates, need to avoid games with 'rescheduleDate'
'url': 'https://www.mlb.com/tv/g747039/vd22541c4-5a29-45f7-822b-635ec041cf5e',
'info_dict': {
'id': '747039',
'ext': 'mp4',
'title': '2024-07-29 - Toronto Blue Jays @ Baltimore Orioles',
'release_date': '20240729',
'release_timestamp': 1722280200,
},
'params': {'skip_download': 'm3u8'},
}]
_GRAPHQL_INIT_QUERY = '''\
mutation initSession($device: InitSessionInput!, $clientType: ClientType!, $experience: ExperienceTypeInput) {
initSession(device: $device, clientType: $clientType, experience: $experience) {
deviceId
sessionId
entitlements {
code
}
location {
countryCode
regionName
zipCode
latitude
longitude
}
clientExperience
features
}
}'''
_GRAPHQL_PLAYBACK_QUERY = '''\
mutation initPlaybackSession(
$adCapabilities: [AdExperienceType]
$mediaId: String!
$deviceId: String!
$sessionId: String!
$quality: PlaybackQuality
) {
initPlaybackSession(
adCapabilities: $adCapabilities
mediaId: $mediaId
deviceId: $deviceId
sessionId: $sessionId
quality: $quality
) {
playbackSessionId
playback {
url
token
expiration
cdn
}
}
}'''
_APP_VERSION = '7.8.2'
_device_id = None
_session_id = None
_access_token = None
_token_expiry = 0
@property
def _api_headers(self):
if (self._token_expiry - 120) <= time.time():
self.write_debug('Access token has expired; re-logging in')
self._perform_login(*self._get_login_info())
return {'Authorization': f'Bearer {self._access_token}'}
def _real_initialize(self):
if not self._access_token:
self.raise_login_required(
'All videos are only available to registered users', method='password')
def _set_device_id(self, username):
if not self._device_id:
self._device_id = self.cache.load(
self._NETRC_MACHINE, 'device_ids', default={}).get(username)
if self._device_id:
return
self._device_id = str(uuid.uuid4())
self.cache.store(self._NETRC_MACHINE, 'device_ids', {username: self._device_id})
def _perform_login(self, username, password):
data = f'grant_type=password&username={urllib.parse.quote(username)}&password={urllib.parse.quote(password)}&scope=openid offline_access&client_id=0oa3e1nutA1HLzAKG356'
access_token = self._download_json(
'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
headers={
'User-Agent': 'okhttp/3.12.1',
'Content-Type': 'application/x-www-form-urlencoded',
}, data=data.encode())['access_token']
try:
self._access_token = self._download_json(
'https://ids.mlb.com/oauth2/aus1m088yK07noBfh356/v1/token', None,
'Logging in', 'Unable to log in', headers={
'User-Agent': 'okhttp/3.12.1',
'Content-Type': 'application/x-www-form-urlencoded',
}, data=urlencode_postdata({
'grant_type': 'password',
'username': username,
'password': password,
'scope': 'openid offline_access',
'client_id': '0oa3e1nutA1HLzAKG356',
}))['access_token']
except ExtractorError as error:
if isinstance(error.cause, HTTPError) and error.cause.status == 400:
raise ExtractorError('Invalid username or password', expected=True)
raise
entitlement = self._download_webpage(
f'https://media-entitlement.mlb.com/api/v3/jwt?os=Android&appname=AtBat&did={uuid.uuid4()}', None,
headers={
'User-Agent': 'okhttp/3.12.1',
'Authorization': f'Bearer {access_token}',
})
self._token_expiry = traverse_obj(self._access_token, ({jwt_decode_hs256}, 'exp', {int})) or 0
self._set_device_id(username)
data = f'grant_type=urn:ietf:params:oauth:grant-type:token-exchange&subject_token={entitlement}&subject_token_type=urn:ietf:params:oauth:token-type:jwt&platform=android-tv'
self._access_token = self._download_json(
'https://us.edge.bamgrid.com/token', None,
self._session_id = self._call_api({
'operationName': 'initSession',
'query': self._GRAPHQL_INIT_QUERY,
'variables': {
'device': {
'appVersion': self._APP_VERSION,
'deviceFamily': 'desktop',
'knownDeviceId': self._device_id,
'languagePreference': 'ENGLISH',
'manufacturer': '',
'model': '',
'os': '',
'osVersion': '',
},
'clientType': 'WEB',
},
}, None, 'session ID')['data']['initSession']['sessionId']
def _call_api(self, data, video_id, description='GraphQL JSON', fatal=True):
return self._download_json(
'https://media-gateway.mlb.com/graphql', video_id,
f'Downloading {description}', f'Unable to download {description}', fatal=fatal,
headers={
**self._api_headers,
'Accept': 'application/json',
'Authorization': 'Bearer bWxidHYmYW5kcm9pZCYxLjAuMA.6LZMbH2r--rbXcgEabaDdIslpo4RyZrlVfWZhsAgXIk',
'Content-Type': 'application/x-www-form-urlencoded',
}, data=data.encode())['access_token']
'Content-Type': 'application/json',
'x-client-name': 'WEB',
'x-client-version': self._APP_VERSION,
}, data=json.dumps(data, separators=(',', ':')).encode())
def _extract_formats_and_subtitles(self, broadcast, video_id):
feed = traverse_obj(broadcast, ('homeAway', {str.title}))
medium = traverse_obj(broadcast, ('type', {str}))
language = traverse_obj(broadcast, ('language', {str.lower}))
format_id = join_nonempty(feed, medium, language)
response = self._call_api({
'operationName': 'initPlaybackSession',
'query': self._GRAPHQL_PLAYBACK_QUERY,
'variables': {
'adCapabilities': ['GOOGLE_STANDALONE_AD_PODS'],
'deviceId': self._device_id,
'mediaId': broadcast['mediaId'],
'quality': 'PLACEHOLDER',
'sessionId': self._session_id,
},
}, video_id, f'{format_id} broadcast JSON', fatal=False)
playback = traverse_obj(response, ('data', 'initPlaybackSession', 'playback', {dict}))
m3u8_url = traverse_obj(playback, ('url', {url_or_none}))
token = traverse_obj(playback, ('token', {str}))
if not (m3u8_url and token):
errors = '; '.join(traverse_obj(response, ('errors', ..., 'message', {str})))
if 'not entitled' in errors:
raise ExtractorError(errors, expected=True)
elif errors: # Only warn when 'blacked out' since radio formats are available
self.report_warning(f'API returned errors for {format_id}: {errors}')
else:
self.report_warning(f'No formats available for {format_id} broadcast; skipping')
return [], {}
cdn_headers = {'x-cdn-token': token}
fmts, subs = self._extract_m3u8_formats_and_subtitles(
m3u8_url.replace(f'/{token}/', '/'), video_id, 'mp4',
m3u8_id=format_id, fatal=False, headers=cdn_headers)
for fmt in fmts:
fmt['http_headers'] = cdn_headers
fmt.setdefault('format_note', join_nonempty(feed, medium, delim=' '))
fmt.setdefault('language', language)
if fmt.get('vcodec') == 'none' and fmt['language'] == 'en':
fmt['source_preference'] = 10
return fmts, subs
def _real_extract(self, url):
video_id = self._match_id(url)
airings = self._download_json(
f'https://search-api-mlbtv.mlb.com/svc/search/v2/graphql/persisted/query/core/Airings?variables=%7B%22partnerProgramIds%22%3A%5B%22{video_id}%22%5D%2C%22applyEsniMediaRightsLabels%22%3Atrue%7D',
video_id)['data']['Airings']
data = self._download_json(
'https://statsapi.mlb.com/api/v1/schedule', video_id, query={
'gamePk': video_id,
'hydrate': 'broadcasts(all),statusFlags',
})
metadata = traverse_obj(data, (
'dates', ..., 'games',
lambda _, v: str(v['gamePk']) == video_id and not v.get('rescheduleDate'), any))
broadcasts = traverse_obj(metadata, (
'broadcasts', lambda _, v: v['mediaId'] and v['mediaState']['mediaStateCode'] != 'MEDIA_OFF'))
formats, subtitles = [], {}
for airing in traverse_obj(airings, lambda _, v: v['playbackUrls'][0]['href']):
format_id = join_nonempty('feedType', 'feedLanguage', from_dict=airing)
m3u8_url = traverse_obj(self._download_json(
airing['playbackUrls'][0]['href'].format(scenario='browser~csai'), video_id,
note=f'Downloading {format_id} stream info JSON',
errnote=f'Failed to download {format_id} stream info, skipping',
fatal=False, headers={
'Authorization': self._access_token,
'Accept': 'application/vnd.media-service+json; version=2',
}), ('stream', 'complete', {url_or_none}))
if not m3u8_url:
continue
f, s = self._extract_m3u8_formats_and_subtitles(
m3u8_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
formats.extend(f)
self._merge_subtitles(s, target=subtitles)
for broadcast in broadcasts:
fmts, subs = self._extract_formats_and_subtitles(broadcast, video_id)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
return {
'id': video_id,
'title': traverse_obj(airings, (..., 'titles', 0, 'episodeName'), get_all=False),
'is_live': traverse_obj(airings, (..., 'mediaConfig', 'productType'), get_all=False) == 'LIVE',
'title': join_nonempty(
traverse_obj(metadata, ('officialDate', {str})),
traverse_obj(metadata, ('teams', ('away', 'home'), 'team', 'name', {str}, all, {' @ '.join})),
delim=' - '),
'is_live': traverse_obj(broadcasts, (..., 'mediaState', 'mediaStateCode', {str}, any)) == 'MEDIA_ON',
'release_timestamp': traverse_obj(metadata, ('gameDate', {parse_iso8601})),
'formats': formats,
'subtitles': subtitles,
'http_headers': {'Authorization': f'Bearer {self._access_token}'},
}

121
yt_dlp/extractor/olympics.py
View File

@ -1,9 +1,19 @@
from .common import InfoExtractor
from ..utils import int_or_none, try_get
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
parse_qs,
try_get,
update_url,
url_or_none,
)
from ..utils.traversal import traverse_obj
class OlympicsReplayIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?olympics\.com(?:/tokyo-2020)?/[a-z]{2}/(?:replay|video)/(?P<id>[^/#&?]+)'
_VALID_URL = r'https?://(?:www\.)?olympics\.com/[a-z]{2}/(?:paris-2024/)?(?:replay|videos?|original-series/episode)/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://olympics.com/fr/video/men-s-109kg-group-a-weightlifting-tokyo-2020-replays',
'info_dict': {
@ -11,26 +21,105 @@ class OlympicsReplayIE(InfoExtractor):
'ext': 'mp4',
'title': '+109kg (H) Groupe A - Haltérophilie | Replay de Tokyo 2020',
'upload_date': '20210801',
'timestamp': 1627783200,
'timestamp': 1627797600,
'description': 'md5:c66af4a5bc7429dbcc43d15845ff03b3',
'uploader': 'International Olympic Committee',
},
'params': {
'skip_download': True,
'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/nua4o7zwyaznoaejpbk2',
'duration': 7017.0,
},
}, {
'url': 'https://olympics.com/tokyo-2020/en/replay/bd242924-4b22-49a5-a846-f1d4c809250d/mens-bronze-medal-match-hun-esp',
'only_matching': True,
'url': 'https://olympics.com/en/original-series/episode/b-boys-and-b-girls-take-the-spotlight-breaking-life-road-to-paris-2024',
'info_dict': {
'id': '32633650-c5ee-4280-8b94-fb6defb6a9b5',
'ext': 'mp4',
'title': 'B-girl Nicka - Breaking Life, Road to Paris 2024 | Episode 1',
'upload_date': '20240517',
'timestamp': 1715948200,
'description': 'md5:f63d728a41270ec628f6ac33ce471bb1',
'thumbnail': 'https://img.olympics.com/images/image/private/t_1-1_1280/primary/a3j96l7j6so3vyfijby1',
'duration': 1321.0,
},
}, {
'url': 'https://olympics.com/en/paris-2024/videos/men-s-preliminaries-gbr-esp-ned-rsa-hockey-olympic-games-paris-2024',
'info_dict': {
'id': '3d96db23-8eee-4b7c-8ef5-488a0361026c',
'ext': 'mp4',
'title': 'Men\'s Preliminaries GBR-ESP & NED-RSA | Hockey | Olympic Games Paris 2024',
'upload_date': '20240727',
'timestamp': 1722066600,
},
'skip': 'Geo-restricted to RU, BR, BT, NP, TM, BD, TL',
}, {
'url': 'https://olympics.com/en/paris-2024/videos/dnp-suni-lee-i-have-goals-and-i-have-expectations-for-myself-but-i-also-am-trying-to-give-myself-grace',
'info_dict': {
'id': 'a42f37ab-8a74-41d0-a7d9-af27b7b02a90',
'ext': 'mp4',
'title': 'md5:c7cfbc9918636a98e66400a812e4d407',
'upload_date': '20240729',
'timestamp': 1722288600,
},
}]
_GEO_BYPASS = False
def _extract_from_nextjs_data(self, webpage, video_id):
data = traverse_obj(self._search_nextjs_data(webpage, video_id, default={}), (
'props', 'pageProps', 'page', 'items',
lambda _, v: v['name'] == 'videoPlaylist', 'data', 'currentVideo', {dict}, any))
if not data:
return None
geo_countries = traverse_obj(data, ('countries', ..., {str}))
if traverse_obj(data, ('geoRestrictedVideo', {bool})):
self.raise_geo_restricted(countries=geo_countries)
is_live = traverse_obj(data, ('streamingStatus', {str})) == 'LIVE'
m3u8_url = traverse_obj(data, ('videoUrl', {url_or_none})) or data['streamUrl']
tokenized_url = self._tokenize_url(m3u8_url, data['jwtToken'], is_live, video_id)
try:
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
tokenized_url, video_id, 'mp4', m3u8_id='hls')
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and 'georestricted' in e.cause.msg:
self.raise_geo_restricted(countries=geo_countries)
raise
return {
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
**traverse_obj(data, {
'id': ('videoID', {str}),
'title': ('title', {str}),
'timestamp': ('contentDate', {parse_iso8601}),
}),
}
def _tokenize_url(self, url, token, is_live, video_id):
return self._download_json(
'https://metering.olympics.com/tokengenerator', video_id,
'Downloading tokenized m3u8 url', query={
**parse_qs(url),
'url': update_url(url, query=None),
'service-id': 'live' if is_live else 'vod',
'user-auth': token,
})['data']['url']
def _legacy_tokenize_url(self, url, video_id):
return self._download_json(
'https://olympics.com/tokenGenerator', video_id,
'Downloading legacy tokenized m3u8 url', query={'url': url})
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if info := self._extract_from_nextjs_data(webpage, video_id):
return info
title = self._html_search_meta(('title', 'og:title', 'twitter:title'), webpage)
uuid = self._html_search_meta('episode_uid', webpage)
video_uuid = self._html_search_meta('episode_uid', webpage)
m3u8_url = self._html_search_meta('video_url', webpage)
json_ld = self._search_json_ld(webpage, uuid)
json_ld = self._search_json_ld(webpage, video_uuid)
thumbnails_list = json_ld.get('image')
if not thumbnails_list:
thumbnails_list = self._html_search_regex(
@ -48,12 +137,12 @@ class OlympicsReplayIE(InfoExtractor):
'width': width,
'height': int_or_none(try_get(width, lambda x: x * height_a / width_a)),
})
m3u8_url = self._download_json(
f'https://olympics.com/tokenGenerator?url={m3u8_url}', uuid, note='Downloading m3u8 url')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, uuid, 'mp4', m3u8_id='hls')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
self._legacy_tokenize_url(m3u8_url, video_uuid), video_uuid, 'mp4', m3u8_id='hls')
return {
'id': uuid,
'id': video_uuid,
'title': title,
'thumbnails': thumbnails,
'formats': formats,

19
yt_dlp/extractor/tiktok.py
View File

@ -23,7 +23,6 @@ from ..utils import (
mimetype2ext,
parse_qs,
qualities,
remove_start,
srt_subtitles_timecode,
str_or_none,
traverse_obj,
@ -254,7 +253,16 @@ class TikTokBaseIE(InfoExtractor):
def _get_subtitles(self, aweme_detail, aweme_id, user_name):
# TODO: Extract text positioning info
EXT_MAP = { # From lowest to highest preference
'creator_caption': 'json',
'srt': 'srt',
'webvtt': 'vtt',
}
preference = qualities(tuple(EXT_MAP.values()))
subtitles = {}
# aweme/detail endpoint subs
captions_info = traverse_obj(
aweme_detail, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type=dict)
@ -278,8 +286,8 @@ class TikTokBaseIE(InfoExtractor):
if not caption.get('url'):
continue
subtitles.setdefault(caption.get('lang') or 'en', []).append({
'ext': remove_start(caption.get('caption_format'), 'web'),
'url': caption['url'],
'ext': EXT_MAP.get(caption.get('Format')),
})
# webpage subs
if not subtitles:
@ -288,9 +296,14 @@ class TikTokBaseIE(InfoExtractor):
self._create_url(user_name, aweme_id), aweme_id, fatal=False)
for caption in traverse_obj(aweme_detail, ('video', 'subtitleInfos', lambda _, v: v['Url'])):
subtitles.setdefault(caption.get('LanguageCodeName') or 'en', []).append({
'ext': remove_start(caption.get('Format'), 'web'),
'url': caption['Url'],
'ext': EXT_MAP.get(caption.get('Format')),
})
# Deprioritize creator_caption json since it can't be embedded or used by media players
for lang, subs_list in subtitles.items():
subtitles[lang] = sorted(subs_list, key=lambda x: preference(x['ext']))
return subtitles
def _parse_url_key(self, url_key):

72
yt_dlp/extractor/tva.py
View File

@ -1,60 +1,29 @@
import functools
import re
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils import float_or_none, int_or_none, smuggle_url, strip_or_none
from ..utils.traversal import traverse_obj
class TVAIE(InfoExtractor):
_VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P<id>\d+)'
IE_NAME = 'tvaplus'
IE_DESC = 'TVA+'
_VALID_URL = r'https?://(?:www\.)?tvaplus\.ca/(?:[^/?#]+/)*[\w-]+-(?P<id>\d+)(?:$|[#?])'
_TESTS = [{
'url': 'https://videos.tva.ca/details/_5596811470001',
'info_dict': {
'id': '5596811470001',
'ext': 'mp4',
'title': 'Un extrait de l\'épisode du dimanche 8 octobre 2017 !',
'uploader_id': '5481942443001',
'upload_date': '20171003',
'timestamp': 1507064617,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'HTTP Error 404: Not Found',
}, {
'url': 'https://video.tva.ca/details/_5596811470001',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
return {
'_type': 'url_transparent',
'id': video_id,
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {'geo_countries': ['CA']}),
'ie_key': 'BrightcoveNew',
}
class QubIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?qub\.ca/(?:[^/]+/)*[0-9a-z-]+-(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.qub.ca/tvaplus/tva/alerte-amber/saison-1/episode-01-1000036619',
'url': 'https://www.tvaplus.ca/tva/alerte-amber/saison-1/episode-01-1000036619',
'md5': '949490fd0e7aee11d0543777611fbd53',
'info_dict': {
'id': '6084352463001',
'ext': 'mp4',
'title': 'Ép 01. Mon dernier jour',
'title': 'Mon dernier jour',
'uploader_id': '5481942443001',
'upload_date': '20190907',
'timestamp': 1567899756,
'description': 'md5:9c0d7fbb90939420c651fd977df90145',
'thumbnail': r're:https://.+\.jpg',
'episode': 'Ép 01. Mon dernier jour',
'episode': 'Mon dernier jour',
'episode_number': 1,
'tags': ['alerte amber', 'alerte amber saison 1', 'surdemande'],
'duration': 2625.963,
@ -64,23 +33,36 @@ class QubIE(InfoExtractor):
'channel': 'TVA',
},
}, {
'url': 'https://www.qub.ca/tele/video/lcn-ca-vous-regarde-rev-30s-ap369664-1009357943',
'only_matching': True,
'url': 'https://www.tvaplus.ca/tva/le-baiser-du-barbu/le-baiser-du-barbu-886644190',
'info_dict': {
'id': '6354448043112',
'ext': 'mp4',
'title': 'Le Baiser du barbu',
'uploader_id': '5481942443001',
'upload_date': '20240606',
'timestamp': 1717694023,
'description': 'md5:025b1219086c1cbf4bc27e4e034e8b57',
'thumbnail': r're:https://.+\.jpg',
'episode': 'Le Baiser du barbu',
'tags': ['fullepisode', 'films'],
'duration': 6053.504,
'series': 'Le Baiser du barbu',
'channel': 'TVA',
},
}]
# reference_id also works with old account_id(5481942443001)
# BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5813221784001/default_default/index.html?videoId=ref:%s'
_BC_URL_TMPL = 'https://players.brightcove.net/5481942443001/default_default/index.html?videoId={}'
def _real_extract(self, url):
entity_id = self._match_id(url)
webpage = self._download_webpage(url, entity_id)
entity = self._search_nextjs_data(webpage, entity_id)['props']['initialProps']['pageProps']['fallbackData']
entity = self._search_nextjs_data(webpage, entity_id)['props']['pageProps']['staticEntity']
video_id = entity['videoId']
episode = strip_or_none(entity.get('name'))
return {
'_type': 'url_transparent',
'url': f'https://videos.tva.ca/details/_{video_id}',
'ie_key': TVAIE.ie_key(),
'url': smuggle_url(self._BC_URL_TMPL.format(video_id), {'geo_countries': ['CA']}),
'ie_key': BrightcoveNewIE.ie_key(),
'id': video_id,
'title': episode,
'episode': episode,

26
yt_dlp/extractor/tver.py
View File

@ -10,7 +10,7 @@ from ..utils import (
class TVerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature|tokyo2020/video)/)+(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature|tokyo2020/video|olympic/paris2024/video)/)+(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'skip': 'videos are only available for 7 days',
'url': 'https://tver.jp/episodes/ep83nf3w4p',
@ -23,6 +23,20 @@ class TVerIE(InfoExtractor):
'channel': 'テレビ朝日',
},
'add_ie': ['BrightcoveNew'],
}, {
'url': 'https://tver.jp/olympic/paris2024/video/6359578055112/',
'info_dict': {
'id': '6359578055112',
'ext': 'mp4',
'title': '堀米雄斗 金メダルで五輪連覇！「みんなの応援が最後に乗れたカギ」',
'timestamp': 1722279928,
'upload_date': '20240729',
'tags': ['20240729', 'japanese', 'japanmedal', 'paris'],
'uploader_id': '4774017240001',
'thumbnail': r're:https?://[^/?#]+boltdns\.net/[^?#]+/1920x1080/match/image\.jpg',
'duration': 670.571,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://tver.jp/corner/f0103888',
'only_matching': True,
@ -47,7 +61,15 @@ class TVerIE(InfoExtractor):
def _real_extract(self, url):
video_id, video_type = self._match_valid_url(url).group('id', 'type')
if video_type not in {'series', 'episodes'}:
if video_type == 'olympic/paris2024/video':
# Player ID is taken from .content.brightcove.E200.pro.pc.account_id:
# https://tver.jp/olympic/paris2024/req/api/hook?q=https%3A%2F%2Folympic-assets.tver.jp%2Fweb-static%2Fjson%2Fconfig.json&d=
return self.url_result(smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % ('4774017240001', video_id),
{'geo_countries': ['JP']}), 'BrightcoveNew')
elif video_type not in {'series', 'episodes'}:
webpage = self._download_webpage(url, video_id, note='Resolving to new URL')
video_id = self._match_id(self._search_regex(
(r'canonical"\s*href="(https?://tver\.jp/[^"]+)"', r'&link=(https?://tver\.jp/[^?&]+)[?&]'),

4
yt_dlp/extractor/unsupported.py
View File

@ -49,6 +49,7 @@ class KnownDRMIE(UnsupportedInfoExtractor):
r'amazon\.(?:\w{2}\.)?\w+/gp/video',
r'music\.amazon\.(?:\w{2}\.)?\w+',
r'(?:watch|front)\.njpwworld\.com',
r'qub\.ca/vrai',
)
_TESTS = [{
@ -149,6 +150,9 @@ class KnownDRMIE(UnsupportedInfoExtractor):
}, {
'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
'only_matching': True,
}, {
'url': 'https://www.qub.ca/vrai/l-effet-bocuse-d-or/saison-1/l-effet-bocuse-d-or-saison-1-bande-annonce-1098225063',
'only_matching': True,
}]
def _real_extract(self, url):

75
yt_dlp/extractor/vimeo.py
View File

@ -212,16 +212,6 @@ class VimeoBaseInfoExtractor(InfoExtractor):
owner = video_data.get('owner') or {}
video_uploader_url = owner.get('url')
duration = int_or_none(video_data.get('duration'))
chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
chapters = [{
'title': current_chapter.get('title'),
'start_time': current_chapter.get('timecode'),
'end_time': next_chapter.get('timecode'),
} for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
if chapters and chapters[0]['start_time']: # Chapters may not start from 0
chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
return {
'id': str_or_none(video_data.get('id')) or video_id,
'title': video_title,
@ -229,8 +219,12 @@ class VimeoBaseInfoExtractor(InfoExtractor):
'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
'uploader_url': video_uploader_url,
'thumbnails': thumbnails,
'duration': duration,
'chapters': chapters or None,
'duration': int_or_none(video_data.get('duration')),
'chapters': sorted(traverse_obj(config, (
'embed', 'chapters', lambda _, v: int(v['timecode']) is not None, {
'title': ('title', {str}),
'start_time': ('timecode', {int_or_none}),
})), key=lambda c: c['start_time']) or None,
'formats': formats,
'subtitles': subtitles,
'live_status': live_status,
@ -708,6 +702,39 @@ class VimeoIE(VimeoBaseInfoExtractor):
'skip_download': True,
},
},
{
# chapters must be sorted, see: https://github.com/yt-dlp/yt-dlp/issues/5308
'url': 'https://player.vimeo.com/video/756714419',
'info_dict': {
'id': '756714419',
'ext': 'mp4',
'title': 'Dr Arielle Schwartz - Therapeutic yoga for optimum sleep',
'uploader': 'Alex Howard',
'uploader_id': 'user54729178',
'uploader_url': 'https://vimeo.com/user54729178',
'thumbnail': r're:https://i\.vimeocdn\.com/video/1520099929-[\da-f]+-d_1280',
'duration': 2636,
'chapters': [
{'start_time': 0, 'end_time': 10, 'title': '<Untitled Chapter 1>'},
{'start_time': 10, 'end_time': 106, 'title': 'Welcoming Dr Arielle Schwartz'},
{'start_time': 106, 'end_time': 305, 'title': 'What is therapeutic yoga?'},
{'start_time': 305, 'end_time': 594, 'title': 'Vagal toning practices'},
{'start_time': 594, 'end_time': 888, 'title': 'Trauma and difficulty letting go'},
{'start_time': 888, 'end_time': 1059, 'title': "Dr Schwartz' insomnia experience"},
{'start_time': 1059, 'end_time': 1471, 'title': 'A strategy for helping sleep issues'},
{'start_time': 1471, 'end_time': 1667, 'title': 'Yoga nidra'},
{'start_time': 1667, 'end_time': 2121, 'title': 'Wisdom in stillness'},
{'start_time': 2121, 'end_time': 2386, 'title': 'What helps us be more able to let go?'},
{'start_time': 2386, 'end_time': 2510, 'title': 'Practical tips to help ourselves'},
{'start_time': 2510, 'end_time': 2636, 'title': 'Where to find out more'},
],
},
'params': {
'http_headers': {'Referer': 'https://sleepsuperconference.com'},
'skip_download': 'm3u8',
},
'expected_warnings': ['Failed to parse XML: not well-formed'],
},
{
# user playlist alias -> https://vimeo.com/258705797
'url': 'https://vimeo.com/user26785108/newspiritualguide',
@ -1240,7 +1267,7 @@ class VimeoGroupsIE(VimeoChannelIE): # XXX: Do not subclass from concrete IE
class VimeoReviewIE(VimeoBaseInfoExtractor):
IE_NAME = 'vimeo:review'
IE_DESC = 'Review pages on vimeo'
_VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
_VALID_URL = r'https?://vimeo\.com/(?P<user>[^/?#]+)/review/(?P<id>\d+)/(?P<hash>[\da-f]{10})'
_TESTS = [{
'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
'md5': 'c507a72f780cacc12b2248bb4006d253',
@ -1286,26 +1313,22 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
}]
def _real_extract(self, url):
page_url, video_id = self._match_valid_url(url).groups()
data = self._download_json(
page_url.replace('/review/', '/review/data/'), video_id)
user, video_id, review_hash = self._match_valid_url(url).group('user', 'id', 'hash')
data_url = f'https://vimeo.com/{user}/review/data/{video_id}/{review_hash}'
data = self._download_json(data_url, video_id)
if data.get('isLocked') is True:
video_password = self._get_video_password()
viewer = self._download_json(
'https://vimeo.com/_rv/viewer', video_id)
webpage = self._verify_video_password(video_id, video_password, viewer['xsrft'])
clip_page_config = self._parse_json(self._search_regex(
r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
webpage, 'clip page config'), video_id)
config_url = clip_page_config['player']['config_url']
clip_data = clip_page_config.get('clip') or {}
else:
clip_data = data['clipData']
config_url = clip_data['configUrl']
self._verify_video_password(video_id, video_password, viewer['xsrft'])
data = self._download_json(data_url, video_id)
clip_data = data['clipData']
config_url = clip_data['configUrl']
config = self._download_json(config_url, video_id)
info_dict = self._parse_config(config, video_id)
source_format = self._extract_original_format(
page_url + '/action', video_id)
f'https://vimeo.com/{user}/review/{video_id}/{review_hash}/action', video_id,
unlisted_hash=traverse_obj(config_url, ({parse_qs}, 'h', -1)))
if source_format:
info_dict['formats'].append(source_format)
info_dict['description'] = clean_html(clip_data.get('description'))

2
yt_dlp/extractor/youku.py
View File

@ -136,7 +136,7 @@ class YoukuIE(InfoExtractor):
# request basic data
basic_data_params = {
'vid': video_id,
'ccode': '0524',
'ccode': '0564',
'client_ip': '192.168.1.1',
'utid': cna,
'client_ts': time.time() / 1000,

286
yt_dlp/extractor/youtube.py
View File

@ -72,133 +72,169 @@ STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
# any clients starting with _ cannot be explicitly requested by the user
INNERTUBE_CLIENTS = {
'web': {
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB',
'clientVersion': '2.20220801.00.00',
'clientVersion': '2.20240726.00.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
},
# Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats
'web_safari': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB',
'clientVersion': '2.20240726.00.00',
'userAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/15.5 Safari/605.1.15,gzip(gfe)',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
},
'web_embedded': {
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_EMBEDDED_PLAYER',
'clientVersion': '1.20220731.00.00',
'clientVersion': '1.20240723.01.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 56,
},
'web_music': {
'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
'INNERTUBE_HOST': 'music.youtube.com',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_REMIX',
'clientVersion': '1.20220727.01.00',
'clientVersion': '1.20240724.00.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
},
'web_creator': {
'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'WEB_CREATOR',
'clientVersion': '1.20220726.00.00',
'clientVersion': '1.20240723.03.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
},
'android': {
'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID',
'clientVersion': '19.09.37',
'clientVersion': '19.29.37',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.youtube/19.29.37 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
'REQUIRE_JS_PLAYER': False,
},
'android_embedded': {
'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_EMBEDDED_PLAYER',
'clientVersion': '19.09.37',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
'REQUIRE_JS_PLAYER': False,
},
'android_music': {
'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_MUSIC',
'clientVersion': '6.42.52',
'clientVersion': '7.11.50',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.music/6.42.52 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.apps.youtube.music/7.11.50 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
'REQUIRE_JS_PLAYER': False,
},
'android_creator': {
'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_CREATOR',
'clientVersion': '22.30.100',
'clientVersion': '24.30.100',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip',
'userAgent': 'com.google.android.apps.youtube.creator/24.30.100 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
'REQUIRE_JS_PLAYER': False,
},
# YouTube Kids videos aren't returned on this client for some reason
'android_vr': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_VR',
'clientVersion': '1.57.29',
'deviceMake': 'Oculus',
'deviceModel': 'Quest 3',
'androidSdkVersion': 32,
'userAgent': 'com.google.android.apps.youtube.vr.oculus/1.57.29 (Linux; U; Android 12L; eureka-user Build/SQ3A.220605.009.A1) gzip',
'osName': 'Android',
'osVersion': '12L',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 28,
'REQUIRE_JS_PLAYER': False,
},
'android_testsuite': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_TESTSUITE',
'clientVersion': '1.9',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.youtube/1.9 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 30,
'REQUIRE_JS_PLAYER': False,
'PLAYER_PARAMS': '2AMB',
},
# This client only has legacy formats and storyboards
'android_producer': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'ANDROID_PRODUCER',
'clientVersion': '0.111.1',
'androidSdkVersion': 30,
'userAgent': 'com.google.android.apps.youtube.producer/0.111.1 (Linux; U; Android 11) gzip',
'osName': 'Android',
'osVersion': '11',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 91,
'REQUIRE_JS_PLAYER': False,
},
# iOS clients have HLS live streams. Setting device model to get 60fps formats.
# See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
'ios': {
'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS',
'clientVersion': '19.09.3',
'deviceModel': 'iPhone14,3',
'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)',
'clientVersion': '19.29.1',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.youtube/19.29.1 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
'REQUIRE_JS_PLAYER': False,
},
'ios_embedded': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_MESSAGES_EXTENSION',
'clientVersion': '19.09.3',
'deviceModel': 'iPhone14,3',
'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
'REQUIRE_JS_PLAYER': False,
},
'ios_music': {
'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_MUSIC',
'clientVersion': '6.33.3',
'deviceModel': 'iPhone14,3',
'userAgent': 'com.google.ios.youtubemusic/6.33.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)',
'clientVersion': '7.08.2',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.youtubemusic/7.08.2 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
@ -208,9 +244,12 @@ INNERTUBE_CLIENTS = {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'IOS_CREATOR',
'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)',
'clientVersion': '24.30.100',
'deviceMake': 'Apple',
'deviceModel': 'iPhone16,2',
'userAgent': 'com.google.ios.ytcreator/24.30.100 (iPhone16,2; U; CPU iOS 17_5_1 like Mac OS X;)',
'osName': 'iPhone',
'osVersion': '17.5.1.21F90',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
@ -219,19 +258,26 @@ INNERTUBE_CLIENTS = {
# mweb has 'ultralow' formats
# See: https://github.com/yt-dlp/yt-dlp/pull/557
'mweb': {
'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'MWEB',
'clientVersion': '2.20220801.00.00',
'clientVersion': '2.20240726.01.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 2,
},
'tv': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'TVHTML5',
'clientVersion': '7.20240724.13.00',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
},
# 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',
@ -249,6 +295,7 @@ INNERTUBE_CLIENTS = {
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 95,
'REQUIRE_JS_PLAYER': False,
},
}
@ -262,7 +309,7 @@ def _split_innertube_client(client_name):
def short_client_name(client_name):
main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
main, *parts = _split_innertube_client(client_name)[0].split('_')
return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
@ -274,23 +321,18 @@ def build_innertube_clients():
priority = qualities(BASE_CLIENTS[::-1])
for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
ytcfg.setdefault('PLAYER_PARAMS', None)
ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
_, base_client, variant = _split_innertube_client(client)
ytcfg['priority'] = 10 * priority(base_client)
if not variant:
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':
if variant == 'embedded':
ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
ytcfg['priority'] -= 2
else:
elif variant:
ytcfg['priority'] -= 3
@ -566,9 +608,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
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'))
def _extract_api_key(self, ytcfg=None, default_client='web'):
return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
def _extract_context(self, ytcfg=None, default_client='web'):
context = get_first(
(ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
@ -614,13 +653,15 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
real_headers.update({'content-type': 'application/json'})
if headers:
real_headers.update(headers)
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))
return self._download_json(
f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
video_id=video_id, fatal=fatal, note=note, errnote=errnote,
data=json.dumps(data).encode('utf8'), headers=real_headers,
query={'key': api_key, 'prettyPrint': 'false'})
query=filter_dict({
'key': self._configuration_arg(
'innertube_key', [api_key], ie_key=YoutubeIE.ie_key(), casesense=True)[0],
'prettyPrint': 'false',
}, cndn=lambda _, v: v))
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)
@ -972,7 +1013,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
ep=ep, fatal=True, headers=headers,
video_id=item_id, query=query, note=note,
context=self._extract_context(ytcfg, default_client),
api_key=self._extract_api_key(ytcfg, default_client),
api_hostname=api_hostname, default_client=default_client)
except ExtractorError as e:
if not isinstance(e.cause, network_exceptions):
@ -1295,6 +1335,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
}
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
_POTOKEN_EXPERIMENTS = ('51217476', '51217102')
_BROKEN_CLIENTS = {
short_client_name(client): client
for client in ('android', 'android_creator', 'android_music')
}
_GEO_BYPASS = False
@ -3129,12 +3173,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.write_debug(f'Decrypted nsig {s} => {ret}')
return ret
def _extract_n_function_name(self, jscode):
def _extract_n_function_name(self, jscode, player_url=None):
# Examples (with placeholders nfunc, narray, idx):
# * .get("n"))&&(b=nfunc(b)
# * .get("n"))&&(b=narray[idx](b)
# * b=String.fromCharCode(110),c=a.get(b))&&c=narray[idx](c)
# * a.D&&(b="nn"[+a.D],c=a.get(b))&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
# * a.D&&(PL(a),b=a.j.n||null)&&(b=narray[0](b),a.set("n",b),narray.length||nfunc("")
funcname, idx = self._search_regex(
r'''(?x)(?:\.get\("n"\)\)&&\(b=|b=String\.fromCharCode\(110\),c=a\.get\(b\)\)&&\(c=)
(?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:
r'''(?x)
(?:
\.get\("n"\)\)&&\(b=|
(?:
b=String\.fromCharCode\(110\)|
(?P<str_idx>[a-zA-Z0-9_$.]+)&&\(b="nn"\[\+(?P=str_idx)\]
),c=a\.get\(b\)\)&&\(c=|
\b(?P<var>[a-zA-Z0-9_$]+)=
)(?P<nfunc>[a-zA-Z0-9_$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z]\)
(?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''',
jscode, 'n function name', group=('nfunc', 'idx'), default=(None, None))
if not funcname:
self.report_warning(join_nonempty(
'Falling back to generic n function search',
player_url and f' player = {player_url}', delim='\n'))
return self._search_regex(
r'''(?xs)
;\s*(?P<name>[a-zA-Z0-9_$]+)\s*=\s*function\([a-zA-Z0-9_$]+\)
\s*\{(?:(?!};).)+?["']enhanced_except_''',
jscode, 'Initial JS player n function name', group='name')
elif not idx:
return funcname
return json.loads(js_to_json(self._search_regex(
@ -3150,7 +3217,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if func_code:
return jsi, player_id, func_code
func_name = self._extract_n_function_name(jscode)
func_name = self._extract_n_function_name(jscode, player_url=player_url)
func_code = jsi.extract_function_code(func_name)
@ -3654,9 +3721,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'videoId': video_id,
}
pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
if pp_arg:
yt_query['params'] = pp_arg
default_pp = traverse_obj(
INNERTUBE_CLIENTS, (_split_innertube_client(client)[0], 'PLAYER_PARAMS', {str}))
if player_params := self._configuration_arg('player_params', [default_pp], casesense=True)[0]:
yt_query['params'] = player_params
yt_query.update(self._generate_player_context(sts))
return self._extract_response(
@ -3668,8 +3736,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _get_requested_clients(self, url, smuggled_data):
requested_clients = []
android_clients = []
default = ['ios', 'web']
broken_clients = []
default = ['ios', 'tv']
allowed_clients = sorted(
(client for client in INNERTUBE_CLIENTS if client[:1] != '_'),
key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
@ -3680,18 +3748,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
requested_clients.extend(allowed_clients)
elif client not in allowed_clients:
self.report_warning(f'Skipping unsupported client {client}')
elif client.startswith('android'):
android_clients.append(client)
elif client in self._BROKEN_CLIENTS.values():
broken_clients.append(client)
else:
requested_clients.append(client)
# Force deprioritization of broken Android clients for format de-duplication
requested_clients.extend(android_clients)
# Force deprioritization of _BROKEN_CLIENTS for format de-duplication
requested_clients.extend(broken_clients)
if not requested_clients:
requested_clients = default
if smuggled_data.get('is_music_url') or self.is_music_url(url):
requested_clients.extend(
f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
for requested_client in requested_clients:
_, base_client, variant = _split_innertube_client(requested_client)
music_client = f'{base_client}_music'
if variant != 'music' and music_client in INNERTUBE_CLIENTS:
requested_clients.append(music_client)
return orderedSet(requested_clients)
@ -3785,14 +3856,27 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
f[STREAMING_DATA_CLIENT_NAME] = name
prs.append(pr)
# creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
append_client(f'{base_client}_creator')
elif self._is_agegated(pr):
if variant == 'tv_embedded':
append_client(f'{base_client}_embedded')
elif not variant:
append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
# tv_embedded can work around age-gate and age-verification IF the video is embeddable
if self._is_agegated(pr) and variant != 'tv_embedded':
append_client(f'tv_embedded.{base_client}')
# Unauthenticated users will only get tv_embedded client formats if age-gated
if self._is_agegated(pr) and not self.is_authenticated:
self.to_screen(
f'{video_id}: This video is age-restricted; some formats may be missing '
f'without authentication. {self._login_hint()}', only_once=True)
# EU countries require age-verification for accounts to access age-restricted videos
# If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
# If embedding is disabled for the video, _is_unplayable() will be truthy for tv_embedded
embedding_is_disabled = variant == 'tv_embedded' and self._is_unplayable(pr)
if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
self.to_screen(
f'{video_id}: This video is age-restricted and YouTube is requiring '
'account age-verification; some formats may be missing', only_once=True)
# web_creator and mediaconnect can work around the age-verification requirement
# _producer, _testsuite, & _vr variants can also work around age-verification
append_client('web_creator', 'mediaconnect')
if skipped_clients:
self.report_warning(
@ -3928,13 +4012,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
# Android client formats are broken due to integrity check enforcement
# _BROKEN_CLIENTS return videoplayback URLs that expire after 30 seconds
# Ref: https://github.com/yt-dlp/yt-dlp/issues/9554
is_broken = client_name and client_name.startswith(short_client_name('android'))
is_broken = client_name in self._BROKEN_CLIENTS
if is_broken:
self.report_warning(
f'{video_id}: Android client formats are broken and may yield HTTP Error 403. '
'They will be deprioritized', only_once=True)
f'{video_id}: {self._BROKEN_CLIENTS[client_name]} client formats are broken '
'and may yield HTTP Error 403. They will be deprioritized', only_once=True)
name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
fps = int_or_none(fmt.get('fps')) or 0

2
yt_dlp/utils/_utils.py
View File

@ -1217,7 +1217,7 @@ def unified_timestamp(date_str, day_first=True):
return None
date_str = re.sub(r'\s+', ' ', re.sub(
r'(?i)[,|]|(mon|tues?|wed(nes)?|thu(rs)?|fri|sat(ur)?)(day)?', '', date_str))
r'(?i)[,|]|(mon|tues?|wed(nes)?|thu(rs)?|fri|sat(ur)?|sun)(day)?', '', date_str))
pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0
timezone, date_str = extract_timezone(date_str)

6
yt_dlp/version.py
View File

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2024.07.16'
__version__ = '2024.08.01'
RELEASE_GIT_HEAD = '89a161e8c62569a662deda1c948664152efcb6b4'
RELEASE_GIT_HEAD = 'ffd7781d6588926f820b44a34b9e6e3068fb9f97'
VARIANT = None
@ -12,4 +12,4 @@ CHANNEL = 'stable'
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2024.07.16'
_pkg_version = '2024.08.01'