2013-11-03 19:08:17 -07:00
|
|
|
|
# encoding: utf-8
|
2014-01-29 15:23:44 -07:00
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2014-02-25 06:26:11 -07:00
|
|
|
|
import re
|
2014-02-25 06:29:16 -07:00
|
|
|
|
import json
|
2014-02-25 06:26:11 -07:00
|
|
|
|
import base64
|
|
|
|
|
import zlib
|
2014-08-30 05:48:56 -06:00
|
|
|
|
import xml.etree.ElementTree
|
2014-02-25 06:26:11 -07:00
|
|
|
|
|
2013-11-03 19:08:17 -07:00
|
|
|
|
from hashlib import sha1
|
|
|
|
|
from math import pow, sqrt, floor
|
2015-02-15 10:21:42 -07:00
|
|
|
|
from .common import InfoExtractor
|
2014-12-13 04:24:42 -07:00
|
|
|
|
from ..compat import (
|
2013-11-03 19:08:17 -07:00
|
|
|
|
compat_urllib_parse,
|
2015-07-17 11:36:58 -06:00
|
|
|
|
compat_urllib_parse_unquote,
|
2013-11-03 19:08:17 -07:00
|
|
|
|
compat_urllib_request,
|
2015-08-18 11:02:57 -06:00
|
|
|
|
compat_urlparse,
|
2014-12-13 04:24:42 -07:00
|
|
|
|
)
|
|
|
|
|
from ..utils import (
|
|
|
|
|
ExtractorError,
|
2013-11-03 19:08:17 -07:00
|
|
|
|
bytes_to_intlist,
|
|
|
|
|
intlist_to_bytes,
|
2015-08-18 11:02:57 -06:00
|
|
|
|
remove_end,
|
2013-11-03 19:08:17 -07:00
|
|
|
|
unified_strdate,
|
2014-08-29 15:32:03 -06:00
|
|
|
|
urlencode_postdata,
|
2013-11-03 19:08:17 -07:00
|
|
|
|
)
|
|
|
|
|
from ..aes import (
|
|
|
|
|
aes_cbc_decrypt,
|
|
|
|
|
)
|
|
|
|
|
|
2014-02-25 06:26:11 -07:00
|
|
|
|
|
2015-02-15 10:21:42 -07:00
|
|
|
|
class CrunchyrollIE(InfoExtractor):
|
2015-07-04 18:29:36 -06:00
|
|
|
|
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
|
2015-03-03 04:59:17 -07:00
|
|
|
|
_NETRC_MACHINE = 'crunchyroll'
|
2014-12-21 11:58:15 -07:00
|
|
|
|
_TESTS = [{
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
|
|
|
|
|
'info_dict': {
|
2014-02-25 06:26:11 -07:00
|
|
|
|
'id': '645513',
|
|
|
|
|
'ext': 'flv',
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'title': 'Wanna be the Strongest in the World Episode 1 – An Idol-Wrestler is Born!',
|
|
|
|
|
'description': 'md5:2d17137920c64f2f49981a7797d275ef',
|
|
|
|
|
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
|
|
|
|
|
'uploader': 'Yomiuri Telecasting Corporation (YTV)',
|
|
|
|
|
'upload_date': '20131013',
|
2014-10-23 15:25:02 -06:00
|
|
|
|
'url': 're:(?!.*&)',
|
2013-11-03 19:08:17 -07:00
|
|
|
|
},
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'params': {
|
2013-11-03 19:08:17 -07:00
|
|
|
|
# rtmp
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'skip_download': True,
|
2013-11-03 19:08:17 -07:00
|
|
|
|
},
|
2015-07-04 18:29:36 -06:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '589804',
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11',
|
|
|
|
|
'description': 'md5:fe2743efedb49d279552926d0bd0cd9e',
|
|
|
|
|
'thumbnail': 're:^https?://.*\.jpg$',
|
|
|
|
|
'uploader': 'Danny Choo Network',
|
|
|
|
|
'upload_date': '20120213',
|
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# rtmp
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
},
|
|
|
|
|
|
2014-12-21 11:58:15 -07:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2013-11-03 19:08:17 -07:00
|
|
|
|
|
|
|
|
|
_FORMAT_IDS = {
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'360': ('60', '106'),
|
|
|
|
|
'480': ('61', '106'),
|
|
|
|
|
'720': ('62', '106'),
|
|
|
|
|
'1080': ('80', '108'),
|
2013-11-03 19:08:17 -07:00
|
|
|
|
}
|
|
|
|
|
|
2014-08-29 15:32:03 -06:00
|
|
|
|
def _login(self):
|
|
|
|
|
(username, password) = self._get_login_info()
|
|
|
|
|
if username is None:
|
|
|
|
|
return
|
|
|
|
|
self.report_login()
|
|
|
|
|
login_url = 'https://www.crunchyroll.com/?a=formhandler'
|
|
|
|
|
data = urlencode_postdata({
|
|
|
|
|
'formname': 'RpcApiUser_Login',
|
|
|
|
|
'name': username,
|
|
|
|
|
'password': password,
|
|
|
|
|
})
|
|
|
|
|
login_request = compat_urllib_request.Request(login_url, data)
|
|
|
|
|
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
|
|
|
|
self._download_webpage(login_request, None, False, 'Wrong login info')
|
|
|
|
|
|
|
|
|
|
def _real_initialize(self):
|
|
|
|
|
self._login()
|
|
|
|
|
|
2013-11-03 19:08:17 -07:00
|
|
|
|
def _decrypt_subtitles(self, data, iv, id):
|
2015-05-30 02:36:45 -06:00
|
|
|
|
data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
|
|
|
|
|
iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
|
2013-11-03 19:08:17 -07:00
|
|
|
|
id = int(id)
|
|
|
|
|
|
|
|
|
|
def obfuscate_key_aux(count, modulo, start):
|
|
|
|
|
output = list(start)
|
|
|
|
|
for _ in range(count):
|
|
|
|
|
output.append(output[-1] + output[-2])
|
|
|
|
|
# cut off start values
|
|
|
|
|
output = output[2:]
|
|
|
|
|
output = list(map(lambda x: x % modulo + 33, output))
|
|
|
|
|
return output
|
|
|
|
|
|
|
|
|
|
def obfuscate_key(key):
|
|
|
|
|
num1 = int(floor(pow(2, 25) * sqrt(6.9)))
|
|
|
|
|
num2 = (num1 ^ key) << 5
|
|
|
|
|
num3 = key ^ num1
|
|
|
|
|
num4 = num3 ^ (num3 >> 3) ^ num2
|
|
|
|
|
prefix = intlist_to_bytes(obfuscate_key_aux(20, 97, (1, 2)))
|
2014-01-29 15:23:44 -07:00
|
|
|
|
shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
|
2013-11-03 19:08:17 -07:00
|
|
|
|
# Extend 160 Bit hash to 256 Bit
|
|
|
|
|
return shaHash + [0] * 12
|
2014-02-25 06:26:11 -07:00
|
|
|
|
|
2013-11-03 19:08:17 -07:00
|
|
|
|
key = obfuscate_key(id)
|
2014-11-23 12:41:03 -07:00
|
|
|
|
|
2013-11-03 19:08:17 -07:00
|
|
|
|
decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
|
|
|
|
|
return zlib.decompress(decrypted_data)
|
|
|
|
|
|
2014-10-29 14:19:20 -06:00
|
|
|
|
def _convert_subtitles_to_srt(self, sub_root):
|
2014-01-29 15:23:44 -07:00
|
|
|
|
output = ''
|
2014-10-29 14:19:20 -06:00
|
|
|
|
|
|
|
|
|
for i, event in enumerate(sub_root.findall('./events/event'), 1):
|
|
|
|
|
start = event.attrib['start'].replace('.', ',')
|
|
|
|
|
end = event.attrib['end'].replace('.', ',')
|
|
|
|
|
text = event.attrib['text'].replace('\\N', '\n')
|
2014-01-29 15:23:44 -07:00
|
|
|
|
output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
|
2013-11-03 19:08:17 -07:00
|
|
|
|
return output
|
|
|
|
|
|
2014-10-29 14:19:20 -06:00
|
|
|
|
def _convert_subtitles_to_ass(self, sub_root):
|
2014-08-30 05:48:56 -06:00
|
|
|
|
output = ''
|
|
|
|
|
|
|
|
|
|
def ass_bool(strvalue):
|
|
|
|
|
assvalue = '0'
|
|
|
|
|
if strvalue == '1':
|
|
|
|
|
assvalue = '-1'
|
|
|
|
|
return assvalue
|
|
|
|
|
|
|
|
|
|
output = '[Script Info]\n'
|
|
|
|
|
output += 'Title: %s\n' % sub_root.attrib["title"]
|
|
|
|
|
output += 'ScriptType: v4.00+\n'
|
|
|
|
|
output += 'WrapStyle: %s\n' % sub_root.attrib["wrap_style"]
|
|
|
|
|
output += 'PlayResX: %s\n' % sub_root.attrib["play_res_x"]
|
|
|
|
|
output += 'PlayResY: %s\n' % sub_root.attrib["play_res_y"]
|
|
|
|
|
output += """ScaledBorderAndShadow: yes
|
|
|
|
|
|
|
|
|
|
[V4+ Styles]
|
|
|
|
|
Format: Name, Fontname, Fontsize, PrimaryColour, SecondaryColour, OutlineColour, BackColour, Bold, Italic, Underline, StrikeOut, ScaleX, ScaleY, Spacing, Angle, BorderStyle, Outline, Shadow, Alignment, MarginL, MarginR, MarginV, Encoding
|
|
|
|
|
"""
|
|
|
|
|
for style in sub_root.findall('./styles/style'):
|
|
|
|
|
output += 'Style: ' + style.attrib["name"]
|
|
|
|
|
output += ',' + style.attrib["font_name"]
|
|
|
|
|
output += ',' + style.attrib["font_size"]
|
|
|
|
|
output += ',' + style.attrib["primary_colour"]
|
|
|
|
|
output += ',' + style.attrib["secondary_colour"]
|
|
|
|
|
output += ',' + style.attrib["outline_colour"]
|
|
|
|
|
output += ',' + style.attrib["back_colour"]
|
|
|
|
|
output += ',' + ass_bool(style.attrib["bold"])
|
|
|
|
|
output += ',' + ass_bool(style.attrib["italic"])
|
|
|
|
|
output += ',' + ass_bool(style.attrib["underline"])
|
|
|
|
|
output += ',' + ass_bool(style.attrib["strikeout"])
|
|
|
|
|
output += ',' + style.attrib["scale_x"]
|
|
|
|
|
output += ',' + style.attrib["scale_y"]
|
|
|
|
|
output += ',' + style.attrib["spacing"]
|
|
|
|
|
output += ',' + style.attrib["angle"]
|
|
|
|
|
output += ',' + style.attrib["border_style"]
|
|
|
|
|
output += ',' + style.attrib["outline"]
|
|
|
|
|
output += ',' + style.attrib["shadow"]
|
|
|
|
|
output += ',' + style.attrib["alignment"]
|
|
|
|
|
output += ',' + style.attrib["margin_l"]
|
|
|
|
|
output += ',' + style.attrib["margin_r"]
|
|
|
|
|
output += ',' + style.attrib["margin_v"]
|
|
|
|
|
output += ',' + style.attrib["encoding"]
|
|
|
|
|
output += '\n'
|
|
|
|
|
|
|
|
|
|
output += """
|
|
|
|
|
[Events]
|
|
|
|
|
Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
|
|
|
|
"""
|
|
|
|
|
for event in sub_root.findall('./events/event'):
|
|
|
|
|
output += 'Dialogue: 0'
|
|
|
|
|
output += ',' + event.attrib["start"]
|
|
|
|
|
output += ',' + event.attrib["end"]
|
|
|
|
|
output += ',' + event.attrib["style"]
|
|
|
|
|
output += ',' + event.attrib["name"]
|
|
|
|
|
output += ',' + event.attrib["margin_l"]
|
|
|
|
|
output += ',' + event.attrib["margin_r"]
|
|
|
|
|
output += ',' + event.attrib["margin_v"]
|
|
|
|
|
output += ',' + event.attrib["effect"]
|
|
|
|
|
output += ',' + event.attrib["text"]
|
|
|
|
|
output += '\n'
|
|
|
|
|
|
|
|
|
|
return output
|
|
|
|
|
|
2015-05-30 02:12:58 -06:00
|
|
|
|
def _extract_subtitles(self, subtitle):
|
|
|
|
|
sub_root = xml.etree.ElementTree.fromstring(subtitle)
|
|
|
|
|
return [{
|
|
|
|
|
'ext': 'srt',
|
|
|
|
|
'data': self._convert_subtitles_to_srt(sub_root),
|
|
|
|
|
}, {
|
|
|
|
|
'ext': 'ass',
|
|
|
|
|
'data': self._convert_subtitles_to_ass(sub_root),
|
|
|
|
|
}]
|
|
|
|
|
|
2015-02-15 10:21:42 -07:00
|
|
|
|
def _get_subtitles(self, video_id, webpage):
|
|
|
|
|
subtitles = {}
|
|
|
|
|
for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
|
|
|
|
|
sub_page = self._download_webpage(
|
|
|
|
|
'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
|
|
|
|
|
video_id, note='Downloading subtitles for ' + sub_name)
|
|
|
|
|
id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False)
|
|
|
|
|
iv = self._search_regex(r'<iv>([^<]+)', sub_page, 'subtitle_iv', fatal=False)
|
|
|
|
|
data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False)
|
|
|
|
|
if not id or not iv or not data:
|
|
|
|
|
continue
|
|
|
|
|
subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
|
|
|
|
|
lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
|
|
|
|
|
if not lang_code:
|
|
|
|
|
continue
|
2015-05-30 02:12:58 -06:00
|
|
|
|
subtitles[lang_code] = self._extract_subtitles(subtitle)
|
2015-02-15 10:21:42 -07:00
|
|
|
|
return subtitles
|
|
|
|
|
|
2014-11-23 12:41:03 -07:00
|
|
|
|
def _real_extract(self, url):
|
2013-11-03 19:08:17 -07:00
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
2014-01-29 15:23:44 -07:00
|
|
|
|
video_id = mobj.group('video_id')
|
|
|
|
|
|
|
|
|
|
if mobj.group('prefix') == 'm':
|
|
|
|
|
mobile_webpage = self._download_webpage(url, video_id, 'Downloading mobile webpage')
|
|
|
|
|
webpage_url = self._search_regex(r'<link rel="canonical" href="([^"]+)" />', mobile_webpage, 'webpage_url')
|
|
|
|
|
else:
|
|
|
|
|
webpage_url = 'http://www.' + mobj.group('url')
|
2013-11-03 19:08:17 -07:00
|
|
|
|
|
2014-01-29 15:23:44 -07:00
|
|
|
|
webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
|
|
|
|
|
note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, 'trailer-notice', default='')
|
2013-11-03 19:08:17 -07:00
|
|
|
|
if note_m:
|
|
|
|
|
raise ExtractorError(note_m)
|
|
|
|
|
|
2014-02-25 06:29:16 -07:00
|
|
|
|
mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
|
|
|
|
|
if mobj:
|
|
|
|
|
msg = json.loads(mobj.group('msg'))
|
|
|
|
|
if msg.get('type') == 'error':
|
|
|
|
|
raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
|
|
|
|
|
|
2014-01-29 15:23:44 -07:00
|
|
|
|
video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
|
|
|
|
|
video_title = re.sub(r' {2,}', ' ', video_title)
|
|
|
|
|
video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
|
2013-11-03 19:08:17 -07:00
|
|
|
|
if not video_description:
|
|
|
|
|
video_description = None
|
2014-01-29 15:23:44 -07:00
|
|
|
|
video_upload_date = self._html_search_regex(r'<div>Availability for free users:(.+?)</div>', webpage, 'video_upload_date', fatal=False, flags=re.DOTALL)
|
2013-11-03 19:08:17 -07:00
|
|
|
|
if video_upload_date:
|
|
|
|
|
video_upload_date = unified_strdate(video_upload_date)
|
2014-01-29 15:23:44 -07:00
|
|
|
|
video_uploader = self._html_search_regex(r'<div>\s*Publisher:(.+?)</div>', webpage, 'video_uploader', fatal=False, flags=re.DOTALL)
|
2013-11-03 19:08:17 -07:00
|
|
|
|
|
2015-07-17 11:36:58 -06:00
|
|
|
|
playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
|
2013-11-03 19:08:17 -07:00
|
|
|
|
playerdata_req = compat_urllib_request.Request(playerdata_url)
|
2014-01-29 15:23:44 -07:00
|
|
|
|
playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
|
|
|
|
|
playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
|
|
|
|
playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
|
2014-02-25 06:26:11 -07:00
|
|
|
|
|
2014-01-29 15:23:44 -07:00
|
|
|
|
stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
|
|
|
|
|
video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
|
2013-11-03 19:08:17 -07:00
|
|
|
|
|
|
|
|
|
formats = []
|
2015-01-02 13:17:10 -07:00
|
|
|
|
for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
|
2013-11-03 19:08:17 -07:00
|
|
|
|
stream_quality, stream_format = self._FORMAT_IDS[fmt]
|
2014-11-23 13:23:05 -07:00
|
|
|
|
video_format = fmt + 'p'
|
2015-07-04 18:29:36 -06:00
|
|
|
|
streamdata_req = compat_urllib_request.Request(
|
|
|
|
|
'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
|
|
|
|
|
% (stream_id, stream_format, stream_quality),
|
|
|
|
|
compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8'))
|
2014-01-29 15:23:44 -07:00
|
|
|
|
streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
2014-10-23 15:25:02 -06:00
|
|
|
|
streamdata = self._download_xml(
|
|
|
|
|
streamdata_req, video_id,
|
|
|
|
|
note='Downloading media info for %s' % video_format)
|
2015-07-04 18:29:36 -06:00
|
|
|
|
stream_info = streamdata.find('./{default}preload/stream_info')
|
|
|
|
|
video_url = stream_info.find('./host').text
|
|
|
|
|
video_play_path = stream_info.find('./file').text
|
2015-08-18 11:02:57 -06:00
|
|
|
|
|
|
|
|
|
if '.fplive.net/' in video_url:
|
|
|
|
|
video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip())
|
|
|
|
|
parsed_video_url = compat_urlparse.urlparse(video_url)
|
|
|
|
|
direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
|
|
|
|
|
netloc='v.lvlt.crcdn.net',
|
|
|
|
|
path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1])))
|
|
|
|
|
if self._is_valid_url(direct_video_url, video_id, video_format):
|
|
|
|
|
formats.append({
|
|
|
|
|
'url': direct_video_url,
|
|
|
|
|
'format_id': video_format,
|
|
|
|
|
})
|
|
|
|
|
continue
|
|
|
|
|
|
2013-11-03 19:08:17 -07:00
|
|
|
|
formats.append({
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'url': video_url,
|
2014-10-23 15:25:02 -06:00
|
|
|
|
'play_path': video_play_path,
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'ext': 'flv',
|
|
|
|
|
'format': video_format,
|
|
|
|
|
'format_id': video_format,
|
2013-11-03 19:08:17 -07:00
|
|
|
|
})
|
|
|
|
|
|
2015-02-15 10:21:42 -07:00
|
|
|
|
subtitles = self.extract_subtitles(video_id, webpage)
|
2014-09-25 08:57:38 -06:00
|
|
|
|
|
2013-11-03 19:08:17 -07:00
|
|
|
|
return {
|
2014-11-23 13:20:46 -07:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'title': video_title,
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'description': video_description,
|
2014-11-23 13:20:46 -07:00
|
|
|
|
'thumbnail': video_thumbnail,
|
|
|
|
|
'uploader': video_uploader,
|
2014-01-29 15:23:44 -07:00
|
|
|
|
'upload_date': video_upload_date,
|
2014-11-23 13:20:46 -07:00
|
|
|
|
'subtitles': subtitles,
|
|
|
|
|
'formats': formats,
|
2014-02-25 12:51:51 -07:00
|
|
|
|
}
|
2014-10-19 23:47:05 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class CrunchyrollShowPlaylistIE(InfoExtractor):
|
|
|
|
|
IE_NAME = "crunchyroll:playlist"
|
2014-10-26 10:28:09 -06:00
|
|
|
|
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$'
|
2014-10-19 23:47:05 -06:00
|
|
|
|
|
|
|
|
|
_TESTS = [{
|
2014-10-26 10:28:09 -06:00
|
|
|
|
'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
|
|
|
|
|
'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
|
2014-10-19 23:47:05 -06:00
|
|
|
|
},
|
2014-10-26 10:28:09 -06:00
|
|
|
|
'playlist_count': 13,
|
2014-10-19 23:47:05 -06:00
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2014-10-26 10:28:09 -06:00
|
|
|
|
show_id = self._match_id(url)
|
|
|
|
|
|
|
|
|
|
webpage = self._download_webpage(url, show_id)
|
|
|
|
|
title = self._html_search_regex(
|
|
|
|
|
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
|
|
|
|
|
webpage, 'title')
|
|
|
|
|
episode_paths = re.findall(
|
|
|
|
|
r'(?s)<li id="showview_videos_media_[0-9]+"[^>]+>.*?<a href="([^"]+)"',
|
|
|
|
|
webpage)
|
|
|
|
|
entries = [
|
|
|
|
|
self.url_result('http://www.crunchyroll.com' + ep, 'Crunchyroll')
|
|
|
|
|
for ep in episode_paths
|
|
|
|
|
]
|
|
|
|
|
entries.reverse()
|
|
|
|
|
|
2014-10-19 23:47:05 -06:00
|
|
|
|
return {
|
2014-10-26 10:28:09 -06:00
|
|
|
|
'_type': 'playlist',
|
|
|
|
|
'id': show_id,
|
|
|
|
|
'title': title,
|
|
|
|
|
'entries': entries,
|
|
|
|
|
}
|