Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-10 12:17:19 +08:00
Code Issues Releases Wiki Activity

.

Browse Source
This commit is contained in:
Avi Peretz 2019-10-27 14:35:17 +02:00
parent da38b739cc
commit a96eb0b5cd
6 changed files with 337 additions and 486 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
youtube_dl/extractor/discoverynetworks.py
View File

@ -3,63 +3,38 @@ from __future__ import unicode_literals
import re import re
from .brightcove import BrightcoveLegacyIE
from .dplay import DPlayIE from .dplay import DPlayIE
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
from ..utils import smuggle_url
class DiscoveryNetworksDeIE(DPlayIE): class DiscoveryNetworksDeIE(DPlayIE):
_VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>discovery|tlc|animalplanet|dmax)\.de/ _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show)/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)'
(?:
.*\#(?P<id>\d+)|
(?:[^/]+/)*videos/(?P<display_id>[^/?#]+)|
programme/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)
)'''
_TESTS = [{ _TESTS = [{
'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001', 'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100',
'info_dict': { 'info_dict': {
'id': '3235167922001', 'id': '78867',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Breaking Amish: Die Welt da draußen', 'title': 'Die Welt da draußen',
'description': ( 'description': 'md5:61033c12b73286e409d99a41742ef608',
'Vier Amische und eine Mennonitin wagen in New York' 'timestamp': 1554069600,
' den Sprung in ein komplett anderes Leben. Begleitet sie auf' 'upload_date': '20190331',
' ihrem spannenden Weg.'), },
'timestamp': 1396598084, 'params': {
'upload_date': '20140404', 'format': 'bestvideo',
'uploader_id': '1659832546', 'skip_download': True,
}, },
}, { }, {
'url': 'http://www.dmax.de/programme/storage-hunters-uk/videos/storage-hunters-uk-episode-6/', 'url': 'https://www.dmax.de/programme/dmax-highlights/video/tuning-star-sidney-hoffmann-exklusiv-bei-dmax/191023082312316',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'http://www.discovery.de/#5332316765001', 'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B',
'only_matching': True, 'only_matching': True,
}] }]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s'
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) domain, programme, alternate_id = re.match(self._VALID_URL, url).groups()
alternate_id = mobj.group('alternate_id') country = 'GB' if domain == 'dplay.co.uk' else 'DE'
if alternate_id: realm = 'questuk' if country == 'GB' else domain.replace('.', '')
self._initialize_geo_bypass({ return self._get_disco_api_info(
'countries': ['DE'], url, '%s/%s' % (programme, alternate_id),
}) 'sonic-eu1-prod.disco-api.com', realm, country)
return self._get_disco_api_info(
url, '%s/%s' % (mobj.group('programme'), alternate_id),
'sonic-eu1-prod.disco-api.com', mobj.group('site') + 'de')
brightcove_id = mobj.group('id')
if not brightcove_id:
title = mobj.group('title')
webpage = self._download_webpage(url, title)
brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
brightcove_id = compat_parse_qs(compat_urlparse.urlparse(
brightcove_legacy_url).query)['@videoPlayer'][0]
return self.url_result(smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['DE']}),
'BrightcoveNew', brightcove_id)

397
youtube_dl/extractor/dplay.py
View File

@ -1,74 +1,68 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re import re
import time
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_HTTPError
compat_HTTPError,
compat_str,
compat_urlparse,
)
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
float_or_none, float_or_none,
int_or_none, int_or_none,
remove_end,
try_get,
unified_strdate,
unified_timestamp, unified_timestamp,
update_url_query,
urljoin,
USER_AGENTS,
) )
class DPlayIE(InfoExtractor): class DPlayIE(InfoExtractor):
_VALID_URL = r'https?://(?P<domain>www\.(?P<host>dplay\.(?P<country>dk|se|no)))/(?:video(?:er|s)/)?(?P<id>[^/]+/[^/?#]+)' _VALID_URL = r'''(?x)https?://
(?P<domain>
(?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))|
(?P<subdomain_country>es|it)\.dplay\.com
)/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
_TESTS = [{ _TESTS = [{
# non geo restricted, via secure api, unsigned download hls URL # non geo restricted, via secure api, unsigned download hls URL
'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/', 'url': 'https://www.dplay.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
'info_dict': { 'info_dict': {
'id': '3172', 'id': '13628',
'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet', 'display_id': 'nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Svensken lär sig njuta av livet', 'title': 'Svensken lär sig njuta av livet',
'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8', 'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
'duration': 2650, 'duration': 2649.856,
'timestamp': 1365454320, 'timestamp': 1365453720,
'upload_date': '20130408', 'upload_date': '20130408',
'creator': 'Kanal 5 (Home)', 'creator': 'Kanal 5',
'series': 'Nugammalt - 77 händelser som format Sverige', 'series': 'Nugammalt - 77 händelser som format Sverige',
'season_number': 1, 'season_number': 1,
'episode_number': 1, 'episode_number': 1,
'age_limit': 0, },
'params': {
'format': 'bestvideo',
'skip_download': True,
}, },
}, { }, {
# geo restricted, via secure api, unsigned download hls URL # geo restricted, via secure api, unsigned download hls URL
'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/', 'url': 'http://www.dplay.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
'info_dict': { 'info_dict': {
'id': '70816', 'id': '104465',
'display_id': 'mig-og-min-mor/season-6-episode-12', 'display_id': 'ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Episode 12', 'title': 'Ted Bundy: Mind Of A Monster',
'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90', 'description': 'md5:8b780f6f18de4dae631668b8a9637995',
'duration': 2563, 'duration': 5290.027,
'timestamp': 1429696800, 'timestamp': 1570694400,
'upload_date': '20150422', 'upload_date': '20191010',
'creator': 'Kanal 4 (Home)', 'creator': 'ID - Investigation Discovery',
'series': 'Mig og min mor', 'series': 'Ted Bundy: Mind Of A Monster',
'season_number': 6, 'season_number': 1,
'episode_number': 12, 'episode_number': 1,
'age_limit': 0, },
'params': {
'format': 'bestvideo',
'skip_download': True,
}, },
}, {
# geo restricted, via direct unsigned hls URL
'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/',
'only_matching': True,
}, { }, {
# disco-api # disco-api
'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7', 'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7',
@ -89,19 +83,59 @@ class DPlayIE(InfoExtractor):
'format': 'bestvideo', 'format': 'bestvideo',
'skip_download': True, 'skip_download': True,
}, },
'skip': 'Available for Premium users',
}, { }, {
'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3', 'md5': '2b808ffb00fc47b884a172ca5d13053c',
'info_dict': {
'id': '6918',
'display_id': 'biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
'ext': 'mp4',
'title': 'Luigi Di Maio: la psicosi di Stanislawskij',
'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
'thumbnail': r're:^https?://.*\.jpe?g',
'upload_date': '20160524',
'timestamp': 1464076800,
'series': 'Biografie imbarazzanti',
'season_number': 1,
'episode': 'Episode 1',
'episode_number': 1,
},
}, {
'url': 'https://es.dplay.com/dmax/la-fiebre-del-oro/temporada-8-episodio-1/',
'info_dict': {
'id': '21652',
'display_id': 'la-fiebre-del-oro/temporada-8-episodio-1',
'ext': 'mp4',
'title': 'Episodio 1',
'description': 'md5:b9dcff2071086e003737485210675f69',
'thumbnail': r're:^https?://.*\.png',
'upload_date': '20180709',
'timestamp': 1531173540,
'series': 'La fiebre del oro',
'season_number': 8,
'episode': 'Episode 1',
'episode_number': 1,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.dplay.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001', 'url': 'https://www.dplay.jp/video/gold-rush/24086',
'only_matching': True, 'only_matching': True,
}] }]
def _get_disco_api_info(self, url, display_id, disco_host, realm): def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
disco_base = 'https://' + disco_host geo_countries = [country.upper()]
self._initialize_geo_bypass({
'countries': geo_countries,
})
disco_base = 'https://%s/' % disco_host
token = self._download_json( token = self._download_json(
'%s/token' % disco_base, display_id, 'Downloading token', disco_base + 'token', display_id, 'Downloading token',
query={ query={
'realm': realm, 'realm': realm,
})['data']['attributes']['token'] })['data']['attributes']['token']
@ -110,17 +144,30 @@ class DPlayIE(InfoExtractor):
'Authorization': 'Bearer ' + token, 'Authorization': 'Bearer ' + token,
} }
video = self._download_json( video = self._download_json(
'%s/content/videos/%s' % (disco_base, display_id), display_id, disco_base + 'content/videos/' + display_id, display_id,
headers=headers, query={ headers=headers, query={
'include': 'show' 'include': 'images,primaryChannel,show,tags'
}) })
video_id = video['data']['id'] video_id = video['data']['id']
info = video['data']['attributes'] info = video['data']['attributes']
title = info['name'] title = info['name'].strip()
formats = [] formats = []
for format_id, format_dict in self._download_json( try:
'%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id), streaming = self._download_json(
display_id, headers=headers)['data']['attributes']['streaming'].items(): disco_base + 'playback/videoPlaybackInfo/' + video_id,
display_id, headers=headers)['data']['attributes']['streaming']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
error = info['errors'][0]
error_code = error.get('code')
if error_code == 'access.denied.geoblocked':
self.raise_geo_restricted(countries=geo_countries)
elif error_code == 'access.denied.missingpackage':
self.raise_login_required()
raise ExtractorError(info['errors'][0]['detail'], expected=True)
raise
for format_id, format_dict in streaming.items():
if not isinstance(format_dict, dict): if not isinstance(format_dict, dict):
continue continue
format_url = format_dict.get('url') format_url = format_dict.get('url')
@ -142,235 +189,55 @@ class DPlayIE(InfoExtractor):
}) })
self._sort_formats(formats) self._sort_formats(formats)
series = None creator = series = None
try: tags = []
included = video.get('included') thumbnails = []
if isinstance(included, list): included = video.get('included') or []
show = next(e for e in included if e.get('type') == 'show') if isinstance(included, list):
series = try_get( for e in included:
show, lambda x: x['attributes']['name'], compat_str) attributes = e.get('attributes')
except StopIteration: if not attributes:
pass continue
e_type = e.get('type')
if e_type == 'channel':
creator = attributes.get('name')
elif e_type == 'image':
src = attributes.get('src')
if src:
thumbnails.append({
'url': src,
'width': int_or_none(attributes.get('width')),
'height': int_or_none(attributes.get('height')),
})
if e_type == 'show':
series = attributes.get('name')
elif e_type == 'tag':
name = attributes.get('name')
if name:
tags.append(name)
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'title': title, 'title': title,
'description': info.get('description'), 'description': info.get('description'),
'duration': float_or_none( 'duration': float_or_none(info.get('videoDuration'), 1000),
info.get('videoDuration'), scale=1000),
'timestamp': unified_timestamp(info.get('publishStart')), 'timestamp': unified_timestamp(info.get('publishStart')),
'series': series, 'series': series,
'season_number': int_or_none(info.get('seasonNumber')), 'season_number': int_or_none(info.get('seasonNumber')),
'episode_number': int_or_none(info.get('episodeNumber')), 'episode_number': int_or_none(info.get('episodeNumber')),
'age_limit': int_or_none(info.get('minimum_age')), 'age_limit': int_or_none(info.get('minimum_age')),
'creator': creator,
'tags': tags,
'thumbnails': thumbnails,
'formats': formats, 'formats': formats,
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id') display_id = mobj.group('id')
domain = mobj.group('domain') domain = mobj.group('domain').lstrip('www.')
country = mobj.group('country') or mobj.group('subdomain_country')
self._initialize_geo_bypass({ host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com'
'countries': [mobj.group('country').upper()], return self._get_disco_api_info(
}) url, display_id, host, 'dplay' + country, country)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-video-id=["\'](\d+)', webpage, 'video id', default=None)
if not video_id:
host = mobj.group('host')
return self._get_disco_api_info(
url, display_id, 'disco-api.' + host, host.replace('.', ''))
info = self._download_json(
'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id),
video_id)['data'][0]
title = info['title']
PROTOCOLS = ('hls', 'hds')
formats = []
def extract_formats(protocol, manifest_url):
if protocol == 'hls':
m3u8_formats = self._extract_m3u8_formats(
manifest_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False)
# Sometimes final URLs inside m3u8 are unsigned, let's fix this
# ourselves. Also fragments' URLs are only served signed for
# Safari user agent.
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query)
for m3u8_format in m3u8_formats:
m3u8_format.update({
'url': update_url_query(m3u8_format['url'], query),
'http_headers': {
'User-Agent': USER_AGENTS['Safari'],
},
})
formats.extend(m3u8_formats)
elif protocol == 'hds':
formats.extend(self._extract_f4m_formats(
manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0',
video_id, f4m_id=protocol, fatal=False))
domain_tld = domain.split('.')[-1]
if domain_tld in ('se', 'dk', 'no'):
for protocol in PROTOCOLS:
# Providing dsc-geo allows to bypass geo restriction in some cases
self._set_cookie(
'secure.dplay.%s' % domain_tld, 'dsc-geo',
json.dumps({
'countryCode': domain_tld.upper(),
'expiry': (time.time() + 20 * 60) * 1000,
}))
stream = self._download_json(
'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s'
% (domain_tld, video_id, protocol), video_id,
'Downloading %s stream JSON' % protocol, fatal=False)
if stream and stream.get(protocol):
extract_formats(protocol, stream[protocol])
# The last resort is to try direct unsigned hls/hds URLs from info dictionary.
# Sometimes this does work even when secure API with dsc-geo has failed (e.g.
# http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/).
if not formats:
for protocol in PROTOCOLS:
if info.get(protocol):
extract_formats(protocol, info[protocol])
self._sort_formats(formats)
subtitles = {}
for lang in ('se', 'sv', 'da', 'nl', 'no'):
for format_id in ('web_vtt', 'vtt', 'srt'):
subtitle_url = info.get('subtitles_%s_%s' % (lang, format_id))
if subtitle_url:
subtitles.setdefault(lang, []).append({'url': subtitle_url})
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': info.get('video_metadata_longDescription'),
'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
'timestamp': int_or_none(info.get('video_publish_date')),
'creator': info.get('video_metadata_homeChannel'),
'series': info.get('video_metadata_show'),
'season_number': int_or_none(info.get('season')),
'episode_number': int_or_none(info.get('episode')),
'age_limit': int_or_none(info.get('minimum_age')),
'formats': formats,
'subtitles': subtitles,
}
class DPlayItIE(InfoExtractor):
_VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['IT']
_TEST = {
'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
'md5': '2b808ffb00fc47b884a172ca5d13053c',
'info_dict': {
'id': '6918',
'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij',
'ext': 'mp4',
'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij',
'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
'thumbnail': r're:^https?://.*\.jpe?g',
'upload_date': '20160524',
'series': 'Biografie imbarazzanti',
'season_number': 1,
'episode': 'Luigi Di Maio: la psicosi di Stanislawskij',
'episode_number': 1,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = remove_end(self._og_search_title(webpage), ' | Dplay')
video_id = None
info = self._search_regex(
r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")',
webpage, 'playback JSON', default=None)
if info:
for _ in range(2):
info = self._parse_json(info, display_id, fatal=False)
if not info:
break
else:
video_id = try_get(info, lambda x: x['data']['id'])
if not info:
info_url = self._search_regex(
(r'playback_json_url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
r'url\s*[:=]\s*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'),
webpage, 'info url', group='url')
info_url = urljoin(url, info_url)
video_id = info_url.rpartition('/')[-1]
try:
info = self._download_json(
info_url, display_id, headers={
'Authorization': 'Bearer %s' % self._get_cookies(url).get(
'dplayit_token').value,
'Referer': url,
})
if isinstance(info, compat_str):
info = self._parse_json(info, display_id)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
error = info['errors'][0]
if error.get('code') == 'access.denied.geoblocked':
self.raise_geo_restricted(
msg=error.get('detail'), countries=self._GEO_COUNTRIES)
raise ExtractorError(info['errors'][0]['detail'], expected=True)
raise
hls_url = info['data']['attributes']['streaming']['hls']['url']
formats = self._extract_m3u8_formats(
hls_url, display_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
self._sort_formats(formats)
series = self._html_search_regex(
r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>',
webpage, 'series', fatal=False)
episode = self._search_regex(
r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)',
webpage, 'episode', fatal=False)
mobj = re.search(
r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})',
webpage)
if mobj:
season_number = int(mobj.group('season_number'))
episode_number = int(mobj.group('episode_number'))
upload_date = unified_strdate(mobj.group('upload_date'))
else:
season_number = episode_number = upload_date = None
return {
'id': compat_str(video_id or display_id),
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'series': series,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'upload_date': upload_date,
'formats': formats,
}

5
youtube_dl/extractor/extractors.py
View File

@ -277,10 +277,7 @@ from .douyutv import (
DouyuShowIE, DouyuShowIE,
DouyuTVIE, DouyuTVIE,
) )
from .dplay import ( from .dplay import DPlayIE
DPlayIE,
DPlayItIE,
)
from .dreisat import DreiSatIE from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE from .drtuber import DrTuberIE

7
youtube_dl/extractor/generic.py
View File

@ -118,6 +118,7 @@ from .foxnews import FoxNewsIE
from .viqeo import ViqeoIE from .viqeo import ViqeoIE
from .expressen import ExpressenIE from .expressen import ExpressenIE
from .zype import ZypeIE from .zype import ZypeIE
from .odnoklassniki import OdnoklassnikiIE
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
@ -2627,9 +2628,9 @@ class GenericIE(InfoExtractor):
return self.url_result(mobj.group('url'), 'VK') return self.url_result(mobj.group('url'), 'VK')
# Look for embedded Odnoklassniki player # Look for embedded Odnoklassniki player
mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage) odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
if mobj is not None: if odnoklassniki_url:
return self.url_result(mobj.group('url'), 'Odnoklassniki') return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
# Look for embedded ivi player # Look for embedded ivi player
mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage) mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)

9
youtube_dl/extractor/odnoklassniki.py
View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_etree_fromstring, compat_etree_fromstring,
@ -136,6 +138,13 @@ class OdnoklassnikiIE(InfoExtractor):
'only_matching': True, 'only_matching': True,
}] }]
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
if mobj:
return mobj.group('url')
def _real_extract(self, url): def _real_extract(self, url):
start_time = int_or_none(compat_parse_qs( start_time = int_or_none(compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0]) compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0])

342
youtube_dl/extractor/vk.py
View File

@ -12,7 +12,6 @@ from ..utils import (
get_element_by_class, get_element_by_class,
int_or_none, int_or_none,
orderedSet, orderedSet,
remove_start,
str_or_none, str_or_none,
str_to_int, str_to_int,
unescapeHTML, unescapeHTML,
@ -21,6 +20,7 @@ from ..utils import (
urlencode_postdata, urlencode_postdata,
) )
from .dailymotion import DailymotionIE from .dailymotion import DailymotionIE
from .odnoklassniki import OdnoklassnikiIE
from .pladform import PladformIE from .pladform import PladformIE
from .vimeo import VimeoIE from .vimeo import VimeoIE
from .youtube import YoutubeIE from .youtube import YoutubeIE
@ -60,6 +60,18 @@ class VKBaseIE(InfoExtractor):
def _real_initialize(self): def _real_initialize(self):
self._login() self._login()
def _download_payload(self, path, video_id, data, fatal=True):
data['al'] = 1
code, payload = self._download_json(
'https://vk.com/%s.php' % path, video_id,
data=urlencode_postdata(data), fatal=fatal,
headers={'X-Requested-With': 'XMLHttpRequest'})['payload']
if code == '3':
self.raise_login_required()
elif code == '8':
raise ExtractorError(clean_html(payload[0][1:-1]), expected=True)
return payload
class VKIE(VKBaseIE): class VKIE(VKBaseIE):
IE_NAME = 'vk' IE_NAME = 'vk'
@ -96,7 +108,6 @@ class VKIE(VKBaseIE):
}, },
{ {
'url': 'http://vk.com/video205387401_165548505', 'url': 'http://vk.com/video205387401_165548505',
'md5': '6c0aeb2e90396ba97035b9cbde548700',
'info_dict': { 'info_dict': {
'id': '205387401_165548505', 'id': '205387401_165548505',
'ext': 'mp4', 'ext': 'mp4',
@ -110,18 +121,18 @@ class VKIE(VKBaseIE):
}, },
{ {
'note': 'Embedded video', 'note': 'Embedded video',
'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1', 'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa',
'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a', 'md5': '7babad3b85ea2e91948005b1b8b0cb84',
'info_dict': { 'info_dict': {
'id': '32194266_162925554', 'id': '-77521_162222515',
'ext': 'mp4', 'ext': 'mp4',
'uploader': 'Vladimir Gavrin', 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
'title': 'Lin Dan', 'title': 'ProtivoGunz - Хуёвая песня',
'duration': 101, 'duration': 195,
'upload_date': '20120730', 'upload_date': '20120212',
'view_count': int, 'timestamp': 1329049880,
'uploader_id': '-77521',
}, },
'skip': 'This video has been removed from public access.',
}, },
{ {
# VIDEO NOW REMOVED # VIDEO NOW REMOVED
@ -138,18 +149,19 @@ class VKIE(VKBaseIE):
'upload_date': '20121218', 'upload_date': '20121218',
'view_count': int, 'view_count': int,
}, },
'skip': 'Requires vk account credentials', 'skip': 'Removed',
}, },
{ {
'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d', 'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
'md5': '4d7a5ef8cf114dfa09577e57b2993202',
'info_dict': { 'info_dict': {
'id': '-43215063_168067957', 'id': '-43215063_168067957',
'ext': 'mp4', 'ext': 'mp4',
'uploader': 'Киномания - лучшее из мира кино', 'uploader': 'Bro Mazter',
'title': ' ', 'title': ' ',
'duration': 7291, 'duration': 7291,
'upload_date': '20140328', 'upload_date': '20140328',
'uploader_id': '223413403',
'timestamp': 1396018030,
}, },
'skip': 'Requires vk account credentials', 'skip': 'Requires vk account credentials',
}, },
@ -165,7 +177,7 @@ class VKIE(VKBaseIE):
'upload_date': '20140626', 'upload_date': '20140626',
'view_count': int, 'view_count': int,
}, },
'skip': 'Only works from Russia', 'skip': 'Removed',
}, },
{ {
# video (removed?) only available with list id # video (removed?) only available with list id
@ -247,6 +259,9 @@ class VKIE(VKBaseIE):
'uploader_id': '-387766', 'uploader_id': '-387766',
'timestamp': 1475137527, 'timestamp': 1475137527,
}, },
'params': {
'skip_download': True,
},
}, },
{ {
# live stream, hls and rtmp links, most likely already finished live # live stream, hls and rtmp links, most likely already finished live
@ -282,100 +297,100 @@ class VKIE(VKBaseIE):
# The video is not available in your region. # The video is not available in your region.
'url': 'https://vk.com/video-51812607_171445436', 'url': 'https://vk.com/video-51812607_171445436',
'only_matching': True, 'only_matching': True,
}, }]
{
# Video %s is not available.
'url': 'https://vk.com/video-173478245_456239188',
'only_matching': True,
},
]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid') video_id = mobj.group('videoid')
mv_data = {}
if video_id: if video_id:
info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id data = {
'act': 'show_inline',
'video': video_id,
}
# Some videos (removed?) can only be downloaded with list id specified # Some videos (removed?) can only be downloaded with list id specified
list_id = mobj.group('list_id') list_id = mobj.group('list_id')
if list_id: if list_id:
info_url += '&list=%s' % list_id data['list'] = list_id
payload = self._download_payload('al_video', video_id, data)
info_page = payload[1]
opts = payload[-1]
mv_data = opts.get('mvData') or {}
player = opts.get('player') or {}
else: else:
info_url = 'http://vk.com/video_ext.php?' + mobj.group('embed_query')
video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id'))
info_page = self._download_webpage(info_url, video_id) info_page = self._download_webpage(
url_page = self._download_webpage(url, video_id) 'http://vk.com/video_ext.php?' + mobj.group('embed_query'), video_id)
error_message = self._html_search_regex( error_message = self._html_search_regex(
[r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>', [r'(?s)<!><div[^>]+class="video_layer_message"[^>]*>(.+?)</div>',
r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'], r'(?s)<div[^>]+id="video_ext_msg"[^>]*>(.+?)</div>'],
info_page, 'error message', default=None) info_page, 'error message', default=None)
if error_message: if error_message:
raise ExtractorError(error_message, expected=True) raise ExtractorError(error_message, expected=True)
if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page): if re.search(r'<!>/login\.php\?.*\bact=security_check', info_page):
raise ExtractorError( raise ExtractorError(
'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
expected=True) expected=True)
ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
ERRORS = { ERRORS = {
r'Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
ERROR_COPYRIGHT, ERROR_COPYRIGHT,
r'The video .*? was removed from public access by request of the copyright holder.<': r'>The video .*? was removed from public access by request of the copyright holder.<':
ERROR_COPYRIGHT, ERROR_COPYRIGHT,
r'Please log in or <': r'<!>Please log in or <':
'Video %s is only available for registered users, ' 'Video %s is only available for registered users, '
'use --username and --password options to provide account credentials.', 'use --username and --password options to provide account credentials.',
r'Unknown error': r'<!>Unknown error':
'Video %s does not exist.', 'Video %s does not exist.',
r'<!>Видео временно недоступно': r'<!>Видео временно недоступно':
'Video %s is temporarily unavailable.', 'Video %s is temporarily unavailable.',
r'Access denied': r'<!>Access denied':
'Access denied to video %s.', 'Access denied to video %s.',
r'Видеозапись недоступна, так как её автор был заблокирован.': r'<!>Видеозапись недоступна, так как её автор был заблокирован.':
'Video %s is no longer available, because its author has been blocked.', 'Video %s is no longer available, because its author has been blocked.',
r'This video is no longer available, because its author has been blocked.': r'<!>This video is no longer available, because its author has been blocked.':
'Video %s is no longer available, because its author has been blocked.', 'Video %s is no longer available, because its author has been blocked.',
r'This video is no longer available, because it has been deleted.': r'<!>This video is no longer available, because it has been deleted.':
'Video %s is no longer available, because it has been deleted.', 'Video %s is no longer available, because it has been deleted.',
r'The video .+? is not available in your region.': r'<!>The video .+? is not available in your region.':
'Video %s is not available in your region.', 'Video %s is not available in your region.',
}
r'The video .+? is unavailable': for error_re, error_msg in ERRORS.items():
'Video %s is not available.', if re.search(error_re, info_page):
r'You need to be a member of this group to view':
'Video %s is for group members only.',
}
for error_re, error_msg in ERRORS.items():
for page in [info_page, url_page]:
if re.search(error_re, page):
raise ExtractorError(error_msg % video_id, expected=True) raise ExtractorError(error_msg % video_id, expected=True)
player = self._parse_json(self._search_regex(
r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n',
info_page, 'player params'), video_id)
youtube_url = YoutubeIE._extract_url(info_page) youtube_url = YoutubeIE._extract_url(info_page)
if youtube_url: if youtube_url:
return self.url_result(youtube_url, ie=YoutubeIE.ie_key()) return self.url_result(youtube_url, YoutubeIE.ie_key())
vimeo_url = VimeoIE._extract_url(url, info_page) vimeo_url = VimeoIE._extract_url(url, info_page)
if vimeo_url is not None: if vimeo_url is not None:
return self.url_result(vimeo_url) return self.url_result(vimeo_url, VimeoIE.ie_key())
pladform_url = PladformIE._extract_url(info_page) pladform_url = PladformIE._extract_url(info_page)
if pladform_url: if pladform_url:
return self.url_result(pladform_url) return self.url_result(pladform_url, PladformIE.ie_key())
m_rutube = re.search( m_rutube = re.search(
r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page) r'\ssrc="((?:https?:)?//rutube\.ru\\?/(?:video|play)\\?/embed(?:.*?))\\?"', info_page)
@ -388,6 +403,10 @@ class VKIE(VKBaseIE):
if dailymotion_urls: if dailymotion_urls:
return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key()) return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
if odnoklassniki_url:
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page) m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
if m_opts: if m_opts:
m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1)) m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1))
@ -397,38 +416,7 @@ class VKIE(VKBaseIE):
opts_url = 'http:' + opts_url opts_url = 'http:' + opts_url
return self.url_result(opts_url) return self.url_result(opts_url)
# vars does not look to be served anymore since 24.10.2016 data = player['params'][0]
data = self._parse_json(
self._search_regex(
r'var\s+vars\s*=\s*({.+?});', info_page, 'vars', default='{}'),
video_id, fatal=False)
# <!json> is served instead
if not data:
data = self._parse_json(
self._search_regex(
[r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'],
info_page, 'json', default='{}'),
video_id)
if data:
data = data['player']['params'][0]
if not data:
data = self._parse_json(
self._search_regex(
r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,
'player params', default='{}'),
video_id)
if data:
data = data['params'][0]
# <!--{...}
if not data:
data = self._parse_json(
self._search_regex(
r'<!--\s*({.+})', info_page, 'payload'),
video_id)['payload'][-1][-1]['player']['params'][0]
title = unescapeHTML(data['md_title']) title = unescapeHTML(data['md_title'])
# 2 = live # 2 = live
@ -477,12 +465,12 @@ class VKIE(VKBaseIE):
'title': title, 'title': title,
'thumbnail': data.get('jpg'), 'thumbnail': data.get('jpg'),
'uploader': data.get('md_author'), 'uploader': data.get('md_author'),
'uploader_id': str_or_none(data.get('author_id')), 'uploader_id': str_or_none(data.get('author_id') or mv_data.get('authorId')),
'duration': data.get('duration'), 'duration': int_or_none(data.get('duration') or mv_data.get('duration')),
'timestamp': timestamp, 'timestamp': timestamp,
'view_count': view_count, 'view_count': view_count,
'like_count': int_or_none(data.get('liked')), 'like_count': int_or_none(mv_data.get('likes')),
'dislike_count': int_or_none(data.get('nolikes')), 'comment_count': int_or_none(mv_data.get('commcount')),
'is_live': is_live, 'is_live': is_live,
} }
@ -496,7 +484,6 @@ class VKUserVideosIE(VKBaseIE):
'url': 'http://vk.com/videos205387401', 'url': 'http://vk.com/videos205387401',
'info_dict': { 'info_dict': {
'id': '205387401', 'id': '205387401',
'title': "Tom Cruise's Videos",
}, },
'playlist_mincount': 4, 'playlist_mincount': 4,
}, { }, {
@ -512,22 +499,25 @@ class VKUserVideosIE(VKBaseIE):
'url': 'http://new.vk.com/videos205387401', 'url': 'http://new.vk.com/videos205387401',
'only_matching': True, 'only_matching': True,
}] }]
_VIDEO = collections.namedtuple(
'Video', ['owner_id', 'id', 'thumb', 'title', 'flags', 'duration', 'hash', 'moder_acts', 'owner', 'date', 'views', 'platform', 'blocked', 'music_video_meta'])
def _real_extract(self, url): def _real_extract(self, url):
page_id = self._match_id(url) page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id) l = self._download_payload('al_video', page_id, {
'act': 'load_videos_silent',
'oid': page_id,
})[0]['']['list']
entries = [ entries = []
self.url_result( for video in l:
'http://vk.com/video' + video_id, 'VK', video_id=video_id) v = self._VIDEO._make(video)
for video_id in orderedSet(re.findall(r'href="/video(-?[0-9_]+)"', webpage))] video_id = '%d_%d' % (v.owner_id, v.id)
entries.append(self.url_result(
'http://vk.com/video' + video_id, 'VK', video_id=video_id))
title = unescapeHTML(self._search_regex( return self.playlist_result(entries, page_id)
r'<title>\s*([^<]+?)\s+\|\s+\d+\s+videos',
webpage, 'title', default=page_id))
return self.playlist_result(entries, page_id, title)
class VKWallPostIE(VKBaseIE): class VKWallPostIE(VKBaseIE):
@ -537,15 +527,15 @@ class VKWallPostIE(VKBaseIE):
# public page URL, audio playlist # public page URL, audio playlist
'url': 'https://vk.com/bs.official?w=wall-23538238_35', 'url': 'https://vk.com/bs.official?w=wall-23538238_35',
'info_dict': { 'info_dict': {
'id': '23538238_35', 'id': '-23538238_35',
'title': 'Black Shadow - Wall post 23538238_35', 'title': 'Black Shadow - Wall post -23538238_35',
'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c', 'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
}, },
'playlist': [{ 'playlist': [{
'md5': '5ba93864ec5b85f7ce19a9af4af080f6', 'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
'info_dict': { 'info_dict': {
'id': '135220665_111806521', 'id': '135220665_111806521',
'ext': 'mp3', 'ext': 'mp4',
'title': 'Black Shadow - Слепое Верование', 'title': 'Black Shadow - Слепое Верование',
'duration': 370, 'duration': 370,
'uploader': 'Black Shadow', 'uploader': 'Black Shadow',
@ -556,18 +546,16 @@ class VKWallPostIE(VKBaseIE):
'md5': '4cc7e804579122b17ea95af7834c9233', 'md5': '4cc7e804579122b17ea95af7834c9233',
'info_dict': { 'info_dict': {
'id': '135220665_111802303', 'id': '135220665_111802303',
'ext': 'mp3', 'ext': 'mp4',
'title': 'Black Shadow - Война - Негасимое Бездны Пламя!', 'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
'duration': 423, 'duration': 423,
'uploader': 'Black Shadow', 'uploader': 'Black Shadow',
'artist': 'Black Shadow', 'artist': 'Black Shadow',
'track': 'Война - Негасимое Бездны Пламя!', 'track': 'Война - Негасимое Бездны Пламя!',
}, },
'params': {
'skip_download': True,
},
}], }],
'params': { 'params': {
'skip_download': True,
'usenetrc': True, 'usenetrc': True,
}, },
'skip': 'Requires vk account credentials', 'skip': 'Requires vk account credentials',
@ -576,7 +564,7 @@ class VKWallPostIE(VKBaseIE):
'url': 'https://vk.com/wall85155021_6319', 'url': 'https://vk.com/wall85155021_6319',
'info_dict': { 'info_dict': {
'id': '85155021_6319', 'id': '85155021_6319',
'title': 'Sergey Gorbunov - Wall post 85155021_6319', 'title': 'Сергей Горбунов - Wall post 85155021_6319',
}, },
'playlist_count': 1, 'playlist_count': 1,
'params': { 'params': {
@ -592,58 +580,72 @@ class VKWallPostIE(VKBaseIE):
'url': 'https://m.vk.com/wall-23538238_35', 'url': 'https://m.vk.com/wall-23538238_35',
'only_matching': True, 'only_matching': True,
}] }]
_BASE64_CHARS = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMN0PQRSTUVWXYZO123456789+/='
_AUDIO = collections.namedtuple(
'Audio', ['id', 'owner_id', 'url', 'title', 'performer', 'duration', 'album_id', 'unk', 'author_link', 'lyrics', 'flags', 'context', 'extra', 'hashes', 'cover_url', 'ads', 'subtitle', 'main_artists', 'feat_artists', 'album', 'track_code', 'restriction', 'album_part', 'new_stats', 'access_key'])
def _decode(self, enc):
dec = ''
e = n = 0
for c in enc:
r = self._BASE64_CHARS.index(c)
cond = n % 4
e = 64 * e + r if cond else r
n += 1
if cond:
dec += chr(255 & e >> (-2 * n & 6))
return dec
def _unmask_url(self, mask_url, vk_id):
if 'audio_api_unavailable' in mask_url:
extra = mask_url.split('?extra=')[1].split('#')
func, base = self._decode(extra[1]).split(chr(11))
mask_url = list(self._decode(extra[0]))
url_len = len(mask_url)
indexes = [None] * url_len
index = int(base) ^ vk_id
for n in range(url_len - 1, -1, -1):
index = (url_len * (n + 1) ^ index + n) % url_len
indexes[n] = index
for n in range(1, url_len):
c = mask_url[n]
index = indexes[url_len - 1 - n]
mask_url[n] = mask_url[index]
mask_url[index] = c
mask_url = ''.join(mask_url)
return mask_url
def _real_extract(self, url): def _real_extract(self, url):
post_id = self._match_id(url) post_id = self._match_id(url)
wall_url = 'https://vk.com/wall%s' % post_id webpage = self._download_payload('wkview', post_id, {
'act': 'show',
post_id = remove_start(post_id, '-') 'w': 'wall' + post_id,
})[1]
webpage = self._download_webpage(wall_url, post_id)
error = self._html_search_regex(
r'>Error</div>\s*<div[^>]+class=["\']body["\'][^>]*>([^<]+)',
webpage, 'error', default=None)
if error:
raise ExtractorError('VK said: %s' % error, expected=True)
description = clean_html(get_element_by_class('wall_post_text', webpage)) description = clean_html(get_element_by_class('wall_post_text', webpage))
uploader = clean_html(get_element_by_class('author', webpage)) uploader = clean_html(get_element_by_class('author', webpage))
thumbnail = self._og_search_thumbnail(webpage)
entries = [] entries = []
audio_ids = re.findall(r'data-full-id=["\'](\d+_\d+)', webpage) for audio in re.findall(r'data-audio="([^"]+)', webpage):
if audio_ids: audio = self._parse_json(unescapeHTML(audio), post_id)
al_audio = self._download_webpage( a = self._AUDIO._make(audio)
'https://vk.com/al_audio.php', post_id, if not a.url:
note='Downloading audio info', fatal=False, continue
data=urlencode_postdata({ title = unescapeHTML(a.title)
'act': 'reload_audio', entries.append({
'al': '1', 'id': '%s_%s' % (a.owner_id, a.id),
'ids': ','.join(audio_ids) 'url': self._unmask_url(a.url, a.ads['vk_id']),
})) 'title': '%s - %s' % (a.performer, title) if a.performer else title,
if al_audio: 'thumbnail': a.cover_url.split(',') if a.cover_url else None,
Audio = collections.namedtuple( 'duration': a.duration,
'Audio', ['id', 'user_id', 'url', 'track', 'artist', 'duration']) 'uploader': uploader,
audios = self._parse_json( 'artist': a.performer,
self._search_regex( 'track': title,
r'<!json>(.+?)<!>', al_audio, 'audios', default='[]'), 'ext': 'mp4',
post_id, fatal=False, transform_source=unescapeHTML) 'protocol': 'm3u8',
if isinstance(audios, list): })
for audio in audios:
a = Audio._make(audio[:6])
entries.append({
'id': '%s_%s' % (a.user_id, a.id),
'url': a.url,
'title': '%s - %s' % (a.artist, a.track) if a.artist and a.track else a.id,
'thumbnail': thumbnail,
'duration': a.duration,
'uploader': uploader,
'artist': a.artist,
'track': a.track,
})
for video in re.finditer( for video in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage): r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):