mirror of
https://github.com/l1ving/youtube-dl
synced 2025-03-10 22:07:16 +08:00
Merge remote-tracking branch 'upstream/master'
# Conflicts: # youtube_dl/extractor/facebook.py
This commit is contained in:
Avi Peretz
commit
d08fed0d41
@ -6,7 +6,6 @@ from ..utils import (
|
||||
ExtractorError,
|
||||
remove_end,
|
||||
)
|
||||
from .rudo import RudoIE
|
||||
|
||||
|
||||
class BioBioChileTVIE(InfoExtractor):
|
||||
@ -41,11 +40,15 @@ class BioBioChileTVIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml',
|
||||
'info_dict': {
|
||||
'id': 'edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos',
|
||||
'id': 'b4xd0LK3SK',
|
||||
'ext': 'mp4',
|
||||
'uploader': '(none)',
|
||||
'upload_date': '20160708',
|
||||
'title': 'Edecanes del Congreso: Figuras decorativas que le cuestan muy caro a los chilenos',
|
||||
# TODO: fix url_transparent information overriding
|
||||
# 'uploader': 'Juan Pablo Echenique',
|
||||
'title': 'Comentario Oscar Cáceres',
|
||||
},
|
||||
'params': {
|
||||
# empty m3u8 manifest
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
|
||||
@ -60,7 +63,9 @@ class BioBioChileTVIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
rudo_url = RudoIE._extract_url(webpage)
|
||||
rudo_url = self._search_regex(
|
||||
r'<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
|
||||
webpage, 'embed URL', None, group='url')
|
||||
if not rudo_url:
|
||||
raise ExtractorError('No videos found')
|
||||
|
||||
@ -68,7 +73,7 @@ class BioBioChileTVIE(InfoExtractor):
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
uploader = self._html_search_regex(
|
||||
r'<a[^>]+href=["\']https?://(?:busca|www)\.biobiochile\.cl/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',
|
||||
r'<a[^>]+href=["\'](?:https?://(?:busca|www)\.biobiochile\.cl)?/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',
|
||||
webpage, 'uploader', fatal=False)
|
||||
|
||||
return {
|
||||
|
||||
@ -71,7 +71,7 @@ class BleacherReportIE(InfoExtractor):
|
||||
video = article_data.get('video')
|
||||
if video:
|
||||
video_type = video['type']
|
||||
if video_type == 'cms.bleacherreport.com':
|
||||
if video_type in ('cms.bleacherreport.com', 'vid.bleacherreport.com'):
|
||||
info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id']
|
||||
elif video_type == 'ooyala.com':
|
||||
info['url'] = 'ooyala:%s' % video['id']
|
||||
@ -87,9 +87,9 @@ class BleacherReportIE(InfoExtractor):
|
||||
|
||||
|
||||
class BleacherReportCMSIE(AMPIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})'
|
||||
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36}|\d{5})'
|
||||
_TESTS = [{
|
||||
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
|
||||
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms',
|
||||
'md5': '2e4b0a997f9228ffa31fada5c53d1ed1',
|
||||
'info_dict': {
|
||||
'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
|
||||
@ -101,6 +101,6 @@ class BleacherReportCMSIE(AMPIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id)
|
||||
info = self._extract_feed_info('http://vid.bleacherreport.com/videos/%s.akamai' % video_id)
|
||||
info['id'] = video_id
|
||||
return info
|
||||
|
||||
@ -7,50 +7,51 @@ from .common import InfoExtractor
|
||||
|
||||
|
||||
class DBTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:[^/]+/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
|
||||
_VALID_URL = r'https?://(?:www\.)?dagbladet\.no/video/(?:(?:embed|(?P<display_id>[^/]+))/)?(?P<id>[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8})'
|
||||
_TESTS = [{
|
||||
'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
|
||||
'md5': '2e24f67936517b143a234b4cadf792ec',
|
||||
'url': 'https://www.dagbladet.no/video/PynxJnNWChE/',
|
||||
'md5': 'b8f850ba1860adbda668d367f9b77699',
|
||||
'info_dict': {
|
||||
'id': '3649835190001',
|
||||
'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
|
||||
'id': 'PynxJnNWChE',
|
||||
'ext': 'mp4',
|
||||
'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
|
||||
'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0',
|
||||
'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'timestamp': 1404039863,
|
||||
'upload_date': '20140629',
|
||||
'duration': 69.544,
|
||||
'uploader_id': '1027729757001',
|
||||
'upload_date': '20160916',
|
||||
'duration': 69,
|
||||
'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ',
|
||||
'uploader': 'Dagbladet',
|
||||
},
|
||||
'add_ie': ['BrightcoveNew']
|
||||
'add_ie': ['Youtube']
|
||||
}, {
|
||||
'url': 'http://dbtv.no/3649835190001',
|
||||
'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://dbtv.no/vice/5000634109001',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://dbtv.no/filmtrailer/3359293614001',
|
||||
'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return [url for _, url in re.findall(
|
||||
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dbtv\.no/(?:lazy)?player/\d+.*?)\1',
|
||||
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dagbladet\.no/video/embed/(?:[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8}).*?)\1',
|
||||
webpage)]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
|
||||
return {
|
||||
display_id, video_id = re.match(self._VALID_URL, url).groups()
|
||||
info = {
|
||||
'_type': 'url_transparent',
|
||||
'url': 'http://players.brightcove.net/1027729757001/default_default/index.html?videoId=%s' % video_id,
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'ie_key': 'BrightcoveNew',
|
||||
}
|
||||
if len(video_id) == 11:
|
||||
info.update({
|
||||
'url': video_id,
|
||||
'ie_key': 'Youtube',
|
||||
})
|
||||
else:
|
||||
info.update({
|
||||
'url': 'jwplatform:' + video_id,
|
||||
'ie_key': 'JWPlatform',
|
||||
})
|
||||
return info
|
||||
|
||||
94
youtube_dl/extractor/dlive.py
Normal file
94
youtube_dl/extractor/dlive.py
Normal file
@ -0,0 +1,94 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class DLiveVODIE(InfoExtractor):
|
||||
IE_NAME = 'dlive:vod'
|
||||
_VALID_URL = r'https?://(?:www\.)?dlive\.tv/p/(?P<uploader_id>.+?)\+(?P<id>[a-zA-Z0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'https://dlive.tv/p/pdp+3mTzOl4WR',
|
||||
'info_dict': {
|
||||
'id': '3mTzOl4WR',
|
||||
'ext': 'mp4',
|
||||
'title': 'Minecraft with james charles epic',
|
||||
'upload_date': '20190701',
|
||||
'timestamp': 1562011015,
|
||||
'uploader_id': 'pdp',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
uploader_id, vod_id = re.match(self._VALID_URL, url).groups()
|
||||
broadcast = self._download_json(
|
||||
'https://graphigo.prd.dlive.tv/', vod_id,
|
||||
data=json.dumps({'query': '''query {
|
||||
pastBroadcast(permlink:"%s+%s") {
|
||||
content
|
||||
createdAt
|
||||
length
|
||||
playbackUrl
|
||||
title
|
||||
thumbnailUrl
|
||||
viewCount
|
||||
}
|
||||
}''' % (uploader_id, vod_id)}).encode())['data']['pastBroadcast']
|
||||
title = broadcast['title']
|
||||
formats = self._extract_m3u8_formats(
|
||||
broadcast['playbackUrl'], vod_id, 'mp4', 'm3u8_native')
|
||||
self._sort_formats(formats)
|
||||
return {
|
||||
'id': vod_id,
|
||||
'title': title,
|
||||
'uploader_id': uploader_id,
|
||||
'formats': formats,
|
||||
'description': broadcast.get('content'),
|
||||
'thumbnail': broadcast.get('thumbnailUrl'),
|
||||
'timestamp': int_or_none(broadcast.get('createdAt'), 1000),
|
||||
'view_count': int_or_none(broadcast.get('viewCount')),
|
||||
}
|
||||
|
||||
|
||||
class DLiveStreamIE(InfoExtractor):
|
||||
IE_NAME = 'dlive:stream'
|
||||
_VALID_URL = r'https?://(?:www\.)?dlive\.tv/(?!p/)(?P<id>[\w.-]+)'
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_name = self._match_id(url)
|
||||
user = self._download_json(
|
||||
'https://graphigo.prd.dlive.tv/', display_name,
|
||||
data=json.dumps({'query': '''query {
|
||||
userByDisplayName(displayname:"%s") {
|
||||
livestream {
|
||||
content
|
||||
createdAt
|
||||
title
|
||||
thumbnailUrl
|
||||
watchingCount
|
||||
}
|
||||
username
|
||||
}
|
||||
}''' % display_name}).encode())['data']['userByDisplayName']
|
||||
livestream = user['livestream']
|
||||
title = livestream['title']
|
||||
username = user['username']
|
||||
formats = self._extract_m3u8_formats(
|
||||
'https://live.prd.dlive.tv/hls/live/%s.m3u8' % username,
|
||||
display_name, 'mp4')
|
||||
self._sort_formats(formats)
|
||||
return {
|
||||
'id': display_name,
|
||||
'title': self._live_title(title),
|
||||
'uploader': display_name,
|
||||
'uploader_id': username,
|
||||
'formats': formats,
|
||||
'description': livestream.get('content'),
|
||||
'thumbnail': livestream.get('thumbnailUrl'),
|
||||
'is_live': True,
|
||||
'timestamp': int_or_none(livestream.get('createdAt'), 1000),
|
||||
'view_count': int_or_none(livestream.get('watchingCount')),
|
||||
}
|
||||
@ -579,6 +579,7 @@ from .linkedin import (
|
||||
)
|
||||
from .linuxacademy import LinuxAcademyIE
|
||||
from .litv import LiTVIE
|
||||
from .livejournal import LiveJournalIE
|
||||
from .liveleak import (
|
||||
LiveLeakIE,
|
||||
LiveLeakEmbedIE,
|
||||
@ -967,7 +968,6 @@ from .rts import RTSIE
|
||||
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
|
||||
from .rtvnh import RTVNHIE
|
||||
from .rtvs import RTVSIE
|
||||
from .rudo import RudoIE
|
||||
from .ruhd import RUHDIE
|
||||
from .rutube import (
|
||||
RutubeIE,
|
||||
@ -1255,6 +1255,10 @@ from .udn import UDNEmbedIE
|
||||
from .ufctv import UFCTVIE
|
||||
from .uktvplay import UKTVPlayIE
|
||||
from .digiteka import DigitekaIE
|
||||
from .dlive import (
|
||||
DLiveVODIE,
|
||||
DLiveStreamIE,
|
||||
)
|
||||
from .umg import UMGDeIE
|
||||
from .unistra import UnistraIE
|
||||
from .unity import UnityIE
|
||||
|
||||
@ -462,8 +462,8 @@ class FacebookIE(InfoExtractor):
|
||||
r'[\'\"]ownerid[\'\"]\s*:\s*[\'\"](\d+)[\'\"]', tahoe_data.secondary,
|
||||
'uploader_id', fatal=False)
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage)
|
||||
if is_live:
|
||||
view_count = parse_count(
|
||||
self._search_regex(r'viewerCount:([\d]+)', webpage, 'views', fatal=False) or \
|
||||
|
||||
42
youtube_dl/extractor/livejournal.py
Normal file
42
youtube_dl/extractor/livejournal.py
Normal file
@ -0,0 +1,42 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class LiveJournalIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272',
|
||||
'md5': 'adaf018388572ced8a6f301ace49d4b2',
|
||||
'info_dict': {
|
||||
'id': '1263729',
|
||||
'ext': 'mp4',
|
||||
'title': 'Истребители против БПЛА',
|
||||
'upload_date': '20190624',
|
||||
'timestamp': 1561406715,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
record = self._parse_json(self._search_regex(
|
||||
r'Site\.page\s*=\s*({.+?});', webpage,
|
||||
'page data'), video_id)['video']['record']
|
||||
storage_id = compat_str(record['storageid'])
|
||||
title = record.get('name')
|
||||
if title:
|
||||
# remove filename extension(.mp4, .mov, etc...)
|
||||
title = title.rsplit('.', 1)[0]
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'thumbnail': record.get('thumbnail'),
|
||||
'timestamp': int_or_none(record.get('timecreate')),
|
||||
'url': 'eagleplatform:vc.videos.livejournal.com:' + storage_id,
|
||||
'ie_key': 'EaglePlatform',
|
||||
}
|
||||
@ -117,6 +117,10 @@ class LyndaIE(LyndaBaseIE):
|
||||
}, {
|
||||
'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Willkommen-Grundlagen-guten-Gestaltung/393570/393572-4.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Status="NotFound", Message="Transcript not found"
|
||||
'url': 'https://www.lynda.com/ASP-NET-tutorials/What-you-should-know/5034180/2811512-4.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _raise_unavailable(self, video_id):
|
||||
@ -247,12 +251,17 @@ class LyndaIE(LyndaBaseIE):
|
||||
|
||||
def _get_subtitles(self, video_id):
|
||||
url = 'https://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
|
||||
subs = self._download_json(url, None, False)
|
||||
subs = self._download_webpage(
|
||||
url, video_id, 'Downloading subtitles JSON', fatal=False)
|
||||
if not subs or 'Status="NotFound"' in subs:
|
||||
return {}
|
||||
subs = self._parse_json(subs, video_id, fatal=False)
|
||||
if not subs:
|
||||
return {}
|
||||
fixed_subs = self._fix_subtitles(subs)
|
||||
if fixed_subs:
|
||||
return {'en': [{'ext': 'srt', 'data': fixed_subs}]}
|
||||
else:
|
||||
return {}
|
||||
return {}
|
||||
|
||||
|
||||
class LyndaCourseIE(LyndaBaseIE):
|
||||
|
||||
@ -4,11 +4,14 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_HTTPError,
|
||||
compat_str,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
strip_or_none,
|
||||
unescapeHTML,
|
||||
str_or_none,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
@ -21,15 +24,14 @@ class RoosterTeethIE(InfoExtractor):
|
||||
'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
|
||||
'md5': 'e2bd7764732d785ef797700a2489f212',
|
||||
'info_dict': {
|
||||
'id': '26576',
|
||||
'id': '9156',
|
||||
'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
|
||||
'ext': 'mp4',
|
||||
'title': 'Million Dollars, But...: Million Dollars, But... The Game Announcement',
|
||||
'description': 'md5:0cc3b21986d54ed815f5faeccd9a9ca5',
|
||||
'title': 'Million Dollars, But... The Game Announcement',
|
||||
'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5',
|
||||
'thumbnail': r're:^https?://.*\.png$',
|
||||
'series': 'Million Dollars, But...',
|
||||
'episode': 'Million Dollars, But... The Game Announcement',
|
||||
'comment_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
|
||||
@ -89,60 +91,55 @@ class RoosterTeethIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
api_episode_url = 'https://svod-be.roosterteeth.com/api/v1/episodes/%s' % display_id
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
episode = strip_or_none(unescapeHTML(self._search_regex(
|
||||
(r'videoTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
|
||||
r'<title>(?P<title>[^<]+)</title>'), webpage, 'title',
|
||||
default=None, group='title')))
|
||||
|
||||
title = strip_or_none(self._og_search_title(
|
||||
webpage, default=None)) or episode
|
||||
|
||||
m3u8_url = self._search_regex(
|
||||
r'file\s*:\s*(["\'])(?P<url>http.+?\.m3u8.*?)\1',
|
||||
webpage, 'm3u8 url', default=None, group='url')
|
||||
|
||||
if not m3u8_url:
|
||||
if re.search(r'<div[^>]+class=["\']non-sponsor', webpage):
|
||||
self.raise_login_required(
|
||||
'%s is only available for FIRST members' % display_id)
|
||||
|
||||
if re.search(r'<div[^>]+class=["\']golive-gate', webpage):
|
||||
self.raise_login_required('%s is not available yet' % display_id)
|
||||
|
||||
raise ExtractorError('Unable to extract m3u8 URL')
|
||||
try:
|
||||
m3u8_url = self._download_json(
|
||||
api_episode_url + '/videos', display_id,
|
||||
'Downloading video JSON metadata')['data'][0]['attributes']['url']
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
|
||||
self.raise_login_required(
|
||||
'%s is only available for FIRST members' % display_id)
|
||||
raise
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
m3u8_url, display_id, ext='mp4',
|
||||
entry_protocol='m3u8_native', m3u8_id='hls')
|
||||
m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls')
|
||||
self._sort_formats(formats)
|
||||
|
||||
description = strip_or_none(self._og_search_description(webpage))
|
||||
thumbnail = self._proto_relative_url(self._og_search_thumbnail(webpage))
|
||||
episode = self._download_json(
|
||||
api_episode_url, display_id,
|
||||
'Downloading episode JSON metadata')['data'][0]
|
||||
attributes = episode['attributes']
|
||||
title = attributes.get('title') or attributes['display_title']
|
||||
video_id = compat_str(episode['id'])
|
||||
|
||||
series = self._search_regex(
|
||||
(r'<h2>More ([^<]+)</h2>', r'<a[^>]+>See All ([^<]+) Videos<'),
|
||||
webpage, 'series', fatal=False)
|
||||
|
||||
comment_count = int_or_none(self._search_regex(
|
||||
r'>Comments \((\d+)\)<', webpage,
|
||||
'comment count', fatal=False))
|
||||
|
||||
video_id = self._search_regex(
|
||||
(r'containerId\s*=\s*["\']episode-(\d+)\1',
|
||||
r'<div[^<]+id=["\']episode-(\d+)'), webpage,
|
||||
'video id', default=display_id)
|
||||
thumbnails = []
|
||||
for image in episode.get('included', {}).get('images', []):
|
||||
if image.get('type') == 'episode_image':
|
||||
img_attributes = image.get('attributes') or {}
|
||||
for k in ('thumb', 'small', 'medium', 'large'):
|
||||
img_url = img_attributes.get(k)
|
||||
if img_url:
|
||||
thumbnails.append({
|
||||
'id': k,
|
||||
'url': img_url,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'series': series,
|
||||
'episode': episode,
|
||||
'comment_count': comment_count,
|
||||
'description': attributes.get('description') or attributes.get('caption'),
|
||||
'thumbnails': thumbnails,
|
||||
'series': attributes.get('show_title'),
|
||||
'season_number': int_or_none(attributes.get('season_number')),
|
||||
'season_id': attributes.get('season_id'),
|
||||
'episode': title,
|
||||
'episode_number': int_or_none(attributes.get('number')),
|
||||
'episode_id': str_or_none(episode.get('uuid')),
|
||||
'formats': formats,
|
||||
'channel_id': attributes.get('channel_id'),
|
||||
'duration': int_or_none(attributes.get('length')),
|
||||
}
|
||||
|
||||
@ -1,53 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
js_to_json,
|
||||
get_element_by_class,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class RudoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://rudo\.video/vod/(?P<id>[0-9a-zA-Z]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://rudo.video/vod/oTzw0MGnyG',
|
||||
'md5': '2a03a5b32dd90a04c83b6d391cf7b415',
|
||||
'info_dict': {
|
||||
'id': 'oTzw0MGnyG',
|
||||
'ext': 'mp4',
|
||||
'title': 'Comentario Tomás Mosciatti',
|
||||
'upload_date': '20160617',
|
||||
},
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def _extract_url(cls, webpage):
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
|
||||
webpage)
|
||||
if mobj:
|
||||
return mobj.group('url')
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id, encoding='iso-8859-1')
|
||||
|
||||
jwplayer_data = self._parse_json(self._search_regex(
|
||||
r'(?s)playerInstance\.setup\(({.+?})\)', webpage, 'jwplayer data'), video_id,
|
||||
transform_source=lambda s: js_to_json(re.sub(r'encodeURI\([^)]+\)', '""', s)))
|
||||
|
||||
info_dict = self._parse_jwplayer_data(
|
||||
jwplayer_data, video_id, require_title=False, m3u8_id='hls', mpd_id='dash')
|
||||
|
||||
info_dict.update({
|
||||
'title': self._og_search_title(webpage),
|
||||
'upload_date': unified_strdate(get_element_by_class('date', webpage)),
|
||||
})
|
||||
|
||||
return info_dict
|
||||
@ -5,6 +5,7 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
merge_dicts,
|
||||
orderedSet,
|
||||
parse_duration,
|
||||
parse_resolution,
|
||||
@ -26,6 +27,8 @@ class SpankBangIE(InfoExtractor):
|
||||
'description': 'dillion harper masturbates on a bed',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'uploader': 'silly2587',
|
||||
'timestamp': 1422571989,
|
||||
'upload_date': '20150129',
|
||||
'age_limit': 18,
|
||||
}
|
||||
}, {
|
||||
@ -106,31 +109,36 @@ class SpankBangIE(InfoExtractor):
|
||||
|
||||
for format_id, format_url in stream.items():
|
||||
if format_id.startswith(STREAM_URL_PREFIX):
|
||||
if format_url and isinstance(format_url, list):
|
||||
format_url = format_url[0]
|
||||
extract_format(
|
||||
format_id[len(STREAM_URL_PREFIX):], format_url)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
info = self._search_json_ld(webpage, video_id, default={})
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
|
||||
r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title', default=None)
|
||||
description = self._search_regex(
|
||||
r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
|
||||
webpage, 'description', fatal=False)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
uploader = self._search_regex(
|
||||
r'class="user"[^>]*><img[^>]+>([^<]+)',
|
||||
webpage, 'description', default=None)
|
||||
thumbnail = self._og_search_thumbnail(webpage, default=None)
|
||||
uploader = self._html_search_regex(
|
||||
(r'(?s)<li[^>]+class=["\']profile[^>]+>(.+?)</a>',
|
||||
r'class="user"[^>]*><img[^>]+>([^<]+)'),
|
||||
webpage, 'uploader', default=None)
|
||||
duration = parse_duration(self._search_regex(
|
||||
r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
|
||||
webpage, 'duration', fatal=False))
|
||||
webpage, 'duration', default=None))
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))
|
||||
r'([\d,.]+)\s+plays', webpage, 'view count', default=None))
|
||||
|
||||
age_limit = self._rta_search(webpage)
|
||||
|
||||
return {
|
||||
return merge_dicts({
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'title': title or video_id,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
@ -138,7 +146,8 @@ class SpankBangIE(InfoExtractor):
|
||||
'view_count': view_count,
|
||||
'formats': formats,
|
||||
'age_limit': age_limit,
|
||||
}
|
||||
}, info
|
||||
)
|
||||
|
||||
|
||||
class SpankBangPlaylistIE(InfoExtractor):
|
||||
|
||||
@ -22,7 +22,7 @@ class BellatorIE(MTVServicesInfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
_FEED_URL = 'http://www.spike.com/feeds/mrss/'
|
||||
_FEED_URL = 'http://www.bellator.com/feeds/mrss/'
|
||||
_GEO_COUNTRIES = ['US']
|
||||
|
||||
|
||||
|
||||
@ -438,11 +438,22 @@ class TwitterIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True, # requires ffmpeg
|
||||
},
|
||||
}, {
|
||||
'url': 'https://twitter.com/foobar/status/1087791357756956680',
|
||||
'info_dict': {
|
||||
'id': '1087791357756956680',
|
||||
'ext': 'mp4',
|
||||
'title': 'Twitter - A new is coming. Some of you got an opt-in to try it now. Check out the emoji button, quick keyboard shortcuts, upgraded trends, advanced search, and more. Let us know your thoughts!',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'description': 'md5:66d493500c013e3e2d434195746a7f78',
|
||||
'uploader': 'Twitter',
|
||||
'uploader_id': 'Twitter',
|
||||
'duration': 61.567,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
user_id = mobj.group('user_id')
|
||||
twid = mobj.group('id')
|
||||
|
||||
webpage, urlh = self._download_webpage_handle(
|
||||
@ -451,8 +462,13 @@ class TwitterIE(InfoExtractor):
|
||||
if 'twitter.com/account/suspended' in urlh.geturl():
|
||||
raise ExtractorError('Account suspended by Twitter.', expected=True)
|
||||
|
||||
if user_id is None:
|
||||
mobj = re.match(self._VALID_URL, urlh.geturl())
|
||||
user_id = None
|
||||
|
||||
redirect_mobj = re.match(self._VALID_URL, urlh.geturl())
|
||||
if redirect_mobj:
|
||||
user_id = redirect_mobj.group('user_id')
|
||||
|
||||
if not user_id:
|
||||
user_id = mobj.group('user_id')
|
||||
|
||||
username = remove_end(self._og_search_title(webpage), ' on Twitter')
|
||||
|
||||
@ -371,10 +371,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
(?:www\.)?hooktube\.com/|
|
||||
(?:www\.)?yourepeat\.com/|
|
||||
tube\.majestyc\.net/|
|
||||
# Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
|
||||
(?:(?:www|dev)\.)?invidio\.us/|
|
||||
(?:www\.)?invidiou\.sh/|
|
||||
(?:www\.)?invidious\.snopyta\.org/|
|
||||
(?:(?:www|no)\.)?invidiou\.sh/|
|
||||
(?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
|
||||
(?:www\.)?invidious\.kabi\.tk/|
|
||||
(?:www\.)?invidious\.enkirton\.net/|
|
||||
(?:www\.)?invidious\.13ad\.de/|
|
||||
(?:www\.)?tube\.poal\.co/|
|
||||
(?:www\.)?vid\.wxzm\.sx/|
|
||||
youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
|
||||
(?:.*?\#/)? # handle anchor (#/) redirect urls
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user