3 from __future__ import unicode_literals
8 from .common import InfoExtractor
9 from .youtube import YoutubeIE
10 from ..compat import (
11 compat_urllib_parse_unquote,
12 compat_urllib_request,
14 compat_xml_parse_error,
32 from .brightcove import BrightcoveIE
33 from .nbc import NBCSportsVPlayerIE
34 from .ooyala import OoyalaIE
35 from .rutv import RUTVIE
36 from .tvc import TVCIE
37 from .sportbox import SportBoxEmbedIE
38 from .smotri import SmotriIE
39 from .myvi import MyviIE
40 from .condenast import CondeNastIE
41 from .udn import UDNEmbedIE
42 from .senateisvp import SenateISVPIE
43 from .bliptv import BlipTVIE
44 from .svt import SVTIE
45 from .pornhub import PornHubIE
46 from .xhamster import XHamsterEmbedIE
47 from .vimeo import VimeoIE
48 from .dailymotion import DailymotionCloudIE
49 from .onionstudios import OnionStudiosIE
50 from .snagfilms import SnagFilmsEmbedIE
51 from .screenwavemedia import ScreenwaveMediaIE
54 class GenericIE(InfoExtractor):
55 IE_DESC = 'Generic downloader that works on some sites'
59 # Direct link to a video
61 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
62 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
67 'upload_date': '20100513',
70 # Direct link to media delivered compressed (until Accept-Encoding is *)
72 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
73 'md5': '128c42e68b13950268b648275386fc74',
75 'id': 'FictionJunction-Parallel_Hearts',
77 'title': 'FictionJunction-Parallel_Hearts',
78 'upload_date': '20140522',
80 'expected_warnings': [
81 'URL could be a direct video link, returning it as such.'
84 # Direct download with broken HEAD
86 'url': 'http://ai-radio.org:8000/radio.opus',
93 'skip_download': True, # infinite live stream
95 'expected_warnings': [
96 r'501.*Not Implemented'
99 # Direct link with incorrect MIME type
101 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
102 'md5': '4ccbebe5f36706d85221f204d7eb5913',
104 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
105 'id': '5_Lennart_Poettering_-_Systemd',
107 'title': '5_Lennart_Poettering_-_Systemd',
108 'upload_date': '20141120',
110 'expected_warnings': [
111 'URL could be a direct video link, returning it as such.'
116 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
119 'title': 'Zero Punctuation',
120 'description': 're:.*groundbreaking video review series.*'
122 'playlist_mincount': 11,
124 # RSS feed with enclosure
126 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
128 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
130 'upload_date': '20150228',
131 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
134 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
136 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
140 'title': 'Automatics, robotics and biocybernetics',
141 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
142 'formats': 'mincount:16',
143 'subtitles': 'mincount:1',
146 'force_generic_extractor': True,
147 'skip_download': True,
150 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
152 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
157 'formats': 'mincount:1',
160 'skip_download': True,
163 # SMIL from https://www.restudy.dk/video/play/id/1637
165 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
169 'title': 'video_1637',
170 'formats': 'mincount:3',
173 'skip_download': True,
176 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
178 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
180 'id': 'smil-service',
182 'title': 'smil-service',
183 'formats': 'mincount:1',
186 'skip_download': True,
189 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
191 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
195 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
196 'formats': 'mincount:3',
199 'skip_download': True,
202 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
204 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
206 'id': 'mZlp2ctYIUEB',
208 'title': 'Tikibad ontruimd wegens brand',
209 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
210 'thumbnail': 're:^https?://.*\.jpg$',
214 'skip_download': True,
219 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
223 'upload_date': '20130224',
224 'uploader_id': 'TheVerge',
225 'description': 're:^Chris Ziegler takes a look at the\.*',
226 'uploader': 'The Verge',
227 'title': 'First Firefox OS phones side-by-side',
230 'skip_download': False,
234 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
235 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
237 'id': '13601338388002',
239 'uploader': 'www.hodiho.fr',
240 'title': 'R\u00e9gis plante sa Jeep',
243 # bandcamp page with custom domain
245 'add_ie': ['Bandcamp'],
246 'url': 'http://bronyrock.com/track/the-pony-mash',
250 'title': 'The Pony Mash',
251 'uploader': 'M_Pallante',
253 'skip': 'There is a limit of 200 free downloads / month for the test song',
255 # embedded brightcove video
256 # it also tests brightcove videos that need to set the 'Referer' in the
259 'add_ie': ['Brightcove'],
260 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
262 'id': '2765128793001',
264 'title': 'Le cours de bourse : l’analyse technique',
265 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
266 'uploader': 'BFM BUSINESS',
269 'skip_download': True,
273 # https://github.com/rg3/youtube-dl/issues/2253
274 'url': 'http://bcove.me/i6nfkrc3',
275 'md5': '0ba9446db037002366bab3b3eb30c88c',
277 'id': '3101154703001',
279 'title': 'Still no power',
280 'uploader': 'thestar.com',
281 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
283 'add_ie': ['Brightcove'],
286 'url': 'http://www.championat.com/video/football/v/87/87499.html',
287 'md5': 'fb973ecf6e4a78a67453647444222983',
289 'id': '3414141473001',
291 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
292 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
293 'uploader': 'Championat',
297 # https://github.com/rg3/youtube-dl/issues/3541
298 'add_ie': ['Brightcove'],
299 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
301 'id': '3866516442001',
303 'title': 'Leer mij vrouwen kennen: Aflevering 1',
304 'description': 'Leer mij vrouwen kennen: Aflevering 1',
305 'uploader': 'SBS Broadcasting',
307 'skip': 'Restricted to Netherlands',
309 'skip_download': True, # m3u8 download
314 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
315 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
317 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
319 'title': '2cc213299525360.mov', # that's what we get
321 'add_ie': ['Ooyala'],
324 # ooyala video embedded with http://player.ooyala.com/iframe.js
325 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
327 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
329 'title': '"Steve Jobs: Man in the Machine" trailer',
330 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
333 'skip_download': True,
336 # multiple ooyala embeds on SBN network websites
338 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
340 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
341 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
343 'playlist_mincount': 3,
345 'skip_download': True,
347 'add_ie': ['Ooyala'],
351 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
355 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
356 'upload_date': '20140225',
357 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
358 'uploader': 'Tested',
359 'uploader_id': 'testedcom',
361 # No need to test YoutubeIE here
363 'skip_download': True,
368 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
372 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
373 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
378 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
382 'title': 'Охотское море стало целиком российским',
383 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
387 'skip_download': True,
392 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
396 'title': 'Дошкольное воспитание',
401 'url': 'http://www.vestifinance.ru/articles/25753',
404 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
409 'title': 'Госзаказ. День 3',
415 'title': 'Госзаказ. День 2',
421 'title': 'Госзаказ. День 1',
427 'skip_download': True,
432 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
434 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
436 'title': 'Ужастики, русский трейлер (2015)',
437 'thumbnail': 're:^https?://.*\.jpg$',
443 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
446 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
448 'playlist_mincount': 7,
452 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
453 'md5': '65fdff94098e4a607385a60c5177c638',
457 'title': 'Hidden miracles of the natural world',
458 'uploader': 'Louie Schwartzberg',
459 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
462 # Embeded Ustream video
464 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
465 'md5': '27b99cdb639c9b12a79bca876a073417',
469 'uploader': 'AU SPA: The NSA and Privacy',
470 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
473 # nowvideo embed hidden behind percent encoding
475 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
476 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
478 'id': '06e53103ca9aa',
480 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
481 'description': 'No description',
486 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
487 'md5': '7653032cbb25bf6c80d80f217055fa43',
489 'id': '048195-004_PLUS7-F',
492 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
493 'upload_date': '20140320',
496 'skip_download': 'Requires rtmpdump'
501 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
505 'title': 'Alcaline, le concert avec Calogero',
506 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
507 'upload_date': '20150226',
508 'timestamp': 1424989860,
513 'skip_download': True,
515 'expected_warnings': [
521 'url': 'http://www.wired.com/2014/04/honda-asimo/',
522 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
524 'id': '53501be369702d3275860000',
526 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
531 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
532 'md5': '441aeeb82eb72c422c7f14ec533999cd',
534 'id': 'k2mm4bCdJ6CQ2i7c8o2',
536 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
539 'add_ie': ['Dailymotion'],
543 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
547 'title': 'The NBL Auction 2014',
548 'uploader': 'BADMINTON England',
549 'uploader_id': 'BADMINTONEvents',
550 'upload_date': '20140603',
551 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
553 'add_ie': ['Youtube'],
555 'skip_download': True,
560 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
561 'md5': '35727f82f58c76d996fc188f9755b0d5',
563 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
566 'description': 'Mario\'s life in the fast lane has never looked so good.',
569 # YouTube embed via <data-embed-url="">
571 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
575 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
576 'uploader': 'Gameloft',
577 'uploader_id': 'gameloft',
578 'upload_date': '20140828',
579 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
582 'skip_download': True,
587 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
589 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
591 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
592 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
597 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
599 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
600 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
606 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
611 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
612 'md5': '9d65602bf31c6e20014319c7d07fba27',
614 'id': '5123ea6d5e5a7',
617 'uploader': 'www.handjobhub.com',
618 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
621 # Multiple brightcove videos
622 # https://github.com/rg3/youtube-dl/issues/2283
624 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
626 'id': 'always-never',
627 'title': 'Always / Never - The New Yorker',
631 'extract_flat': False,
632 'skip_download': True,
637 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
638 'md5': '96f09a37e44da40dd083e12d9a683327',
642 'title': 'Ump changes call to ball',
643 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
645 'timestamp': 1401537900,
646 'upload_date': '20140531',
647 'thumbnail': 're:^https?://.*\.jpg$',
652 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
653 'md5': '8788b683c777a5cf25621eaf286d0c23',
657 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
659 'filesize': 182808282,
660 'uploader': 'education-portal.com',
664 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
665 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
669 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
671 'uploader': 'thoughtworks.wistia.com',
676 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
680 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
681 'uploader': 'Sophos Security',
682 'title': 'Chet Chat 171 - Oct 29, 2014',
683 'upload_date': '20141029',
688 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
692 'upload_date': '20141112',
693 'title': 'Rosetta #CometLanding webcast HL 10',
698 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
701 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
703 'playlist_mincount': 2,
707 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
711 'upload_date': '20141126',
712 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
717 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
719 'id': '730m_DandD_1901_512k',
721 'uploader': 'www.abc.net.au',
722 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
725 # embedded viddler video
727 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
731 'uploader': 'deadspin',
732 'title': 'WALL-TO-GORTAT',
733 'timestamp': 1422285291,
734 'upload_date': '20150126',
736 'add_ie': ['Viddler'],
740 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
744 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
745 'description': 'md5:601cb790edd05908957dae8aaa866465',
746 'upload_date': '20150220',
751 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
755 'upload_date': '20150212',
756 'uploader': 'The National Archives UK',
757 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
758 'uploader_id': 'NationalArchives08',
759 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
764 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
765 'playlist_mincount': 5,
767 'id': 'aanslagen-kopenhagen',
768 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
773 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
777 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
782 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
786 'upload_date': '20150226',
787 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
789 'title': 'John Carlson Postgame 2/25/15',
792 # Kaltura embed (different embed code)
794 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
798 'upload_date': '20150127',
799 'uploader_id': 'PremierMedia',
801 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
804 # Eagle.Platform embed (generic URL)
806 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
810 'title': 'Навальный вышел на свободу',
811 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
812 'thumbnail': 're:^https?://.*\.jpg$',
818 # ClipYou (Eagle.Platform) embed (custom URL)
820 'url': 'http://muz-tv.ru/play/7129/',
824 'title': "'O Sole Mio",
825 'thumbnail': 're:^https?://.*\.jpg$',
832 'url': 'http://muz-tv.ru/kinozal/view/7400/',
836 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
837 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
838 'thumbnail': 're:^https?://.*\.jpg$',
845 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
849 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
850 'thumbnail': 're:^https?://.*\.png$',
856 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
857 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
861 'title': 'Facebook Creates "On This Day" | Crunch Report',
866 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
870 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
875 # Crooks and Liars embed
877 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
881 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
882 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
883 'timestamp': 1428207000,
884 'upload_date': '20150405',
885 'uploader': 'Heather',
888 # Crooks and Liars external embed
890 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
892 'id': 'MTE3MjUtMzQ2MzA',
894 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
895 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
896 'timestamp': 1265032391,
897 'upload_date': '20100201',
898 'uploader': 'Heather',
901 # NBC Sports vplayer embed
903 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
905 'id': 'ln7x1qSThw4k',
907 'title': "PFT Live: New leader in the 'new-look' defense",
908 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
913 'url': 'http://www.udn.com/news/story/7314/822787',
914 'md5': 'fd2060e988c326991037b9aff9df21a6',
918 'title': '中一中男師變性 全校師生力挺',
919 'thumbnail': 're:^https?://.*\.jpg$',
924 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
926 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
928 'description': 'VIDEO: Index/Match versus VLOOKUP.',
929 'title': 'This is what separates the Excel masters from the wannabes',
933 'skip_download': True,
936 # Contains a SMIL manifest
938 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
942 'title': '+ Football: Lottery Champions League Europe',
943 'uploader': 'www.telewebion.com',
947 'skip_download': True,
950 # Brightcove URL in single quotes
952 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
953 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
955 'id': '4255764656001',
957 'title': 'SN Presents: Russell Martin, World Citizen',
958 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
959 'uploader': 'Rogers Sportsnet',
962 # Dailymotion Cloud video
964 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
965 'md5': '49444254273501a64675a7e68c502681',
967 'id': '5585de919473990de4bee11b',
970 'thumbnail': 're:^https?://.*\.jpe?g$',
975 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
979 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
980 'thumbnail': 're:^https?://.*\.jpe?g$',
981 'uploader': 'ClickHole',
982 'uploader_id': 'clickhole',
987 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
989 'id': '74849a00-85a9-11e1-9660-123139220831',
991 'title': '#whilewewatch',
996 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
997 'md5': '43662b577c018ad707a63766462b1e87',
1001 'title': 'New experience with Acrobat DC',
1002 'description': 'New experience with Acrobat DC',
1003 'duration': 248.667,
1006 # ScreenwaveMedia embed
1008 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1009 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1011 'id': 'cinemasnob-55d26273809dd',
1013 'title': 'cinemasnob',
1018 def report_following_redirect(self, new_url):
1019 """Report information extraction."""
1020 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1022 def _extract_rss(self, url, video_id, doc):
1023 playlist_title = doc.find('./channel/title').text
1024 playlist_desc_el = doc.find('./channel/description')
1025 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1028 for it in doc.findall('./channel/item'):
1029 next_url = xpath_text(it, 'link', fatal=False)
1031 enclosure_nodes = it.findall('./enclosure')
1032 for e in enclosure_nodes:
1033 next_url = e.attrib.get('url')
1043 'title': it.find('title').text,
1047 '_type': 'playlist',
1049 'title': playlist_title,
1050 'description': playlist_desc,
1054 def _extract_camtasia(self, url, video_id, webpage):
1055 """ Returns None if no camtasia video can be found. """
1057 camtasia_cfg = self._search_regex(
1058 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1059 webpage, 'camtasia configuration file', default=None)
1060 if camtasia_cfg is None:
1063 title = self._html_search_meta('DC.title', webpage, fatal=True)
1065 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1066 camtasia_cfg = self._download_xml(
1067 camtasia_url, video_id,
1068 note='Downloading camtasia configuration',
1069 errnote='Failed to download camtasia configuration')
1070 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1073 for n in fileset_node.getchildren():
1074 url_n = n.find('./uri')
1079 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1080 'title': '%s - %s' % (title, n.tag),
1081 'url': compat_urlparse.urljoin(url, url_n.text),
1082 'duration': float_or_none(n.find('./duration').text),
1086 '_type': 'playlist',
1091 def _real_extract(self, url):
1092 if url.startswith('//'):
1095 'url': self.http_scheme() + url,
1098 parsed_url = compat_urlparse.urlparse(url)
1099 if not parsed_url.scheme:
1100 default_search = self._downloader.params.get('default_search')
1101 if default_search is None:
1102 default_search = 'fixup_error'
1104 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1106 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1107 return self.url_result('http://' + url)
1108 elif default_search != 'fixup_error':
1109 if default_search == 'auto_warning':
1110 if re.match(r'^(?:url|URL)$', url):
1111 raise ExtractorError(
1112 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1115 self._downloader.report_warning(
1116 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1117 return self.url_result('ytsearch:' + url)
1119 if default_search in ('error', 'fixup_error'):
1120 raise ExtractorError(
1121 '%r is not a valid URL. '
1122 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1123 % (url, url), expected=True)
1125 if ':' not in default_search:
1126 default_search += ':'
1127 return self.url_result(default_search + url)
1129 url, smuggled_data = unsmuggle_url(url)
1130 force_videoid = None
1131 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1132 if smuggled_data and 'force_videoid' in smuggled_data:
1133 force_videoid = smuggled_data['force_videoid']
1134 video_id = force_videoid
1136 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1138 self.to_screen('%s: Requesting header' % video_id)
1140 head_req = HEADRequest(url)
1141 head_response = self._request_webpage(
1143 note=False, errnote='Could not send HEAD request to %s' % url,
1146 if head_response is not False:
1147 # Check for redirect
1148 new_url = head_response.geturl()
1150 self.report_following_redirect(new_url)
1152 new_url = smuggle_url(
1153 new_url, {'force_videoid': force_videoid})
1154 return self.url_result(new_url)
1156 full_response = None
1157 if head_response is False:
1158 request = compat_urllib_request.Request(url)
1159 request.add_header('Accept-Encoding', '*')
1160 full_response = self._request_webpage(request, video_id)
1161 head_response = full_response
1163 # Check for direct link to a video
1164 content_type = head_response.headers.get('Content-Type', '')
1165 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1167 upload_date = unified_strdate(
1168 head_response.headers.get('Last-Modified'))
1171 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1174 'format_id': m.group('format_id'),
1176 'vcodec': 'none' if m.group('type') == 'audio' else None
1178 'upload_date': upload_date,
1181 if not self._downloader.params.get('test', False) and not is_intentional:
1182 force = self._downloader.params.get('force_generic_extractor', False)
1183 self._downloader.report_warning(
1184 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1186 if not full_response:
1187 request = compat_urllib_request.Request(url)
1188 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1189 # making it impossible to download only chunk of the file (yet we need only 512kB to
1190 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1191 # that will always result in downloading the whole file that is not desirable.
1192 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1193 # to accept raw bytes and being able to download only a chunk.
1194 # It may probably better to solve this by checking Content-Type for application/octet-stream
1195 # after HEAD request finishes, but not sure if we can rely on this.
1196 request.add_header('Accept-Encoding', '*')
1197 full_response = self._request_webpage(request, video_id)
1199 # Maybe it's a direct link to a video?
1200 # Be careful not to download the whole thing!
1201 first_bytes = full_response.read(512)
1202 if not is_html(first_bytes):
1203 self._downloader.report_warning(
1204 'URL could be a direct video link, returning it as such.')
1205 upload_date = unified_strdate(
1206 head_response.headers.get('Last-Modified'))
1209 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1212 'upload_date': upload_date,
1215 webpage = self._webpage_read_content(
1216 full_response, url, video_id, prefix=first_bytes)
1218 self.report_extraction(video_id)
1220 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1222 doc = parse_xml(webpage)
1223 if doc.tag == 'rss':
1224 return self._extract_rss(url, video_id, doc)
1225 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1226 return self._parse_smil(doc, url, video_id)
1227 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1228 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1229 except compat_xml_parse_error:
1232 # Is it a Camtasia project?
1233 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1234 if camtasia_res is not None:
1237 # Sometimes embedded video player is hidden behind percent encoding
1238 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1239 # Unescaping the whole page allows to handle those cases in a generic way
1240 webpage = compat_urllib_parse_unquote(webpage)
1242 # it's tempting to parse this further, but you would
1243 # have to take into account all the variations like
1244 # Video Title - Site Name
1245 # Site Name | Video Title
1246 # Video Title - Tagline | Site Name
1247 # and so on and so forth; it's just not practical
1248 video_title = self._html_search_regex(
1249 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1252 # Try to detect age limit automatically
1253 age_limit = self._rta_search(webpage)
1254 # And then there are the jokers who advertise that they use RTA,
1255 # but actually don't.
1256 AGE_LIMIT_MARKERS = [
1257 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1259 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1262 # video uploader is domain name
1263 video_uploader = self._search_regex(
1264 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1267 def _playlist_from_matches(matches, getter=None, ie=None):
1269 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1271 return self.playlist_result(
1272 urlrs, playlist_id=video_id, playlist_title=video_title)
1274 # Look for BrightCove:
1275 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1277 self.to_screen('Brightcove video detected.')
1280 'url': smuggle_url(bc_url, {'Referer': url}),
1281 'ie_key': 'Brightcove'
1282 } for bc_url in bc_urls]
1285 '_type': 'playlist',
1286 'title': video_title,
1291 # Look for embedded rtl.nl player
1292 matches = re.findall(
1293 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1296 return _playlist_from_matches(matches, ie='RtlNl')
1298 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1299 if vimeo_url is not None:
1300 return self.url_result(vimeo_url)
1302 vid_me_embed_url = self._search_regex(
1303 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1304 webpage, 'vid.me embed', default=None)
1305 if vid_me_embed_url is not None:
1306 return self.url_result(vid_me_embed_url, 'Vidme')
1308 # Look for embedded YouTube player
1309 matches = re.findall(r'''(?x)
1318 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1322 return _playlist_from_matches(
1323 matches, lambda m: unescapeHTML(m[1]))
1325 # Look for lazyYT YouTube embed
1326 matches = re.findall(
1327 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1329 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1331 # Look for embedded Dailymotion player
1332 matches = re.findall(
1333 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1335 return _playlist_from_matches(
1336 matches, lambda m: unescapeHTML(m[1]))
1338 # Look for embedded Dailymotion playlist player (#3822)
1340 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1342 playlists = re.findall(
1343 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1345 return _playlist_from_matches(
1346 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1348 # Look for embedded Wistia player
1350 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1352 embed_url = self._proto_relative_url(
1353 unescapeHTML(match.group('url')))
1355 '_type': 'url_transparent',
1358 'uploader': video_uploader,
1359 'title': video_title,
1363 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1366 '_type': 'url_transparent',
1367 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1369 'uploader': video_uploader,
1370 'title': video_title,
1371 'id': match.group('id')
1374 # Look for embedded blip.tv player
1375 bliptv_url = BlipTVIE._extract_url(webpage)
1377 return self.url_result(bliptv_url, 'BlipTV')
1379 # Look for SVT player
1380 svt_url = SVTIE._extract_url(webpage)
1382 return self.url_result(svt_url, 'SVT')
1384 # Look for embedded condenast player
1385 matches = re.findall(
1386 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1390 '_type': 'playlist',
1393 'ie_key': 'CondeNast',
1395 } for ma in matches],
1396 'title': video_title,
1400 # Look for Bandcamp pages with custom domain
1401 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1402 if mobj is not None:
1403 burl = unescapeHTML(mobj.group(1))
1404 # Don't set the extractor because it can be a track url or an album
1405 return self.url_result(burl)
1407 # Look for embedded Vevo player
1409 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1410 if mobj is not None:
1411 return self.url_result(mobj.group('url'))
1413 # Look for embedded Viddler player
1415 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1417 if mobj is not None:
1418 return self.url_result(mobj.group('url'))
1420 # Look for NYTimes player
1422 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1424 if mobj is not None:
1425 return self.url_result(mobj.group('url'))
1427 # Look for Libsyn player
1429 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1430 if mobj is not None:
1431 return self.url_result(mobj.group('url'))
1433 # Look for Ooyala videos
1434 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1435 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1436 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1437 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1438 if mobj is not None:
1439 return OoyalaIE._build_url_result(mobj.group('ec'))
1441 # Look for multiple Ooyala embeds on SBN network websites
1442 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1443 if mobj is not None:
1444 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1446 return _playlist_from_matches(
1447 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1449 # Look for Aparat videos
1450 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1451 if mobj is not None:
1452 return self.url_result(mobj.group(1), 'Aparat')
1454 # Look for MPORA videos
1455 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1456 if mobj is not None:
1457 return self.url_result(mobj.group(1), 'Mpora')
1459 # Look for embedded NovaMov-based player
1461 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1462 (?P<url>http://(?:(?:embed|www)\.)?
1464 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1465 videoweed\.(?:es|com)|
1466 movshare\.(?:net|sx|ag)|
1467 divxstage\.(?:eu|net|ch|co|at|ag))
1468 /embed\.php.+?)\1''', webpage)
1469 if mobj is not None:
1470 return self.url_result(mobj.group('url'))
1472 # Look for embedded Facebook player
1474 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1475 if mobj is not None:
1476 return self.url_result(mobj.group('url'), 'Facebook')
1478 # Look for embedded VK player
1479 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1480 if mobj is not None:
1481 return self.url_result(mobj.group('url'), 'VK')
1483 # Look for embedded ivi player
1484 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1485 if mobj is not None:
1486 return self.url_result(mobj.group('url'), 'Ivi')
1488 # Look for embedded Huffington Post player
1490 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1491 if mobj is not None:
1492 return self.url_result(mobj.group('url'), 'HuffPost')
1495 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1496 if mobj is not None:
1497 return self.url_result(mobj.group('url'))
1498 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1499 if mobj is not None:
1500 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1502 # Look for funnyordie embed
1503 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1505 return _playlist_from_matches(
1506 matches, getter=unescapeHTML, ie='FunnyOrDie')
1508 # Look for BBC iPlayer embed
1509 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1511 return _playlist_from_matches(matches, ie='BBCCoUk')
1513 # Look for embedded RUTV player
1514 rutv_url = RUTVIE._extract_url(webpage)
1516 return self.url_result(rutv_url, 'RUTV')
1518 # Look for embedded TVC player
1519 tvc_url = TVCIE._extract_url(webpage)
1521 return self.url_result(tvc_url, 'TVC')
1523 # Look for embedded SportBox player
1524 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1526 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1528 # Look for embedded PornHub player
1529 pornhub_url = PornHubIE._extract_url(webpage)
1531 return self.url_result(pornhub_url, 'PornHub')
1533 # Look for embedded XHamster player
1534 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1536 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1538 # Look for embedded Tvigle player
1540 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1541 if mobj is not None:
1542 return self.url_result(mobj.group('url'), 'Tvigle')
1544 # Look for embedded TED player
1546 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1547 if mobj is not None:
1548 return self.url_result(mobj.group('url'), 'TED')
1550 # Look for embedded Ustream videos
1552 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1553 if mobj is not None:
1554 return self.url_result(mobj.group('url'), 'Ustream')
1556 # Look for embedded arte.tv player
1558 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1560 if mobj is not None:
1561 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1563 # Look for embedded francetv player
1565 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1567 if mobj is not None:
1568 return self.url_result(mobj.group('url'))
1570 # Look for embedded smotri.com player
1571 smotri_url = SmotriIE._extract_url(webpage)
1573 return self.url_result(smotri_url, 'Smotri')
1575 # Look for embedded Myvi.ru player
1576 myvi_url = MyviIE._extract_url(webpage)
1578 return self.url_result(myvi_url)
1580 # Look for embeded soundcloud player
1582 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1584 if mobj is not None:
1585 url = unescapeHTML(mobj.group('url'))
1586 return self.url_result(url)
1588 # Look for embedded vulture.com player
1590 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1592 if mobj is not None:
1593 url = unescapeHTML(mobj.group('url'))
1594 return self.url_result(url, ie='Vulture')
1596 # Look for embedded mtvservices player
1598 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1600 if mobj is not None:
1601 url = unescapeHTML(mobj.group('url'))
1602 return self.url_result(url, ie='MTVServicesEmbedded')
1604 # Look for embedded yahoo player
1606 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1608 if mobj is not None:
1609 return self.url_result(mobj.group('url'), 'Yahoo')
1611 # Look for embedded sbs.com.au player
1615 <meta\s+property="og:video"\s+content=|
1618 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1620 if mobj is not None:
1621 return self.url_result(mobj.group('url'), 'SBS')
1623 # Look for embedded Cinchcast player
1625 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1627 if mobj is not None:
1628 return self.url_result(mobj.group('url'), 'Cinchcast')
1631 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1635 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1637 if mobj is not None:
1638 return self.url_result(mobj.group('url'), 'MLB')
1641 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1643 if mobj is not None:
1644 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1647 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1649 if mobj is not None:
1650 return self.url_result(mobj.group('url'), 'Livestream')
1652 # Look for Zapiks embed
1654 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1655 if mobj is not None:
1656 return self.url_result(mobj.group('url'), 'Zapiks')
1658 # Look for Kaltura embeds
1659 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1660 re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
1661 if mobj is not None:
1662 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1664 # Look for Eagle.Platform embeds
1666 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1667 if mobj is not None:
1668 return self.url_result(mobj.group('url'), 'EaglePlatform')
1670 # Look for ClipYou (uses Eagle.Platform) embeds
1672 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1673 if mobj is not None:
1674 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1676 # Look for Pladform embeds
1678 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1679 if mobj is not None:
1680 return self.url_result(mobj.group('url'), 'Pladform')
1682 # Look for Playwire embeds
1684 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1685 if mobj is not None:
1686 return self.url_result(mobj.group('url'))
1688 # Look for 5min embeds
1690 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1691 if mobj is not None:
1692 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1694 # Look for Crooks and Liars embeds
1696 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'))
1700 # Look for NBC Sports VPlayer embeds
1701 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1703 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1705 # Look for UDN embeds
1707 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1708 if mobj is not None:
1709 return self.url_result(
1710 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1712 # Look for Senate ISVP iframe
1713 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1715 return self.url_result(senate_isvp_url, 'SenateISVP')
1717 # Look for Dailymotion Cloud videos
1718 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1720 return self.url_result(dmcloud_url, 'DailymotionCloud')
1722 # Look for OnionStudios embeds
1723 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1724 if onionstudios_url:
1725 return self.url_result(onionstudios_url)
1727 # Look for SnagFilms embeds
1728 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1730 return self.url_result(snagfilms_url)
1732 # Look for ScreenwaveMedia embeds
1733 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1734 if mobj is not None:
1735 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1737 # Look for AdobeTVVideo embeds
1739 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1741 if mobj is not None:
1742 return self.url_result(
1743 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1746 def check_video(vurl):
1747 if YoutubeIE.suitable(vurl):
1749 vpath = compat_urlparse.urlparse(vurl).path
1750 vext = determine_ext(vpath)
1751 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1753 def filter_video(urls):
1754 return list(filter(check_video, urls))
1756 # Start with something easy: JW Player in SWFObject
1757 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1759 # Look for gorilla-vid style embedding
1760 found = filter_video(re.findall(r'''(?sx)
1764 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1767 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1769 # Broaden the search a little bit
1770 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1772 # Broaden the findall a little bit: JWPlayer JS loader
1773 found = filter_video(re.findall(
1774 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1777 found = filter_video(re.findall(r'''(?xs)
1778 flowplayer\("[^"]+",\s*
1780 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1781 ["']?url["']?\s*:\s*["']([^"']+)["']
1786 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1788 # Try to find twitter cards info
1789 found = filter_video(re.findall(
1790 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1792 # We look for Open Graph info:
1793 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1794 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1795 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1796 if m_video_type is not None:
1797 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1800 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1802 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1804 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1805 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1808 # Look also in Refresh HTTP header
1809 refresh_header = head_response.headers.get('Refresh')
1811 found = re.search(REDIRECT_REGEX, refresh_header)
1813 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1814 self.report_following_redirect(new_url)
1820 raise UnsupportedError(url)
1823 for video_url in found:
1824 video_url = compat_urlparse.urljoin(url, video_url)
1825 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1827 # Sometimes, jwplayer extraction will result in a YouTube URL
1828 if YoutubeIE.suitable(video_url):
1829 entries.append(self.url_result(video_url, 'Youtube'))
1832 # here's a fun little line of code for you:
1833 video_id = os.path.splitext(video_id)[0]
1835 ext = determine_ext(video_url)
1839 'formats': self._extract_smil_formats(video_url, video_id),
1840 'uploader': video_uploader,
1841 'title': video_title,
1842 'age_limit': age_limit,
1845 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1850 'uploader': video_uploader,
1851 'title': video_title,
1852 'age_limit': age_limit,
1855 if len(entries) == 1:
1858 for num, e in enumerate(entries, start=1):
1859 # 'url' results don't have a title
1860 if e.get('title') is not None:
1861 e['title'] = '%s (%d)' % (e['title'], num)
1863 '_type': 'playlist',