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
53 class GenericIE(InfoExtractor):
54 IE_DESC = 'Generic downloader that works on some sites'
58 # Direct link to a video
60 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
61 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
66 'upload_date': '20100513',
69 # Direct link to media delivered compressed (until Accept-Encoding is *)
71 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
72 'md5': '128c42e68b13950268b648275386fc74',
74 'id': 'FictionJunction-Parallel_Hearts',
76 'title': 'FictionJunction-Parallel_Hearts',
77 'upload_date': '20140522',
79 'expected_warnings': [
80 'URL could be a direct video link, returning it as such.'
83 # Direct download with broken HEAD
85 'url': 'http://ai-radio.org:8000/radio.opus',
92 'skip_download': True, # infinite live stream
94 'expected_warnings': [
95 r'501.*Not Implemented'
98 # Direct link with incorrect MIME type
100 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
101 'md5': '4ccbebe5f36706d85221f204d7eb5913',
103 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
104 'id': '5_Lennart_Poettering_-_Systemd',
106 'title': '5_Lennart_Poettering_-_Systemd',
107 'upload_date': '20141120',
109 'expected_warnings': [
110 'URL could be a direct video link, returning it as such.'
115 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
117 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
118 'title': 'Zero Punctuation',
119 'description': 're:.*groundbreaking video review series.*'
121 'playlist_mincount': 11,
123 # RSS feed with enclosure
125 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
127 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
129 'upload_date': '20150228',
130 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
133 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
135 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
139 'title': 'Automatics, robotics and biocybernetics',
140 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
141 'formats': 'mincount:16',
142 'subtitles': 'mincount:1',
145 'force_generic_extractor': True,
146 'skip_download': True,
149 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
151 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
156 'formats': 'mincount:1',
159 'skip_download': True,
162 # SMIL from https://www.restudy.dk/video/play/id/1637
164 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
168 'title': 'video_1637',
169 'formats': 'mincount:3',
172 'skip_download': True,
175 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
177 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
179 'id': 'smil-service',
181 'title': 'smil-service',
182 'formats': 'mincount:1',
185 'skip_download': True,
188 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
190 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
194 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
195 'formats': 'mincount:3',
198 'skip_download': True,
203 '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',
207 'upload_date': '20130224',
208 'uploader_id': 'TheVerge',
209 'description': 're:^Chris Ziegler takes a look at the\.*',
210 'uploader': 'The Verge',
211 'title': 'First Firefox OS phones side-by-side',
214 'skip_download': False,
218 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
219 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
221 'id': '13601338388002',
223 'uploader': 'www.hodiho.fr',
224 'title': 'R\u00e9gis plante sa Jeep',
227 # bandcamp page with custom domain
229 'add_ie': ['Bandcamp'],
230 'url': 'http://bronyrock.com/track/the-pony-mash',
234 'title': 'The Pony Mash',
235 'uploader': 'M_Pallante',
237 'skip': 'There is a limit of 200 free downloads / month for the test song',
239 # embedded brightcove video
240 # it also tests brightcove videos that need to set the 'Referer' in the
243 'add_ie': ['Brightcove'],
244 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
246 'id': '2765128793001',
248 'title': 'Le cours de bourse : l’analyse technique',
249 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
250 'uploader': 'BFM BUSINESS',
253 'skip_download': True,
257 # https://github.com/rg3/youtube-dl/issues/2253
258 'url': 'http://bcove.me/i6nfkrc3',
259 'md5': '0ba9446db037002366bab3b3eb30c88c',
261 'id': '3101154703001',
263 'title': 'Still no power',
264 'uploader': 'thestar.com',
265 '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.',
267 'add_ie': ['Brightcove'],
270 'url': 'http://www.championat.com/video/football/v/87/87499.html',
271 'md5': 'fb973ecf6e4a78a67453647444222983',
273 'id': '3414141473001',
275 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
276 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
277 'uploader': 'Championat',
281 # https://github.com/rg3/youtube-dl/issues/3541
282 'add_ie': ['Brightcove'],
283 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
285 'id': '3866516442001',
287 'title': 'Leer mij vrouwen kennen: Aflevering 1',
288 'description': 'Leer mij vrouwen kennen: Aflevering 1',
289 'uploader': 'SBS Broadcasting',
291 'skip': 'Restricted to Netherlands',
293 'skip_download': True, # m3u8 download
298 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
299 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
301 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
303 'title': '2cc213299525360.mov', # that's what we get
305 'add_ie': ['Ooyala'],
308 # ooyala video embedded with http://player.ooyala.com/iframe.js
309 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
311 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
313 'title': '"Steve Jobs: Man in the Machine" trailer',
314 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
317 'skip_download': True,
320 # multiple ooyala embeds on SBN network websites
322 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
324 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
325 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
327 'playlist_mincount': 3,
329 'skip_download': True,
331 'add_ie': ['Ooyala'],
335 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
339 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
340 'upload_date': '20140225',
341 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
342 'uploader': 'Tested',
343 'uploader_id': 'testedcom',
345 # No need to test YoutubeIE here
347 'skip_download': True,
352 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
356 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
357 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
362 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
366 'title': 'Охотское море стало целиком российским',
367 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
371 'skip_download': True,
376 '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/',
380 'title': 'Дошкольное воспитание',
385 'url': 'http://www.vestifinance.ru/articles/25753',
388 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
393 'title': 'Госзаказ. День 3',
399 'title': 'Госзаказ. День 2',
405 'title': 'Госзаказ. День 1',
411 'skip_download': True,
416 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
418 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
420 'title': 'Ужастики, русский трейлер (2015)',
421 'thumbnail': 're:^https?://.*\.jpg$',
427 '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',
430 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
432 'playlist_mincount': 7,
436 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
437 'md5': '65fdff94098e4a607385a60c5177c638',
441 'title': 'Hidden miracles of the natural world',
442 'uploader': 'Louie Schwartzberg',
443 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
446 # Embeded Ustream video
448 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
449 'md5': '27b99cdb639c9b12a79bca876a073417',
453 'uploader': 'AU SPA: The NSA and Privacy',
454 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
457 # nowvideo embed hidden behind percent encoding
459 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
460 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
462 'id': '06e53103ca9aa',
464 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
465 'description': 'No description',
470 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
471 'md5': '7653032cbb25bf6c80d80f217055fa43',
473 'id': '048195-004_PLUS7-F',
476 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
477 'upload_date': '20140320',
480 'skip_download': 'Requires rtmpdump'
485 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
489 'title': 'Alcaline, le concert avec Calogero',
490 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
491 'upload_date': '20150226',
492 'timestamp': 1424989860,
497 'skip_download': True,
499 'expected_warnings': [
505 'url': 'http://www.wired.com/2014/04/honda-asimo/',
506 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
508 'id': '53501be369702d3275860000',
510 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
515 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
516 'md5': '441aeeb82eb72c422c7f14ec533999cd',
518 'id': 'k2mm4bCdJ6CQ2i7c8o2',
520 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
523 'add_ie': ['Dailymotion'],
527 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
531 'title': 'The NBL Auction 2014',
532 'uploader': 'BADMINTON England',
533 'uploader_id': 'BADMINTONEvents',
534 'upload_date': '20140603',
535 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
537 'add_ie': ['Youtube'],
539 'skip_download': True,
544 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
545 'md5': '35727f82f58c76d996fc188f9755b0d5',
547 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
550 'description': 'Mario\'s life in the fast lane has never looked so good.',
553 # YouTube embed via <data-embed-url="">
555 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
559 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
560 'uploader': 'Gameloft',
561 'uploader_id': 'gameloft',
562 'upload_date': '20140828',
563 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
566 'skip_download': True,
571 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
573 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
575 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
576 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
581 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
583 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
584 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
590 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
595 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
596 'md5': '9d65602bf31c6e20014319c7d07fba27',
598 'id': '5123ea6d5e5a7',
601 'uploader': 'www.handjobhub.com',
602 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
605 # Multiple brightcove videos
606 # https://github.com/rg3/youtube-dl/issues/2283
608 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
610 'id': 'always-never',
611 'title': 'Always / Never - The New Yorker',
615 'extract_flat': False,
616 'skip_download': True,
621 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
622 'md5': '96f09a37e44da40dd083e12d9a683327',
626 'title': 'Ump changes call to ball',
627 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
629 'timestamp': 1401537900,
630 'upload_date': '20140531',
631 'thumbnail': 're:^https?://.*\.jpg$',
636 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
637 'md5': '8788b683c777a5cf25621eaf286d0c23',
641 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
643 'filesize': 182808282,
644 'uploader': 'education-portal.com',
648 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
649 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
653 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
655 'uploader': 'thoughtworks.wistia.com',
660 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
664 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
665 'uploader': 'Sophos Security',
666 'title': 'Chet Chat 171 - Oct 29, 2014',
667 'upload_date': '20141029',
672 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
676 'upload_date': '20141112',
677 'title': 'Rosetta #CometLanding webcast HL 10',
682 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
685 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
687 'playlist_mincount': 2,
691 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
695 'upload_date': '20141126',
696 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
701 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
703 'id': '730m_DandD_1901_512k',
705 'uploader': 'www.abc.net.au',
706 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
709 # embedded viddler video
711 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
715 'uploader': 'deadspin',
716 'title': 'WALL-TO-GORTAT',
717 'timestamp': 1422285291,
718 'upload_date': '20150126',
720 'add_ie': ['Viddler'],
724 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
728 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
729 'description': 'md5:601cb790edd05908957dae8aaa866465',
730 'upload_date': '20150220',
735 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
739 'upload_date': '20150212',
740 'uploader': 'The National Archives UK',
741 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
742 'uploader_id': 'NationalArchives08',
743 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
748 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
749 'playlist_mincount': 5,
751 'id': 'aanslagen-kopenhagen',
752 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
757 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
761 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
766 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
770 'upload_date': '20150226',
771 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
773 'title': 'John Carlson Postgame 2/25/15',
776 # Kaltura embed (different embed code)
778 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
782 'upload_date': '20150127',
783 'uploader_id': 'PremierMedia',
785 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
788 # Eagle.Platform embed (generic URL)
790 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
794 'title': 'Навальный вышел на свободу',
795 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
796 'thumbnail': 're:^https?://.*\.jpg$',
802 # ClipYou (Eagle.Platform) embed (custom URL)
804 'url': 'http://muz-tv.ru/play/7129/',
808 'title': "'O Sole Mio",
809 'thumbnail': 're:^https?://.*\.jpg$',
816 'url': 'http://muz-tv.ru/kinozal/view/7400/',
820 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
821 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
822 'thumbnail': 're:^https?://.*\.jpg$',
829 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
833 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
834 'thumbnail': 're:^https?://.*\.png$',
840 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
841 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
845 'title': 'Facebook Creates "On This Day" | Crunch Report',
850 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
854 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
859 # Crooks and Liars embed
861 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
865 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
866 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
867 'timestamp': 1428207000,
868 'upload_date': '20150405',
869 'uploader': 'Heather',
872 # Crooks and Liars external embed
874 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
876 'id': 'MTE3MjUtMzQ2MzA',
878 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
879 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
880 'timestamp': 1265032391,
881 'upload_date': '20100201',
882 'uploader': 'Heather',
885 # NBC Sports vplayer embed
887 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
889 'id': 'ln7x1qSThw4k',
891 'title': "PFT Live: New leader in the 'new-look' defense",
892 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
897 'url': 'http://www.udn.com/news/story/7314/822787',
898 'md5': 'fd2060e988c326991037b9aff9df21a6',
902 'title': '中一中男師變性 全校師生力挺',
903 'thumbnail': 're:^https?://.*\.jpg$',
908 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
910 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
912 'description': 'VIDEO: Index/Match versus VLOOKUP.',
913 'title': 'This is what separates the Excel masters from the wannabes',
917 'skip_download': True,
920 # Contains a SMIL manifest
922 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
926 'title': '+ Football: Lottery Champions League Europe',
927 'uploader': 'www.telewebion.com',
931 'skip_download': True,
934 # Brightcove URL in single quotes
936 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
937 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
939 'id': '4255764656001',
941 'title': 'SN Presents: Russell Martin, World Citizen',
942 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
943 'uploader': 'Rogers Sportsnet',
946 # Dailymotion Cloud video
948 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
949 'md5': '49444254273501a64675a7e68c502681',
951 'id': '5585de919473990de4bee11b',
954 'thumbnail': 're:^https?://.*\.jpe?g$',
959 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
963 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
964 'thumbnail': 're:^https?://.*\.jpe?g$',
965 'uploader': 'ClickHole',
966 'uploader_id': 'clickhole',
971 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
973 'id': '74849a00-85a9-11e1-9660-123139220831',
975 'title': '#whilewewatch',
980 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
981 'md5': '43662b577c018ad707a63766462b1e87',
985 'title': 'New experience with Acrobat DC',
986 'description': 'New experience with Acrobat DC',
992 def report_following_redirect(self, new_url):
993 """Report information extraction."""
994 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
996 def _extract_rss(self, url, video_id, doc):
997 playlist_title = doc.find('./channel/title').text
998 playlist_desc_el = doc.find('./channel/description')
999 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1002 for it in doc.findall('./channel/item'):
1003 next_url = xpath_text(it, 'link', fatal=False)
1005 enclosure_nodes = it.findall('./enclosure')
1006 for e in enclosure_nodes:
1007 next_url = e.attrib.get('url')
1017 'title': it.find('title').text,
1021 '_type': 'playlist',
1023 'title': playlist_title,
1024 'description': playlist_desc,
1028 def _extract_camtasia(self, url, video_id, webpage):
1029 """ Returns None if no camtasia video can be found. """
1031 camtasia_cfg = self._search_regex(
1032 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1033 webpage, 'camtasia configuration file', default=None)
1034 if camtasia_cfg is None:
1037 title = self._html_search_meta('DC.title', webpage, fatal=True)
1039 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1040 camtasia_cfg = self._download_xml(
1041 camtasia_url, video_id,
1042 note='Downloading camtasia configuration',
1043 errnote='Failed to download camtasia configuration')
1044 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1047 for n in fileset_node.getchildren():
1048 url_n = n.find('./uri')
1053 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1054 'title': '%s - %s' % (title, n.tag),
1055 'url': compat_urlparse.urljoin(url, url_n.text),
1056 'duration': float_or_none(n.find('./duration').text),
1060 '_type': 'playlist',
1065 def _real_extract(self, url):
1066 if url.startswith('//'):
1069 'url': self.http_scheme() + url,
1072 parsed_url = compat_urlparse.urlparse(url)
1073 if not parsed_url.scheme:
1074 default_search = self._downloader.params.get('default_search')
1075 if default_search is None:
1076 default_search = 'fixup_error'
1078 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1080 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1081 return self.url_result('http://' + url)
1082 elif default_search != 'fixup_error':
1083 if default_search == 'auto_warning':
1084 if re.match(r'^(?:url|URL)$', url):
1085 raise ExtractorError(
1086 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1089 self._downloader.report_warning(
1090 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1091 return self.url_result('ytsearch:' + url)
1093 if default_search in ('error', 'fixup_error'):
1094 raise ExtractorError(
1095 '%r is not a valid URL. '
1096 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1097 % (url, url), expected=True)
1099 if ':' not in default_search:
1100 default_search += ':'
1101 return self.url_result(default_search + url)
1103 url, smuggled_data = unsmuggle_url(url)
1104 force_videoid = None
1105 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1106 if smuggled_data and 'force_videoid' in smuggled_data:
1107 force_videoid = smuggled_data['force_videoid']
1108 video_id = force_videoid
1110 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1112 self.to_screen('%s: Requesting header' % video_id)
1114 head_req = HEADRequest(url)
1115 head_response = self._request_webpage(
1117 note=False, errnote='Could not send HEAD request to %s' % url,
1120 if head_response is not False:
1121 # Check for redirect
1122 new_url = head_response.geturl()
1124 self.report_following_redirect(new_url)
1126 new_url = smuggle_url(
1127 new_url, {'force_videoid': force_videoid})
1128 return self.url_result(new_url)
1130 full_response = None
1131 if head_response is False:
1132 request = compat_urllib_request.Request(url)
1133 request.add_header('Accept-Encoding', '*')
1134 full_response = self._request_webpage(request, video_id)
1135 head_response = full_response
1137 # Check for direct link to a video
1138 content_type = head_response.headers.get('Content-Type', '')
1139 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1141 upload_date = unified_strdate(
1142 head_response.headers.get('Last-Modified'))
1145 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1148 'format_id': m.group('format_id'),
1150 'vcodec': 'none' if m.group('type') == 'audio' else None
1152 'upload_date': upload_date,
1155 if not self._downloader.params.get('test', False) and not is_intentional:
1156 force = self._downloader.params.get('force_generic_extractor', False)
1157 self._downloader.report_warning(
1158 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1160 if not full_response:
1161 request = compat_urllib_request.Request(url)
1162 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1163 # making it impossible to download only chunk of the file (yet we need only 512kB to
1164 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1165 # that will always result in downloading the whole file that is not desirable.
1166 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1167 # to accept raw bytes and being able to download only a chunk.
1168 # It may probably better to solve this by checking Content-Type for application/octet-stream
1169 # after HEAD request finishes, but not sure if we can rely on this.
1170 request.add_header('Accept-Encoding', '*')
1171 full_response = self._request_webpage(request, video_id)
1173 # Maybe it's a direct link to a video?
1174 # Be careful not to download the whole thing!
1175 first_bytes = full_response.read(512)
1176 if not is_html(first_bytes):
1177 self._downloader.report_warning(
1178 'URL could be a direct video link, returning it as such.')
1179 upload_date = unified_strdate(
1180 head_response.headers.get('Last-Modified'))
1183 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1186 'upload_date': upload_date,
1189 webpage = self._webpage_read_content(
1190 full_response, url, video_id, prefix=first_bytes)
1192 self.report_extraction(video_id)
1194 # Is it an RSS feed or a SMIL file?
1196 doc = parse_xml(webpage)
1197 if doc.tag == 'rss':
1198 return self._extract_rss(url, video_id, doc)
1199 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1200 return self._parse_smil(doc, url, video_id)
1201 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1202 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1203 except compat_xml_parse_error:
1206 # Is it a Camtasia project?
1207 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1208 if camtasia_res is not None:
1211 # Sometimes embedded video player is hidden behind percent encoding
1212 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1213 # Unescaping the whole page allows to handle those cases in a generic way
1214 webpage = compat_urllib_parse_unquote(webpage)
1216 # it's tempting to parse this further, but you would
1217 # have to take into account all the variations like
1218 # Video Title - Site Name
1219 # Site Name | Video Title
1220 # Video Title - Tagline | Site Name
1221 # and so on and so forth; it's just not practical
1222 video_title = self._html_search_regex(
1223 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1226 # Try to detect age limit automatically
1227 age_limit = self._rta_search(webpage)
1228 # And then there are the jokers who advertise that they use RTA,
1229 # but actually don't.
1230 AGE_LIMIT_MARKERS = [
1231 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1233 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1236 # video uploader is domain name
1237 video_uploader = self._search_regex(
1238 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1241 def _playlist_from_matches(matches, getter=None, ie=None):
1243 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1245 return self.playlist_result(
1246 urlrs, playlist_id=video_id, playlist_title=video_title)
1248 # Look for BrightCove:
1249 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1251 self.to_screen('Brightcove video detected.')
1254 'url': smuggle_url(bc_url, {'Referer': url}),
1255 'ie_key': 'Brightcove'
1256 } for bc_url in bc_urls]
1259 '_type': 'playlist',
1260 'title': video_title,
1265 # Look for embedded rtl.nl player
1266 matches = re.findall(
1267 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1270 return _playlist_from_matches(matches, ie='RtlNl')
1272 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1273 if vimeo_url is not None:
1274 return self.url_result(vimeo_url)
1276 vid_me_embed_url = self._search_regex(
1277 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1278 webpage, 'vid.me embed', default=None)
1279 if vid_me_embed_url is not None:
1280 return self.url_result(vid_me_embed_url, 'Vidme')
1282 # Look for embedded YouTube player
1283 matches = re.findall(r'''(?x)
1292 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1296 return _playlist_from_matches(
1297 matches, lambda m: unescapeHTML(m[1]))
1299 # Look for lazyYT YouTube embed
1300 matches = re.findall(
1301 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1303 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1305 # Look for embedded Dailymotion player
1306 matches = re.findall(
1307 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1309 return _playlist_from_matches(
1310 matches, lambda m: unescapeHTML(m[1]))
1312 # Look for embedded Dailymotion playlist player (#3822)
1314 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1316 playlists = re.findall(
1317 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1319 return _playlist_from_matches(
1320 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1322 # Look for embedded Wistia player
1324 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1326 embed_url = self._proto_relative_url(
1327 unescapeHTML(match.group('url')))
1329 '_type': 'url_transparent',
1332 'uploader': video_uploader,
1333 'title': video_title,
1337 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1340 '_type': 'url_transparent',
1341 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1343 'uploader': video_uploader,
1344 'title': video_title,
1345 'id': match.group('id')
1348 # Look for embedded blip.tv player
1349 bliptv_url = BlipTVIE._extract_url(webpage)
1351 return self.url_result(bliptv_url, 'BlipTV')
1353 # Look for SVT player
1354 svt_url = SVTIE._extract_url(webpage)
1356 return self.url_result(svt_url, 'SVT')
1358 # Look for embedded condenast player
1359 matches = re.findall(
1360 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1364 '_type': 'playlist',
1367 'ie_key': 'CondeNast',
1369 } for ma in matches],
1370 'title': video_title,
1374 # Look for Bandcamp pages with custom domain
1375 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1376 if mobj is not None:
1377 burl = unescapeHTML(mobj.group(1))
1378 # Don't set the extractor because it can be a track url or an album
1379 return self.url_result(burl)
1381 # Look for embedded Vevo player
1383 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1384 if mobj is not None:
1385 return self.url_result(mobj.group('url'))
1387 # Look for embedded Viddler player
1389 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1391 if mobj is not None:
1392 return self.url_result(mobj.group('url'))
1394 # Look for NYTimes player
1396 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1398 if mobj is not None:
1399 return self.url_result(mobj.group('url'))
1401 # Look for Libsyn player
1403 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1404 if mobj is not None:
1405 return self.url_result(mobj.group('url'))
1407 # Look for Ooyala videos
1408 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1409 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1410 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1411 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1412 if mobj is not None:
1413 return OoyalaIE._build_url_result(mobj.group('ec'))
1415 # Look for multiple Ooyala embeds on SBN network websites
1416 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1417 if mobj is not None:
1418 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1420 return _playlist_from_matches(
1421 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1423 # Look for Aparat videos
1424 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1425 if mobj is not None:
1426 return self.url_result(mobj.group(1), 'Aparat')
1428 # Look for MPORA videos
1429 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1430 if mobj is not None:
1431 return self.url_result(mobj.group(1), 'Mpora')
1433 # Look for embedded NovaMov-based player
1435 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1436 (?P<url>http://(?:(?:embed|www)\.)?
1438 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1439 videoweed\.(?:es|com)|
1440 movshare\.(?:net|sx|ag)|
1441 divxstage\.(?:eu|net|ch|co|at|ag))
1442 /embed\.php.+?)\1''', webpage)
1443 if mobj is not None:
1444 return self.url_result(mobj.group('url'))
1446 # Look for embedded Facebook player
1448 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1449 if mobj is not None:
1450 return self.url_result(mobj.group('url'), 'Facebook')
1452 # Look for embedded VK player
1453 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1454 if mobj is not None:
1455 return self.url_result(mobj.group('url'), 'VK')
1457 # Look for embedded ivi player
1458 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1459 if mobj is not None:
1460 return self.url_result(mobj.group('url'), 'Ivi')
1462 # Look for embedded Huffington Post player
1464 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1465 if mobj is not None:
1466 return self.url_result(mobj.group('url'), 'HuffPost')
1469 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1470 if mobj is not None:
1471 return self.url_result(mobj.group('url'))
1472 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1473 if mobj is not None:
1474 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1476 # Look for funnyordie embed
1477 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1479 return _playlist_from_matches(
1480 matches, getter=unescapeHTML, ie='FunnyOrDie')
1482 # Look for BBC iPlayer embed
1483 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1485 return _playlist_from_matches(matches, ie='BBCCoUk')
1487 # Look for embedded RUTV player
1488 rutv_url = RUTVIE._extract_url(webpage)
1490 return self.url_result(rutv_url, 'RUTV')
1492 # Look for embedded TVC player
1493 tvc_url = TVCIE._extract_url(webpage)
1495 return self.url_result(tvc_url, 'TVC')
1497 # Look for embedded SportBox player
1498 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1500 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1502 # Look for embedded PornHub player
1503 pornhub_url = PornHubIE._extract_url(webpage)
1505 return self.url_result(pornhub_url, 'PornHub')
1507 # Look for embedded XHamster player
1508 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1510 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1512 # Look for embedded Tvigle player
1514 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1515 if mobj is not None:
1516 return self.url_result(mobj.group('url'), 'Tvigle')
1518 # Look for embedded TED player
1520 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1521 if mobj is not None:
1522 return self.url_result(mobj.group('url'), 'TED')
1524 # Look for embedded Ustream videos
1526 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1527 if mobj is not None:
1528 return self.url_result(mobj.group('url'), 'Ustream')
1530 # Look for embedded arte.tv player
1532 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1534 if mobj is not None:
1535 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1537 # Look for embedded francetv player
1539 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1541 if mobj is not None:
1542 return self.url_result(mobj.group('url'))
1544 # Look for embedded smotri.com player
1545 smotri_url = SmotriIE._extract_url(webpage)
1547 return self.url_result(smotri_url, 'Smotri')
1549 # Look for embedded Myvi.ru player
1550 myvi_url = MyviIE._extract_url(webpage)
1552 return self.url_result(myvi_url)
1554 # Look for embeded soundcloud player
1556 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1558 if mobj is not None:
1559 url = unescapeHTML(mobj.group('url'))
1560 return self.url_result(url)
1562 # Look for embedded vulture.com player
1564 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1566 if mobj is not None:
1567 url = unescapeHTML(mobj.group('url'))
1568 return self.url_result(url, ie='Vulture')
1570 # Look for embedded mtvservices player
1572 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1574 if mobj is not None:
1575 url = unescapeHTML(mobj.group('url'))
1576 return self.url_result(url, ie='MTVServicesEmbedded')
1578 # Look for embedded yahoo player
1580 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1582 if mobj is not None:
1583 return self.url_result(mobj.group('url'), 'Yahoo')
1585 # Look for embedded sbs.com.au player
1589 <meta\s+property="og:video"\s+content=|
1592 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1594 if mobj is not None:
1595 return self.url_result(mobj.group('url'), 'SBS')
1597 # Look for embedded Cinchcast player
1599 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1601 if mobj is not None:
1602 return self.url_result(mobj.group('url'), 'Cinchcast')
1605 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1609 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1611 if mobj is not None:
1612 return self.url_result(mobj.group('url'), 'MLB')
1615 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1617 if mobj is not None:
1618 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1621 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1623 if mobj is not None:
1624 return self.url_result(mobj.group('url'), 'Livestream')
1626 # Look for Zapiks embed
1628 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1629 if mobj is not None:
1630 return self.url_result(mobj.group('url'), 'Zapiks')
1632 # Look for Kaltura embeds
1633 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1634 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))
1635 if mobj is not None:
1636 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1638 # Look for Eagle.Platform embeds
1640 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1641 if mobj is not None:
1642 return self.url_result(mobj.group('url'), 'EaglePlatform')
1644 # Look for ClipYou (uses Eagle.Platform) embeds
1646 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1647 if mobj is not None:
1648 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1650 # Look for Pladform embeds
1652 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1653 if mobj is not None:
1654 return self.url_result(mobj.group('url'), 'Pladform')
1656 # Look for Playwire embeds
1658 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1659 if mobj is not None:
1660 return self.url_result(mobj.group('url'))
1662 # Look for 5min embeds
1664 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1665 if mobj is not None:
1666 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1668 # Look for Crooks and Liars embeds
1670 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1671 if mobj is not None:
1672 return self.url_result(mobj.group('url'))
1674 # Look for NBC Sports VPlayer embeds
1675 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1677 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1679 # Look for UDN embeds
1681 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1682 if mobj is not None:
1683 return self.url_result(
1684 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1686 # Look for Senate ISVP iframe
1687 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1689 return self.url_result(senate_isvp_url, 'SenateISVP')
1691 # Look for Dailymotion Cloud videos
1692 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1694 return self.url_result(dmcloud_url, 'DailymotionCloud')
1696 # Look for OnionStudios embeds
1697 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1698 if onionstudios_url:
1699 return self.url_result(onionstudios_url)
1701 # Look for SnagFilms embeds
1702 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1704 return self.url_result(snagfilms_url)
1706 # Look for AdobeTVVideo embeds
1708 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1710 if mobj is not None:
1711 return self.url_result(
1712 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1715 def check_video(vurl):
1716 if YoutubeIE.suitable(vurl):
1718 vpath = compat_urlparse.urlparse(vurl).path
1719 vext = determine_ext(vpath)
1720 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1722 def filter_video(urls):
1723 return list(filter(check_video, urls))
1725 # Start with something easy: JW Player in SWFObject
1726 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1728 # Look for gorilla-vid style embedding
1729 found = filter_video(re.findall(r'''(?sx)
1733 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1736 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1738 # Broaden the search a little bit
1739 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1741 # Broaden the findall a little bit: JWPlayer JS loader
1742 found = filter_video(re.findall(
1743 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1746 found = filter_video(re.findall(r'''(?xs)
1747 flowplayer\("[^"]+",\s*
1749 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1750 ["']?url["']?\s*:\s*["']([^"']+)["']
1755 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1757 # Try to find twitter cards info
1758 found = filter_video(re.findall(
1759 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1761 # We look for Open Graph info:
1762 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1763 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1764 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1765 if m_video_type is not None:
1766 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1769 found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1771 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1773 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1774 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1777 # Look also in Refresh HTTP header
1778 refresh_header = head_response.headers.get('Refresh')
1780 found = re.search(REDIRECT_REGEX, refresh_header)
1782 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1783 self.report_following_redirect(new_url)
1789 raise UnsupportedError(url)
1792 for video_url in found:
1793 video_url = compat_urlparse.urljoin(url, video_url)
1794 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1796 # Sometimes, jwplayer extraction will result in a YouTube URL
1797 if YoutubeIE.suitable(video_url):
1798 entries.append(self.url_result(video_url, 'Youtube'))
1801 # here's a fun little line of code for you:
1802 video_id = os.path.splitext(video_id)[0]
1804 ext = determine_ext(video_url)
1808 'formats': self._extract_smil_formats(video_url, video_id),
1809 'uploader': video_uploader,
1810 'title': video_title,
1811 'age_limit': age_limit,
1814 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1819 'uploader': video_uploader,
1820 'title': video_title,
1821 'age_limit': age_limit,
1824 if len(entries) == 1:
1827 for num, e in enumerate(entries, start=1):
1828 # 'url' results don't have a title
1829 if e.get('title') is not None:
1830 e['title'] = '%s (%d)' % (e['title'], num)
1832 '_type': 'playlist',