3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_urllib_parse_unquote,
13 compat_urllib_request,
15 compat_xml_parse_error,
33 from .brightcove import BrightcoveIE
34 from .nbc import NBCSportsVPlayerIE
35 from .ooyala import OoyalaIE
36 from .rutv import RUTVIE
37 from .tvc import TVCIE
38 from .sportbox import SportBoxEmbedIE
39 from .smotri import SmotriIE
40 from .myvi import MyviIE
41 from .condenast import CondeNastIE
42 from .udn import UDNEmbedIE
43 from .senateisvp import SenateISVPIE
44 from .bliptv import BlipTVIE
45 from .svt import SVTIE
46 from .pornhub import PornHubIE
47 from .xhamster import XHamsterEmbedIE
48 from .vimeo import VimeoIE
49 from .dailymotion import DailymotionCloudIE
50 from .onionstudios import OnionStudiosIE
51 from .snagfilms import SnagFilmsEmbedIE
52 from .screenwavemedia import ScreenwaveMediaIE
53 from .ultimedia import UltimediaIE
56 class GenericIE(InfoExtractor):
57 IE_DESC = 'Generic downloader that works on some sites'
61 # Direct link to a video
63 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
64 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
69 'upload_date': '20100513',
72 # Direct link to media delivered compressed (until Accept-Encoding is *)
74 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
75 'md5': '128c42e68b13950268b648275386fc74',
77 'id': 'FictionJunction-Parallel_Hearts',
79 'title': 'FictionJunction-Parallel_Hearts',
80 'upload_date': '20140522',
82 'expected_warnings': [
83 'URL could be a direct video link, returning it as such.'
86 # Direct download with broken HEAD
88 'url': 'http://ai-radio.org:8000/radio.opus',
95 'skip_download': True, # infinite live stream
97 'expected_warnings': [
98 r'501.*Not Implemented'
101 # Direct link with incorrect MIME type
103 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
104 'md5': '4ccbebe5f36706d85221f204d7eb5913',
106 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
107 'id': '5_Lennart_Poettering_-_Systemd',
109 'title': '5_Lennart_Poettering_-_Systemd',
110 'upload_date': '20141120',
112 'expected_warnings': [
113 'URL could be a direct video link, returning it as such.'
118 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
120 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
121 'title': 'Zero Punctuation',
122 'description': 're:.*groundbreaking video review series.*'
124 'playlist_mincount': 11,
126 # RSS feed with enclosure
128 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
130 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
132 'upload_date': '20150228',
133 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
136 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
138 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
142 'title': 'Automatics, robotics and biocybernetics',
143 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
144 'formats': 'mincount:16',
145 'subtitles': 'mincount:1',
148 'force_generic_extractor': True,
149 'skip_download': True,
152 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
154 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
159 'formats': 'mincount:1',
162 'skip_download': True,
165 # SMIL from https://www.restudy.dk/video/play/id/1637
167 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
171 'title': 'video_1637',
172 'formats': 'mincount:3',
175 'skip_download': True,
178 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
180 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
182 'id': 'smil-service',
184 'title': 'smil-service',
185 'formats': 'mincount:1',
188 'skip_download': True,
191 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
193 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
197 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
198 'formats': 'mincount:3',
201 'skip_download': True,
204 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
206 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
208 'id': 'mZlp2ctYIUEB',
210 'title': 'Tikibad ontruimd wegens brand',
211 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
212 'thumbnail': 're:^https?://.*\.jpg$',
216 'skip_download': True,
221 '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',
225 'upload_date': '20130224',
226 'uploader_id': 'TheVerge',
227 'description': 're:^Chris Ziegler takes a look at the\.*',
228 'uploader': 'The Verge',
229 'title': 'First Firefox OS phones side-by-side',
232 'skip_download': False,
236 # redirect in Refresh HTTP header
237 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
241 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
242 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
243 'upload_date': '20150917',
244 'uploader_id': 'brtvofficial',
245 'uploader': 'Boiler Room',
248 'skip_download': False,
252 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
253 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
255 'id': '13601338388002',
257 'uploader': 'www.hodiho.fr',
258 'title': 'R\u00e9gis plante sa Jeep',
261 # bandcamp page with custom domain
263 'add_ie': ['Bandcamp'],
264 'url': 'http://bronyrock.com/track/the-pony-mash',
268 'title': 'The Pony Mash',
269 'uploader': 'M_Pallante',
271 'skip': 'There is a limit of 200 free downloads / month for the test song',
273 # embedded brightcove video
274 # it also tests brightcove videos that need to set the 'Referer' in the
277 'add_ie': ['Brightcove'],
278 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
280 'id': '2765128793001',
282 'title': 'Le cours de bourse : l’analyse technique',
283 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
284 'uploader': 'BFM BUSINESS',
287 'skip_download': True,
291 # https://github.com/rg3/youtube-dl/issues/2253
292 'url': 'http://bcove.me/i6nfkrc3',
293 'md5': '0ba9446db037002366bab3b3eb30c88c',
295 'id': '3101154703001',
297 'title': 'Still no power',
298 'uploader': 'thestar.com',
299 '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.',
301 'add_ie': ['Brightcove'],
304 'url': 'http://www.championat.com/video/football/v/87/87499.html',
305 'md5': 'fb973ecf6e4a78a67453647444222983',
307 'id': '3414141473001',
309 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
310 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
311 'uploader': 'Championat',
315 # https://github.com/rg3/youtube-dl/issues/3541
316 'add_ie': ['Brightcove'],
317 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
319 'id': '3866516442001',
321 'title': 'Leer mij vrouwen kennen: Aflevering 1',
322 'description': 'Leer mij vrouwen kennen: Aflevering 1',
323 'uploader': 'SBS Broadcasting',
325 'skip': 'Restricted to Netherlands',
327 'skip_download': True, # m3u8 download
332 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
333 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
335 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
337 'title': '2cc213299525360.mov', # that's what we get
339 'add_ie': ['Ooyala'],
342 # ooyala video embedded with http://player.ooyala.com/iframe.js
343 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
345 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
347 'title': '"Steve Jobs: Man in the Machine" trailer',
348 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
351 'skip_download': True,
354 # multiple ooyala embeds on SBN network websites
356 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
358 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
359 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
361 'playlist_mincount': 3,
363 'skip_download': True,
365 'add_ie': ['Ooyala'],
369 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
373 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
374 'upload_date': '20140225',
375 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
376 'uploader': 'Tested',
377 'uploader_id': 'testedcom',
379 # No need to test YoutubeIE here
381 'skip_download': True,
386 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
390 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
391 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
396 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
400 'title': 'Охотское море стало целиком российским',
401 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
405 'skip_download': True,
410 '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/',
414 'title': 'Дошкольное воспитание',
419 'url': 'http://www.vestifinance.ru/articles/25753',
422 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
427 'title': 'Госзаказ. День 3',
433 'title': 'Госзаказ. День 2',
439 'title': 'Госзаказ. День 1',
445 'skip_download': True,
450 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
452 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
454 'title': 'Ужастики, русский трейлер (2015)',
455 'thumbnail': 're:^https?://.*\.jpg$',
461 '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',
464 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
466 'playlist_mincount': 7,
470 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
471 'md5': '65fdff94098e4a607385a60c5177c638',
475 'title': 'Hidden miracles of the natural world',
476 'uploader': 'Louie Schwartzberg',
477 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
480 # Embeded Ustream video
482 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
483 'md5': '27b99cdb639c9b12a79bca876a073417',
487 'uploader': 'AU SPA: The NSA and Privacy',
488 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
491 # nowvideo embed hidden behind percent encoding
493 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
494 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
496 'id': '06e53103ca9aa',
498 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
499 'description': 'No description',
504 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
505 'md5': '7653032cbb25bf6c80d80f217055fa43',
507 'id': '048195-004_PLUS7-F',
510 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
511 'upload_date': '20140320',
514 'skip_download': 'Requires rtmpdump'
519 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
523 'title': 'Alcaline, le concert avec Calogero',
524 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
525 'upload_date': '20150226',
526 'timestamp': 1424989860,
531 'skip_download': True,
533 'expected_warnings': [
539 'url': 'http://www.wired.com/2014/04/honda-asimo/',
540 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
542 'id': '53501be369702d3275860000',
544 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
549 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
550 'md5': '441aeeb82eb72c422c7f14ec533999cd',
552 'id': 'k2mm4bCdJ6CQ2i7c8o2',
554 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
557 'add_ie': ['Dailymotion'],
561 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
565 'title': 'The NBL Auction 2014',
566 'uploader': 'BADMINTON England',
567 'uploader_id': 'BADMINTONEvents',
568 'upload_date': '20140603',
569 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
571 'add_ie': ['Youtube'],
573 'skip_download': True,
578 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
579 'md5': '35727f82f58c76d996fc188f9755b0d5',
581 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
584 'description': 'Mario\'s life in the fast lane has never looked so good.',
587 # YouTube embed via <data-embed-url="">
589 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
593 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
594 'uploader': 'Gameloft',
595 'uploader_id': 'gameloft',
596 'upload_date': '20140828',
597 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
600 'skip_download': True,
605 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
607 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
609 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
610 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
615 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
617 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
618 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
624 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
629 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
630 'md5': '9d65602bf31c6e20014319c7d07fba27',
632 'id': '5123ea6d5e5a7',
635 'uploader': 'www.handjobhub.com',
636 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
639 # Multiple brightcove videos
640 # https://github.com/rg3/youtube-dl/issues/2283
642 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
644 'id': 'always-never',
645 'title': 'Always / Never - The New Yorker',
649 'extract_flat': False,
650 'skip_download': True,
655 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
656 'md5': '96f09a37e44da40dd083e12d9a683327',
660 'title': 'Ump changes call to ball',
661 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
663 'timestamp': 1401537900,
664 'upload_date': '20140531',
665 'thumbnail': 're:^https?://.*\.jpg$',
670 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
671 'md5': '8788b683c777a5cf25621eaf286d0c23',
675 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
677 'filesize': 182808282,
678 'uploader': 'education-portal.com',
682 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
683 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
687 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
689 'uploader': 'thoughtworks.wistia.com',
694 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
698 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
699 'uploader': 'Sophos Security',
700 'title': 'Chet Chat 171 - Oct 29, 2014',
701 'upload_date': '20141029',
706 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
710 'upload_date': '20141112',
711 'title': 'Rosetta #CometLanding webcast HL 10',
716 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
719 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
721 'playlist_mincount': 2,
725 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
729 'upload_date': '20141126',
730 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
735 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
737 'id': '730m_DandD_1901_512k',
739 'uploader': 'www.abc.net.au',
740 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
743 # embedded viddler video
745 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
749 'uploader': 'deadspin',
750 'title': 'WALL-TO-GORTAT',
751 'timestamp': 1422285291,
752 'upload_date': '20150126',
754 'add_ie': ['Viddler'],
758 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
762 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
763 'description': 'md5:601cb790edd05908957dae8aaa866465',
764 'upload_date': '20150220',
769 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
773 'upload_date': '20150212',
774 'uploader': 'The National Archives UK',
775 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
776 'uploader_id': 'NationalArchives08',
777 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
782 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
783 'playlist_mincount': 5,
785 'id': 'aanslagen-kopenhagen',
786 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
791 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
795 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
800 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
804 'upload_date': '20150226',
805 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
807 'title': 'John Carlson Postgame 2/25/15',
810 # Kaltura embed (different embed code)
812 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
816 'upload_date': '20150127',
817 'uploader_id': 'PremierMedia',
819 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
822 # Eagle.Platform embed (generic URL)
824 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
828 'title': 'Навальный вышел на свободу',
829 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
830 'thumbnail': 're:^https?://.*\.jpg$',
836 # ClipYou (Eagle.Platform) embed (custom URL)
838 'url': 'http://muz-tv.ru/play/7129/',
842 'title': "'O Sole Mio",
843 'thumbnail': 're:^https?://.*\.jpg$',
850 'url': 'http://muz-tv.ru/kinozal/view/7400/',
854 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
855 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
856 'thumbnail': 're:^https?://.*\.jpg$',
863 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
867 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
868 'thumbnail': 're:^https?://.*\.png$',
874 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
875 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
879 'title': 'Facebook Creates "On This Day" | Crunch Report',
884 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
888 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
893 # Crooks and Liars embed
895 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
899 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
900 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
901 'timestamp': 1428207000,
902 'upload_date': '20150405',
903 'uploader': 'Heather',
906 # Crooks and Liars external embed
908 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
910 'id': 'MTE3MjUtMzQ2MzA',
912 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
913 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
914 'timestamp': 1265032391,
915 'upload_date': '20100201',
916 'uploader': 'Heather',
919 # NBC Sports vplayer embed
921 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
923 'id': 'ln7x1qSThw4k',
925 'title': "PFT Live: New leader in the 'new-look' defense",
926 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
931 'url': 'http://www.udn.com/news/story/7314/822787',
932 'md5': 'fd2060e988c326991037b9aff9df21a6',
936 'title': '中一中男師變性 全校師生力挺',
937 'thumbnail': 're:^https?://.*\.jpg$',
942 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
944 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
946 'description': 'VIDEO: Index/Match versus VLOOKUP.',
947 'title': 'This is what separates the Excel masters from the wannabes',
951 'skip_download': True,
954 # Contains a SMIL manifest
956 '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',
960 'title': '+ Football: Lottery Champions League Europe',
961 'uploader': 'www.telewebion.com',
965 'skip_download': True,
968 # Brightcove URL in single quotes
970 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
971 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
973 'id': '4255764656001',
975 'title': 'SN Presents: Russell Martin, World Citizen',
976 '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.',
977 'uploader': 'Rogers Sportsnet',
980 # Dailymotion Cloud video
982 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
983 'md5': '49444254273501a64675a7e68c502681',
985 'id': '5585de919473990de4bee11b',
988 'thumbnail': 're:^https?://.*\.jpe?g$',
993 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
997 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
998 'thumbnail': 're:^https?://.*\.jpe?g$',
999 'uploader': 'ClickHole',
1000 'uploader_id': 'clickhole',
1005 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1007 'id': '74849a00-85a9-11e1-9660-123139220831',
1009 'title': '#whilewewatch',
1012 # AdobeTVVideo embed
1014 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1015 'md5': '43662b577c018ad707a63766462b1e87',
1019 'title': 'New experience with Acrobat DC',
1020 'description': 'New experience with Acrobat DC',
1021 'duration': 248.667,
1024 # ScreenwaveMedia embed
1026 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1027 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1029 'id': 'cinemasnob-55d26273809dd',
1031 'title': 'cinemasnob',
1036 'url': 'http://www.jukebox.es/kosheen/videoclip,pride,r303r.html',
1037 'md5': '25551df6e7c7ab8096ceeeae048c5f64',
1041 'title': 'Kosheen - Pride (live)',
1042 'thumbnail': 're:^https?://.*\.jpg',
1044 'upload_date': '20081103',
1045 'timestamp': 1225733392,
1046 'uploader_id': '33m03',
1051 def report_following_redirect(self, new_url):
1052 """Report information extraction."""
1053 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1055 def _extract_rss(self, url, video_id, doc):
1056 playlist_title = doc.find('./channel/title').text
1057 playlist_desc_el = doc.find('./channel/description')
1058 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1061 for it in doc.findall('./channel/item'):
1062 next_url = xpath_text(it, 'link', fatal=False)
1064 enclosure_nodes = it.findall('./enclosure')
1065 for e in enclosure_nodes:
1066 next_url = e.attrib.get('url')
1076 'title': it.find('title').text,
1080 '_type': 'playlist',
1082 'title': playlist_title,
1083 'description': playlist_desc,
1087 def _extract_camtasia(self, url, video_id, webpage):
1088 """ Returns None if no camtasia video can be found. """
1090 camtasia_cfg = self._search_regex(
1091 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1092 webpage, 'camtasia configuration file', default=None)
1093 if camtasia_cfg is None:
1096 title = self._html_search_meta('DC.title', webpage, fatal=True)
1098 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1099 camtasia_cfg = self._download_xml(
1100 camtasia_url, video_id,
1101 note='Downloading camtasia configuration',
1102 errnote='Failed to download camtasia configuration')
1103 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1106 for n in fileset_node.getchildren():
1107 url_n = n.find('./uri')
1112 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1113 'title': '%s - %s' % (title, n.tag),
1114 'url': compat_urlparse.urljoin(url, url_n.text),
1115 'duration': float_or_none(n.find('./duration').text),
1119 '_type': 'playlist',
1124 def _real_extract(self, url):
1125 if url.startswith('//'):
1128 'url': self.http_scheme() + url,
1131 parsed_url = compat_urlparse.urlparse(url)
1132 if not parsed_url.scheme:
1133 default_search = self._downloader.params.get('default_search')
1134 if default_search is None:
1135 default_search = 'fixup_error'
1137 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1139 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1140 return self.url_result('http://' + url)
1141 elif default_search != 'fixup_error':
1142 if default_search == 'auto_warning':
1143 if re.match(r'^(?:url|URL)$', url):
1144 raise ExtractorError(
1145 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1148 self._downloader.report_warning(
1149 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1150 return self.url_result('ytsearch:' + url)
1152 if default_search in ('error', 'fixup_error'):
1153 raise ExtractorError(
1154 '%r is not a valid URL. '
1155 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1156 % (url, url), expected=True)
1158 if ':' not in default_search:
1159 default_search += ':'
1160 return self.url_result(default_search + url)
1162 url, smuggled_data = unsmuggle_url(url)
1163 force_videoid = None
1164 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1165 if smuggled_data and 'force_videoid' in smuggled_data:
1166 force_videoid = smuggled_data['force_videoid']
1167 video_id = force_videoid
1169 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1171 self.to_screen('%s: Requesting header' % video_id)
1173 head_req = HEADRequest(url)
1174 head_response = self._request_webpage(
1176 note=False, errnote='Could not send HEAD request to %s' % url,
1179 if head_response is not False:
1180 # Check for redirect
1181 new_url = head_response.geturl()
1183 self.report_following_redirect(new_url)
1185 new_url = smuggle_url(
1186 new_url, {'force_videoid': force_videoid})
1187 return self.url_result(new_url)
1189 full_response = None
1190 if head_response is False:
1191 request = compat_urllib_request.Request(url)
1192 request.add_header('Accept-Encoding', '*')
1193 full_response = self._request_webpage(request, video_id)
1194 head_response = full_response
1196 # Check for direct link to a video
1197 content_type = head_response.headers.get('Content-Type', '')
1198 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1200 upload_date = unified_strdate(
1201 head_response.headers.get('Last-Modified'))
1204 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1207 'format_id': m.group('format_id'),
1209 'vcodec': 'none' if m.group('type') == 'audio' else None
1211 'upload_date': upload_date,
1214 if not self._downloader.params.get('test', False) and not is_intentional:
1215 force = self._downloader.params.get('force_generic_extractor', False)
1216 self._downloader.report_warning(
1217 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1219 if not full_response:
1220 request = compat_urllib_request.Request(url)
1221 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1222 # making it impossible to download only chunk of the file (yet we need only 512kB to
1223 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1224 # that will always result in downloading the whole file that is not desirable.
1225 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1226 # to accept raw bytes and being able to download only a chunk.
1227 # It may probably better to solve this by checking Content-Type for application/octet-stream
1228 # after HEAD request finishes, but not sure if we can rely on this.
1229 request.add_header('Accept-Encoding', '*')
1230 full_response = self._request_webpage(request, video_id)
1232 # Maybe it's a direct link to a video?
1233 # Be careful not to download the whole thing!
1234 first_bytes = full_response.read(512)
1235 if not is_html(first_bytes):
1236 self._downloader.report_warning(
1237 'URL could be a direct video link, returning it as such.')
1238 upload_date = unified_strdate(
1239 head_response.headers.get('Last-Modified'))
1242 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1245 'upload_date': upload_date,
1248 webpage = self._webpage_read_content(
1249 full_response, url, video_id, prefix=first_bytes)
1251 self.report_extraction(video_id)
1253 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1255 doc = parse_xml(webpage)
1256 if doc.tag == 'rss':
1257 return self._extract_rss(url, video_id, doc)
1258 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1259 return self._parse_smil(doc, url, video_id)
1260 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1261 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1262 except compat_xml_parse_error:
1265 # Is it a Camtasia project?
1266 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1267 if camtasia_res is not None:
1270 # Sometimes embedded video player is hidden behind percent encoding
1271 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1272 # Unescaping the whole page allows to handle those cases in a generic way
1273 webpage = compat_urllib_parse_unquote(webpage)
1275 # it's tempting to parse this further, but you would
1276 # have to take into account all the variations like
1277 # Video Title - Site Name
1278 # Site Name | Video Title
1279 # Video Title - Tagline | Site Name
1280 # and so on and so forth; it's just not practical
1281 video_title = self._html_search_regex(
1282 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1285 # Try to detect age limit automatically
1286 age_limit = self._rta_search(webpage)
1287 # And then there are the jokers who advertise that they use RTA,
1288 # but actually don't.
1289 AGE_LIMIT_MARKERS = [
1290 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1292 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1295 # video uploader is domain name
1296 video_uploader = self._search_regex(
1297 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1300 def _playlist_from_matches(matches, getter=None, ie=None):
1302 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1304 return self.playlist_result(
1305 urlrs, playlist_id=video_id, playlist_title=video_title)
1307 # Look for BrightCove:
1308 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1310 self.to_screen('Brightcove video detected.')
1313 'url': smuggle_url(bc_url, {'Referer': url}),
1314 'ie_key': 'Brightcove'
1315 } for bc_url in bc_urls]
1318 '_type': 'playlist',
1319 'title': video_title,
1324 # Look for embedded rtl.nl player
1325 matches = re.findall(
1326 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1329 return _playlist_from_matches(matches, ie='RtlNl')
1331 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1332 if vimeo_url is not None:
1333 return self.url_result(vimeo_url)
1335 vid_me_embed_url = self._search_regex(
1336 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1337 webpage, 'vid.me embed', default=None)
1338 if vid_me_embed_url is not None:
1339 return self.url_result(vid_me_embed_url, 'Vidme')
1341 # Look for embedded YouTube player
1342 matches = re.findall(r'''(?x)
1351 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1355 return _playlist_from_matches(
1356 matches, lambda m: unescapeHTML(m[1]))
1358 # Look for lazyYT YouTube embed
1359 matches = re.findall(
1360 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1362 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1364 # Look for embedded Dailymotion player
1365 matches = re.findall(
1366 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1368 return _playlist_from_matches(
1369 matches, lambda m: unescapeHTML(m[1]))
1371 # Look for embedded Dailymotion playlist player (#3822)
1373 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1375 playlists = re.findall(
1376 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1378 return _playlist_from_matches(
1379 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1381 # Look for embedded Wistia player
1383 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1385 embed_url = self._proto_relative_url(
1386 unescapeHTML(match.group('url')))
1388 '_type': 'url_transparent',
1391 'uploader': video_uploader,
1392 'title': video_title,
1396 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1399 '_type': 'url_transparent',
1400 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1402 'uploader': video_uploader,
1403 'title': video_title,
1404 'id': match.group('id')
1407 # Look for embedded blip.tv player
1408 bliptv_url = BlipTVIE._extract_url(webpage)
1410 return self.url_result(bliptv_url, 'BlipTV')
1412 # Look for SVT player
1413 svt_url = SVTIE._extract_url(webpage)
1415 return self.url_result(svt_url, 'SVT')
1417 # Look for embedded condenast player
1418 matches = re.findall(
1419 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1423 '_type': 'playlist',
1426 'ie_key': 'CondeNast',
1428 } for ma in matches],
1429 'title': video_title,
1433 # Look for Bandcamp pages with custom domain
1434 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1435 if mobj is not None:
1436 burl = unescapeHTML(mobj.group(1))
1437 # Don't set the extractor because it can be a track url or an album
1438 return self.url_result(burl)
1440 # Look for embedded Vevo player
1442 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1443 if mobj is not None:
1444 return self.url_result(mobj.group('url'))
1446 # Look for embedded Viddler player
1448 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1450 if mobj is not None:
1451 return self.url_result(mobj.group('url'))
1453 # Look for NYTimes player
1455 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1457 if mobj is not None:
1458 return self.url_result(mobj.group('url'))
1460 # Look for Libsyn player
1462 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1463 if mobj is not None:
1464 return self.url_result(mobj.group('url'))
1466 # Look for Ooyala videos
1467 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1468 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1469 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1470 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1471 if mobj is not None:
1472 return OoyalaIE._build_url_result(mobj.group('ec'))
1474 # Look for multiple Ooyala embeds on SBN network websites
1475 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1476 if mobj is not None:
1477 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1479 return _playlist_from_matches(
1480 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1482 # Look for Aparat videos
1483 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1484 if mobj is not None:
1485 return self.url_result(mobj.group(1), 'Aparat')
1487 # Look for MPORA videos
1488 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1489 if mobj is not None:
1490 return self.url_result(mobj.group(1), 'Mpora')
1492 # Look for embedded NovaMov-based player
1494 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1495 (?P<url>http://(?:(?:embed|www)\.)?
1497 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1498 videoweed\.(?:es|com)|
1499 movshare\.(?:net|sx|ag)|
1500 divxstage\.(?:eu|net|ch|co|at|ag))
1501 /embed\.php.+?)\1''', webpage)
1502 if mobj is not None:
1503 return self.url_result(mobj.group('url'))
1505 # Look for embedded Facebook player
1507 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1508 if mobj is not None:
1509 return self.url_result(mobj.group('url'), 'Facebook')
1511 # Look for embedded VK player
1512 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1513 if mobj is not None:
1514 return self.url_result(mobj.group('url'), 'VK')
1516 # Look for embedded ivi player
1517 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1518 if mobj is not None:
1519 return self.url_result(mobj.group('url'), 'Ivi')
1521 # Look for embedded Huffington Post player
1523 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1524 if mobj is not None:
1525 return self.url_result(mobj.group('url'), 'HuffPost')
1528 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1529 if mobj is not None:
1530 return self.url_result(mobj.group('url'))
1531 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1532 if mobj is not None:
1533 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1535 # Look for funnyordie embed
1536 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1538 return _playlist_from_matches(
1539 matches, getter=unescapeHTML, ie='FunnyOrDie')
1541 # Look for BBC iPlayer embed
1542 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1544 return _playlist_from_matches(matches, ie='BBCCoUk')
1546 # Look for embedded RUTV player
1547 rutv_url = RUTVIE._extract_url(webpage)
1549 return self.url_result(rutv_url, 'RUTV')
1551 # Look for embedded TVC player
1552 tvc_url = TVCIE._extract_url(webpage)
1554 return self.url_result(tvc_url, 'TVC')
1556 # Look for embedded SportBox player
1557 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1559 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1561 # Look for embedded PornHub player
1562 pornhub_url = PornHubIE._extract_url(webpage)
1564 return self.url_result(pornhub_url, 'PornHub')
1566 # Look for embedded XHamster player
1567 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1569 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1571 # Look for embedded Tvigle player
1573 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1574 if mobj is not None:
1575 return self.url_result(mobj.group('url'), 'Tvigle')
1577 # Look for embedded TED player
1579 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1580 if mobj is not None:
1581 return self.url_result(mobj.group('url'), 'TED')
1583 # Look for embedded Ustream videos
1585 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1586 if mobj is not None:
1587 return self.url_result(mobj.group('url'), 'Ustream')
1589 # Look for embedded arte.tv player
1591 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1593 if mobj is not None:
1594 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1596 # Look for embedded francetv player
1598 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1600 if mobj is not None:
1601 return self.url_result(mobj.group('url'))
1603 # Look for embedded smotri.com player
1604 smotri_url = SmotriIE._extract_url(webpage)
1606 return self.url_result(smotri_url, 'Smotri')
1608 # Look for embedded Myvi.ru player
1609 myvi_url = MyviIE._extract_url(webpage)
1611 return self.url_result(myvi_url)
1613 # Look for embeded soundcloud player
1615 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1617 if mobj is not None:
1618 url = unescapeHTML(mobj.group('url'))
1619 return self.url_result(url)
1621 # Look for embedded vulture.com player
1623 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1625 if mobj is not None:
1626 url = unescapeHTML(mobj.group('url'))
1627 return self.url_result(url, ie='Vulture')
1629 # Look for embedded mtvservices player
1631 r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
1633 if mobj is not None:
1634 url = unescapeHTML(mobj.group('url'))
1635 return self.url_result(url, ie='MTVServicesEmbedded')
1637 # Look for embedded yahoo player
1639 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1641 if mobj is not None:
1642 return self.url_result(mobj.group('url'), 'Yahoo')
1644 # Look for embedded sbs.com.au player
1648 <meta\s+property="og:video"\s+content=|
1651 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1653 if mobj is not None:
1654 return self.url_result(mobj.group('url'), 'SBS')
1656 # Look for embedded Cinchcast player
1658 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1660 if mobj is not None:
1661 return self.url_result(mobj.group('url'), 'Cinchcast')
1664 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1668 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1670 if mobj is not None:
1671 return self.url_result(mobj.group('url'), 'MLB')
1674 r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1676 if mobj is not None:
1677 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1680 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1682 if mobj is not None:
1683 return self.url_result(mobj.group('url'), 'Livestream')
1685 # Look for Zapiks embed
1687 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1688 if mobj is not None:
1689 return self.url_result(mobj.group('url'), 'Zapiks')
1691 # Look for Kaltura embeds
1692 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1693 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))
1694 if mobj is not None:
1695 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1697 # Look for Eagle.Platform embeds
1699 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1700 if mobj is not None:
1701 return self.url_result(mobj.group('url'), 'EaglePlatform')
1703 # Look for ClipYou (uses Eagle.Platform) embeds
1705 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1706 if mobj is not None:
1707 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1709 # Look for Pladform embeds
1711 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1712 if mobj is not None:
1713 return self.url_result(mobj.group('url'), 'Pladform')
1715 # Look for Playwire embeds
1717 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1718 if mobj is not None:
1719 return self.url_result(mobj.group('url'))
1721 # Look for 5min embeds
1723 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1724 if mobj is not None:
1725 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1727 # Look for Crooks and Liars embeds
1729 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1730 if mobj is not None:
1731 return self.url_result(mobj.group('url'))
1733 # Look for NBC Sports VPlayer embeds
1734 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1736 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1738 # Look for UDN embeds
1740 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1741 if mobj is not None:
1742 return self.url_result(
1743 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1745 # Look for Senate ISVP iframe
1746 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1748 return self.url_result(senate_isvp_url, 'SenateISVP')
1750 # Look for Dailymotion Cloud videos
1751 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1753 return self.url_result(dmcloud_url, 'DailymotionCloud')
1755 # Look for OnionStudios embeds
1756 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1757 if onionstudios_url:
1758 return self.url_result(onionstudios_url)
1760 # Look for SnagFilms embeds
1761 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1763 return self.url_result(snagfilms_url)
1765 # Look for ScreenwaveMedia embeds
1766 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1767 if mobj is not None:
1768 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1770 # Look for Ulltimedia embeds
1771 ultimedia_url = UltimediaIE._extract_url(webpage)
1773 return self.url_result(self._proto_relative_url(ultimedia_url), 'Ultimedia')
1775 # Look for AdobeTVVideo embeds
1777 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1779 if mobj is not None:
1780 return self.url_result(
1781 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1784 def check_video(vurl):
1785 if YoutubeIE.suitable(vurl):
1787 vpath = compat_urlparse.urlparse(vurl).path
1788 vext = determine_ext(vpath)
1789 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1791 def filter_video(urls):
1792 return list(filter(check_video, urls))
1794 # Start with something easy: JW Player in SWFObject
1795 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1797 # Look for gorilla-vid style embedding
1798 found = filter_video(re.findall(r'''(?sx)
1802 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1805 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1807 # Broaden the search a little bit
1808 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1810 # Broaden the findall a little bit: JWPlayer JS loader
1811 found = filter_video(re.findall(
1812 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1815 found = filter_video(re.findall(r'''(?xs)
1816 flowplayer\("[^"]+",\s*
1818 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1819 ["']?url["']?\s*:\s*["']([^"']+)["']
1824 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1826 # Try to find twitter cards info
1827 found = filter_video(re.findall(
1828 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1830 # We look for Open Graph info:
1831 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1832 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1833 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1834 if m_video_type is not None:
1835 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1838 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1840 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1842 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1843 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1846 # Look also in Refresh HTTP header
1847 refresh_header = head_response.headers.get('Refresh')
1849 # In python 2 response HTTP headers are bytestrings
1850 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1851 refresh_header = refresh_header.decode('iso-8859-1')
1852 found = re.search(REDIRECT_REGEX, refresh_header)
1854 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1855 self.report_following_redirect(new_url)
1861 raise UnsupportedError(url)
1864 for video_url in found:
1865 video_url = compat_urlparse.urljoin(url, video_url)
1866 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1868 # Sometimes, jwplayer extraction will result in a YouTube URL
1869 if YoutubeIE.suitable(video_url):
1870 entries.append(self.url_result(video_url, 'Youtube'))
1873 # here's a fun little line of code for you:
1874 video_id = os.path.splitext(video_id)[0]
1876 ext = determine_ext(video_url)
1880 'formats': self._extract_smil_formats(video_url, video_id),
1881 'uploader': video_uploader,
1882 'title': video_title,
1883 'age_limit': age_limit,
1886 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1891 'uploader': video_uploader,
1892 'title': video_title,
1893 'age_limit': age_limit,
1896 if len(entries) == 1:
1899 for num, e in enumerate(entries, start=1):
1900 # 'url' results don't have a title
1901 if e.get('title') is not None:
1902 e['title'] = '%s (%d)' % (e['title'], num)
1904 '_type': 'playlist',