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 .mtv import MTVServicesEmbeddedIE
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
340 'add_ie': ['Ooyala'],
343 # ooyala video embedded with http://player.ooyala.com/iframe.js
344 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
346 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
348 'title': '"Steve Jobs: Man in the Machine" trailer',
349 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
353 'skip_download': True,
356 # multiple ooyala embeds on SBN network websites
358 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
360 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
361 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
363 'playlist_mincount': 3,
365 'skip_download': True,
367 'add_ie': ['Ooyala'],
371 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
375 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
376 'upload_date': '20140225',
377 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
378 'uploader': 'Tested',
379 'uploader_id': 'testedcom',
381 # No need to test YoutubeIE here
383 'skip_download': True,
388 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
392 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
393 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
398 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
402 'title': 'Охотское море стало целиком российским',
403 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
407 'skip_download': True,
412 '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/',
416 'title': 'Дошкольное воспитание',
421 'url': 'http://www.vestifinance.ru/articles/25753',
424 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
429 'title': 'Госзаказ. День 3',
435 'title': 'Госзаказ. День 2',
441 'title': 'Госзаказ. День 1',
447 'skip_download': True,
452 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
454 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
456 'title': 'Ужастики, русский трейлер (2015)',
457 'thumbnail': 're:^https?://.*\.jpg$',
463 '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',
466 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
468 'playlist_mincount': 7,
472 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
473 'md5': '65fdff94098e4a607385a60c5177c638',
477 'title': 'Hidden miracles of the natural world',
478 'uploader': 'Louie Schwartzberg',
479 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
482 # Embeded Ustream video
484 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
485 'md5': '27b99cdb639c9b12a79bca876a073417',
489 'uploader': 'AU SPA: The NSA and Privacy',
490 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
493 # nowvideo embed hidden behind percent encoding
495 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
496 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
498 'id': '06e53103ca9aa',
500 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
501 'description': 'No description',
506 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
507 'md5': '7653032cbb25bf6c80d80f217055fa43',
509 'id': '048195-004_PLUS7-F',
512 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
513 'upload_date': '20140320',
516 'skip_download': 'Requires rtmpdump'
521 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
525 'title': 'Alcaline, le concert avec Calogero',
526 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
527 'upload_date': '20150226',
528 'timestamp': 1424989860,
533 'skip_download': True,
535 'expected_warnings': [
541 'url': 'http://www.wired.com/2014/04/honda-asimo/',
542 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
544 'id': '53501be369702d3275860000',
546 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
551 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
552 'md5': '441aeeb82eb72c422c7f14ec533999cd',
554 'id': 'k2mm4bCdJ6CQ2i7c8o2',
556 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
559 'add_ie': ['Dailymotion'],
563 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
567 'title': 'The NBL Auction 2014',
568 'uploader': 'BADMINTON England',
569 'uploader_id': 'BADMINTONEvents',
570 'upload_date': '20140603',
571 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
573 'add_ie': ['Youtube'],
575 'skip_download': True,
580 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
581 'md5': '35727f82f58c76d996fc188f9755b0d5',
583 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
586 'description': 'Mario\'s life in the fast lane has never looked so good.',
589 # YouTube embed via <data-embed-url="">
591 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
595 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
596 'uploader': 'Gameloft',
597 'uploader_id': 'gameloft',
598 'upload_date': '20140828',
599 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
602 'skip_download': True,
607 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
609 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
611 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
612 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
617 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
619 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
620 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
626 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
631 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
632 'md5': '9d65602bf31c6e20014319c7d07fba27',
634 'id': '5123ea6d5e5a7',
637 'uploader': 'www.handjobhub.com',
638 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
641 # Multiple brightcove videos
642 # https://github.com/rg3/youtube-dl/issues/2283
644 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
646 'id': 'always-never',
647 'title': 'Always / Never - The New Yorker',
651 'extract_flat': False,
652 'skip_download': True,
657 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
658 'md5': '96f09a37e44da40dd083e12d9a683327',
662 'title': 'Ump changes call to ball',
663 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
665 'timestamp': 1401537900,
666 'upload_date': '20140531',
667 'thumbnail': 're:^https?://.*\.jpg$',
672 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
673 'md5': '8788b683c777a5cf25621eaf286d0c23',
677 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
679 'filesize': 182808282,
680 'uploader': 'education-portal.com',
684 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
685 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
689 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
691 'uploader': 'thoughtworks.wistia.com',
696 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
700 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
701 'uploader': 'Sophos Security',
702 'title': 'Chet Chat 171 - Oct 29, 2014',
703 'upload_date': '20141029',
708 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
712 'upload_date': '20141112',
713 'title': 'Rosetta #CometLanding webcast HL 10',
718 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
721 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
723 'playlist_mincount': 2,
727 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
731 'upload_date': '20141126',
732 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
737 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
739 'id': '730m_DandD_1901_512k',
741 'uploader': 'www.abc.net.au',
742 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
745 # embedded viddler video
747 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
751 'uploader': 'deadspin',
752 'title': 'WALL-TO-GORTAT',
753 'timestamp': 1422285291,
754 'upload_date': '20150126',
756 'add_ie': ['Viddler'],
760 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
764 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
765 'description': 'md5:601cb790edd05908957dae8aaa866465',
766 'upload_date': '20150220',
771 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
775 'upload_date': '20150212',
776 'uploader': 'The National Archives UK',
777 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
778 'uploader_id': 'NationalArchives08',
779 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
784 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
785 'playlist_mincount': 5,
787 'id': 'aanslagen-kopenhagen',
788 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
793 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
797 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
802 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
806 'upload_date': '20150226',
807 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
809 'title': 'John Carlson Postgame 2/25/15',
812 # Kaltura embed (different embed code)
814 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
818 'upload_date': '20150127',
819 'uploader_id': 'PremierMedia',
821 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
824 # Eagle.Platform embed (generic URL)
826 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
830 'title': 'Навальный вышел на свободу',
831 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
832 'thumbnail': 're:^https?://.*\.jpg$',
838 # ClipYou (Eagle.Platform) embed (custom URL)
840 'url': 'http://muz-tv.ru/play/7129/',
844 'title': "'O Sole Mio",
845 'thumbnail': 're:^https?://.*\.jpg$',
852 'url': 'http://muz-tv.ru/kinozal/view/7400/',
856 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
857 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
858 'thumbnail': 're:^https?://.*\.jpg$',
865 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
869 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
870 'thumbnail': 're:^https?://.*\.png$',
876 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
877 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
881 'title': 'Facebook Creates "On This Day" | Crunch Report',
886 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
890 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
895 # Crooks and Liars embed
897 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
901 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
902 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
903 'timestamp': 1428207000,
904 'upload_date': '20150405',
905 'uploader': 'Heather',
908 # Crooks and Liars external embed
910 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
912 'id': 'MTE3MjUtMzQ2MzA',
914 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
915 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
916 'timestamp': 1265032391,
917 'upload_date': '20100201',
918 'uploader': 'Heather',
921 # NBC Sports vplayer embed
923 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
925 'id': 'ln7x1qSThw4k',
927 'title': "PFT Live: New leader in the 'new-look' defense",
928 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
933 'url': 'http://www.udn.com/news/story/7314/822787',
934 'md5': 'fd2060e988c326991037b9aff9df21a6',
938 'title': '中一中男師變性 全校師生力挺',
939 'thumbnail': 're:^https?://.*\.jpg$',
944 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
946 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
948 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
949 'title': 'This is what separates the Excel masters from the wannabes',
954 'skip_download': True,
957 # Contains a SMIL manifest
959 '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',
963 'title': '+ Football: Lottery Champions League Europe',
964 'uploader': 'www.telewebion.com',
968 'skip_download': True,
971 # Brightcove URL in single quotes
973 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
974 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
976 'id': '4255764656001',
978 'title': 'SN Presents: Russell Martin, World Citizen',
979 '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.',
980 'uploader': 'Rogers Sportsnet',
983 # Dailymotion Cloud video
985 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
986 'md5': '49444254273501a64675a7e68c502681',
988 'id': '5585de919473990de4bee11b',
991 'thumbnail': 're:^https?://.*\.jpe?g$',
996 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1000 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1001 'thumbnail': 're:^https?://.*\.jpe?g$',
1002 'uploader': 'ClickHole',
1003 'uploader_id': 'clickhole',
1008 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1010 'id': '74849a00-85a9-11e1-9660-123139220831',
1012 'title': '#whilewewatch',
1015 # AdobeTVVideo embed
1017 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1018 'md5': '43662b577c018ad707a63766462b1e87',
1022 'title': 'New experience with Acrobat DC',
1023 'description': 'New experience with Acrobat DC',
1024 'duration': 248.667,
1027 # ScreenwaveMedia embed
1029 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1030 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1032 'id': 'cinemasnob-55d26273809dd',
1034 'title': 'cinemasnob',
1039 def report_following_redirect(self, new_url):
1040 """Report information extraction."""
1041 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1043 def _extract_rss(self, url, video_id, doc):
1044 playlist_title = doc.find('./channel/title').text
1045 playlist_desc_el = doc.find('./channel/description')
1046 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1049 for it in doc.findall('./channel/item'):
1050 next_url = xpath_text(it, 'link', fatal=False)
1052 enclosure_nodes = it.findall('./enclosure')
1053 for e in enclosure_nodes:
1054 next_url = e.attrib.get('url')
1064 'title': it.find('title').text,
1068 '_type': 'playlist',
1070 'title': playlist_title,
1071 'description': playlist_desc,
1075 def _extract_camtasia(self, url, video_id, webpage):
1076 """ Returns None if no camtasia video can be found. """
1078 camtasia_cfg = self._search_regex(
1079 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1080 webpage, 'camtasia configuration file', default=None)
1081 if camtasia_cfg is None:
1084 title = self._html_search_meta('DC.title', webpage, fatal=True)
1086 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1087 camtasia_cfg = self._download_xml(
1088 camtasia_url, video_id,
1089 note='Downloading camtasia configuration',
1090 errnote='Failed to download camtasia configuration')
1091 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1094 for n in fileset_node.getchildren():
1095 url_n = n.find('./uri')
1100 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1101 'title': '%s - %s' % (title, n.tag),
1102 'url': compat_urlparse.urljoin(url, url_n.text),
1103 'duration': float_or_none(n.find('./duration').text),
1107 '_type': 'playlist',
1112 def _real_extract(self, url):
1113 if url.startswith('//'):
1116 'url': self.http_scheme() + url,
1119 parsed_url = compat_urlparse.urlparse(url)
1120 if not parsed_url.scheme:
1121 default_search = self._downloader.params.get('default_search')
1122 if default_search is None:
1123 default_search = 'fixup_error'
1125 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1127 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1128 return self.url_result('http://' + url)
1129 elif default_search != 'fixup_error':
1130 if default_search == 'auto_warning':
1131 if re.match(r'^(?:url|URL)$', url):
1132 raise ExtractorError(
1133 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1136 self._downloader.report_warning(
1137 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1138 return self.url_result('ytsearch:' + url)
1140 if default_search in ('error', 'fixup_error'):
1141 raise ExtractorError(
1142 '%r is not a valid URL. '
1143 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1144 % (url, url), expected=True)
1146 if ':' not in default_search:
1147 default_search += ':'
1148 return self.url_result(default_search + url)
1150 url, smuggled_data = unsmuggle_url(url)
1151 force_videoid = None
1152 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1153 if smuggled_data and 'force_videoid' in smuggled_data:
1154 force_videoid = smuggled_data['force_videoid']
1155 video_id = force_videoid
1157 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1159 self.to_screen('%s: Requesting header' % video_id)
1161 head_req = HEADRequest(url)
1162 head_response = self._request_webpage(
1164 note=False, errnote='Could not send HEAD request to %s' % url,
1167 if head_response is not False:
1168 # Check for redirect
1169 new_url = head_response.geturl()
1171 self.report_following_redirect(new_url)
1173 new_url = smuggle_url(
1174 new_url, {'force_videoid': force_videoid})
1175 return self.url_result(new_url)
1177 full_response = None
1178 if head_response is False:
1179 request = compat_urllib_request.Request(url)
1180 request.add_header('Accept-Encoding', '*')
1181 full_response = self._request_webpage(request, video_id)
1182 head_response = full_response
1184 # Check for direct link to a video
1185 content_type = head_response.headers.get('Content-Type', '')
1186 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1188 upload_date = unified_strdate(
1189 head_response.headers.get('Last-Modified'))
1192 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1195 'format_id': m.group('format_id'),
1197 'vcodec': 'none' if m.group('type') == 'audio' else None
1199 'upload_date': upload_date,
1202 if not self._downloader.params.get('test', False) and not is_intentional:
1203 force = self._downloader.params.get('force_generic_extractor', False)
1204 self._downloader.report_warning(
1205 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1207 if not full_response:
1208 request = compat_urllib_request.Request(url)
1209 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1210 # making it impossible to download only chunk of the file (yet we need only 512kB to
1211 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1212 # that will always result in downloading the whole file that is not desirable.
1213 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1214 # to accept raw bytes and being able to download only a chunk.
1215 # It may probably better to solve this by checking Content-Type for application/octet-stream
1216 # after HEAD request finishes, but not sure if we can rely on this.
1217 request.add_header('Accept-Encoding', '*')
1218 full_response = self._request_webpage(request, video_id)
1220 # Maybe it's a direct link to a video?
1221 # Be careful not to download the whole thing!
1222 first_bytes = full_response.read(512)
1223 if not is_html(first_bytes):
1224 self._downloader.report_warning(
1225 'URL could be a direct video link, returning it as such.')
1226 upload_date = unified_strdate(
1227 head_response.headers.get('Last-Modified'))
1230 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1233 'upload_date': upload_date,
1236 webpage = self._webpage_read_content(
1237 full_response, url, video_id, prefix=first_bytes)
1239 self.report_extraction(video_id)
1241 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1243 doc = parse_xml(webpage)
1244 if doc.tag == 'rss':
1245 return self._extract_rss(url, video_id, doc)
1246 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1247 return self._parse_smil(doc, url, video_id)
1248 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1249 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1250 except compat_xml_parse_error:
1253 # Is it a Camtasia project?
1254 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1255 if camtasia_res is not None:
1258 # Sometimes embedded video player is hidden behind percent encoding
1259 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1260 # Unescaping the whole page allows to handle those cases in a generic way
1261 webpage = compat_urllib_parse_unquote(webpage)
1263 # it's tempting to parse this further, but you would
1264 # have to take into account all the variations like
1265 # Video Title - Site Name
1266 # Site Name | Video Title
1267 # Video Title - Tagline | Site Name
1268 # and so on and so forth; it's just not practical
1269 video_title = self._html_search_regex(
1270 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1273 # Try to detect age limit automatically
1274 age_limit = self._rta_search(webpage)
1275 # And then there are the jokers who advertise that they use RTA,
1276 # but actually don't.
1277 AGE_LIMIT_MARKERS = [
1278 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1280 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1283 # video uploader is domain name
1284 video_uploader = self._search_regex(
1285 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1288 def _playlist_from_matches(matches, getter=None, ie=None):
1290 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1292 return self.playlist_result(
1293 urlrs, playlist_id=video_id, playlist_title=video_title)
1295 # Look for BrightCove:
1296 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1298 self.to_screen('Brightcove video detected.')
1301 'url': smuggle_url(bc_url, {'Referer': url}),
1302 'ie_key': 'Brightcove'
1303 } for bc_url in bc_urls]
1306 '_type': 'playlist',
1307 'title': video_title,
1312 # Look for embedded rtl.nl player
1313 matches = re.findall(
1314 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1317 return _playlist_from_matches(matches, ie='RtlNl')
1319 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1320 if vimeo_url is not None:
1321 return self.url_result(vimeo_url)
1323 vid_me_embed_url = self._search_regex(
1324 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1325 webpage, 'vid.me embed', default=None)
1326 if vid_me_embed_url is not None:
1327 return self.url_result(vid_me_embed_url, 'Vidme')
1329 # Look for embedded YouTube player
1330 matches = re.findall(r'''(?x)
1339 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1343 return _playlist_from_matches(
1344 matches, lambda m: unescapeHTML(m[1]))
1346 # Look for lazyYT YouTube embed
1347 matches = re.findall(
1348 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1350 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1352 # Look for embedded Dailymotion player
1353 matches = re.findall(
1354 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1356 return _playlist_from_matches(
1357 matches, lambda m: unescapeHTML(m[1]))
1359 # Look for embedded Dailymotion playlist player (#3822)
1361 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1363 playlists = re.findall(
1364 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1366 return _playlist_from_matches(
1367 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1369 # Look for embedded Wistia player
1371 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1373 embed_url = self._proto_relative_url(
1374 unescapeHTML(match.group('url')))
1376 '_type': 'url_transparent',
1379 'uploader': video_uploader,
1380 'title': video_title,
1384 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1387 '_type': 'url_transparent',
1388 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1390 'uploader': video_uploader,
1391 'title': video_title,
1392 'id': match.group('id')
1395 # Look for embedded blip.tv player
1396 bliptv_url = BlipTVIE._extract_url(webpage)
1398 return self.url_result(bliptv_url, 'BlipTV')
1400 # Look for SVT player
1401 svt_url = SVTIE._extract_url(webpage)
1403 return self.url_result(svt_url, 'SVT')
1405 # Look for embedded condenast player
1406 matches = re.findall(
1407 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1411 '_type': 'playlist',
1414 'ie_key': 'CondeNast',
1416 } for ma in matches],
1417 'title': video_title,
1421 # Look for Bandcamp pages with custom domain
1422 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1423 if mobj is not None:
1424 burl = unescapeHTML(mobj.group(1))
1425 # Don't set the extractor because it can be a track url or an album
1426 return self.url_result(burl)
1428 # Look for embedded Vevo player
1430 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1431 if mobj is not None:
1432 return self.url_result(mobj.group('url'))
1434 # Look for embedded Viddler player
1436 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1438 if mobj is not None:
1439 return self.url_result(mobj.group('url'))
1441 # Look for NYTimes player
1443 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1445 if mobj is not None:
1446 return self.url_result(mobj.group('url'))
1448 # Look for Libsyn player
1450 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1451 if mobj is not None:
1452 return self.url_result(mobj.group('url'))
1454 # Look for Ooyala videos
1455 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1456 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1457 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1458 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1459 if mobj is not None:
1460 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1462 # Look for multiple Ooyala embeds on SBN network websites
1463 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1464 if mobj is not None:
1465 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1467 return _playlist_from_matches(
1468 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1470 # Look for Aparat videos
1471 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1472 if mobj is not None:
1473 return self.url_result(mobj.group(1), 'Aparat')
1475 # Look for MPORA videos
1476 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1477 if mobj is not None:
1478 return self.url_result(mobj.group(1), 'Mpora')
1480 # Look for embedded NovaMov-based player
1482 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1483 (?P<url>http://(?:(?:embed|www)\.)?
1485 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1486 videoweed\.(?:es|com)|
1487 movshare\.(?:net|sx|ag)|
1488 divxstage\.(?:eu|net|ch|co|at|ag))
1489 /embed\.php.+?)\1''', webpage)
1490 if mobj is not None:
1491 return self.url_result(mobj.group('url'))
1493 # Look for embedded Facebook player
1495 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1496 if mobj is not None:
1497 return self.url_result(mobj.group('url'), 'Facebook')
1499 # Look for embedded VK player
1500 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1501 if mobj is not None:
1502 return self.url_result(mobj.group('url'), 'VK')
1504 # Look for embedded ivi player
1505 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1506 if mobj is not None:
1507 return self.url_result(mobj.group('url'), 'Ivi')
1509 # Look for embedded Huffington Post player
1511 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1512 if mobj is not None:
1513 return self.url_result(mobj.group('url'), 'HuffPost')
1516 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1517 if mobj is not None:
1518 return self.url_result(mobj.group('url'))
1519 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1520 if mobj is not None:
1521 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1523 # Look for funnyordie embed
1524 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1526 return _playlist_from_matches(
1527 matches, getter=unescapeHTML, ie='FunnyOrDie')
1529 # Look for BBC iPlayer embed
1530 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1532 return _playlist_from_matches(matches, ie='BBCCoUk')
1534 # Look for embedded RUTV player
1535 rutv_url = RUTVIE._extract_url(webpage)
1537 return self.url_result(rutv_url, 'RUTV')
1539 # Look for embedded TVC player
1540 tvc_url = TVCIE._extract_url(webpage)
1542 return self.url_result(tvc_url, 'TVC')
1544 # Look for embedded SportBox player
1545 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1547 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1549 # Look for embedded PornHub player
1550 pornhub_url = PornHubIE._extract_url(webpage)
1552 return self.url_result(pornhub_url, 'PornHub')
1554 # Look for embedded XHamster player
1555 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1557 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1559 # Look for embedded Tvigle player
1561 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1562 if mobj is not None:
1563 return self.url_result(mobj.group('url'), 'Tvigle')
1565 # Look for embedded TED player
1567 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1568 if mobj is not None:
1569 return self.url_result(mobj.group('url'), 'TED')
1571 # Look for embedded Ustream videos
1573 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1574 if mobj is not None:
1575 return self.url_result(mobj.group('url'), 'Ustream')
1577 # Look for embedded arte.tv player
1579 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1581 if mobj is not None:
1582 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1584 # Look for embedded francetv player
1586 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1588 if mobj is not None:
1589 return self.url_result(mobj.group('url'))
1591 # Look for embedded smotri.com player
1592 smotri_url = SmotriIE._extract_url(webpage)
1594 return self.url_result(smotri_url, 'Smotri')
1596 # Look for embedded Myvi.ru player
1597 myvi_url = MyviIE._extract_url(webpage)
1599 return self.url_result(myvi_url)
1601 # Look for embeded soundcloud player
1603 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1605 if mobj is not None:
1606 url = unescapeHTML(mobj.group('url'))
1607 return self.url_result(url)
1609 # Look for embedded vulture.com player
1611 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1613 if mobj is not None:
1614 url = unescapeHTML(mobj.group('url'))
1615 return self.url_result(url, ie='Vulture')
1617 # Look for embedded mtvservices player
1618 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1620 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1622 # Look for embedded yahoo player
1624 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1626 if mobj is not None:
1627 return self.url_result(mobj.group('url'), 'Yahoo')
1629 # Look for embedded sbs.com.au player
1633 <meta\s+property="og:video"\s+content=|
1636 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1638 if mobj is not None:
1639 return self.url_result(mobj.group('url'), 'SBS')
1641 # Look for embedded Cinchcast player
1643 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1645 if mobj is not None:
1646 return self.url_result(mobj.group('url'), 'Cinchcast')
1649 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1653 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1655 if mobj is not None:
1656 return self.url_result(mobj.group('url'), 'MLB')
1659 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1661 if mobj is not None:
1662 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1665 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1667 if mobj is not None:
1668 return self.url_result(mobj.group('url'), 'Livestream')
1670 # Look for Zapiks embed
1672 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1673 if mobj is not None:
1674 return self.url_result(mobj.group('url'), 'Zapiks')
1676 # Look for Kaltura embeds
1677 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1678 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))
1679 if mobj is not None:
1680 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1682 # Look for Eagle.Platform embeds
1684 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1685 if mobj is not None:
1686 return self.url_result(mobj.group('url'), 'EaglePlatform')
1688 # Look for ClipYou (uses Eagle.Platform) embeds
1690 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1691 if mobj is not None:
1692 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1694 # Look for Pladform embeds
1696 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'), 'Pladform')
1700 # Look for Playwire embeds
1702 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1703 if mobj is not None:
1704 return self.url_result(mobj.group('url'))
1706 # Look for 5min embeds
1708 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1709 if mobj is not None:
1710 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1712 # Look for Crooks and Liars embeds
1714 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1715 if mobj is not None:
1716 return self.url_result(mobj.group('url'))
1718 # Look for NBC Sports VPlayer embeds
1719 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1721 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1723 # Look for UDN embeds
1725 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1726 if mobj is not None:
1727 return self.url_result(
1728 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1730 # Look for Senate ISVP iframe
1731 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1733 return self.url_result(senate_isvp_url, 'SenateISVP')
1735 # Look for Dailymotion Cloud videos
1736 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1738 return self.url_result(dmcloud_url, 'DailymotionCloud')
1740 # Look for OnionStudios embeds
1741 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1742 if onionstudios_url:
1743 return self.url_result(onionstudios_url)
1745 # Look for SnagFilms embeds
1746 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1748 return self.url_result(snagfilms_url)
1750 # Look for ScreenwaveMedia embeds
1751 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1752 if mobj is not None:
1753 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1755 # Look for AdobeTVVideo embeds
1757 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1759 if mobj is not None:
1760 return self.url_result(
1761 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1764 def check_video(vurl):
1765 if YoutubeIE.suitable(vurl):
1767 vpath = compat_urlparse.urlparse(vurl).path
1768 vext = determine_ext(vpath)
1769 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1771 def filter_video(urls):
1772 return list(filter(check_video, urls))
1774 # Start with something easy: JW Player in SWFObject
1775 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1777 # Look for gorilla-vid style embedding
1778 found = filter_video(re.findall(r'''(?sx)
1782 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1785 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1787 # Broaden the search a little bit
1788 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1790 # Broaden the findall a little bit: JWPlayer JS loader
1791 found = filter_video(re.findall(
1792 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1795 found = filter_video(re.findall(r'''(?xs)
1796 flowplayer\("[^"]+",\s*
1798 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1799 ["']?url["']?\s*:\s*["']([^"']+)["']
1804 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1806 # Try to find twitter cards info
1807 found = filter_video(re.findall(
1808 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1810 # We look for Open Graph info:
1811 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1812 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1813 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1814 if m_video_type is not None:
1815 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1818 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1820 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1822 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1823 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1826 # Look also in Refresh HTTP header
1827 refresh_header = head_response.headers.get('Refresh')
1829 # In python 2 response HTTP headers are bytestrings
1830 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1831 refresh_header = refresh_header.decode('iso-8859-1')
1832 found = re.search(REDIRECT_REGEX, refresh_header)
1834 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1835 self.report_following_redirect(new_url)
1841 raise UnsupportedError(url)
1844 for video_url in found:
1845 video_url = compat_urlparse.urljoin(url, video_url)
1846 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1848 # Sometimes, jwplayer extraction will result in a YouTube URL
1849 if YoutubeIE.suitable(video_url):
1850 entries.append(self.url_result(video_url, 'Youtube'))
1853 # here's a fun little line of code for you:
1854 video_id = os.path.splitext(video_id)[0]
1856 ext = determine_ext(video_url)
1860 'formats': self._extract_smil_formats(video_url, video_id),
1861 'uploader': video_uploader,
1862 'title': video_title,
1863 'age_limit': age_limit,
1866 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1871 'uploader': video_uploader,
1872 'title': video_title,
1873 'age_limit': age_limit,
1876 if len(entries) == 1:
1879 for num, e in enumerate(entries, start=1):
1880 # 'url' results don't have a title
1881 if e.get('title') is not None:
1882 e['title'] = '%s (%d)' % (e['title'], num)
1884 '_type': 'playlist',