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 .svt import SVTIE
45 from .pornhub import PornHubIE
46 from .xhamster import XHamsterEmbedIE
47 from .vimeo import VimeoIE
48 from .dailymotion import DailymotionCloudIE
49 from .onionstudios import OnionStudiosIE
50 from .snagfilms import SnagFilmsEmbedIE
51 from .screenwavemedia import ScreenwaveMediaIE
52 from .mtv import MTVServicesEmbeddedIE
55 class GenericIE(InfoExtractor):
56 IE_DESC = 'Generic downloader that works on some sites'
60 # Direct link to a video
62 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
63 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
68 'upload_date': '20100513',
71 # Direct link to media delivered compressed (until Accept-Encoding is *)
73 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
74 'md5': '128c42e68b13950268b648275386fc74',
76 'id': 'FictionJunction-Parallel_Hearts',
78 'title': 'FictionJunction-Parallel_Hearts',
79 'upload_date': '20140522',
81 'expected_warnings': [
82 'URL could be a direct video link, returning it as such.'
85 # Direct download with broken HEAD
87 'url': 'http://ai-radio.org:8000/radio.opus',
94 'skip_download': True, # infinite live stream
96 'expected_warnings': [
97 r'501.*Not Implemented'
100 # Direct link with incorrect MIME type
102 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
103 'md5': '4ccbebe5f36706d85221f204d7eb5913',
105 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
106 'id': '5_Lennart_Poettering_-_Systemd',
108 'title': '5_Lennart_Poettering_-_Systemd',
109 'upload_date': '20141120',
111 'expected_warnings': [
112 'URL could be a direct video link, returning it as such.'
117 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
119 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
120 'title': 'Zero Punctuation',
121 'description': 're:.*groundbreaking video review series.*'
123 'playlist_mincount': 11,
125 # RSS feed with enclosure
127 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
129 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
131 'upload_date': '20150228',
132 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
135 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
137 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
141 'title': 'Automatics, robotics and biocybernetics',
142 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
143 'formats': 'mincount:16',
144 'subtitles': 'mincount:1',
147 'force_generic_extractor': True,
148 'skip_download': True,
151 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
153 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
158 'formats': 'mincount:1',
161 'skip_download': True,
164 # SMIL from https://www.restudy.dk/video/play/id/1637
166 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
170 'title': 'video_1637',
171 'formats': 'mincount:3',
174 'skip_download': True,
177 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
179 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
181 'id': 'smil-service',
183 'title': 'smil-service',
184 'formats': 'mincount:1',
187 'skip_download': True,
190 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
192 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
196 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
197 'formats': 'mincount:3',
200 'skip_download': True,
203 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
205 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
207 'id': 'mZlp2ctYIUEB',
209 'title': 'Tikibad ontruimd wegens brand',
210 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
211 'thumbnail': 're:^https?://.*\.jpg$',
215 'skip_download': True,
220 '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',
224 'upload_date': '20130224',
225 'uploader_id': 'TheVerge',
226 'description': 're:^Chris Ziegler takes a look at the\.*',
227 'uploader': 'The Verge',
228 'title': 'First Firefox OS phones side-by-side',
231 'skip_download': False,
235 # redirect in Refresh HTTP header
236 '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',
240 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
241 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
242 'upload_date': '20150917',
243 'uploader_id': 'brtvofficial',
244 'uploader': 'Boiler Room',
247 'skip_download': False,
251 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
252 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
254 'id': '13601338388002',
256 'uploader': 'www.hodiho.fr',
257 'title': 'R\u00e9gis plante sa Jeep',
260 # bandcamp page with custom domain
262 'add_ie': ['Bandcamp'],
263 'url': 'http://bronyrock.com/track/the-pony-mash',
267 'title': 'The Pony Mash',
268 'uploader': 'M_Pallante',
270 'skip': 'There is a limit of 200 free downloads / month for the test song',
272 # embedded brightcove video
273 # it also tests brightcove videos that need to set the 'Referer' in the
276 'add_ie': ['Brightcove'],
277 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
279 'id': '2765128793001',
281 'title': 'Le cours de bourse : l’analyse technique',
282 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
283 'uploader': 'BFM BUSINESS',
286 'skip_download': True,
290 # https://github.com/rg3/youtube-dl/issues/2253
291 'url': 'http://bcove.me/i6nfkrc3',
292 'md5': '0ba9446db037002366bab3b3eb30c88c',
294 'id': '3101154703001',
296 'title': 'Still no power',
297 'uploader': 'thestar.com',
298 '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.',
300 'add_ie': ['Brightcove'],
303 'url': 'http://www.championat.com/video/football/v/87/87499.html',
304 'md5': 'fb973ecf6e4a78a67453647444222983',
306 'id': '3414141473001',
308 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
309 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
310 'uploader': 'Championat',
314 # https://github.com/rg3/youtube-dl/issues/3541
315 'add_ie': ['Brightcove'],
316 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
318 'id': '3866516442001',
320 'title': 'Leer mij vrouwen kennen: Aflevering 1',
321 'description': 'Leer mij vrouwen kennen: Aflevering 1',
322 'uploader': 'SBS Broadcasting',
324 'skip': 'Restricted to Netherlands',
326 'skip_download': True, # m3u8 download
331 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
332 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
334 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
336 'title': '2cc213299525360.mov', # that's what we get
338 'add_ie': ['Ooyala'],
341 # ooyala video embedded with http://player.ooyala.com/iframe.js
342 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
344 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
346 'title': '"Steve Jobs: Man in the Machine" trailer',
347 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
350 'skip_download': True,
353 # multiple ooyala embeds on SBN network websites
355 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
357 'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
358 'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
360 'playlist_mincount': 3,
362 'skip_download': True,
364 'add_ie': ['Ooyala'],
368 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
372 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
373 'upload_date': '20140225',
374 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
375 'uploader': 'Tested',
376 'uploader_id': 'testedcom',
378 # No need to test YoutubeIE here
380 'skip_download': True,
385 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
389 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
390 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
395 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
399 'title': 'Охотское море стало целиком российским',
400 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
404 'skip_download': True,
409 '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/',
413 'title': 'Дошкольное воспитание',
418 'url': 'http://www.vestifinance.ru/articles/25753',
421 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
426 'title': 'Госзаказ. День 3',
432 'title': 'Госзаказ. День 2',
438 'title': 'Госзаказ. День 1',
444 'skip_download': True,
449 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
451 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
453 'title': 'Ужастики, русский трейлер (2015)',
454 'thumbnail': 're:^https?://.*\.jpg$',
460 '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',
463 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
465 'playlist_mincount': 7,
469 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
470 'md5': '65fdff94098e4a607385a60c5177c638',
474 'title': 'Hidden miracles of the natural world',
475 'uploader': 'Louie Schwartzberg',
476 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
479 # Embeded Ustream video
481 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
482 'md5': '27b99cdb639c9b12a79bca876a073417',
486 'uploader': 'AU SPA: The NSA and Privacy',
487 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
490 # nowvideo embed hidden behind percent encoding
492 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
493 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
495 'id': '06e53103ca9aa',
497 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
498 'description': 'No description',
503 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
504 'md5': '7653032cbb25bf6c80d80f217055fa43',
506 'id': '048195-004_PLUS7-F',
509 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
510 'upload_date': '20140320',
513 'skip_download': 'Requires rtmpdump'
518 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
522 'title': 'Alcaline, le concert avec Calogero',
523 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
524 'upload_date': '20150226',
525 'timestamp': 1424989860,
530 'skip_download': True,
532 'expected_warnings': [
538 'url': 'http://www.wired.com/2014/04/honda-asimo/',
539 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
541 'id': '53501be369702d3275860000',
543 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
548 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
549 'md5': '441aeeb82eb72c422c7f14ec533999cd',
551 'id': 'k2mm4bCdJ6CQ2i7c8o2',
553 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
556 'add_ie': ['Dailymotion'],
560 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
564 'title': 'The NBL Auction 2014',
565 'uploader': 'BADMINTON England',
566 'uploader_id': 'BADMINTONEvents',
567 'upload_date': '20140603',
568 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
570 'add_ie': ['Youtube'],
572 'skip_download': True,
577 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
578 'md5': '35727f82f58c76d996fc188f9755b0d5',
580 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
583 'description': 'Mario\'s life in the fast lane has never looked so good.',
586 # YouTube embed via <data-embed-url="">
588 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
592 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
593 'uploader': 'Gameloft',
594 'uploader_id': 'gameloft',
595 'upload_date': '20140828',
596 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
599 'skip_download': True,
604 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
606 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
608 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
609 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
614 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
616 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
617 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
623 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
628 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
629 'md5': '9d65602bf31c6e20014319c7d07fba27',
631 'id': '5123ea6d5e5a7',
634 'uploader': 'www.handjobhub.com',
635 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
638 # Multiple brightcove videos
639 # https://github.com/rg3/youtube-dl/issues/2283
641 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
643 'id': 'always-never',
644 'title': 'Always / Never - The New Yorker',
648 'extract_flat': False,
649 'skip_download': True,
654 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
655 'md5': '96f09a37e44da40dd083e12d9a683327',
659 'title': 'Ump changes call to ball',
660 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
662 'timestamp': 1401537900,
663 'upload_date': '20140531',
664 'thumbnail': 're:^https?://.*\.jpg$',
669 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
670 'md5': '8788b683c777a5cf25621eaf286d0c23',
674 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
676 'filesize': 182808282,
677 'uploader': 'education-portal.com',
681 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
682 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
686 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
688 'uploader': 'thoughtworks.wistia.com',
693 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
697 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
698 'uploader': 'Sophos Security',
699 'title': 'Chet Chat 171 - Oct 29, 2014',
700 'upload_date': '20141029',
705 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
709 'upload_date': '20141112',
710 'title': 'Rosetta #CometLanding webcast HL 10',
715 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
718 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
720 'playlist_mincount': 2,
724 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
728 'upload_date': '20141126',
729 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
734 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
736 'id': '730m_DandD_1901_512k',
738 'uploader': 'www.abc.net.au',
739 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
742 # embedded viddler video
744 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
748 'uploader': 'deadspin',
749 'title': 'WALL-TO-GORTAT',
750 'timestamp': 1422285291,
751 'upload_date': '20150126',
753 'add_ie': ['Viddler'],
757 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
761 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
762 'description': 'md5:601cb790edd05908957dae8aaa866465',
763 'upload_date': '20150220',
768 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
772 'upload_date': '20150212',
773 'uploader': 'The National Archives UK',
774 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
775 'uploader_id': 'NationalArchives08',
776 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
781 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
782 'playlist_mincount': 5,
784 'id': 'aanslagen-kopenhagen',
785 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
790 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
794 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
799 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
803 'upload_date': '20150226',
804 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
806 'title': 'John Carlson Postgame 2/25/15',
809 # Kaltura embed (different embed code)
811 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
815 'upload_date': '20150127',
816 'uploader_id': 'PremierMedia',
818 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
821 # Eagle.Platform embed (generic URL)
823 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
827 'title': 'Навальный вышел на свободу',
828 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
829 'thumbnail': 're:^https?://.*\.jpg$',
835 # ClipYou (Eagle.Platform) embed (custom URL)
837 'url': 'http://muz-tv.ru/play/7129/',
841 'title': "'O Sole Mio",
842 'thumbnail': 're:^https?://.*\.jpg$',
849 'url': 'http://muz-tv.ru/kinozal/view/7400/',
853 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
854 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
855 'thumbnail': 're:^https?://.*\.jpg$',
862 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
866 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
867 'thumbnail': 're:^https?://.*\.png$',
873 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
874 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
878 'title': 'Facebook Creates "On This Day" | Crunch Report',
883 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
887 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
892 # Crooks and Liars embed
894 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
898 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
899 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
900 'timestamp': 1428207000,
901 'upload_date': '20150405',
902 'uploader': 'Heather',
905 # Crooks and Liars external embed
907 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
909 'id': 'MTE3MjUtMzQ2MzA',
911 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
912 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
913 'timestamp': 1265032391,
914 'upload_date': '20100201',
915 'uploader': 'Heather',
918 # NBC Sports vplayer embed
920 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
922 'id': 'ln7x1qSThw4k',
924 'title': "PFT Live: New leader in the 'new-look' defense",
925 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
930 'url': 'http://www.udn.com/news/story/7314/822787',
931 'md5': 'fd2060e988c326991037b9aff9df21a6',
935 'title': '中一中男師變性 全校師生力挺',
936 'thumbnail': 're:^https?://.*\.jpg$',
941 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
943 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
945 'description': 'VIDEO: Index/Match versus VLOOKUP.',
946 'title': 'This is what separates the Excel masters from the wannabes',
950 'skip_download': True,
953 # Contains a SMIL manifest
955 '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',
959 'title': '+ Football: Lottery Champions League Europe',
960 'uploader': 'www.telewebion.com',
964 'skip_download': True,
967 # Brightcove URL in single quotes
969 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
970 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
972 'id': '4255764656001',
974 'title': 'SN Presents: Russell Martin, World Citizen',
975 '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.',
976 'uploader': 'Rogers Sportsnet',
979 # Dailymotion Cloud video
981 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
982 'md5': '49444254273501a64675a7e68c502681',
984 'id': '5585de919473990de4bee11b',
987 'thumbnail': 're:^https?://.*\.jpe?g$',
992 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
996 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
997 'thumbnail': 're:^https?://.*\.jpe?g$',
998 'uploader': 'ClickHole',
999 'uploader_id': 'clickhole',
1004 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1006 'id': '74849a00-85a9-11e1-9660-123139220831',
1008 'title': '#whilewewatch',
1011 # AdobeTVVideo embed
1013 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1014 'md5': '43662b577c018ad707a63766462b1e87',
1018 'title': 'New experience with Acrobat DC',
1019 'description': 'New experience with Acrobat DC',
1020 'duration': 248.667,
1023 # ScreenwaveMedia embed
1025 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1026 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1028 'id': 'cinemasnob-55d26273809dd',
1030 'title': 'cinemasnob',
1035 def report_following_redirect(self, new_url):
1036 """Report information extraction."""
1037 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1039 def _extract_rss(self, url, video_id, doc):
1040 playlist_title = doc.find('./channel/title').text
1041 playlist_desc_el = doc.find('./channel/description')
1042 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1045 for it in doc.findall('./channel/item'):
1046 next_url = xpath_text(it, 'link', fatal=False)
1048 enclosure_nodes = it.findall('./enclosure')
1049 for e in enclosure_nodes:
1050 next_url = e.attrib.get('url')
1060 'title': it.find('title').text,
1064 '_type': 'playlist',
1066 'title': playlist_title,
1067 'description': playlist_desc,
1071 def _extract_camtasia(self, url, video_id, webpage):
1072 """ Returns None if no camtasia video can be found. """
1074 camtasia_cfg = self._search_regex(
1075 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1076 webpage, 'camtasia configuration file', default=None)
1077 if camtasia_cfg is None:
1080 title = self._html_search_meta('DC.title', webpage, fatal=True)
1082 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1083 camtasia_cfg = self._download_xml(
1084 camtasia_url, video_id,
1085 note='Downloading camtasia configuration',
1086 errnote='Failed to download camtasia configuration')
1087 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1090 for n in fileset_node.getchildren():
1091 url_n = n.find('./uri')
1096 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1097 'title': '%s - %s' % (title, n.tag),
1098 'url': compat_urlparse.urljoin(url, url_n.text),
1099 'duration': float_or_none(n.find('./duration').text),
1103 '_type': 'playlist',
1108 def _real_extract(self, url):
1109 if url.startswith('//'):
1112 'url': self.http_scheme() + url,
1115 parsed_url = compat_urlparse.urlparse(url)
1116 if not parsed_url.scheme:
1117 default_search = self._downloader.params.get('default_search')
1118 if default_search is None:
1119 default_search = 'fixup_error'
1121 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1123 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1124 return self.url_result('http://' + url)
1125 elif default_search != 'fixup_error':
1126 if default_search == 'auto_warning':
1127 if re.match(r'^(?:url|URL)$', url):
1128 raise ExtractorError(
1129 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1132 self._downloader.report_warning(
1133 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1134 return self.url_result('ytsearch:' + url)
1136 if default_search in ('error', 'fixup_error'):
1137 raise ExtractorError(
1138 '%r is not a valid URL. '
1139 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1140 % (url, url), expected=True)
1142 if ':' not in default_search:
1143 default_search += ':'
1144 return self.url_result(default_search + url)
1146 url, smuggled_data = unsmuggle_url(url)
1147 force_videoid = None
1148 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1149 if smuggled_data and 'force_videoid' in smuggled_data:
1150 force_videoid = smuggled_data['force_videoid']
1151 video_id = force_videoid
1153 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1155 self.to_screen('%s: Requesting header' % video_id)
1157 head_req = HEADRequest(url)
1158 head_response = self._request_webpage(
1160 note=False, errnote='Could not send HEAD request to %s' % url,
1163 if head_response is not False:
1164 # Check for redirect
1165 new_url = head_response.geturl()
1167 self.report_following_redirect(new_url)
1169 new_url = smuggle_url(
1170 new_url, {'force_videoid': force_videoid})
1171 return self.url_result(new_url)
1173 full_response = None
1174 if head_response is False:
1175 request = compat_urllib_request.Request(url)
1176 request.add_header('Accept-Encoding', '*')
1177 full_response = self._request_webpage(request, video_id)
1178 head_response = full_response
1180 # Check for direct link to a video
1181 content_type = head_response.headers.get('Content-Type', '')
1182 m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
1184 upload_date = unified_strdate(
1185 head_response.headers.get('Last-Modified'))
1188 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1191 'format_id': m.group('format_id'),
1193 'vcodec': 'none' if m.group('type') == 'audio' else None
1195 'upload_date': upload_date,
1198 if not self._downloader.params.get('test', False) and not is_intentional:
1199 force = self._downloader.params.get('force_generic_extractor', False)
1200 self._downloader.report_warning(
1201 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1203 if not full_response:
1204 request = compat_urllib_request.Request(url)
1205 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1206 # making it impossible to download only chunk of the file (yet we need only 512kB to
1207 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1208 # that will always result in downloading the whole file that is not desirable.
1209 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1210 # to accept raw bytes and being able to download only a chunk.
1211 # It may probably better to solve this by checking Content-Type for application/octet-stream
1212 # after HEAD request finishes, but not sure if we can rely on this.
1213 request.add_header('Accept-Encoding', '*')
1214 full_response = self._request_webpage(request, video_id)
1216 # Maybe it's a direct link to a video?
1217 # Be careful not to download the whole thing!
1218 first_bytes = full_response.read(512)
1219 if not is_html(first_bytes):
1220 self._downloader.report_warning(
1221 'URL could be a direct video link, returning it as such.')
1222 upload_date = unified_strdate(
1223 head_response.headers.get('Last-Modified'))
1226 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1229 'upload_date': upload_date,
1232 webpage = self._webpage_read_content(
1233 full_response, url, video_id, prefix=first_bytes)
1235 self.report_extraction(video_id)
1237 # Is it an RSS feed, a SMIL file or a XSPF playlist?
1239 doc = parse_xml(webpage)
1240 if doc.tag == 'rss':
1241 return self._extract_rss(url, video_id, doc)
1242 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1243 return self._parse_smil(doc, url, video_id)
1244 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1245 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1246 except compat_xml_parse_error:
1249 # Is it a Camtasia project?
1250 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1251 if camtasia_res is not None:
1254 # Sometimes embedded video player is hidden behind percent encoding
1255 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1256 # Unescaping the whole page allows to handle those cases in a generic way
1257 webpage = compat_urllib_parse_unquote(webpage)
1259 # it's tempting to parse this further, but you would
1260 # have to take into account all the variations like
1261 # Video Title - Site Name
1262 # Site Name | Video Title
1263 # Video Title - Tagline | Site Name
1264 # and so on and so forth; it's just not practical
1265 video_title = self._html_search_regex(
1266 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1269 # Try to detect age limit automatically
1270 age_limit = self._rta_search(webpage)
1271 # And then there are the jokers who advertise that they use RTA,
1272 # but actually don't.
1273 AGE_LIMIT_MARKERS = [
1274 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1276 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1279 # video uploader is domain name
1280 video_uploader = self._search_regex(
1281 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1284 def _playlist_from_matches(matches, getter=None, ie=None):
1286 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1288 return self.playlist_result(
1289 urlrs, playlist_id=video_id, playlist_title=video_title)
1291 # Look for BrightCove:
1292 bc_urls = BrightcoveIE._extract_brightcove_urls(webpage)
1294 self.to_screen('Brightcove video detected.')
1297 'url': smuggle_url(bc_url, {'Referer': url}),
1298 'ie_key': 'Brightcove'
1299 } for bc_url in bc_urls]
1302 '_type': 'playlist',
1303 'title': video_title,
1308 # Look for embedded rtl.nl player
1309 matches = re.findall(
1310 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1313 return _playlist_from_matches(matches, ie='RtlNl')
1315 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1316 if vimeo_url is not None:
1317 return self.url_result(vimeo_url)
1319 vid_me_embed_url = self._search_regex(
1320 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1321 webpage, 'vid.me embed', default=None)
1322 if vid_me_embed_url is not None:
1323 return self.url_result(vid_me_embed_url, 'Vidme')
1325 # Look for embedded YouTube player
1326 matches = re.findall(r'''(?x)
1335 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1339 return _playlist_from_matches(
1340 matches, lambda m: unescapeHTML(m[1]))
1342 # Look for lazyYT YouTube embed
1343 matches = re.findall(
1344 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1346 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1348 # Look for embedded Dailymotion player
1349 matches = re.findall(
1350 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
1352 return _playlist_from_matches(
1353 matches, lambda m: unescapeHTML(m[1]))
1355 # Look for embedded Dailymotion playlist player (#3822)
1357 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1359 playlists = re.findall(
1360 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1362 return _playlist_from_matches(
1363 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1365 # Look for embedded Wistia player
1367 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1369 embed_url = self._proto_relative_url(
1370 unescapeHTML(match.group('url')))
1372 '_type': 'url_transparent',
1375 'uploader': video_uploader,
1376 'title': video_title,
1380 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1383 '_type': 'url_transparent',
1384 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1386 'uploader': video_uploader,
1387 'title': video_title,
1388 'id': match.group('id')
1391 # Look for SVT player
1392 svt_url = SVTIE._extract_url(webpage)
1394 return self.url_result(svt_url, 'SVT')
1396 # Look for embedded condenast player
1397 matches = re.findall(
1398 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1402 '_type': 'playlist',
1405 'ie_key': 'CondeNast',
1407 } for ma in matches],
1408 'title': video_title,
1412 # Look for Bandcamp pages with custom domain
1413 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1414 if mobj is not None:
1415 burl = unescapeHTML(mobj.group(1))
1416 # Don't set the extractor because it can be a track url or an album
1417 return self.url_result(burl)
1419 # Look for embedded Vevo player
1421 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1422 if mobj is not None:
1423 return self.url_result(mobj.group('url'))
1425 # Look for embedded Viddler player
1427 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1429 if mobj is not None:
1430 return self.url_result(mobj.group('url'))
1432 # Look for NYTimes player
1434 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1436 if mobj is not None:
1437 return self.url_result(mobj.group('url'))
1439 # Look for Libsyn player
1441 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1442 if mobj is not None:
1443 return self.url_result(mobj.group('url'))
1445 # Look for Ooyala videos
1446 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1447 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1448 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1449 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1450 if mobj is not None:
1451 return OoyalaIE._build_url_result(mobj.group('ec'))
1453 # Look for multiple Ooyala embeds on SBN network websites
1454 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1455 if mobj is not None:
1456 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1458 return _playlist_from_matches(
1459 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala')
1461 # Look for Aparat videos
1462 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1463 if mobj is not None:
1464 return self.url_result(mobj.group(1), 'Aparat')
1466 # Look for MPORA videos
1467 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1468 if mobj is not None:
1469 return self.url_result(mobj.group(1), 'Mpora')
1471 # Look for embedded NovaMov-based player
1473 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1474 (?P<url>http://(?:(?:embed|www)\.)?
1476 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1477 videoweed\.(?:es|com)|
1478 movshare\.(?:net|sx|ag)|
1479 divxstage\.(?:eu|net|ch|co|at|ag))
1480 /embed\.php.+?)\1''', webpage)
1481 if mobj is not None:
1482 return self.url_result(mobj.group('url'))
1484 # Look for embedded Facebook player
1486 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1487 if mobj is not None:
1488 return self.url_result(mobj.group('url'), 'Facebook')
1490 # Look for embedded VK player
1491 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1492 if mobj is not None:
1493 return self.url_result(mobj.group('url'), 'VK')
1495 # Look for embedded ivi player
1496 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1497 if mobj is not None:
1498 return self.url_result(mobj.group('url'), 'Ivi')
1500 # Look for embedded Huffington Post player
1502 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1503 if mobj is not None:
1504 return self.url_result(mobj.group('url'), 'HuffPost')
1507 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1508 if mobj is not None:
1509 return self.url_result(mobj.group('url'))
1510 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1511 if mobj is not None:
1512 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1514 # Look for funnyordie embed
1515 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1517 return _playlist_from_matches(
1518 matches, getter=unescapeHTML, ie='FunnyOrDie')
1520 # Look for BBC iPlayer embed
1521 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1523 return _playlist_from_matches(matches, ie='BBCCoUk')
1525 # Look for embedded RUTV player
1526 rutv_url = RUTVIE._extract_url(webpage)
1528 return self.url_result(rutv_url, 'RUTV')
1530 # Look for embedded TVC player
1531 tvc_url = TVCIE._extract_url(webpage)
1533 return self.url_result(tvc_url, 'TVC')
1535 # Look for embedded SportBox player
1536 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1538 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1540 # Look for embedded PornHub player
1541 pornhub_url = PornHubIE._extract_url(webpage)
1543 return self.url_result(pornhub_url, 'PornHub')
1545 # Look for embedded XHamster player
1546 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1548 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1550 # Look for embedded Tvigle player
1552 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1553 if mobj is not None:
1554 return self.url_result(mobj.group('url'), 'Tvigle')
1556 # Look for embedded TED player
1558 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1559 if mobj is not None:
1560 return self.url_result(mobj.group('url'), 'TED')
1562 # Look for embedded Ustream videos
1564 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1565 if mobj is not None:
1566 return self.url_result(mobj.group('url'), 'Ustream')
1568 # Look for embedded arte.tv player
1570 r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
1572 if mobj is not None:
1573 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1575 # Look for embedded francetv player
1577 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1579 if mobj is not None:
1580 return self.url_result(mobj.group('url'))
1582 # Look for embedded smotri.com player
1583 smotri_url = SmotriIE._extract_url(webpage)
1585 return self.url_result(smotri_url, 'Smotri')
1587 # Look for embedded Myvi.ru player
1588 myvi_url = MyviIE._extract_url(webpage)
1590 return self.url_result(myvi_url)
1592 # Look for embeded soundcloud player
1594 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1596 if mobj is not None:
1597 url = unescapeHTML(mobj.group('url'))
1598 return self.url_result(url)
1600 # Look for embedded vulture.com player
1602 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1604 if mobj is not None:
1605 url = unescapeHTML(mobj.group('url'))
1606 return self.url_result(url, ie='Vulture')
1608 # Look for embedded mtvservices player
1609 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1611 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1613 # Look for embedded yahoo player
1615 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1617 if mobj is not None:
1618 return self.url_result(mobj.group('url'), 'Yahoo')
1620 # Look for embedded sbs.com.au player
1624 <meta\s+property="og:video"\s+content=|
1627 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1629 if mobj is not None:
1630 return self.url_result(mobj.group('url'), 'SBS')
1632 # Look for embedded Cinchcast player
1634 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1636 if mobj is not None:
1637 return self.url_result(mobj.group('url'), 'Cinchcast')
1640 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1644 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1646 if mobj is not None:
1647 return self.url_result(mobj.group('url'), 'MLB')
1650 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1652 if mobj is not None:
1653 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1656 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1658 if mobj is not None:
1659 return self.url_result(mobj.group('url'), 'Livestream')
1661 # Look for Zapiks embed
1663 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1664 if mobj is not None:
1665 return self.url_result(mobj.group('url'), 'Zapiks')
1667 # Look for Kaltura embeds
1668 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
1669 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))
1670 if mobj is not None:
1671 return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
1673 # Look for Eagle.Platform embeds
1675 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1676 if mobj is not None:
1677 return self.url_result(mobj.group('url'), 'EaglePlatform')
1679 # Look for ClipYou (uses Eagle.Platform) embeds
1681 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1682 if mobj is not None:
1683 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1685 # Look for Pladform embeds
1687 r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
1688 if mobj is not None:
1689 return self.url_result(mobj.group('url'), 'Pladform')
1691 # Look for Playwire embeds
1693 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1694 if mobj is not None:
1695 return self.url_result(mobj.group('url'))
1697 # Look for 5min embeds
1699 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1700 if mobj is not None:
1701 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1703 # Look for Crooks and Liars embeds
1705 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1706 if mobj is not None:
1707 return self.url_result(mobj.group('url'))
1709 # Look for NBC Sports VPlayer embeds
1710 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1712 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1714 # Look for UDN embeds
1716 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
1717 if mobj is not None:
1718 return self.url_result(
1719 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1721 # Look for Senate ISVP iframe
1722 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1724 return self.url_result(senate_isvp_url, 'SenateISVP')
1726 # Look for Dailymotion Cloud videos
1727 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1729 return self.url_result(dmcloud_url, 'DailymotionCloud')
1731 # Look for OnionStudios embeds
1732 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1733 if onionstudios_url:
1734 return self.url_result(onionstudios_url)
1736 # Look for SnagFilms embeds
1737 snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
1739 return self.url_result(snagfilms_url)
1741 # Look for ScreenwaveMedia embeds
1742 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1743 if mobj is not None:
1744 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1746 # Look for AdobeTVVideo embeds
1748 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1750 if mobj is not None:
1751 return self.url_result(
1752 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1755 def check_video(vurl):
1756 if YoutubeIE.suitable(vurl):
1758 vpath = compat_urlparse.urlparse(vurl).path
1759 vext = determine_ext(vpath)
1760 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
1762 def filter_video(urls):
1763 return list(filter(check_video, urls))
1765 # Start with something easy: JW Player in SWFObject
1766 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
1768 # Look for gorilla-vid style embedding
1769 found = filter_video(re.findall(r'''(?sx)
1773 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
1776 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
1778 # Broaden the search a little bit
1779 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
1781 # Broaden the findall a little bit: JWPlayer JS loader
1782 found = filter_video(re.findall(
1783 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
1786 found = filter_video(re.findall(r'''(?xs)
1787 flowplayer\("[^"]+",\s*
1789 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
1790 ["']?url["']?\s*:\s*["']([^"']+)["']
1795 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
1797 # Try to find twitter cards info
1798 found = filter_video(re.findall(
1799 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
1801 # We look for Open Graph info:
1802 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
1803 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
1804 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
1805 if m_video_type is not None:
1806 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
1809 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
1811 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
1813 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
1814 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
1817 # Look also in Refresh HTTP header
1818 refresh_header = head_response.headers.get('Refresh')
1820 # In python 2 response HTTP headers are bytestrings
1821 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
1822 refresh_header = refresh_header.decode('iso-8859-1')
1823 found = re.search(REDIRECT_REGEX, refresh_header)
1825 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
1826 self.report_following_redirect(new_url)
1832 raise UnsupportedError(url)
1835 for video_url in found:
1836 video_url = compat_urlparse.urljoin(url, video_url)
1837 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
1839 # Sometimes, jwplayer extraction will result in a YouTube URL
1840 if YoutubeIE.suitable(video_url):
1841 entries.append(self.url_result(video_url, 'Youtube'))
1844 # here's a fun little line of code for you:
1845 video_id = os.path.splitext(video_id)[0]
1847 ext = determine_ext(video_url)
1851 'formats': self._extract_smil_formats(video_url, video_id),
1852 'uploader': video_uploader,
1853 'title': video_title,
1854 'age_limit': age_limit,
1857 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
1862 'uploader': video_uploader,
1863 'title': video_title,
1864 'age_limit': age_limit,
1867 if len(entries) == 1:
1870 for num, e in enumerate(entries, start=1):
1871 # 'url' results don't have a title
1872 if e.get('title') is not None:
1873 e['title'] = '%s (%d)' % (e['title'], num)
1875 '_type': 'playlist',