3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .brightcove import (
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .tnaflix import TNAFlixNetworkEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import DailymotionCloudIE
53 from .onionstudios import OnionStudiosIE
54 from .viewlift import ViewLiftEmbedIE
55 from .screenwavemedia import ScreenwaveMediaIE
56 from .mtv import MTVServicesEmbeddedIE
57 from .pladform import PladformIE
58 from .videomore import VideomoreIE
59 from .googledrive import GoogleDriveIE
60 from .jwplatform import JWPlatformIE
61 from .digiteka import DigitekaIE
62 from .instagram import InstagramIE
63 from .liveleak import LiveLeakIE
64 from .threeqsdn import ThreeQSDNIE
67 class GenericIE(InfoExtractor):
68 IE_DESC = 'Generic downloader that works on some sites'
72 # Direct link to a video
74 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
75 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
80 'upload_date': '20100513',
83 # Direct link to media delivered compressed (until Accept-Encoding is *)
85 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
86 'md5': '128c42e68b13950268b648275386fc74',
88 'id': 'FictionJunction-Parallel_Hearts',
90 'title': 'FictionJunction-Parallel_Hearts',
91 'upload_date': '20140522',
93 'expected_warnings': [
94 'URL could be a direct video link, returning it as such.'
97 # Direct download with broken HEAD
99 'url': 'http://ai-radio.org:8000/radio.opus',
106 'skip_download': True, # infinite live stream
108 'expected_warnings': [
109 r'501.*Not Implemented',
113 # Direct link with incorrect MIME type
115 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
116 'md5': '4ccbebe5f36706d85221f204d7eb5913',
118 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
119 'id': '5_Lennart_Poettering_-_Systemd',
121 'title': '5_Lennart_Poettering_-_Systemd',
122 'upload_date': '20141120',
124 'expected_warnings': [
125 'URL could be a direct video link, returning it as such.'
130 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
132 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
133 'title': 'Zero Punctuation',
134 'description': 're:.*groundbreaking video review series.*'
136 'playlist_mincount': 11,
138 # RSS feed with enclosure
140 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
142 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
144 'upload_date': '20150228',
145 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
148 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
150 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
154 'title': 'Automatics, robotics and biocybernetics',
155 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
156 'upload_date': '20130627',
157 'formats': 'mincount:16',
158 'subtitles': 'mincount:1',
161 'force_generic_extractor': True,
162 'skip_download': True,
165 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
167 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
172 'formats': 'mincount:1',
175 'skip_download': True,
178 # SMIL from https://www.restudy.dk/video/play/id/1637
180 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
184 'title': 'video_1637',
185 'formats': 'mincount:3',
188 'skip_download': True,
191 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
193 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
195 'id': 'smil-service',
197 'title': 'smil-service',
198 'formats': 'mincount:1',
201 'skip_download': True,
204 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
206 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
210 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
211 'formats': 'mincount:3',
214 'skip_download': True,
217 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
219 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
221 'id': 'mZlp2ctYIUEB',
223 'title': 'Tikibad ontruimd wegens brand',
224 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
225 'thumbnail': 're:^https?://.*\.jpg$',
229 'skip_download': True,
232 # MPD from http://dash-mse-test.appspot.com/media.html
234 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
235 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
237 'id': 'car-20120827-manifest',
239 'title': 'car-20120827-manifest',
240 'formats': 'mincount:9',
241 'upload_date': '20130904',
244 'format': 'bestvideo',
247 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
249 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
254 'formats': 'mincount:8',
258 'skip_download': True,
261 # m3u8 served with Content-Type: text/plain
263 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
268 'upload_date': '20140720',
269 'formats': 'mincount:11',
273 'skip_download': True,
278 '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',
282 'upload_date': '20130224',
283 'uploader_id': 'TheVerge',
284 'description': 're:^Chris Ziegler takes a look at the\.*',
285 'uploader': 'The Verge',
286 'title': 'First Firefox OS phones side-by-side',
289 'skip_download': False,
293 # redirect in Refresh HTTP header
294 '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',
298 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
299 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
300 'upload_date': '20150917',
301 'uploader_id': 'brtvofficial',
302 'uploader': 'Boiler Room',
305 'skip_download': False,
309 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
310 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
312 'id': '13601338388002',
314 'uploader': 'www.hodiho.fr',
315 'title': 'R\u00e9gis plante sa Jeep',
318 # bandcamp page with custom domain
320 'add_ie': ['Bandcamp'],
321 'url': 'http://bronyrock.com/track/the-pony-mash',
325 'title': 'The Pony Mash',
326 'uploader': 'M_Pallante',
328 'skip': 'There is a limit of 200 free downloads / month for the test song',
330 # embedded brightcove video
331 # it also tests brightcove videos that need to set the 'Referer' in the
334 'add_ie': ['BrightcoveLegacy'],
335 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
337 'id': '2765128793001',
339 'title': 'Le cours de bourse : l’analyse technique',
340 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
341 'uploader': 'BFM BUSINESS',
344 'skip_download': True,
348 # https://github.com/rg3/youtube-dl/issues/2253
349 'url': 'http://bcove.me/i6nfkrc3',
350 'md5': '0ba9446db037002366bab3b3eb30c88c',
352 'id': '3101154703001',
354 'title': 'Still no power',
355 'uploader': 'thestar.com',
356 '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.',
358 'add_ie': ['BrightcoveLegacy'],
361 'url': 'http://www.championat.com/video/football/v/87/87499.html',
362 'md5': 'fb973ecf6e4a78a67453647444222983',
364 'id': '3414141473001',
366 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
367 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
368 'uploader': 'Championat',
372 # https://github.com/rg3/youtube-dl/issues/3541
373 'add_ie': ['BrightcoveLegacy'],
374 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
376 'id': '3866516442001',
378 'title': 'Leer mij vrouwen kennen: Aflevering 1',
379 'description': 'Leer mij vrouwen kennen: Aflevering 1',
380 'uploader': 'SBS Broadcasting',
382 'skip': 'Restricted to Netherlands',
384 'skip_download': True, # m3u8 download
389 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
390 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
392 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
394 'title': '2cc213299525360.mov', # that's what we get
397 'add_ie': ['Ooyala'],
400 # ooyala video embedded with http://player.ooyala.com/iframe.js
401 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
403 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
405 'title': '"Steve Jobs: Man in the Machine" trailer',
406 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
410 'skip_download': True,
415 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
419 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
420 'upload_date': '20140225',
421 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
422 'uploader': 'Tested',
423 'uploader_id': 'testedcom',
425 # No need to test YoutubeIE here
427 'skip_download': True,
432 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
436 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
437 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
442 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
446 'title': 'Охотское море стало целиком российским',
447 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
451 'skip_download': True,
456 '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/',
460 'title': 'Дошкольное воспитание',
465 'url': 'http://www.vestifinance.ru/articles/25753',
468 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
473 'title': 'Госзаказ. День 3',
479 'title': 'Госзаказ. День 2',
485 'title': 'Госзаказ. День 1',
491 'skip_download': True,
496 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
498 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
500 'title': 'Ужастики, русский трейлер (2015)',
501 'thumbnail': 're:^https?://.*\.jpg$',
507 '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',
510 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
512 'playlist_mincount': 7,
516 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
517 'md5': '65fdff94098e4a607385a60c5177c638',
521 'title': 'Hidden miracles of the natural world',
522 'uploader': 'Louie Schwartzberg',
523 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
526 # Embedded Ustream video
528 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
529 'md5': '27b99cdb639c9b12a79bca876a073417',
533 'uploader': 'AU SPA: The NSA and Privacy',
534 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
537 # nowvideo embed hidden behind percent encoding
539 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
540 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
542 'id': '06e53103ca9aa',
544 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
545 'description': 'No description',
550 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
551 'md5': '7653032cbb25bf6c80d80f217055fa43',
553 'id': '048195-004_PLUS7-F',
556 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
557 'upload_date': '20140320',
560 'skip_download': 'Requires rtmpdump'
565 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
569 'title': 'Alcaline, le concert avec Calogero',
570 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
571 'upload_date': '20150226',
572 'timestamp': 1424989860,
577 'skip_download': True,
579 'expected_warnings': [
585 'url': 'http://www.wired.com/2014/04/honda-asimo/',
586 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
588 'id': '53501be369702d3275860000',
590 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
595 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
596 'md5': '441aeeb82eb72c422c7f14ec533999cd',
598 'id': 'k2mm4bCdJ6CQ2i7c8o2',
600 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
601 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
603 'uploader_id': 'xgditw',
604 'upload_date': '20140425',
605 'timestamp': 1398441542,
607 'add_ie': ['Dailymotion'],
611 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
615 'title': 'The NBL Auction 2014',
616 'uploader': 'BADMINTON England',
617 'uploader_id': 'BADMINTONEvents',
618 'upload_date': '20140603',
619 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
621 'add_ie': ['Youtube'],
623 'skip_download': True,
628 'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
629 'md5': '35727f82f58c76d996fc188f9755b0d5',
631 'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
634 'description': 'Mario\'s life in the fast lane has never looked so good.',
637 # YouTube embed via <data-embed-url="">
639 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
643 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
644 'uploader': 'Gameloft',
645 'uploader_id': 'gameloft',
646 'upload_date': '20140828',
647 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
650 'skip_download': True,
655 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
657 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
659 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
660 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
665 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
667 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
668 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
674 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
679 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
680 'md5': '9d65602bf31c6e20014319c7d07fba27',
682 'id': '5123ea6d5e5a7',
685 'uploader': 'www.handjobhub.com',
686 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
689 # Multiple brightcove videos
690 # https://github.com/rg3/youtube-dl/issues/2283
692 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
694 'id': 'always-never',
695 'title': 'Always / Never - The New Yorker',
699 'extract_flat': False,
700 'skip_download': True,
705 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
706 'md5': '96f09a37e44da40dd083e12d9a683327',
710 'title': 'Ump changes call to ball',
711 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
713 'timestamp': 1401537900,
714 'upload_date': '20140531',
715 'thumbnail': 're:^https?://.*\.jpg$',
720 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
721 'md5': '8788b683c777a5cf25621eaf286d0c23',
725 'title': 'md5:51364a8d3d009997ba99656004b5e20d',
727 'filesize': 182808282,
728 'uploader': 'education-portal.com',
732 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
733 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
737 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
738 'description': 'a Martin Fowler video from ThoughtWorks',
740 'uploader': 'thoughtworks.wistia.com',
741 'upload_date': '20140603',
742 'timestamp': 1401832161,
745 # Wistia standard embed (async)
747 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
751 'title': 'Drip Brennan Dunn Workshop',
752 'description': 'a JV Webinars video from getdrip-1',
754 'upload_date': '20160518',
755 'timestamp': 1463607249,
758 'skip_download': True,
763 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
767 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
768 'uploader': 'Sophos Security',
769 'title': 'Chet Chat 171 - Oct 29, 2014',
770 'upload_date': '20141029',
775 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
779 'upload_date': '20141112',
780 'title': 'Rosetta #CometLanding webcast HL 10',
785 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
788 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
790 'playlist_mincount': 2,
794 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
798 'upload_date': '20141126',
799 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
804 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
806 'id': '730m_DandD_1901_512k',
808 'uploader': 'www.abc.net.au',
809 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
812 # embedded viddler video
814 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
818 'uploader': 'deadspin',
819 'title': 'WALL-TO-GORTAT',
820 'timestamp': 1422285291,
821 'upload_date': '20150126',
823 'add_ie': ['Viddler'],
827 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
831 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
832 'description': 'md5:601cb790edd05908957dae8aaa866465',
833 'upload_date': '20150220',
838 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
842 'upload_date': '20150212',
843 'uploader': 'The National Archives UK',
844 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
845 'uploader_id': 'NationalArchives08',
846 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
851 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
852 'playlist_mincount': 5,
854 'id': 'aanslagen-kopenhagen',
855 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
860 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
864 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
869 'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
873 'upload_date': '20150226',
874 'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
876 'title': 'John Carlson Postgame 2/25/15',
879 # Kaltura embed (different embed code)
881 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
885 'upload_date': '20150127',
886 'uploader_id': 'PremierMedia',
888 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
891 # Kaltura embed protected with referrer
893 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
897 'title': 'Violetta - Achter De Schermen - Ruggero',
898 'description': 'Achter de schermen met Ruggero',
899 'timestamp': 1435133761,
900 'upload_date': '20150624',
901 'uploader_id': 'echojecka',
904 # Eagle.Platform embed (generic URL)
906 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
907 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
911 'title': 'Навальный вышел на свободу',
912 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
913 'thumbnail': 're:^https?://.*\.jpg$',
919 # ClipYou (Eagle.Platform) embed (custom URL)
921 'url': 'http://muz-tv.ru/play/7129/',
922 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
926 'title': "'O Sole Mio",
927 'thumbnail': 're:^https?://.*\.jpg$',
934 'url': 'http://muz-tv.ru/kinozal/view/7400/',
938 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
939 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
940 'thumbnail': 're:^https?://.*\.jpg$',
947 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
951 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
952 'thumbnail': 're:^https?://.*\.png$',
958 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
959 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
963 'title': 'Facebook Creates "On This Day" | Crunch Report',
968 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
972 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
977 # Crooks and Liars embed
979 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
983 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
984 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
985 'timestamp': 1428207000,
986 'upload_date': '20150405',
987 'uploader': 'Heather',
990 # Crooks and Liars external embed
992 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
994 'id': 'MTE3MjUtMzQ2MzA',
996 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
997 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
998 'timestamp': 1265032391,
999 'upload_date': '20100201',
1000 'uploader': 'Heather',
1003 # NBC Sports vplayer embed
1005 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1007 'id': 'ln7x1qSThw4k',
1009 'title': "PFT Live: New leader in the 'new-look' defense",
1010 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1011 'uploader': 'NBCU-SPORTS',
1012 'upload_date': '20140107',
1013 'timestamp': 1389118457,
1018 'url': 'http://www.udn.com/news/story/7314/822787',
1019 'md5': 'fd2060e988c326991037b9aff9df21a6',
1023 'title': '中一中男師變性 全校師生力挺',
1024 'thumbnail': 're:^https?://.*\.jpg$',
1029 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1031 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1033 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1034 'title': 'This is what separates the Excel masters from the wannabes',
1035 'duration': 191.933,
1039 'skip_download': True,
1042 # Contains a SMIL manifest
1044 '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',
1048 'title': '+ Football: Lottery Champions League Europe',
1049 'uploader': 'www.telewebion.com',
1053 'skip_download': True,
1056 # Brightcove URL in single quotes
1058 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1059 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1061 'id': '4255764656001',
1063 'title': 'SN Presents: Russell Martin, World Citizen',
1064 '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.',
1065 'uploader': 'Rogers Sportsnet',
1066 'uploader_id': '1704050871',
1067 'upload_date': '20150525',
1068 'timestamp': 1432570283,
1071 # Dailymotion Cloud video
1073 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1074 'md5': '49444254273501a64675a7e68c502681',
1076 'id': '5585de919473990de4bee11b',
1078 'title': 'Le débat',
1079 'thumbnail': 're:^https?://.*\.jpe?g$',
1082 # OnionStudios embed
1084 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1088 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1089 'thumbnail': 're:^https?://.*\.jpe?g$',
1090 'uploader': 'ClickHole',
1091 'uploader_id': 'clickhole',
1096 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1098 'id': '74849a00-85a9-11e1-9660-123139220831',
1100 'title': '#whilewewatch',
1103 # AdobeTVVideo embed
1105 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1106 'md5': '43662b577c018ad707a63766462b1e87',
1110 'title': 'New experience with Acrobat DC',
1111 'description': 'New experience with Acrobat DC',
1112 'duration': 248.667,
1115 # ScreenwaveMedia embed
1117 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1118 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1120 'id': 'cinemasnob-55d26273809dd',
1122 'title': 'cinemasnob',
1125 # BrightcoveInPageEmbed embed
1127 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1129 'id': '4238694884001',
1131 'title': 'Tabletop: Dread, Last Thoughts',
1132 'description': 'Tabletop: Dread, Last Thoughts',
1136 # JWPlayer with M3U8
1138 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1142 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1143 'uploader': 'ren.tv',
1147 'skip_download': True,
1150 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1151 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1153 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1155 'id': '4785848093001',
1157 'title': 'The Cardinal Pell Interview',
1158 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1159 'uploader': 'GlobeCast Australia - GlobeStream',
1160 'uploader_id': '2733773828001',
1161 'upload_date': '20160304',
1162 'timestamp': 1457083087,
1166 'skip_download': True,
1169 # Another form of arte.tv embed
1171 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1172 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1174 'id': '030273-562_PLUS7-F',
1176 'title': 'ARTE Reportage - Nulle part, en France',
1177 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1178 'upload_date': '20160409',
1183 'url': 'http://www.wykop.pl/link/3088787/',
1184 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1186 'id': '874_1459135191',
1188 'title': 'Man shows poor quality of new apartment building',
1189 'description': 'The wall is like a sand pile.',
1190 'uploader': 'Lake8737',
1195 def report_following_redirect(self, new_url):
1196 """Report information extraction."""
1197 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1199 def _extract_rss(self, url, video_id, doc):
1200 playlist_title = doc.find('./channel/title').text
1201 playlist_desc_el = doc.find('./channel/description')
1202 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1205 for it in doc.findall('./channel/item'):
1206 next_url = xpath_text(it, 'link', fatal=False)
1208 enclosure_nodes = it.findall('./enclosure')
1209 for e in enclosure_nodes:
1210 next_url = e.attrib.get('url')
1220 'title': it.find('title').text,
1224 '_type': 'playlist',
1226 'title': playlist_title,
1227 'description': playlist_desc,
1231 def _extract_camtasia(self, url, video_id, webpage):
1232 """ Returns None if no camtasia video can be found. """
1234 camtasia_cfg = self._search_regex(
1235 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1236 webpage, 'camtasia configuration file', default=None)
1237 if camtasia_cfg is None:
1240 title = self._html_search_meta('DC.title', webpage, fatal=True)
1242 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1243 camtasia_cfg = self._download_xml(
1244 camtasia_url, video_id,
1245 note='Downloading camtasia configuration',
1246 errnote='Failed to download camtasia configuration')
1247 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1250 for n in fileset_node.getchildren():
1251 url_n = n.find('./uri')
1256 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1257 'title': '%s - %s' % (title, n.tag),
1258 'url': compat_urlparse.urljoin(url, url_n.text),
1259 'duration': float_or_none(n.find('./duration').text),
1263 '_type': 'playlist',
1268 def _real_extract(self, url):
1269 if url.startswith('//'):
1272 'url': self.http_scheme() + url,
1275 parsed_url = compat_urlparse.urlparse(url)
1276 if not parsed_url.scheme:
1277 default_search = self._downloader.params.get('default_search')
1278 if default_search is None:
1279 default_search = 'fixup_error'
1281 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1283 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1284 return self.url_result('http://' + url)
1285 elif default_search != 'fixup_error':
1286 if default_search == 'auto_warning':
1287 if re.match(r'^(?:url|URL)$', url):
1288 raise ExtractorError(
1289 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1292 self._downloader.report_warning(
1293 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1294 return self.url_result('ytsearch:' + url)
1296 if default_search in ('error', 'fixup_error'):
1297 raise ExtractorError(
1298 '%r is not a valid URL. '
1299 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1300 % (url, url), expected=True)
1302 if ':' not in default_search:
1303 default_search += ':'
1304 return self.url_result(default_search + url)
1306 url, smuggled_data = unsmuggle_url(url)
1307 force_videoid = None
1308 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1309 if smuggled_data and 'force_videoid' in smuggled_data:
1310 force_videoid = smuggled_data['force_videoid']
1311 video_id = force_videoid
1313 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1315 self.to_screen('%s: Requesting header' % video_id)
1317 head_req = HEADRequest(url)
1318 head_response = self._request_webpage(
1320 note=False, errnote='Could not send HEAD request to %s' % url,
1323 if head_response is not False:
1324 # Check for redirect
1325 new_url = head_response.geturl()
1327 self.report_following_redirect(new_url)
1329 new_url = smuggle_url(
1330 new_url, {'force_videoid': force_videoid})
1331 return self.url_result(new_url)
1333 full_response = None
1334 if head_response is False:
1335 request = sanitized_Request(url)
1336 request.add_header('Accept-Encoding', '*')
1337 full_response = self._request_webpage(request, video_id)
1338 head_response = full_response
1342 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1343 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1346 # Check for direct link to a video
1347 content_type = head_response.headers.get('Content-Type', '').lower()
1348 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1350 format_id = m.group('format_id')
1351 if format_id.endswith('mpegurl'):
1352 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1353 elif format_id == 'f4m':
1354 formats = self._extract_f4m_formats(url, video_id)
1357 'format_id': m.group('format_id'),
1359 'vcodec': 'none' if m.group('type') == 'audio' else None
1361 info_dict['direct'] = True
1362 self._sort_formats(formats)
1363 info_dict['formats'] = formats
1366 if not self._downloader.params.get('test', False) and not is_intentional:
1367 force = self._downloader.params.get('force_generic_extractor', False)
1368 self._downloader.report_warning(
1369 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1371 if not full_response:
1372 request = sanitized_Request(url)
1373 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1374 # making it impossible to download only chunk of the file (yet we need only 512kB to
1375 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1376 # that will always result in downloading the whole file that is not desirable.
1377 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1378 # to accept raw bytes and being able to download only a chunk.
1379 # It may probably better to solve this by checking Content-Type for application/octet-stream
1380 # after HEAD request finishes, but not sure if we can rely on this.
1381 request.add_header('Accept-Encoding', '*')
1382 full_response = self._request_webpage(request, video_id)
1384 first_bytes = full_response.read(512)
1386 # Is it an M3U playlist?
1387 if first_bytes.startswith(b'#EXTM3U'):
1388 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1389 self._sort_formats(info_dict['formats'])
1392 # Maybe it's a direct link to a video?
1393 # Be careful not to download the whole thing!
1394 if not is_html(first_bytes):
1395 self._downloader.report_warning(
1396 'URL could be a direct video link, returning it as such.')
1403 webpage = self._webpage_read_content(
1404 full_response, url, video_id, prefix=first_bytes)
1406 self.report_extraction(video_id)
1408 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1410 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1411 if doc.tag == 'rss':
1412 return self._extract_rss(url, video_id, doc)
1413 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1414 smil = self._parse_smil(doc, url, video_id)
1415 self._sort_formats(smil['formats'])
1417 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1418 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1419 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1420 info_dict['formats'] = self._parse_mpd_formats(
1421 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1422 self._sort_formats(info_dict['formats'])
1424 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1425 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1426 self._sort_formats(info_dict['formats'])
1428 except compat_xml_parse_error:
1431 # Is it a Camtasia project?
1432 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1433 if camtasia_res is not None:
1436 # Sometimes embedded video player is hidden behind percent encoding
1437 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1438 # Unescaping the whole page allows to handle those cases in a generic way
1439 webpage = compat_urllib_parse_unquote(webpage)
1441 # it's tempting to parse this further, but you would
1442 # have to take into account all the variations like
1443 # Video Title - Site Name
1444 # Site Name | Video Title
1445 # Video Title - Tagline | Site Name
1446 # and so on and so forth; it's just not practical
1447 video_title = self._og_search_title(
1448 webpage, default=None) or self._html_search_regex(
1449 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1452 # Try to detect age limit automatically
1453 age_limit = self._rta_search(webpage)
1454 # And then there are the jokers who advertise that they use RTA,
1455 # but actually don't.
1456 AGE_LIMIT_MARKERS = [
1457 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1459 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1462 # video uploader is domain name
1463 video_uploader = self._search_regex(
1464 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1466 video_description = self._og_search_description(webpage, default=None)
1467 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1470 def _playlist_from_matches(matches, getter=None, ie=None):
1472 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1474 return self.playlist_result(
1475 urlrs, playlist_id=video_id, playlist_title=video_title)
1477 # Look for Brightcove Legacy Studio embeds
1478 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1480 self.to_screen('Brightcove video detected.')
1483 'url': smuggle_url(bc_url, {'Referer': url}),
1484 'ie_key': 'BrightcoveLegacy'
1485 } for bc_url in bc_urls]
1488 '_type': 'playlist',
1489 'title': video_title,
1494 # Look for Brightcove New Studio embeds
1495 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1497 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1499 # Look for embedded rtl.nl player
1500 matches = re.findall(
1501 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1504 return _playlist_from_matches(matches, ie='RtlNl')
1506 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1507 if vimeo_url is not None:
1508 return self.url_result(vimeo_url)
1510 vid_me_embed_url = self._search_regex(
1511 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1512 webpage, 'vid.me embed', default=None)
1513 if vid_me_embed_url is not None:
1514 return self.url_result(vid_me_embed_url, 'Vidme')
1516 # Look for embedded YouTube player
1517 matches = re.findall(r'''(?x)
1526 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1530 return _playlist_from_matches(
1531 matches, lambda m: unescapeHTML(m[1]))
1533 # Look for lazyYT YouTube embed
1534 matches = re.findall(
1535 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1537 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1539 # Look for embedded Dailymotion player
1540 matches = re.findall(
1541 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1543 return _playlist_from_matches(
1544 matches, lambda m: unescapeHTML(m[1]))
1546 # Look for embedded Dailymotion playlist player (#3822)
1548 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1550 playlists = re.findall(
1551 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1553 return _playlist_from_matches(
1554 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1556 # Look for embedded Wistia player
1558 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1560 embed_url = self._proto_relative_url(
1561 unescapeHTML(match.group('url')))
1563 '_type': 'url_transparent',
1566 'uploader': video_uploader,
1567 'title': video_title,
1571 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1574 '_type': 'url_transparent',
1575 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
1577 'uploader': video_uploader,
1578 'title': video_title,
1579 'id': match.group('id')
1584 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1585 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1588 return self.url_result(self._proto_relative_url(
1589 'wistia:%s' % match.group('id')), 'Wistia')
1591 # Look for SVT player
1592 svt_url = SVTIE._extract_url(webpage)
1594 return self.url_result(svt_url, 'SVT')
1596 # Look for embedded condenast player
1597 matches = re.findall(
1598 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1602 '_type': 'playlist',
1605 'ie_key': 'CondeNast',
1607 } for ma in matches],
1608 'title': video_title,
1612 # Look for Bandcamp pages with custom domain
1613 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1614 if mobj is not None:
1615 burl = unescapeHTML(mobj.group(1))
1616 # Don't set the extractor because it can be a track url or an album
1617 return self.url_result(burl)
1619 # Look for embedded Vevo player
1621 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1622 if mobj is not None:
1623 return self.url_result(mobj.group('url'))
1625 # Look for embedded Viddler player
1627 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1629 if mobj is not None:
1630 return self.url_result(mobj.group('url'))
1632 # Look for NYTimes player
1634 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1636 if mobj is not None:
1637 return self.url_result(mobj.group('url'))
1639 # Look for Libsyn player
1641 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1642 if mobj is not None:
1643 return self.url_result(mobj.group('url'))
1645 # Look for Ooyala videos
1646 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1647 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1648 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1649 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1650 if mobj is not None:
1651 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1653 # Look for multiple Ooyala embeds on SBN network websites
1654 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1655 if mobj is not None:
1656 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1658 return _playlist_from_matches(
1659 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1661 # Look for Aparat videos
1662 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1663 if mobj is not None:
1664 return self.url_result(mobj.group(1), 'Aparat')
1666 # Look for MPORA videos
1667 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1668 if mobj is not None:
1669 return self.url_result(mobj.group(1), 'Mpora')
1671 # Look for embedded NovaMov-based player
1673 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1674 (?P<url>http://(?:(?:embed|www)\.)?
1676 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1677 videoweed\.(?:es|com)|
1678 movshare\.(?:net|sx|ag)|
1679 divxstage\.(?:eu|net|ch|co|at|ag))
1680 /embed\.php.+?)\1''', webpage)
1681 if mobj is not None:
1682 return self.url_result(mobj.group('url'))
1684 # Look for embedded Facebook player
1686 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1687 if mobj is not None:
1688 return self.url_result(mobj.group('url'), 'Facebook')
1690 # Look for embedded VK player
1691 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1692 if mobj is not None:
1693 return self.url_result(mobj.group('url'), 'VK')
1695 # Look for embedded Odnoklassniki player
1696 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1700 # Look for embedded ivi player
1701 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1702 if mobj is not None:
1703 return self.url_result(mobj.group('url'), 'Ivi')
1705 # Look for embedded Huffington Post player
1707 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1708 if mobj is not None:
1709 return self.url_result(mobj.group('url'), 'HuffPost')
1712 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1713 if mobj is not None:
1714 return self.url_result(mobj.group('url'))
1715 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1716 if mobj is not None:
1717 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1719 # Look for funnyordie embed
1720 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1722 return _playlist_from_matches(
1723 matches, getter=unescapeHTML, ie='FunnyOrDie')
1725 # Look for BBC iPlayer embed
1726 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1728 return _playlist_from_matches(matches, ie='BBCCoUk')
1730 # Look for embedded RUTV player
1731 rutv_url = RUTVIE._extract_url(webpage)
1733 return self.url_result(rutv_url, 'RUTV')
1735 # Look for embedded TVC player
1736 tvc_url = TVCIE._extract_url(webpage)
1738 return self.url_result(tvc_url, 'TVC')
1740 # Look for embedded SportBox player
1741 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1743 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1745 # Look for embedded PornHub player
1746 pornhub_url = PornHubIE._extract_url(webpage)
1748 return self.url_result(pornhub_url, 'PornHub')
1750 # Look for embedded XHamster player
1751 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1753 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1755 # Look for embedded TNAFlixNetwork player
1756 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1758 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1760 # Look for embedded Tvigle player
1762 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1763 if mobj is not None:
1764 return self.url_result(mobj.group('url'), 'Tvigle')
1766 # Look for embedded TED player
1768 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1769 if mobj is not None:
1770 return self.url_result(mobj.group('url'), 'TED')
1772 # Look for embedded Ustream videos
1774 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1775 if mobj is not None:
1776 return self.url_result(mobj.group('url'), 'Ustream')
1778 # Look for embedded arte.tv player
1780 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1782 if mobj is not None:
1783 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1785 # Look for embedded francetv player
1787 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1789 if mobj is not None:
1790 return self.url_result(mobj.group('url'))
1792 # Look for embedded smotri.com player
1793 smotri_url = SmotriIE._extract_url(webpage)
1795 return self.url_result(smotri_url, 'Smotri')
1797 # Look for embedded Myvi.ru player
1798 myvi_url = MyviIE._extract_url(webpage)
1800 return self.url_result(myvi_url)
1802 # Look for embedded soundcloud player
1804 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1806 if mobj is not None:
1807 url = unescapeHTML(mobj.group('url'))
1808 return self.url_result(url)
1810 # Look for embedded vulture.com player
1812 r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
1814 if mobj is not None:
1815 url = unescapeHTML(mobj.group('url'))
1816 return self.url_result(url, ie='Vulture')
1818 # Look for embedded mtvservices player
1819 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1821 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1823 # Look for embedded yahoo player
1825 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1827 if mobj is not None:
1828 return self.url_result(mobj.group('url'), 'Yahoo')
1830 # Look for embedded sbs.com.au player
1834 <meta\s+property="og:video"\s+content=|
1837 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1839 if mobj is not None:
1840 return self.url_result(mobj.group('url'), 'SBS')
1842 # Look for embedded Cinchcast player
1844 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1846 if mobj is not None:
1847 return self.url_result(mobj.group('url'), 'Cinchcast')
1850 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1854 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1856 if mobj is not None:
1857 return self.url_result(mobj.group('url'), 'MLB')
1860 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1862 if mobj is not None:
1863 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1866 r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
1868 if mobj is not None:
1869 return self.url_result(mobj.group('url'), 'Livestream')
1871 # Look for Zapiks embed
1873 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1874 if mobj is not None:
1875 return self.url_result(mobj.group('url'), 'Zapiks')
1877 # Look for Kaltura embeds
1878 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_?[Ii]d'\s*:\s*'(?P<id>[^']+)',", webpage) or
1879 re.search(r'(?s)(?P<q1>["\'])(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?(?P=q1).*?entry_?[Ii]d\s*:\s*(?P<q2>["\'])(?P<id>.+?)(?P=q2)', webpage))
1880 if mobj is not None:
1881 return self.url_result(smuggle_url(
1882 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1883 {'source_url': url}), 'Kaltura')
1885 # Look for Eagle.Platform embeds
1887 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1888 if mobj is not None:
1889 return self.url_result(mobj.group('url'), 'EaglePlatform')
1891 # Look for ClipYou (uses Eagle.Platform) embeds
1893 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1894 if mobj is not None:
1895 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1897 # Look for Pladform embeds
1898 pladform_url = PladformIE._extract_url(webpage)
1900 return self.url_result(pladform_url)
1902 # Look for Videomore embeds
1903 videomore_url = VideomoreIE._extract_url(webpage)
1905 return self.url_result(videomore_url)
1907 # Look for Playwire embeds
1909 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1910 if mobj is not None:
1911 return self.url_result(mobj.group('url'))
1913 # Look for 5min embeds
1915 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1916 if mobj is not None:
1917 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1919 # Look for Crooks and Liars embeds
1921 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1922 if mobj is not None:
1923 return self.url_result(mobj.group('url'))
1925 # Look for NBC Sports VPlayer embeds
1926 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1928 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1930 # Look for Google Drive embeds
1931 google_drive_url = GoogleDriveIE._extract_url(webpage)
1932 if google_drive_url:
1933 return self.url_result(google_drive_url, 'GoogleDrive')
1935 # Look for UDN embeds
1937 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1938 if mobj is not None:
1939 return self.url_result(
1940 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1942 # Look for Senate ISVP iframe
1943 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1945 return self.url_result(senate_isvp_url, 'SenateISVP')
1947 # Look for Dailymotion Cloud videos
1948 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1950 return self.url_result(dmcloud_url, 'DailymotionCloud')
1952 # Look for OnionStudios embeds
1953 onionstudios_url = OnionStudiosIE._extract_url(webpage)
1954 if onionstudios_url:
1955 return self.url_result(onionstudios_url)
1957 # Look for ViewLift embeds
1958 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
1960 return self.url_result(viewlift_url)
1962 # Look for JWPlatform embeds
1963 jwplatform_url = JWPlatformIE._extract_url(webpage)
1965 return self.url_result(jwplatform_url, 'JWPlatform')
1967 # Look for ScreenwaveMedia embeds
1968 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
1969 if mobj is not None:
1970 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
1972 # Look for Digiteka embeds
1973 digiteka_url = DigitekaIE._extract_url(webpage)
1975 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
1977 # Look for Limelight embeds
1978 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
1982 'Channel': 'channel',
1983 'ChannelList': 'channel_list',
1985 return self.url_result('limelight:%s:%s' % (
1986 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
1988 # Look for AdobeTVVideo embeds
1990 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
1992 if mobj is not None:
1993 return self.url_result(
1994 self._proto_relative_url(unescapeHTML(mobj.group(1))),
1997 # Look for Vine embeds
1999 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2001 if mobj is not None:
2002 return self.url_result(
2003 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2005 # Look for Instagram embeds
2006 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2007 if instagram_embed_url is not None:
2008 return self.url_result(
2009 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2011 # Look for LiveLeak embeds
2012 liveleak_url = LiveLeakIE._extract_url(webpage)
2014 return self.url_result(liveleak_url, 'LiveLeak')
2016 # Look for 3Q SDN embeds
2017 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2020 '_type': 'url_transparent',
2021 'ie_key': ThreeQSDNIE.ie_key(),
2022 'url': self._proto_relative_url(threeqsdn_url),
2023 'title': video_title,
2024 'description': video_description,
2025 'thumbnail': video_thumbnail,
2026 'uploader': video_uploader,
2029 def check_video(vurl):
2030 if YoutubeIE.suitable(vurl):
2032 vpath = compat_urlparse.urlparse(vurl).path
2033 vext = determine_ext(vpath)
2034 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2036 def filter_video(urls):
2037 return list(filter(check_video, urls))
2039 # Start with something easy: JW Player in SWFObject
2040 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2042 # Look for gorilla-vid style embedding
2043 found = filter_video(re.findall(r'''(?sx)
2047 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2050 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2052 # Broaden the search a little bit
2053 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2055 # Broaden the findall a little bit: JWPlayer JS loader
2056 found = filter_video(re.findall(
2057 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2060 found = filter_video(re.findall(r'''(?xs)
2061 flowplayer\("[^"]+",\s*
2063 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2064 ["']?url["']?\s*:\s*["']([^"']+)["']
2069 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2071 # Try to find twitter cards info
2072 found = filter_video(re.findall(
2073 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2075 # We look for Open Graph info:
2076 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2077 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2078 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2079 if m_video_type is not None:
2080 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2083 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2085 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2087 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2088 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2091 # Look also in Refresh HTTP header
2092 refresh_header = head_response.headers.get('Refresh')
2094 # In python 2 response HTTP headers are bytestrings
2095 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2096 refresh_header = refresh_header.decode('iso-8859-1')
2097 found = re.search(REDIRECT_REGEX, refresh_header)
2099 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2100 self.report_following_redirect(new_url)
2106 raise UnsupportedError(url)
2109 for video_url in found:
2110 video_url = unescapeHTML(video_url)
2111 video_url = video_url.replace('\\/', '/')
2112 video_url = compat_urlparse.urljoin(url, video_url)
2113 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2115 # Sometimes, jwplayer extraction will result in a YouTube URL
2116 if YoutubeIE.suitable(video_url):
2117 entries.append(self.url_result(video_url, 'Youtube'))
2120 # here's a fun little line of code for you:
2121 video_id = os.path.splitext(video_id)[0]
2125 'uploader': video_uploader,
2126 'title': video_title,
2127 'age_limit': age_limit,
2130 ext = determine_ext(video_url)
2132 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2134 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2136 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2138 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2140 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2142 entry_info_dict['url'] = video_url
2144 if entry_info_dict.get('formats'):
2145 self._sort_formats(entry_info_dict['formats'])
2147 entries.append(entry_info_dict)
2149 if len(entries) == 1:
2152 for num, e in enumerate(entries, start=1):
2153 # 'url' results don't have a title
2154 if e.get('title') is not None:
2155 e['title'] = '%s (%d)' % (e['title'], num)
2157 '_type': 'playlist',