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
65 from .theplatform import ThePlatformIE
66 from .vessel import VesselIE
67 from .kaltura import KalturaIE
68 from .eagleplatform import EaglePlatformIE
71 class GenericIE(InfoExtractor):
72 IE_DESC = 'Generic downloader that works on some sites'
76 # Direct link to a video
78 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
79 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
84 'upload_date': '20100513',
87 # Direct link to media delivered compressed (until Accept-Encoding is *)
89 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
90 'md5': '128c42e68b13950268b648275386fc74',
92 'id': 'FictionJunction-Parallel_Hearts',
94 'title': 'FictionJunction-Parallel_Hearts',
95 'upload_date': '20140522',
97 'expected_warnings': [
98 'URL could be a direct video link, returning it as such.'
101 # Direct download with broken HEAD
103 'url': 'http://ai-radio.org:8000/radio.opus',
110 'skip_download': True, # infinite live stream
112 'expected_warnings': [
113 r'501.*Not Implemented',
117 # Direct link with incorrect MIME type
119 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
120 'md5': '4ccbebe5f36706d85221f204d7eb5913',
122 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
123 'id': '5_Lennart_Poettering_-_Systemd',
125 'title': '5_Lennart_Poettering_-_Systemd',
126 'upload_date': '20141120',
128 'expected_warnings': [
129 'URL could be a direct video link, returning it as such.'
134 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
136 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
137 'title': 'Zero Punctuation',
138 'description': 're:.*groundbreaking video review series.*'
140 'playlist_mincount': 11,
142 # RSS feed with enclosure
144 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
146 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
148 'upload_date': '20150228',
149 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
152 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
154 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
158 'title': 'Automatics, robotics and biocybernetics',
159 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
160 'upload_date': '20130627',
161 'formats': 'mincount:16',
162 'subtitles': 'mincount:1',
165 'force_generic_extractor': True,
166 'skip_download': True,
169 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
171 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
176 'formats': 'mincount:1',
179 'skip_download': True,
182 # SMIL from https://www.restudy.dk/video/play/id/1637
184 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
188 'title': 'video_1637',
189 'formats': 'mincount:3',
192 'skip_download': True,
195 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
197 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
199 'id': 'smil-service',
201 'title': 'smil-service',
202 'formats': 'mincount:1',
205 'skip_download': True,
208 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
210 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
214 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
215 'formats': 'mincount:3',
218 'skip_download': True,
221 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
223 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
225 'id': 'mZlp2ctYIUEB',
227 'title': 'Tikibad ontruimd wegens brand',
228 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
229 'thumbnail': 're:^https?://.*\.jpg$',
233 'skip_download': True,
236 # MPD from http://dash-mse-test.appspot.com/media.html
238 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
239 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
241 'id': 'car-20120827-manifest',
243 'title': 'car-20120827-manifest',
244 'formats': 'mincount:9',
245 'upload_date': '20130904',
248 'format': 'bestvideo',
251 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
253 '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',
258 'formats': 'mincount:8',
262 'skip_download': True,
265 # m3u8 served with Content-Type: text/plain
267 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
272 'upload_date': '20140720',
273 'formats': 'mincount:11',
277 'skip_download': True,
282 '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',
286 'upload_date': '20130224',
287 'uploader_id': 'TheVerge',
288 'description': 're:^Chris Ziegler takes a look at the\.*',
289 'uploader': 'The Verge',
290 'title': 'First Firefox OS phones side-by-side',
293 'skip_download': False,
297 # redirect in Refresh HTTP header
298 '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',
302 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
303 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
304 'upload_date': '20150917',
305 'uploader_id': 'brtvofficial',
306 'uploader': 'Boiler Room',
309 'skip_download': False,
313 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
314 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
316 'id': '13601338388002',
318 'uploader': 'www.hodiho.fr',
319 'title': 'R\u00e9gis plante sa Jeep',
322 # bandcamp page with custom domain
324 'add_ie': ['Bandcamp'],
325 'url': 'http://bronyrock.com/track/the-pony-mash',
329 'title': 'The Pony Mash',
330 'uploader': 'M_Pallante',
332 'skip': 'There is a limit of 200 free downloads / month for the test song',
334 # embedded brightcove video
335 # it also tests brightcove videos that need to set the 'Referer' in the
338 'add_ie': ['BrightcoveLegacy'],
339 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
341 'id': '2765128793001',
343 'title': 'Le cours de bourse : l’analyse technique',
344 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
345 'uploader': 'BFM BUSINESS',
348 'skip_download': True,
352 # https://github.com/rg3/youtube-dl/issues/2253
353 'url': 'http://bcove.me/i6nfkrc3',
354 'md5': '0ba9446db037002366bab3b3eb30c88c',
356 'id': '3101154703001',
358 'title': 'Still no power',
359 'uploader': 'thestar.com',
360 '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.',
362 'add_ie': ['BrightcoveLegacy'],
365 'url': 'http://www.championat.com/video/football/v/87/87499.html',
366 'md5': 'fb973ecf6e4a78a67453647444222983',
368 'id': '3414141473001',
370 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
371 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
372 'uploader': 'Championat',
376 # https://github.com/rg3/youtube-dl/issues/3541
377 'add_ie': ['BrightcoveLegacy'],
378 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
380 'id': '3866516442001',
382 'title': 'Leer mij vrouwen kennen: Aflevering 1',
383 'description': 'Leer mij vrouwen kennen: Aflevering 1',
384 'uploader': 'SBS Broadcasting',
386 'skip': 'Restricted to Netherlands',
388 'skip_download': True, # m3u8 download
393 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
394 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
396 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
398 'title': '2cc213299525360.mov', # that's what we get
401 'add_ie': ['Ooyala'],
404 # ooyala video embedded with http://player.ooyala.com/iframe.js
405 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
407 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
409 'title': '"Steve Jobs: Man in the Machine" trailer',
410 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
414 'skip_download': True,
419 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
423 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
424 'upload_date': '20140225',
425 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
426 'uploader': 'Tested',
427 'uploader_id': 'testedcom',
429 # No need to test YoutubeIE here
431 'skip_download': True,
436 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
440 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
441 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
446 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
450 'title': 'Охотское море стало целиком российским',
451 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
455 'skip_download': True,
460 '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/',
464 'title': 'Дошкольное воспитание',
469 'url': 'http://www.vestifinance.ru/articles/25753',
472 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
477 'title': 'Госзаказ. День 3',
483 'title': 'Госзаказ. День 2',
489 'title': 'Госзаказ. День 1',
495 'skip_download': True,
500 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
502 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
504 'title': 'Ужастики, русский трейлер (2015)',
505 'thumbnail': 're:^https?://.*\.jpg$',
511 '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',
514 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
516 'playlist_mincount': 7,
520 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
521 'md5': '65fdff94098e4a607385a60c5177c638',
525 'title': 'Hidden miracles of the natural world',
526 'uploader': 'Louie Schwartzberg',
527 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
530 # Embedded Ustream video
532 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
533 'md5': '27b99cdb639c9b12a79bca876a073417',
537 'uploader': 'AU SPA: The NSA and Privacy',
538 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
541 # nowvideo embed hidden behind percent encoding
543 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
544 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
546 'id': '06e53103ca9aa',
548 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
549 'description': 'No description',
554 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
555 'md5': '7653032cbb25bf6c80d80f217055fa43',
557 'id': '048195-004_PLUS7-F',
560 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
561 'upload_date': '20140320',
564 'skip_download': 'Requires rtmpdump'
569 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
573 'title': 'Alcaline, le concert avec Calogero',
574 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
575 'upload_date': '20150226',
576 'timestamp': 1424989860,
581 'skip_download': True,
583 'expected_warnings': [
589 'url': 'http://www.wired.com/2014/04/honda-asimo/',
590 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
592 'id': '53501be369702d3275860000',
594 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
599 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
600 'md5': '441aeeb82eb72c422c7f14ec533999cd',
602 'id': 'k2mm4bCdJ6CQ2i7c8o2',
604 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
605 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
607 'uploader_id': 'xgditw',
608 'upload_date': '20140425',
609 'timestamp': 1398441542,
611 'add_ie': ['Dailymotion'],
615 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
619 'title': 'The NBL Auction 2014',
620 'uploader': 'BADMINTON England',
621 'uploader_id': 'BADMINTONEvents',
622 'upload_date': '20140603',
623 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
625 'add_ie': ['Youtube'],
627 'skip_download': True,
632 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
633 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
635 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
637 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
638 'description': 'Two valets share their love for movie star Liam Neesons.',
641 # YouTube embed via <data-embed-url="">
643 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
647 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
648 'uploader': 'Gameloft',
649 'uploader_id': 'gameloft',
650 'upload_date': '20140828',
651 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
654 'skip_download': True,
659 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
661 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
663 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
664 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
669 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
671 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
672 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
678 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
683 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
684 'md5': '9d65602bf31c6e20014319c7d07fba27',
686 'id': '5123ea6d5e5a7',
689 'uploader': 'www.handjobhub.com',
690 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
693 # Multiple brightcove videos
694 # https://github.com/rg3/youtube-dl/issues/2283
696 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
698 'id': 'always-never',
699 'title': 'Always / Never - The New Yorker',
703 'extract_flat': False,
704 'skip_download': True,
709 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
710 'md5': '96f09a37e44da40dd083e12d9a683327',
714 'title': 'Ump changes call to ball',
715 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
717 'timestamp': 1401537900,
718 'upload_date': '20140531',
719 'thumbnail': 're:^https?://.*\.jpg$',
724 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
725 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
729 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
730 'description': 'a Paywall Videos video from Remilon',
732 'uploader': 'study.com',
733 'timestamp': 1459678540,
734 'upload_date': '20160403',
735 'filesize': 24687186,
739 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
740 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
744 'title': 'Conversation about Hexagonal Rails Part 1',
745 'description': 'a Martin Fowler video from ThoughtWorks',
747 'uploader': 'thoughtworks.wistia.com',
748 'timestamp': 1401832161,
749 'upload_date': '20140603',
752 # Wistia standard embed (async)
754 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
758 'title': 'Drip Brennan Dunn Workshop',
759 'description': 'a JV Webinars video from getdrip-1',
761 'timestamp': 1463607249,
762 'upload_date': '20160518',
765 'skip_download': True,
770 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
774 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
775 'uploader': 'Sophos Security',
776 'title': 'Chet Chat 171 - Oct 29, 2014',
777 'upload_date': '20141029',
782 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
786 'upload_date': '20141112',
787 'title': 'Rosetta #CometLanding webcast HL 10',
790 # Another Livestream embed, without 'new.' in URL
792 'url': 'https://www.freespeech.org/',
796 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
800 'skip_download': True,
805 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
808 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
810 'playlist_mincount': 2,
814 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
818 'upload_date': '20141126',
819 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
824 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
826 'id': '730m_DandD_1901_512k',
828 'uploader': 'www.abc.net.au',
829 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
832 # embedded viddler video
834 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
838 'uploader': 'deadspin',
839 'title': 'WALL-TO-GORTAT',
840 'timestamp': 1422285291,
841 'upload_date': '20150126',
843 'add_ie': ['Viddler'],
847 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
851 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
852 'description': 'md5:601cb790edd05908957dae8aaa866465',
853 'upload_date': '20150220',
858 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
862 'upload_date': '20150212',
863 'uploader': 'The National Archives UK',
864 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
865 'uploader_id': 'NationalArchives08',
866 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
871 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
872 'playlist_mincount': 5,
874 'id': 'aanslagen-kopenhagen',
875 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
880 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
884 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
887 # Kaltura embed (different embed code)
889 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
893 'upload_date': '20150127',
894 'uploader_id': 'PremierMedia',
896 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
899 # Kaltura embed protected with referrer
901 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
905 'title': 'Violetta - Achter De Schermen - Ruggero',
906 'description': 'Achter de schermen met Ruggero',
907 'timestamp': 1435133761,
908 'upload_date': '20150624',
909 'uploader_id': 'echojecka',
912 # Kaltura embed with single quotes
914 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
919 'timestamp': 1355743100,
920 'upload_date': '20121217',
921 'uploader_id': 'batchUser',
923 'add_ie': ['Kaltura'],
926 # Kaltura embedded via quoted entry_id
927 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
931 'title': '06_matthew_brender_raj_dutt',
932 'timestamp': 1466638791,
933 'upload_date': '20160622',
935 'add_ie': ['Kaltura'],
936 'expected_warnings': [
937 'Could not send HEAD request'
940 'skip_download': True,
943 # Eagle.Platform embed (generic URL)
945 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
946 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
950 'title': 'Навальный вышел на свободу',
951 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
952 'thumbnail': 're:^https?://.*\.jpg$',
958 # ClipYou (Eagle.Platform) embed (custom URL)
960 'url': 'http://muz-tv.ru/play/7129/',
961 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
965 'title': "'O Sole Mio",
966 'thumbnail': 're:^https?://.*\.jpg$',
973 'url': 'http://muz-tv.ru/kinozal/view/7400/',
977 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
978 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
979 'thumbnail': 're:^https?://.*\.jpg$',
986 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
990 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
991 'thumbnail': 're:^https?://.*\.png$',
997 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
998 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1002 'title': 'Facebook Creates "On This Day" | Crunch Report',
1007 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1011 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1016 # Crooks and Liars embed
1018 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1022 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1023 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1024 'timestamp': 1428207000,
1025 'upload_date': '20150405',
1026 'uploader': 'Heather',
1029 # Crooks and Liars external embed
1031 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1033 'id': 'MTE3MjUtMzQ2MzA',
1035 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1036 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1037 'timestamp': 1265032391,
1038 'upload_date': '20100201',
1039 'uploader': 'Heather',
1042 # NBC Sports vplayer embed
1044 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1046 'id': 'ln7x1qSThw4k',
1048 'title': "PFT Live: New leader in the 'new-look' defense",
1049 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1050 'uploader': 'NBCU-SPORTS',
1051 'upload_date': '20140107',
1052 'timestamp': 1389118457,
1057 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1058 'md5': '1aa589c675898ae6d37a17913cf68d66',
1060 'id': '701714499682',
1062 'title': 'PREVIEW: On Assignment: David Letterman',
1063 'description': 'A preview of Tom Brokaw\'s interview with David Letterman as part of the On Assignment series powered by Dateline. Airs Sunday June 12 at 7/6c.',
1068 'url': 'https://video.udn.com/news/300346',
1069 'md5': 'fd2060e988c326991037b9aff9df21a6',
1073 'title': '中一中男師變性 全校師生力挺',
1074 'thumbnail': 're:^https?://.*\.jpg$',
1078 'skip_download': True,
1083 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1085 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1087 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1088 'title': 'This is what separates the Excel masters from the wannabes',
1089 'duration': 191.933,
1093 'skip_download': True,
1096 # Brightcove URL in single quotes
1098 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1099 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1101 'id': '4255764656001',
1103 'title': 'SN Presents: Russell Martin, World Citizen',
1104 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1105 'uploader': 'Rogers Sportsnet',
1106 'uploader_id': '1704050871',
1107 'upload_date': '20150525',
1108 'timestamp': 1432570283,
1111 # Dailymotion Cloud video
1113 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1114 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1118 'title': 'Sauvons les abeilles ! - Le débat',
1119 'description': 'md5:d9082128b1c5277987825d684939ca26',
1120 'thumbnail': 're:^https?://.*\.jpe?g$',
1121 'timestamp': 1434970506,
1122 'upload_date': '20150622',
1123 'uploader': 'Public Sénat',
1124 'uploader_id': 'xa9gza',
1127 # OnionStudios embed
1129 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1133 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1134 'thumbnail': 're:^https?://.*\.jpe?g$',
1135 'uploader': 'ClickHole',
1136 'uploader_id': 'clickhole',
1141 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1143 'id': '74849a00-85a9-11e1-9660-123139220831',
1145 'title': '#whilewewatch',
1148 # AdobeTVVideo embed
1150 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1151 'md5': '43662b577c018ad707a63766462b1e87',
1155 'title': 'New experience with Acrobat DC',
1156 'description': 'New experience with Acrobat DC',
1157 'duration': 248.667,
1160 # ScreenwaveMedia embed
1162 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1163 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1165 'id': 'cinemasnob-55d26273809dd',
1167 'title': 'cinemasnob',
1170 # BrightcoveInPageEmbed embed
1172 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1174 'id': '4238694884001',
1176 'title': 'Tabletop: Dread, Last Thoughts',
1177 'description': 'Tabletop: Dread, Last Thoughts',
1181 # JWPlayer with M3U8
1183 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1187 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1188 'uploader': 'ren.tv',
1192 'skip_download': True,
1195 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1196 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1198 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1200 'id': '4785848093001',
1202 'title': 'The Cardinal Pell Interview',
1203 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1204 'uploader': 'GlobeCast Australia - GlobeStream',
1205 'uploader_id': '2733773828001',
1206 'upload_date': '20160304',
1207 'timestamp': 1457083087,
1211 'skip_download': True,
1214 # Another form of arte.tv embed
1216 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1217 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1219 'id': '030273-562_PLUS7-F',
1221 'title': 'ARTE Reportage - Nulle part, en France',
1222 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1223 'upload_date': '20160409',
1228 'url': 'http://www.wykop.pl/link/3088787/',
1229 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1231 'id': '874_1459135191',
1233 'title': 'Man shows poor quality of new apartment building',
1234 'description': 'The wall is like a sand pile.',
1235 'uploader': 'Lake8737',
1238 # Duplicated embedded video URLs
1240 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1242 'id': '149298443_480_16c25b74_2',
1244 'title': 'vs. Blue Orange Spring Game',
1245 'uploader': 'www.hudl.com',
1248 # twitter:player embed
1250 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1251 'md5': 'a3e0df96369831de324f0778e126653c',
1253 'id': '4909620399001',
1255 'title': 'What Do Black Holes Sound Like?',
1256 'description': 'what do black holes sound like',
1257 'upload_date': '20160524',
1258 'uploader_id': '29913724001',
1259 'timestamp': 1464107587,
1260 'uploader': 'TheAtlantic',
1262 'add_ie': ['BrightcoveLegacy'],
1266 def report_following_redirect(self, new_url):
1267 """Report information extraction."""
1268 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1270 def _extract_rss(self, url, video_id, doc):
1271 playlist_title = doc.find('./channel/title').text
1272 playlist_desc_el = doc.find('./channel/description')
1273 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1276 for it in doc.findall('./channel/item'):
1277 next_url = xpath_text(it, 'link', fatal=False)
1279 enclosure_nodes = it.findall('./enclosure')
1280 for e in enclosure_nodes:
1281 next_url = e.attrib.get('url')
1291 'title': it.find('title').text,
1295 '_type': 'playlist',
1297 'title': playlist_title,
1298 'description': playlist_desc,
1302 def _extract_camtasia(self, url, video_id, webpage):
1303 """ Returns None if no camtasia video can be found. """
1305 camtasia_cfg = self._search_regex(
1306 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1307 webpage, 'camtasia configuration file', default=None)
1308 if camtasia_cfg is None:
1311 title = self._html_search_meta('DC.title', webpage, fatal=True)
1313 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1314 camtasia_cfg = self._download_xml(
1315 camtasia_url, video_id,
1316 note='Downloading camtasia configuration',
1317 errnote='Failed to download camtasia configuration')
1318 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1321 for n in fileset_node.getchildren():
1322 url_n = n.find('./uri')
1327 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1328 'title': '%s - %s' % (title, n.tag),
1329 'url': compat_urlparse.urljoin(url, url_n.text),
1330 'duration': float_or_none(n.find('./duration').text),
1334 '_type': 'playlist',
1339 def _real_extract(self, url):
1340 if url.startswith('//'):
1343 'url': self.http_scheme() + url,
1346 parsed_url = compat_urlparse.urlparse(url)
1347 if not parsed_url.scheme:
1348 default_search = self._downloader.params.get('default_search')
1349 if default_search is None:
1350 default_search = 'fixup_error'
1352 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1354 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1355 return self.url_result('http://' + url)
1356 elif default_search != 'fixup_error':
1357 if default_search == 'auto_warning':
1358 if re.match(r'^(?:url|URL)$', url):
1359 raise ExtractorError(
1360 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1363 self._downloader.report_warning(
1364 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1365 return self.url_result('ytsearch:' + url)
1367 if default_search in ('error', 'fixup_error'):
1368 raise ExtractorError(
1369 '%r is not a valid URL. '
1370 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1371 % (url, url), expected=True)
1373 if ':' not in default_search:
1374 default_search += ':'
1375 return self.url_result(default_search + url)
1377 url, smuggled_data = unsmuggle_url(url)
1378 force_videoid = None
1379 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1380 if smuggled_data and 'force_videoid' in smuggled_data:
1381 force_videoid = smuggled_data['force_videoid']
1382 video_id = force_videoid
1384 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1386 self.to_screen('%s: Requesting header' % video_id)
1388 head_req = HEADRequest(url)
1389 head_response = self._request_webpage(
1391 note=False, errnote='Could not send HEAD request to %s' % url,
1394 if head_response is not False:
1395 # Check for redirect
1396 new_url = head_response.geturl()
1398 self.report_following_redirect(new_url)
1400 new_url = smuggle_url(
1401 new_url, {'force_videoid': force_videoid})
1402 return self.url_result(new_url)
1404 full_response = None
1405 if head_response is False:
1406 request = sanitized_Request(url)
1407 request.add_header('Accept-Encoding', '*')
1408 full_response = self._request_webpage(request, video_id)
1409 head_response = full_response
1413 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1414 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1417 # Check for direct link to a video
1418 content_type = head_response.headers.get('Content-Type', '').lower()
1419 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1421 format_id = m.group('format_id')
1422 if format_id.endswith('mpegurl'):
1423 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1424 elif format_id == 'f4m':
1425 formats = self._extract_f4m_formats(url, video_id)
1428 'format_id': m.group('format_id'),
1430 'vcodec': 'none' if m.group('type') == 'audio' else None
1432 info_dict['direct'] = True
1433 self._sort_formats(formats)
1434 info_dict['formats'] = formats
1437 if not self._downloader.params.get('test', False) and not is_intentional:
1438 force = self._downloader.params.get('force_generic_extractor', False)
1439 self._downloader.report_warning(
1440 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1442 if not full_response:
1443 request = sanitized_Request(url)
1444 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1445 # making it impossible to download only chunk of the file (yet we need only 512kB to
1446 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1447 # that will always result in downloading the whole file that is not desirable.
1448 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1449 # to accept raw bytes and being able to download only a chunk.
1450 # It may probably better to solve this by checking Content-Type for application/octet-stream
1451 # after HEAD request finishes, but not sure if we can rely on this.
1452 request.add_header('Accept-Encoding', '*')
1453 full_response = self._request_webpage(request, video_id)
1455 first_bytes = full_response.read(512)
1457 # Is it an M3U playlist?
1458 if first_bytes.startswith(b'#EXTM3U'):
1459 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1460 self._sort_formats(info_dict['formats'])
1463 # Maybe it's a direct link to a video?
1464 # Be careful not to download the whole thing!
1465 if not is_html(first_bytes):
1466 self._downloader.report_warning(
1467 'URL could be a direct video link, returning it as such.')
1474 webpage = self._webpage_read_content(
1475 full_response, url, video_id, prefix=first_bytes)
1477 self.report_extraction(video_id)
1479 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1481 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1482 if doc.tag == 'rss':
1483 return self._extract_rss(url, video_id, doc)
1484 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1485 smil = self._parse_smil(doc, url, video_id)
1486 self._sort_formats(smil['formats'])
1488 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1489 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1490 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1491 info_dict['formats'] = self._parse_mpd_formats(
1492 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1493 self._sort_formats(info_dict['formats'])
1495 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1496 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1497 self._sort_formats(info_dict['formats'])
1499 except compat_xml_parse_error:
1502 # Is it a Camtasia project?
1503 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1504 if camtasia_res is not None:
1507 # Sometimes embedded video player is hidden behind percent encoding
1508 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1509 # Unescaping the whole page allows to handle those cases in a generic way
1510 webpage = compat_urllib_parse_unquote(webpage)
1512 # it's tempting to parse this further, but you would
1513 # have to take into account all the variations like
1514 # Video Title - Site Name
1515 # Site Name | Video Title
1516 # Video Title - Tagline | Site Name
1517 # and so on and so forth; it's just not practical
1518 video_title = self._og_search_title(
1519 webpage, default=None) or self._html_search_regex(
1520 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1523 # Try to detect age limit automatically
1524 age_limit = self._rta_search(webpage)
1525 # And then there are the jokers who advertise that they use RTA,
1526 # but actually don't.
1527 AGE_LIMIT_MARKERS = [
1528 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1530 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1533 # video uploader is domain name
1534 video_uploader = self._search_regex(
1535 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1537 video_description = self._og_search_description(webpage, default=None)
1538 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1541 def _playlist_from_matches(matches, getter=None, ie=None):
1543 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1545 return self.playlist_result(
1546 urlrs, playlist_id=video_id, playlist_title=video_title)
1548 # Look for Brightcove Legacy Studio embeds
1549 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1551 self.to_screen('Brightcove video detected.')
1554 'url': smuggle_url(bc_url, {'Referer': url}),
1555 'ie_key': 'BrightcoveLegacy'
1556 } for bc_url in bc_urls]
1559 '_type': 'playlist',
1560 'title': video_title,
1565 # Look for Brightcove New Studio embeds
1566 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1568 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1570 # Look for ThePlatform embeds
1571 tp_urls = ThePlatformIE._extract_urls(webpage)
1573 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1575 # Look for Vessel embeds
1576 vessel_urls = VesselIE._extract_urls(webpage)
1578 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1580 # Look for embedded rtl.nl player
1581 matches = re.findall(
1582 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1585 return _playlist_from_matches(matches, ie='RtlNl')
1587 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1588 if vimeo_url is not None:
1589 return self.url_result(vimeo_url)
1591 vid_me_embed_url = self._search_regex(
1592 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1593 webpage, 'vid.me embed', default=None)
1594 if vid_me_embed_url is not None:
1595 return self.url_result(vid_me_embed_url, 'Vidme')
1597 # Look for embedded YouTube player
1598 matches = re.findall(r'''(?x)
1607 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1611 return _playlist_from_matches(
1612 matches, lambda m: unescapeHTML(m[1]))
1614 # Look for lazyYT YouTube embed
1615 matches = re.findall(
1616 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1618 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1620 # Look for embedded Dailymotion player
1621 matches = re.findall(
1622 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1624 return _playlist_from_matches(
1625 matches, lambda m: unescapeHTML(m[1]))
1627 # Look for embedded Dailymotion playlist player (#3822)
1629 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1631 playlists = re.findall(
1632 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1634 return _playlist_from_matches(
1635 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1637 # Look for embedded Wistia player
1639 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1641 embed_url = self._proto_relative_url(
1642 unescapeHTML(match.group('url')))
1644 '_type': 'url_transparent',
1647 'uploader': video_uploader,
1650 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1653 '_type': 'url_transparent',
1654 'url': 'wistia:%s' % match.group('id'),
1656 'uploader': video_uploader,
1661 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1662 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1665 return self.url_result(self._proto_relative_url(
1666 'wistia:%s' % match.group('id')), 'Wistia')
1668 # Look for SVT player
1669 svt_url = SVTIE._extract_url(webpage)
1671 return self.url_result(svt_url, 'SVT')
1673 # Look for embedded condenast player
1674 matches = re.findall(
1675 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1679 '_type': 'playlist',
1682 'ie_key': 'CondeNast',
1684 } for ma in matches],
1685 'title': video_title,
1689 # Look for Bandcamp pages with custom domain
1690 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1691 if mobj is not None:
1692 burl = unescapeHTML(mobj.group(1))
1693 # Don't set the extractor because it can be a track url or an album
1694 return self.url_result(burl)
1696 # Look for embedded Vevo player
1698 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1699 if mobj is not None:
1700 return self.url_result(mobj.group('url'))
1702 # Look for embedded Viddler player
1704 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1706 if mobj is not None:
1707 return self.url_result(mobj.group('url'))
1709 # Look for NYTimes player
1711 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1713 if mobj is not None:
1714 return self.url_result(mobj.group('url'))
1716 # Look for Libsyn player
1718 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1719 if mobj is not None:
1720 return self.url_result(mobj.group('url'))
1722 # Look for Ooyala videos
1723 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1724 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1725 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1726 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1727 if mobj is not None:
1728 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1730 # Look for multiple Ooyala embeds on SBN network websites
1731 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1732 if mobj is not None:
1733 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1735 return _playlist_from_matches(
1736 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1738 # Look for Aparat videos
1739 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1740 if mobj is not None:
1741 return self.url_result(mobj.group(1), 'Aparat')
1743 # Look for MPORA videos
1744 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1745 if mobj is not None:
1746 return self.url_result(mobj.group(1), 'Mpora')
1748 # Look for embedded NovaMov-based player
1750 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1751 (?P<url>http://(?:(?:embed|www)\.)?
1753 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1754 videoweed\.(?:es|com)|
1755 movshare\.(?:net|sx|ag)|
1756 divxstage\.(?:eu|net|ch|co|at|ag))
1757 /embed\.php.+?)\1''', webpage)
1758 if mobj is not None:
1759 return self.url_result(mobj.group('url'))
1761 # Look for embedded Facebook player
1763 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1764 if mobj is not None:
1765 return self.url_result(mobj.group('url'), 'Facebook')
1767 # Look for embedded VK player
1768 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1769 if mobj is not None:
1770 return self.url_result(mobj.group('url'), 'VK')
1772 # Look for embedded Odnoklassniki player
1773 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1774 if mobj is not None:
1775 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1777 # Look for embedded ivi player
1778 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1779 if mobj is not None:
1780 return self.url_result(mobj.group('url'), 'Ivi')
1782 # Look for embedded Huffington Post player
1784 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1785 if mobj is not None:
1786 return self.url_result(mobj.group('url'), 'HuffPost')
1789 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1790 if mobj is not None:
1791 return self.url_result(mobj.group('url'))
1792 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1793 if mobj is not None:
1794 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1796 # Look for funnyordie embed
1797 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1799 return _playlist_from_matches(
1800 matches, getter=unescapeHTML, ie='FunnyOrDie')
1802 # Look for BBC iPlayer embed
1803 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1805 return _playlist_from_matches(matches, ie='BBCCoUk')
1807 # Look for embedded RUTV player
1808 rutv_url = RUTVIE._extract_url(webpage)
1810 return self.url_result(rutv_url, 'RUTV')
1812 # Look for embedded TVC player
1813 tvc_url = TVCIE._extract_url(webpage)
1815 return self.url_result(tvc_url, 'TVC')
1817 # Look for embedded SportBox player
1818 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1820 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1822 # Look for embedded PornHub player
1823 pornhub_url = PornHubIE._extract_url(webpage)
1825 return self.url_result(pornhub_url, 'PornHub')
1827 # Look for embedded XHamster player
1828 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1830 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1832 # Look for embedded TNAFlixNetwork player
1833 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1835 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1837 # Look for embedded Tvigle player
1839 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1840 if mobj is not None:
1841 return self.url_result(mobj.group('url'), 'Tvigle')
1843 # Look for embedded TED player
1845 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1846 if mobj is not None:
1847 return self.url_result(mobj.group('url'), 'TED')
1849 # Look for embedded Ustream videos
1851 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1852 if mobj is not None:
1853 return self.url_result(mobj.group('url'), 'Ustream')
1855 # Look for embedded arte.tv player
1857 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1859 if mobj is not None:
1860 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1862 # Look for embedded francetv player
1864 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1866 if mobj is not None:
1867 return self.url_result(mobj.group('url'))
1869 # Look for embedded smotri.com player
1870 smotri_url = SmotriIE._extract_url(webpage)
1872 return self.url_result(smotri_url, 'Smotri')
1874 # Look for embedded Myvi.ru player
1875 myvi_url = MyviIE._extract_url(webpage)
1877 return self.url_result(myvi_url)
1879 # Look for embedded soundcloud player
1881 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1883 if mobj is not None:
1884 url = unescapeHTML(mobj.group('url'))
1885 return self.url_result(url)
1887 # Look for embedded mtvservices player
1888 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1890 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1892 # Look for embedded yahoo player
1894 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1896 if mobj is not None:
1897 return self.url_result(mobj.group('url'), 'Yahoo')
1899 # Look for embedded sbs.com.au player
1903 <meta\s+property="og:video"\s+content=|
1906 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1908 if mobj is not None:
1909 return self.url_result(mobj.group('url'), 'SBS')
1911 # Look for embedded Cinchcast player
1913 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1915 if mobj is not None:
1916 return self.url_result(mobj.group('url'), 'Cinchcast')
1919 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1923 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1925 if mobj is not None:
1926 return self.url_result(mobj.group('url'), 'MLB')
1929 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1931 if mobj is not None:
1932 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1935 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1937 if mobj is not None:
1938 return self.url_result(mobj.group('url'), 'Livestream')
1940 # Look for Zapiks embed
1942 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1943 if mobj is not None:
1944 return self.url_result(mobj.group('url'), 'Zapiks')
1946 # Look for Kaltura embeds
1947 kaltura_url = KalturaIE._extract_url(webpage)
1949 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
1951 # Look for Eagle.Platform embeds
1952 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
1953 if eagleplatform_url:
1954 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
1956 # Look for ClipYou (uses Eagle.Platform) embeds
1958 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1959 if mobj is not None:
1960 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1962 # Look for Pladform embeds
1963 pladform_url = PladformIE._extract_url(webpage)
1965 return self.url_result(pladform_url)
1967 # Look for Videomore embeds
1968 videomore_url = VideomoreIE._extract_url(webpage)
1970 return self.url_result(videomore_url)
1972 # Look for Playwire embeds
1974 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1975 if mobj is not None:
1976 return self.url_result(mobj.group('url'))
1978 # Look for 5min embeds
1980 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1981 if mobj is not None:
1982 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1984 # Look for Crooks and Liars embeds
1986 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1987 if mobj is not None:
1988 return self.url_result(mobj.group('url'))
1990 # Look for NBC Sports VPlayer embeds
1991 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1993 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1995 # Look for NBC News embeds
1996 nbc_news_embed_url = re.search(
1997 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
1998 if nbc_news_embed_url:
1999 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2001 # Look for Google Drive embeds
2002 google_drive_url = GoogleDriveIE._extract_url(webpage)
2003 if google_drive_url:
2004 return self.url_result(google_drive_url, 'GoogleDrive')
2006 # Look for UDN embeds
2008 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2009 if mobj is not None:
2010 return self.url_result(
2011 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2013 # Look for Senate ISVP iframe
2014 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2016 return self.url_result(senate_isvp_url, 'SenateISVP')
2018 # Look for Dailymotion Cloud videos
2019 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2021 return self.url_result(dmcloud_url, 'DailymotionCloud')
2023 # Look for OnionStudios embeds
2024 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2025 if onionstudios_url:
2026 return self.url_result(onionstudios_url)
2028 # Look for ViewLift embeds
2029 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2031 return self.url_result(viewlift_url)
2033 # Look for JWPlatform embeds
2034 jwplatform_url = JWPlatformIE._extract_url(webpage)
2036 return self.url_result(jwplatform_url, 'JWPlatform')
2038 # Look for ScreenwaveMedia embeds
2039 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2040 if mobj is not None:
2041 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2043 # Look for Digiteka embeds
2044 digiteka_url = DigitekaIE._extract_url(webpage)
2046 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2048 # Look for Limelight embeds
2049 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2053 'Channel': 'channel',
2054 'ChannelList': 'channel_list',
2056 return self.url_result('limelight:%s:%s' % (
2057 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2059 # Look for AdobeTVVideo embeds
2061 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2063 if mobj is not None:
2064 return self.url_result(
2065 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2068 # Look for Vine embeds
2070 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2072 if mobj is not None:
2073 return self.url_result(
2074 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2076 # Look for Instagram embeds
2077 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2078 if instagram_embed_url is not None:
2079 return self.url_result(
2080 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2082 # Look for LiveLeak embeds
2083 liveleak_url = LiveLeakIE._extract_url(webpage)
2085 return self.url_result(liveleak_url, 'LiveLeak')
2087 # Look for 3Q SDN embeds
2088 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2091 '_type': 'url_transparent',
2092 'ie_key': ThreeQSDNIE.ie_key(),
2093 'url': self._proto_relative_url(threeqsdn_url),
2094 'title': video_title,
2095 'description': video_description,
2096 'thumbnail': video_thumbnail,
2097 'uploader': video_uploader,
2100 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser
2101 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2103 return self.url_result(embed_url)
2105 def check_video(vurl):
2106 if YoutubeIE.suitable(vurl):
2108 vpath = compat_urlparse.urlparse(vurl).path
2109 vext = determine_ext(vpath)
2110 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2112 def filter_video(urls):
2113 return list(filter(check_video, urls))
2115 # Start with something easy: JW Player in SWFObject
2116 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2118 # Look for gorilla-vid style embedding
2119 found = filter_video(re.findall(r'''(?sx)
2123 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2126 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2128 # Broaden the search a little bit
2129 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2131 # Broaden the findall a little bit: JWPlayer JS loader
2132 found = filter_video(re.findall(
2133 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2136 found = filter_video(re.findall(r'''(?xs)
2137 flowplayer\("[^"]+",\s*
2139 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2140 ["']?url["']?\s*:\s*["']([^"']+)["']
2145 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2147 # Try to find twitter cards info
2148 found = filter_video(re.findall(
2149 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2151 # We look for Open Graph info:
2152 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2153 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2154 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2155 if m_video_type is not None:
2156 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2159 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2161 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2163 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2164 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2167 # Look also in Refresh HTTP header
2168 refresh_header = head_response.headers.get('Refresh')
2170 # In python 2 response HTTP headers are bytestrings
2171 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2172 refresh_header = refresh_header.decode('iso-8859-1')
2173 found = re.search(REDIRECT_REGEX, refresh_header)
2175 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2176 self.report_following_redirect(new_url)
2182 raise UnsupportedError(url)
2185 for video_url in orderedSet(found):
2186 video_url = unescapeHTML(video_url)
2187 video_url = video_url.replace('\\/', '/')
2188 video_url = compat_urlparse.urljoin(url, video_url)
2189 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2191 # Sometimes, jwplayer extraction will result in a YouTube URL
2192 if YoutubeIE.suitable(video_url):
2193 entries.append(self.url_result(video_url, 'Youtube'))
2196 # here's a fun little line of code for you:
2197 video_id = os.path.splitext(video_id)[0]
2201 'uploader': video_uploader,
2202 'title': video_title,
2203 'age_limit': age_limit,
2206 ext = determine_ext(video_url)
2208 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2210 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2212 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2214 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2216 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2218 entry_info_dict['url'] = video_url
2220 if entry_info_dict.get('formats'):
2221 self._sort_formats(entry_info_dict['formats'])
2223 entries.append(entry_info_dict)
2225 if len(entries) == 1:
2228 for num, e in enumerate(entries, start=1):
2229 # 'url' results don't have a title
2230 if e.get('title') is not None:
2231 e['title'] = '%s (%d)' % (e['title'], num)
2233 '_type': 'playlist',