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
69 class GenericIE(InfoExtractor):
70 IE_DESC = 'Generic downloader that works on some sites'
74 # Direct link to a video
76 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
77 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
82 'upload_date': '20100513',
85 # Direct link to media delivered compressed (until Accept-Encoding is *)
87 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
88 'md5': '128c42e68b13950268b648275386fc74',
90 'id': 'FictionJunction-Parallel_Hearts',
92 'title': 'FictionJunction-Parallel_Hearts',
93 'upload_date': '20140522',
95 'expected_warnings': [
96 'URL could be a direct video link, returning it as such.'
99 # Direct download with broken HEAD
101 'url': 'http://ai-radio.org:8000/radio.opus',
108 'skip_download': True, # infinite live stream
110 'expected_warnings': [
111 r'501.*Not Implemented',
115 # Direct link with incorrect MIME type
117 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
118 'md5': '4ccbebe5f36706d85221f204d7eb5913',
120 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
121 'id': '5_Lennart_Poettering_-_Systemd',
123 'title': '5_Lennart_Poettering_-_Systemd',
124 'upload_date': '20141120',
126 'expected_warnings': [
127 'URL could be a direct video link, returning it as such.'
132 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
134 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
135 'title': 'Zero Punctuation',
136 'description': 're:.*groundbreaking video review series.*'
138 'playlist_mincount': 11,
140 # RSS feed with enclosure
142 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
144 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
146 'upload_date': '20150228',
147 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
150 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
152 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
156 'title': 'Automatics, robotics and biocybernetics',
157 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
158 'upload_date': '20130627',
159 'formats': 'mincount:16',
160 'subtitles': 'mincount:1',
163 'force_generic_extractor': True,
164 'skip_download': True,
167 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
169 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
174 'formats': 'mincount:1',
177 'skip_download': True,
180 # SMIL from https://www.restudy.dk/video/play/id/1637
182 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
186 'title': 'video_1637',
187 'formats': 'mincount:3',
190 'skip_download': True,
193 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
195 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
197 'id': 'smil-service',
199 'title': 'smil-service',
200 'formats': 'mincount:1',
203 'skip_download': True,
206 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
208 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
212 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
213 'formats': 'mincount:3',
216 'skip_download': True,
219 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
221 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
223 'id': 'mZlp2ctYIUEB',
225 'title': 'Tikibad ontruimd wegens brand',
226 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
227 'thumbnail': 're:^https?://.*\.jpg$',
231 'skip_download': True,
234 # MPD from http://dash-mse-test.appspot.com/media.html
236 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
237 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
239 'id': 'car-20120827-manifest',
241 'title': 'car-20120827-manifest',
242 'formats': 'mincount:9',
243 'upload_date': '20130904',
246 'format': 'bestvideo',
249 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
251 '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',
256 'formats': 'mincount:8',
260 'skip_download': True,
263 # m3u8 served with Content-Type: text/plain
265 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
270 'upload_date': '20140720',
271 'formats': 'mincount:11',
275 'skip_download': True,
280 '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',
284 'upload_date': '20130224',
285 'uploader_id': 'TheVerge',
286 'description': 're:^Chris Ziegler takes a look at the\.*',
287 'uploader': 'The Verge',
288 'title': 'First Firefox OS phones side-by-side',
291 'skip_download': False,
295 # redirect in Refresh HTTP header
296 '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',
300 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
301 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
302 'upload_date': '20150917',
303 'uploader_id': 'brtvofficial',
304 'uploader': 'Boiler Room',
307 'skip_download': False,
311 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
312 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
314 'id': '13601338388002',
316 'uploader': 'www.hodiho.fr',
317 'title': 'R\u00e9gis plante sa Jeep',
320 # bandcamp page with custom domain
322 'add_ie': ['Bandcamp'],
323 'url': 'http://bronyrock.com/track/the-pony-mash',
327 'title': 'The Pony Mash',
328 'uploader': 'M_Pallante',
330 'skip': 'There is a limit of 200 free downloads / month for the test song',
332 # embedded brightcove video
333 # it also tests brightcove videos that need to set the 'Referer' in the
336 'add_ie': ['BrightcoveLegacy'],
337 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
339 'id': '2765128793001',
341 'title': 'Le cours de bourse : l’analyse technique',
342 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
343 'uploader': 'BFM BUSINESS',
346 'skip_download': True,
350 # https://github.com/rg3/youtube-dl/issues/2253
351 'url': 'http://bcove.me/i6nfkrc3',
352 'md5': '0ba9446db037002366bab3b3eb30c88c',
354 'id': '3101154703001',
356 'title': 'Still no power',
357 'uploader': 'thestar.com',
358 '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.',
360 'add_ie': ['BrightcoveLegacy'],
363 'url': 'http://www.championat.com/video/football/v/87/87499.html',
364 'md5': 'fb973ecf6e4a78a67453647444222983',
366 'id': '3414141473001',
368 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
369 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
370 'uploader': 'Championat',
374 # https://github.com/rg3/youtube-dl/issues/3541
375 'add_ie': ['BrightcoveLegacy'],
376 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
378 'id': '3866516442001',
380 'title': 'Leer mij vrouwen kennen: Aflevering 1',
381 'description': 'Leer mij vrouwen kennen: Aflevering 1',
382 'uploader': 'SBS Broadcasting',
384 'skip': 'Restricted to Netherlands',
386 'skip_download': True, # m3u8 download
391 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
392 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
394 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
396 'title': '2cc213299525360.mov', # that's what we get
399 'add_ie': ['Ooyala'],
402 # ooyala video embedded with http://player.ooyala.com/iframe.js
403 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
405 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
407 'title': '"Steve Jobs: Man in the Machine" trailer',
408 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
412 'skip_download': True,
417 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
421 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
422 'upload_date': '20140225',
423 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
424 'uploader': 'Tested',
425 'uploader_id': 'testedcom',
427 # No need to test YoutubeIE here
429 'skip_download': True,
434 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
438 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
439 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
444 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
448 'title': 'Охотское море стало целиком российским',
449 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
453 'skip_download': True,
458 '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/',
462 'title': 'Дошкольное воспитание',
467 'url': 'http://www.vestifinance.ru/articles/25753',
470 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
475 'title': 'Госзаказ. День 3',
481 'title': 'Госзаказ. День 2',
487 'title': 'Госзаказ. День 1',
493 'skip_download': True,
498 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
500 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
502 'title': 'Ужастики, русский трейлер (2015)',
503 'thumbnail': 're:^https?://.*\.jpg$',
509 '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',
512 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
514 'playlist_mincount': 7,
518 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
519 'md5': '65fdff94098e4a607385a60c5177c638',
523 'title': 'Hidden miracles of the natural world',
524 'uploader': 'Louie Schwartzberg',
525 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
528 # Embedded Ustream video
530 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
531 'md5': '27b99cdb639c9b12a79bca876a073417',
535 'uploader': 'AU SPA: The NSA and Privacy',
536 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
539 # nowvideo embed hidden behind percent encoding
541 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
542 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
544 'id': '06e53103ca9aa',
546 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
547 'description': 'No description',
552 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
553 'md5': '7653032cbb25bf6c80d80f217055fa43',
555 'id': '048195-004_PLUS7-F',
558 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
559 'upload_date': '20140320',
562 'skip_download': 'Requires rtmpdump'
567 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
571 'title': 'Alcaline, le concert avec Calogero',
572 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
573 'upload_date': '20150226',
574 'timestamp': 1424989860,
579 'skip_download': True,
581 'expected_warnings': [
587 'url': 'http://www.wired.com/2014/04/honda-asimo/',
588 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
590 'id': '53501be369702d3275860000',
592 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
597 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
598 'md5': '441aeeb82eb72c422c7f14ec533999cd',
600 'id': 'k2mm4bCdJ6CQ2i7c8o2',
602 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
603 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
605 'uploader_id': 'xgditw',
606 'upload_date': '20140425',
607 'timestamp': 1398441542,
609 'add_ie': ['Dailymotion'],
613 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
617 'title': 'The NBL Auction 2014',
618 'uploader': 'BADMINTON England',
619 'uploader_id': 'BADMINTONEvents',
620 'upload_date': '20140603',
621 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
623 'add_ie': ['Youtube'],
625 'skip_download': True,
630 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
631 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
633 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
635 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
636 'description': 'Two valets share their love for movie star Liam Neesons.',
639 # YouTube embed via <data-embed-url="">
641 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
645 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
646 'uploader': 'Gameloft',
647 'uploader_id': 'gameloft',
648 'upload_date': '20140828',
649 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
652 'skip_download': True,
657 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
659 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
661 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
662 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
667 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
669 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
670 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
676 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
681 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
682 'md5': '9d65602bf31c6e20014319c7d07fba27',
684 'id': '5123ea6d5e5a7',
687 'uploader': 'www.handjobhub.com',
688 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
691 # Multiple brightcove videos
692 # https://github.com/rg3/youtube-dl/issues/2283
694 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
696 'id': 'always-never',
697 'title': 'Always / Never - The New Yorker',
701 'extract_flat': False,
702 'skip_download': True,
707 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
708 'md5': '96f09a37e44da40dd083e12d9a683327',
712 'title': 'Ump changes call to ball',
713 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
715 'timestamp': 1401537900,
716 'upload_date': '20140531',
717 'thumbnail': 're:^https?://.*\.jpg$',
722 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
723 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
727 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
728 'description': 'a Paywall Videos video from Remilon',
730 'uploader': 'study.com',
731 'timestamp': 1459678540,
732 'upload_date': '20160403',
733 'filesize': 24687186,
737 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
738 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
742 'title': 'Conversation about Hexagonal Rails Part 1',
743 'description': 'a Martin Fowler video from ThoughtWorks',
745 'uploader': 'thoughtworks.wistia.com',
746 'timestamp': 1401832161,
747 'upload_date': '20140603',
750 # Wistia standard embed (async)
752 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
756 'title': 'Drip Brennan Dunn Workshop',
757 'description': 'a JV Webinars video from getdrip-1',
759 'timestamp': 1463607249,
760 'upload_date': '20160518',
763 'skip_download': True,
768 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
772 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
773 'uploader': 'Sophos Security',
774 'title': 'Chet Chat 171 - Oct 29, 2014',
775 'upload_date': '20141029',
780 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
784 'upload_date': '20141112',
785 'title': 'Rosetta #CometLanding webcast HL 10',
788 # Another Livestream embed, without 'new.' in URL
790 'url': 'https://www.freespeech.org/',
794 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
798 'skip_download': True,
803 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
806 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
808 'playlist_mincount': 2,
812 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
816 'upload_date': '20141126',
817 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
822 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
824 'id': '730m_DandD_1901_512k',
826 'uploader': 'www.abc.net.au',
827 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
830 # embedded viddler video
832 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
836 'uploader': 'deadspin',
837 'title': 'WALL-TO-GORTAT',
838 'timestamp': 1422285291,
839 'upload_date': '20150126',
841 'add_ie': ['Viddler'],
845 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
849 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
850 'description': 'md5:601cb790edd05908957dae8aaa866465',
851 'upload_date': '20150220',
856 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
860 'upload_date': '20150212',
861 'uploader': 'The National Archives UK',
862 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
863 'uploader_id': 'NationalArchives08',
864 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
869 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
870 'playlist_mincount': 5,
872 'id': 'aanslagen-kopenhagen',
873 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
878 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
882 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
885 # Kaltura embed (different embed code)
887 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
891 'upload_date': '20150127',
892 'uploader_id': 'PremierMedia',
894 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
897 # Kaltura embed protected with referrer
899 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
903 'title': 'Violetta - Achter De Schermen - Ruggero',
904 'description': 'Achter de schermen met Ruggero',
905 'timestamp': 1435133761,
906 'upload_date': '20150624',
907 'uploader_id': 'echojecka',
910 # Kaltura embed with single quotes
912 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
917 'timestamp': 1355743100,
918 'upload_date': '20121217',
919 'uploader_id': 'batchUser',
921 'add_ie': ['Kaltura'],
923 # Eagle.Platform embed (generic URL)
925 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
926 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
930 'title': 'Навальный вышел на свободу',
931 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
932 'thumbnail': 're:^https?://.*\.jpg$',
938 # ClipYou (Eagle.Platform) embed (custom URL)
940 'url': 'http://muz-tv.ru/play/7129/',
941 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
945 'title': "'O Sole Mio",
946 'thumbnail': 're:^https?://.*\.jpg$',
953 'url': 'http://muz-tv.ru/kinozal/view/7400/',
957 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
958 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
959 'thumbnail': 're:^https?://.*\.jpg$',
966 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
970 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
971 'thumbnail': 're:^https?://.*\.png$',
977 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
978 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
982 'title': 'Facebook Creates "On This Day" | Crunch Report',
987 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
991 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
996 # Crooks and Liars embed
998 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1002 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1003 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1004 'timestamp': 1428207000,
1005 'upload_date': '20150405',
1006 'uploader': 'Heather',
1009 # Crooks and Liars external embed
1011 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1013 'id': 'MTE3MjUtMzQ2MzA',
1015 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1016 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1017 'timestamp': 1265032391,
1018 'upload_date': '20100201',
1019 'uploader': 'Heather',
1022 # NBC Sports vplayer embed
1024 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1026 'id': 'ln7x1qSThw4k',
1028 'title': "PFT Live: New leader in the 'new-look' defense",
1029 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1030 'uploader': 'NBCU-SPORTS',
1031 'upload_date': '20140107',
1032 'timestamp': 1389118457,
1037 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1038 'md5': '1aa589c675898ae6d37a17913cf68d66',
1040 'id': '701714499682',
1042 'title': 'PREVIEW: On Assignment: David Letterman',
1043 '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.',
1048 'url': 'https://video.udn.com/news/300346',
1049 'md5': 'fd2060e988c326991037b9aff9df21a6',
1053 'title': '中一中男師變性 全校師生力挺',
1054 'thumbnail': 're:^https?://.*\.jpg$',
1058 'skip_download': True,
1063 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1065 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1067 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1068 'title': 'This is what separates the Excel masters from the wannabes',
1069 'duration': 191.933,
1073 'skip_download': True,
1076 # Contains a SMIL manifest
1078 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
1082 'title': '+ Football: Lottery Champions League Europe',
1083 'uploader': 'www.telewebion.com',
1087 'skip_download': True,
1090 # Brightcove URL in single quotes
1092 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1093 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1095 'id': '4255764656001',
1097 'title': 'SN Presents: Russell Martin, World Citizen',
1098 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1099 'uploader': 'Rogers Sportsnet',
1100 'uploader_id': '1704050871',
1101 'upload_date': '20150525',
1102 'timestamp': 1432570283,
1105 # Dailymotion Cloud video
1107 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1108 'md5': '49444254273501a64675a7e68c502681',
1110 'id': '5585de919473990de4bee11b',
1112 'title': 'Le débat',
1113 'thumbnail': 're:^https?://.*\.jpe?g$',
1116 # OnionStudios embed
1118 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1122 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1123 'thumbnail': 're:^https?://.*\.jpe?g$',
1124 'uploader': 'ClickHole',
1125 'uploader_id': 'clickhole',
1130 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1132 'id': '74849a00-85a9-11e1-9660-123139220831',
1134 'title': '#whilewewatch',
1137 # AdobeTVVideo embed
1139 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1140 'md5': '43662b577c018ad707a63766462b1e87',
1144 'title': 'New experience with Acrobat DC',
1145 'description': 'New experience with Acrobat DC',
1146 'duration': 248.667,
1149 # ScreenwaveMedia embed
1151 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1152 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1154 'id': 'cinemasnob-55d26273809dd',
1156 'title': 'cinemasnob',
1159 # BrightcoveInPageEmbed embed
1161 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1163 'id': '4238694884001',
1165 'title': 'Tabletop: Dread, Last Thoughts',
1166 'description': 'Tabletop: Dread, Last Thoughts',
1170 # JWPlayer with M3U8
1172 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1176 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1177 'uploader': 'ren.tv',
1181 'skip_download': True,
1184 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1185 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1187 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1189 'id': '4785848093001',
1191 'title': 'The Cardinal Pell Interview',
1192 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1193 'uploader': 'GlobeCast Australia - GlobeStream',
1194 'uploader_id': '2733773828001',
1195 'upload_date': '20160304',
1196 'timestamp': 1457083087,
1200 'skip_download': True,
1203 # Another form of arte.tv embed
1205 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1206 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1208 'id': '030273-562_PLUS7-F',
1210 'title': 'ARTE Reportage - Nulle part, en France',
1211 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1212 'upload_date': '20160409',
1217 'url': 'http://www.wykop.pl/link/3088787/',
1218 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1220 'id': '874_1459135191',
1222 'title': 'Man shows poor quality of new apartment building',
1223 'description': 'The wall is like a sand pile.',
1224 'uploader': 'Lake8737',
1227 # Duplicated embedded video URLs
1229 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1231 'id': '149298443_480_16c25b74_2',
1233 'title': 'vs. Blue Orange Spring Game',
1234 'uploader': 'www.hudl.com',
1239 def report_following_redirect(self, new_url):
1240 """Report information extraction."""
1241 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1243 def _extract_rss(self, url, video_id, doc):
1244 playlist_title = doc.find('./channel/title').text
1245 playlist_desc_el = doc.find('./channel/description')
1246 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1249 for it in doc.findall('./channel/item'):
1250 next_url = xpath_text(it, 'link', fatal=False)
1252 enclosure_nodes = it.findall('./enclosure')
1253 for e in enclosure_nodes:
1254 next_url = e.attrib.get('url')
1264 'title': it.find('title').text,
1268 '_type': 'playlist',
1270 'title': playlist_title,
1271 'description': playlist_desc,
1275 def _extract_camtasia(self, url, video_id, webpage):
1276 """ Returns None if no camtasia video can be found. """
1278 camtasia_cfg = self._search_regex(
1279 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1280 webpage, 'camtasia configuration file', default=None)
1281 if camtasia_cfg is None:
1284 title = self._html_search_meta('DC.title', webpage, fatal=True)
1286 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1287 camtasia_cfg = self._download_xml(
1288 camtasia_url, video_id,
1289 note='Downloading camtasia configuration',
1290 errnote='Failed to download camtasia configuration')
1291 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1294 for n in fileset_node.getchildren():
1295 url_n = n.find('./uri')
1300 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1301 'title': '%s - %s' % (title, n.tag),
1302 'url': compat_urlparse.urljoin(url, url_n.text),
1303 'duration': float_or_none(n.find('./duration').text),
1307 '_type': 'playlist',
1312 def _real_extract(self, url):
1313 if url.startswith('//'):
1316 'url': self.http_scheme() + url,
1319 parsed_url = compat_urlparse.urlparse(url)
1320 if not parsed_url.scheme:
1321 default_search = self._downloader.params.get('default_search')
1322 if default_search is None:
1323 default_search = 'fixup_error'
1325 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1327 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1328 return self.url_result('http://' + url)
1329 elif default_search != 'fixup_error':
1330 if default_search == 'auto_warning':
1331 if re.match(r'^(?:url|URL)$', url):
1332 raise ExtractorError(
1333 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1336 self._downloader.report_warning(
1337 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1338 return self.url_result('ytsearch:' + url)
1340 if default_search in ('error', 'fixup_error'):
1341 raise ExtractorError(
1342 '%r is not a valid URL. '
1343 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1344 % (url, url), expected=True)
1346 if ':' not in default_search:
1347 default_search += ':'
1348 return self.url_result(default_search + url)
1350 url, smuggled_data = unsmuggle_url(url)
1351 force_videoid = None
1352 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1353 if smuggled_data and 'force_videoid' in smuggled_data:
1354 force_videoid = smuggled_data['force_videoid']
1355 video_id = force_videoid
1357 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1359 self.to_screen('%s: Requesting header' % video_id)
1361 head_req = HEADRequest(url)
1362 head_response = self._request_webpage(
1364 note=False, errnote='Could not send HEAD request to %s' % url,
1367 if head_response is not False:
1368 # Check for redirect
1369 new_url = head_response.geturl()
1371 self.report_following_redirect(new_url)
1373 new_url = smuggle_url(
1374 new_url, {'force_videoid': force_videoid})
1375 return self.url_result(new_url)
1377 full_response = None
1378 if head_response is False:
1379 request = sanitized_Request(url)
1380 request.add_header('Accept-Encoding', '*')
1381 full_response = self._request_webpage(request, video_id)
1382 head_response = full_response
1386 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1387 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1390 # Check for direct link to a video
1391 content_type = head_response.headers.get('Content-Type', '').lower()
1392 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1394 format_id = m.group('format_id')
1395 if format_id.endswith('mpegurl'):
1396 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1397 elif format_id == 'f4m':
1398 formats = self._extract_f4m_formats(url, video_id)
1401 'format_id': m.group('format_id'),
1403 'vcodec': 'none' if m.group('type') == 'audio' else None
1405 info_dict['direct'] = True
1406 self._sort_formats(formats)
1407 info_dict['formats'] = formats
1410 if not self._downloader.params.get('test', False) and not is_intentional:
1411 force = self._downloader.params.get('force_generic_extractor', False)
1412 self._downloader.report_warning(
1413 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1415 if not full_response:
1416 request = sanitized_Request(url)
1417 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1418 # making it impossible to download only chunk of the file (yet we need only 512kB to
1419 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1420 # that will always result in downloading the whole file that is not desirable.
1421 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1422 # to accept raw bytes and being able to download only a chunk.
1423 # It may probably better to solve this by checking Content-Type for application/octet-stream
1424 # after HEAD request finishes, but not sure if we can rely on this.
1425 request.add_header('Accept-Encoding', '*')
1426 full_response = self._request_webpage(request, video_id)
1428 first_bytes = full_response.read(512)
1430 # Is it an M3U playlist?
1431 if first_bytes.startswith(b'#EXTM3U'):
1432 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1433 self._sort_formats(info_dict['formats'])
1436 # Maybe it's a direct link to a video?
1437 # Be careful not to download the whole thing!
1438 if not is_html(first_bytes):
1439 self._downloader.report_warning(
1440 'URL could be a direct video link, returning it as such.')
1447 webpage = self._webpage_read_content(
1448 full_response, url, video_id, prefix=first_bytes)
1450 self.report_extraction(video_id)
1452 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1454 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1455 if doc.tag == 'rss':
1456 return self._extract_rss(url, video_id, doc)
1457 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1458 smil = self._parse_smil(doc, url, video_id)
1459 self._sort_formats(smil['formats'])
1461 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1462 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1463 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1464 info_dict['formats'] = self._parse_mpd_formats(
1465 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1466 self._sort_formats(info_dict['formats'])
1468 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1469 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1470 self._sort_formats(info_dict['formats'])
1472 except compat_xml_parse_error:
1475 # Is it a Camtasia project?
1476 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1477 if camtasia_res is not None:
1480 # Sometimes embedded video player is hidden behind percent encoding
1481 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1482 # Unescaping the whole page allows to handle those cases in a generic way
1483 webpage = compat_urllib_parse_unquote(webpage)
1485 # it's tempting to parse this further, but you would
1486 # have to take into account all the variations like
1487 # Video Title - Site Name
1488 # Site Name | Video Title
1489 # Video Title - Tagline | Site Name
1490 # and so on and so forth; it's just not practical
1491 video_title = self._og_search_title(
1492 webpage, default=None) or self._html_search_regex(
1493 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1496 # Try to detect age limit automatically
1497 age_limit = self._rta_search(webpage)
1498 # And then there are the jokers who advertise that they use RTA,
1499 # but actually don't.
1500 AGE_LIMIT_MARKERS = [
1501 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1503 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1506 # video uploader is domain name
1507 video_uploader = self._search_regex(
1508 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1510 video_description = self._og_search_description(webpage, default=None)
1511 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1514 def _playlist_from_matches(matches, getter=None, ie=None):
1516 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1518 return self.playlist_result(
1519 urlrs, playlist_id=video_id, playlist_title=video_title)
1521 # Look for Brightcove Legacy Studio embeds
1522 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1524 self.to_screen('Brightcove video detected.')
1527 'url': smuggle_url(bc_url, {'Referer': url}),
1528 'ie_key': 'BrightcoveLegacy'
1529 } for bc_url in bc_urls]
1532 '_type': 'playlist',
1533 'title': video_title,
1538 # Look for Brightcove New Studio embeds
1539 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1541 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1543 # Look for ThePlatform embeds
1544 tp_urls = ThePlatformIE._extract_urls(webpage)
1546 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1548 # Look for Vessel embeds
1549 vessel_urls = VesselIE._extract_urls(webpage)
1551 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1553 # Look for embedded rtl.nl player
1554 matches = re.findall(
1555 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1558 return _playlist_from_matches(matches, ie='RtlNl')
1560 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1561 if vimeo_url is not None:
1562 return self.url_result(vimeo_url)
1564 vid_me_embed_url = self._search_regex(
1565 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1566 webpage, 'vid.me embed', default=None)
1567 if vid_me_embed_url is not None:
1568 return self.url_result(vid_me_embed_url, 'Vidme')
1570 # Look for embedded YouTube player
1571 matches = re.findall(r'''(?x)
1580 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1584 return _playlist_from_matches(
1585 matches, lambda m: unescapeHTML(m[1]))
1587 # Look for lazyYT YouTube embed
1588 matches = re.findall(
1589 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1591 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1593 # Look for embedded Dailymotion player
1594 matches = re.findall(
1595 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
1597 return _playlist_from_matches(
1598 matches, lambda m: unescapeHTML(m[1]))
1600 # Look for embedded Dailymotion playlist player (#3822)
1602 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1604 playlists = re.findall(
1605 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1607 return _playlist_from_matches(
1608 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1610 # Look for embedded Wistia player
1612 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1614 embed_url = self._proto_relative_url(
1615 unescapeHTML(match.group('url')))
1617 '_type': 'url_transparent',
1620 'uploader': video_uploader,
1623 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1626 '_type': 'url_transparent',
1627 'url': 'wistia:%s' % match.group('id'),
1629 'uploader': video_uploader,
1634 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1635 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1638 return self.url_result(self._proto_relative_url(
1639 'wistia:%s' % match.group('id')), 'Wistia')
1641 # Look for SVT player
1642 svt_url = SVTIE._extract_url(webpage)
1644 return self.url_result(svt_url, 'SVT')
1646 # Look for embedded condenast player
1647 matches = re.findall(
1648 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1652 '_type': 'playlist',
1655 'ie_key': 'CondeNast',
1657 } for ma in matches],
1658 'title': video_title,
1662 # Look for Bandcamp pages with custom domain
1663 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1664 if mobj is not None:
1665 burl = unescapeHTML(mobj.group(1))
1666 # Don't set the extractor because it can be a track url or an album
1667 return self.url_result(burl)
1669 # Look for embedded Vevo player
1671 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1672 if mobj is not None:
1673 return self.url_result(mobj.group('url'))
1675 # Look for embedded Viddler player
1677 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1679 if mobj is not None:
1680 return self.url_result(mobj.group('url'))
1682 # Look for NYTimes player
1684 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1686 if mobj is not None:
1687 return self.url_result(mobj.group('url'))
1689 # Look for Libsyn player
1691 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1692 if mobj is not None:
1693 return self.url_result(mobj.group('url'))
1695 # Look for Ooyala videos
1696 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1697 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1698 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1699 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1700 if mobj is not None:
1701 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1703 # Look for multiple Ooyala embeds on SBN network websites
1704 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1705 if mobj is not None:
1706 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1708 return _playlist_from_matches(
1709 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1711 # Look for Aparat videos
1712 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1713 if mobj is not None:
1714 return self.url_result(mobj.group(1), 'Aparat')
1716 # Look for MPORA videos
1717 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1718 if mobj is not None:
1719 return self.url_result(mobj.group(1), 'Mpora')
1721 # Look for embedded NovaMov-based player
1723 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1724 (?P<url>http://(?:(?:embed|www)\.)?
1726 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1727 videoweed\.(?:es|com)|
1728 movshare\.(?:net|sx|ag)|
1729 divxstage\.(?:eu|net|ch|co|at|ag))
1730 /embed\.php.+?)\1''', webpage)
1731 if mobj is not None:
1732 return self.url_result(mobj.group('url'))
1734 # Look for embedded Facebook player
1736 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
1737 if mobj is not None:
1738 return self.url_result(mobj.group('url'), 'Facebook')
1740 # Look for embedded VK player
1741 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1742 if mobj is not None:
1743 return self.url_result(mobj.group('url'), 'VK')
1745 # Look for embedded Odnoklassniki player
1746 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1747 if mobj is not None:
1748 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1750 # Look for embedded ivi player
1751 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1752 if mobj is not None:
1753 return self.url_result(mobj.group('url'), 'Ivi')
1755 # Look for embedded Huffington Post player
1757 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1758 if mobj is not None:
1759 return self.url_result(mobj.group('url'), 'HuffPost')
1762 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1763 if mobj is not None:
1764 return self.url_result(mobj.group('url'))
1765 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1766 if mobj is not None:
1767 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1769 # Look for funnyordie embed
1770 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1772 return _playlist_from_matches(
1773 matches, getter=unescapeHTML, ie='FunnyOrDie')
1775 # Look for BBC iPlayer embed
1776 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1778 return _playlist_from_matches(matches, ie='BBCCoUk')
1780 # Look for embedded RUTV player
1781 rutv_url = RUTVIE._extract_url(webpage)
1783 return self.url_result(rutv_url, 'RUTV')
1785 # Look for embedded TVC player
1786 tvc_url = TVCIE._extract_url(webpage)
1788 return self.url_result(tvc_url, 'TVC')
1790 # Look for embedded SportBox player
1791 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1793 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1795 # Look for embedded PornHub player
1796 pornhub_url = PornHubIE._extract_url(webpage)
1798 return self.url_result(pornhub_url, 'PornHub')
1800 # Look for embedded XHamster player
1801 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1803 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1805 # Look for embedded TNAFlixNetwork player
1806 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1808 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1810 # Look for embedded Tvigle player
1812 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1813 if mobj is not None:
1814 return self.url_result(mobj.group('url'), 'Tvigle')
1816 # Look for embedded TED player
1818 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1819 if mobj is not None:
1820 return self.url_result(mobj.group('url'), 'TED')
1822 # Look for embedded Ustream videos
1824 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1825 if mobj is not None:
1826 return self.url_result(mobj.group('url'), 'Ustream')
1828 # Look for embedded arte.tv player
1830 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
1832 if mobj is not None:
1833 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1835 # Look for embedded francetv player
1837 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1839 if mobj is not None:
1840 return self.url_result(mobj.group('url'))
1842 # Look for embedded smotri.com player
1843 smotri_url = SmotriIE._extract_url(webpage)
1845 return self.url_result(smotri_url, 'Smotri')
1847 # Look for embedded Myvi.ru player
1848 myvi_url = MyviIE._extract_url(webpage)
1850 return self.url_result(myvi_url)
1852 # Look for embedded soundcloud player
1854 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
1856 if mobj is not None:
1857 url = unescapeHTML(mobj.group('url'))
1858 return self.url_result(url)
1860 # Look for embedded mtvservices player
1861 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1863 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
1865 # Look for embedded yahoo player
1867 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1869 if mobj is not None:
1870 return self.url_result(mobj.group('url'), 'Yahoo')
1872 # Look for embedded sbs.com.au player
1876 <meta\s+property="og:video"\s+content=|
1879 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
1881 if mobj is not None:
1882 return self.url_result(mobj.group('url'), 'SBS')
1884 # Look for embedded Cinchcast player
1886 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1888 if mobj is not None:
1889 return self.url_result(mobj.group('url'), 'Cinchcast')
1892 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1896 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1898 if mobj is not None:
1899 return self.url_result(mobj.group('url'), 'MLB')
1902 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1904 if mobj is not None:
1905 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1908 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
1910 if mobj is not None:
1911 return self.url_result(mobj.group('url'), 'Livestream')
1913 # Look for Zapiks embed
1915 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1916 if mobj is not None:
1917 return self.url_result(mobj.group('url'), 'Zapiks')
1919 # Look for Kaltura embeds
1920 mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?(?P<q1>['\"])wid(?P=q1)\s*:\s*(?P<q2>['\"])_?(?P<partner_id>[^'\"]+)(?P=q2),.*?(?P<q3>['\"])entry_?[Ii]d(?P=q3)\s*:\s*(?P<q4>['\"])(?P<id>[^'\"]+)(?P=q4),", webpage) or
1921 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))
1922 if mobj is not None:
1923 return self.url_result(smuggle_url(
1924 'kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(),
1925 {'source_url': url}), 'Kaltura')
1927 # Look for Eagle.Platform embeds
1929 r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
1930 if mobj is not None:
1931 return self.url_result(mobj.group('url'), 'EaglePlatform')
1933 # Look for ClipYou (uses Eagle.Platform) embeds
1935 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1936 if mobj is not None:
1937 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1939 # Look for Pladform embeds
1940 pladform_url = PladformIE._extract_url(webpage)
1942 return self.url_result(pladform_url)
1944 # Look for Videomore embeds
1945 videomore_url = VideomoreIE._extract_url(webpage)
1947 return self.url_result(videomore_url)
1949 # Look for Playwire embeds
1951 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1952 if mobj is not None:
1953 return self.url_result(mobj.group('url'))
1955 # Look for 5min embeds
1957 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1958 if mobj is not None:
1959 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1961 # Look for Crooks and Liars embeds
1963 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1964 if mobj is not None:
1965 return self.url_result(mobj.group('url'))
1967 # Look for NBC Sports VPlayer embeds
1968 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1970 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1972 # Look for NBC News embeds
1973 nbc_news_embed_url = re.search(
1974 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
1975 if nbc_news_embed_url:
1976 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
1978 # Look for Google Drive embeds
1979 google_drive_url = GoogleDriveIE._extract_url(webpage)
1980 if google_drive_url:
1981 return self.url_result(google_drive_url, 'GoogleDrive')
1983 # Look for UDN embeds
1985 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
1986 if mobj is not None:
1987 return self.url_result(
1988 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
1990 # Look for Senate ISVP iframe
1991 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1993 return self.url_result(senate_isvp_url, 'SenateISVP')
1995 # Look for Dailymotion Cloud videos
1996 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
1998 return self.url_result(dmcloud_url, 'DailymotionCloud')
2000 # Look for OnionStudios embeds
2001 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2002 if onionstudios_url:
2003 return self.url_result(onionstudios_url)
2005 # Look for ViewLift embeds
2006 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2008 return self.url_result(viewlift_url)
2010 # Look for JWPlatform embeds
2011 jwplatform_url = JWPlatformIE._extract_url(webpage)
2013 return self.url_result(jwplatform_url, 'JWPlatform')
2015 # Look for ScreenwaveMedia embeds
2016 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2017 if mobj is not None:
2018 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2020 # Look for Digiteka embeds
2021 digiteka_url = DigitekaIE._extract_url(webpage)
2023 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2025 # Look for Limelight embeds
2026 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2030 'Channel': 'channel',
2031 'ChannelList': 'channel_list',
2033 return self.url_result('limelight:%s:%s' % (
2034 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2036 # Look for AdobeTVVideo embeds
2038 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2040 if mobj is not None:
2041 return self.url_result(
2042 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2045 # Look for Vine embeds
2047 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2049 if mobj is not None:
2050 return self.url_result(
2051 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2053 # Look for Instagram embeds
2054 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2055 if instagram_embed_url is not None:
2056 return self.url_result(
2057 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2059 # Look for LiveLeak embeds
2060 liveleak_url = LiveLeakIE._extract_url(webpage)
2062 return self.url_result(liveleak_url, 'LiveLeak')
2064 # Look for 3Q SDN embeds
2065 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2068 '_type': 'url_transparent',
2069 'ie_key': ThreeQSDNIE.ie_key(),
2070 'url': self._proto_relative_url(threeqsdn_url),
2071 'title': video_title,
2072 'description': video_description,
2073 'thumbnail': video_thumbnail,
2074 'uploader': video_uploader,
2077 def check_video(vurl):
2078 if YoutubeIE.suitable(vurl):
2080 vpath = compat_urlparse.urlparse(vurl).path
2081 vext = determine_ext(vpath)
2082 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2084 def filter_video(urls):
2085 return list(filter(check_video, urls))
2087 # Start with something easy: JW Player in SWFObject
2088 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2090 # Look for gorilla-vid style embedding
2091 found = filter_video(re.findall(r'''(?sx)
2095 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2098 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2100 # Broaden the search a little bit
2101 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2103 # Broaden the findall a little bit: JWPlayer JS loader
2104 found = filter_video(re.findall(
2105 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2108 found = filter_video(re.findall(r'''(?xs)
2109 flowplayer\("[^"]+",\s*
2111 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2112 ["']?url["']?\s*:\s*["']([^"']+)["']
2117 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2119 # Try to find twitter cards info
2120 found = filter_video(re.findall(
2121 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2123 # We look for Open Graph info:
2124 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2125 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2126 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2127 if m_video_type is not None:
2128 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2131 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2133 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2135 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2136 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2139 # Look also in Refresh HTTP header
2140 refresh_header = head_response.headers.get('Refresh')
2142 # In python 2 response HTTP headers are bytestrings
2143 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2144 refresh_header = refresh_header.decode('iso-8859-1')
2145 found = re.search(REDIRECT_REGEX, refresh_header)
2147 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2148 self.report_following_redirect(new_url)
2154 raise UnsupportedError(url)
2157 for video_url in orderedSet(found):
2158 video_url = unescapeHTML(video_url)
2159 video_url = video_url.replace('\\/', '/')
2160 video_url = compat_urlparse.urljoin(url, video_url)
2161 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2163 # Sometimes, jwplayer extraction will result in a YouTube URL
2164 if YoutubeIE.suitable(video_url):
2165 entries.append(self.url_result(video_url, 'Youtube'))
2168 # here's a fun little line of code for you:
2169 video_id = os.path.splitext(video_id)[0]
2173 'uploader': video_uploader,
2174 'title': video_title,
2175 'age_limit': age_limit,
2178 ext = determine_ext(video_url)
2180 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2182 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2184 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2186 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2188 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2190 entry_info_dict['url'] = video_url
2192 if entry_info_dict.get('formats'):
2193 self._sort_formats(entry_info_dict['formats'])
2195 entries.append(entry_info_dict)
2197 if len(entries) == 1:
2200 for num, e in enumerate(entries, start=1):
2201 # 'url' results don't have a title
2202 if e.get('title') is not None:
2203 e['title'] = '%s (%d)' % (e['title'], num)
2205 '_type': 'playlist',