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,
32 from .brightcove import (
36 from .nbc import NBCSportsVPlayerIE
37 from .ooyala import OoyalaIE
38 from .rutv import RUTVIE
39 from .tvc import TVCIE
40 from .sportbox import SportBoxEmbedIE
41 from .smotri import SmotriIE
42 from .myvi import MyviIE
43 from .condenast import CondeNastIE
44 from .udn import UDNEmbedIE
45 from .senateisvp import SenateISVPIE
46 from .svt import SVTIE
47 from .pornhub import PornHubIE
48 from .xhamster import XHamsterEmbedIE
49 from .tnaflix import TNAFlixNetworkEmbedIE
50 from .vimeo import VimeoIE
51 from .dailymotion import (
55 from .onionstudios import OnionStudiosIE
56 from .viewlift import ViewLiftEmbedIE
57 from .screenwavemedia import ScreenwaveMediaIE
58 from .mtv import MTVServicesEmbeddedIE
59 from .pladform import PladformIE
60 from .videomore import VideomoreIE
61 from .googledrive import GoogleDriveIE
62 from .jwplatform import JWPlatformIE
63 from .digiteka import DigitekaIE
64 from .arkena import ArkenaIE
65 from .instagram import InstagramIE
66 from .liveleak import LiveLeakIE
67 from .threeqsdn import ThreeQSDNIE
68 from .theplatform import ThePlatformIE
69 from .vessel import VesselIE
70 from .kaltura import KalturaIE
71 from .eagleplatform import EaglePlatformIE
72 from .facebook import FacebookIE
73 from .soundcloud import SoundcloudIE
74 from .vbox7 import Vbox7IE
75 from .dbtv import DBTVIE
78 class GenericIE(InfoExtractor):
79 IE_DESC = 'Generic downloader that works on some sites'
83 # Direct link to a video
85 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
86 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
91 'upload_date': '20100513',
94 # Direct link to media delivered compressed (until Accept-Encoding is *)
96 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
97 'md5': '128c42e68b13950268b648275386fc74',
99 'id': 'FictionJunction-Parallel_Hearts',
101 'title': 'FictionJunction-Parallel_Hearts',
102 'upload_date': '20140522',
104 'expected_warnings': [
105 'URL could be a direct video link, returning it as such.'
107 'skip': 'URL invalid',
109 # Direct download with broken HEAD
111 'url': 'http://ai-radio.org:8000/radio.opus',
118 'skip_download': True, # infinite live stream
120 'expected_warnings': [
121 r'501.*Not Implemented',
125 # Direct link with incorrect MIME type
127 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
128 'md5': '4ccbebe5f36706d85221f204d7eb5913',
130 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
131 'id': '5_Lennart_Poettering_-_Systemd',
133 'title': '5_Lennart_Poettering_-_Systemd',
134 'upload_date': '20141120',
136 'expected_warnings': [
137 'URL could be a direct video link, returning it as such.'
142 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
144 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
145 'title': 'Zero Punctuation',
146 'description': 're:.*groundbreaking video review series.*'
148 'playlist_mincount': 11,
150 # RSS feed with enclosure
152 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
154 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
156 'upload_date': '20150228',
157 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
160 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
162 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
166 'title': 'Automatics, robotics and biocybernetics',
167 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
168 'upload_date': '20130627',
169 'formats': 'mincount:16',
170 'subtitles': 'mincount:1',
173 'force_generic_extractor': True,
174 'skip_download': True,
177 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
179 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
184 'formats': 'mincount:1',
187 'skip_download': True,
190 # SMIL from https://www.restudy.dk/video/play/id/1637
192 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
196 'title': 'video_1637',
197 'formats': 'mincount:3',
200 'skip_download': True,
203 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
205 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
207 'id': 'smil-service',
209 'title': 'smil-service',
210 'formats': 'mincount:1',
213 'skip_download': True,
216 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
218 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
222 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
223 'formats': 'mincount:3',
226 'skip_download': True,
229 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
231 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
233 'id': 'mZlp2ctYIUEB',
235 'title': 'Tikibad ontruimd wegens brand',
236 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
237 'thumbnail': 're:^https?://.*\.jpg$',
241 'skip_download': True,
244 # MPD from http://dash-mse-test.appspot.com/media.html
246 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
247 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
249 'id': 'car-20120827-manifest',
251 'title': 'car-20120827-manifest',
252 'formats': 'mincount:9',
253 'upload_date': '20130904',
256 'format': 'bestvideo',
259 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
261 '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',
266 'formats': 'mincount:8',
270 'skip_download': True,
272 'skip': 'video gone',
274 # m3u8 served with Content-Type: text/plain
276 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
281 'upload_date': '20140720',
282 'formats': 'mincount:11',
286 'skip_download': True,
288 'skip': 'video gone',
292 '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',
296 'upload_date': '20130224',
297 'uploader_id': 'TheVerge',
298 'description': 're:^Chris Ziegler takes a look at the\.*',
299 'uploader': 'The Verge',
300 'title': 'First Firefox OS phones side-by-side',
303 'skip_download': False,
307 # redirect in Refresh HTTP header
308 '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',
312 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
313 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
314 'upload_date': '20150917',
315 'uploader_id': 'brtvofficial',
316 'uploader': 'Boiler Room',
319 'skip_download': False,
323 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
324 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
326 'id': '13601338388002',
328 'uploader': 'www.hodiho.fr',
329 'title': 'R\u00e9gis plante sa Jeep',
332 # bandcamp page with custom domain
334 'add_ie': ['Bandcamp'],
335 'url': 'http://bronyrock.com/track/the-pony-mash',
339 'title': 'The Pony Mash',
340 'uploader': 'M_Pallante',
342 'skip': 'There is a limit of 200 free downloads / month for the test song',
344 # embedded brightcove video
345 # it also tests brightcove videos that need to set the 'Referer' in the
348 'add_ie': ['BrightcoveLegacy'],
349 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
351 'id': '2765128793001',
353 'title': 'Le cours de bourse : l’analyse technique',
354 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
355 'uploader': 'BFM BUSINESS',
358 'skip_download': True,
362 # https://github.com/rg3/youtube-dl/issues/2253
363 'url': 'http://bcove.me/i6nfkrc3',
364 'md5': '0ba9446db037002366bab3b3eb30c88c',
366 'id': '3101154703001',
368 'title': 'Still no power',
369 'uploader': 'thestar.com',
370 '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.',
372 'add_ie': ['BrightcoveLegacy'],
373 'skip': 'video gone',
376 'url': 'http://www.championat.com/video/football/v/87/87499.html',
377 'md5': 'fb973ecf6e4a78a67453647444222983',
379 'id': '3414141473001',
381 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
382 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
383 'uploader': 'Championat',
387 # https://github.com/rg3/youtube-dl/issues/3541
388 'add_ie': ['BrightcoveLegacy'],
389 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
391 'id': '3866516442001',
393 'title': 'Leer mij vrouwen kennen: Aflevering 1',
394 'description': 'Leer mij vrouwen kennen: Aflevering 1',
395 'uploader': 'SBS Broadcasting',
397 'skip': 'Restricted to Netherlands',
399 'skip_download': True, # m3u8 download
404 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
405 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
407 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
409 'title': '2cc213299525360.mov', # that's what we get
412 'add_ie': ['Ooyala'],
415 # ooyala video embedded with http://player.ooyala.com/iframe.js
416 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
418 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
420 'title': '"Steve Jobs: Man in the Machine" trailer',
421 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
425 'skip_download': True,
427 'skip': 'movie expired',
431 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
435 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
436 'upload_date': '20140225',
437 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
438 'uploader': 'Tested',
439 'uploader_id': 'testedcom',
441 # No need to test YoutubeIE here
443 'skip_download': True,
448 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
452 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
453 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
455 # HEAD requests lead to endless 301, while GET is OK
456 'expected_warnings': ['301'],
460 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
464 'title': 'Охотское море стало целиком российским',
465 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
469 'skip_download': True,
474 '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/',
478 'title': 'Дошкольное воспитание',
483 'url': 'http://www.vestifinance.ru/articles/25753',
486 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
491 'title': 'Госзаказ. День 3',
497 'title': 'Госзаказ. День 2',
503 'title': 'Госзаказ. День 1',
509 'skip_download': True,
514 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
516 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
518 'title': 'Ужастики, русский трейлер (2015)',
519 'thumbnail': 're:^https?://.*\.jpg$',
525 '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',
528 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
530 'playlist_mincount': 7,
531 # This forum does not allow <iframe> syntaxes anymore
532 # Now HTML tags are displayed as-is
533 'skip': 'No videos on this page',
537 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
538 'md5': '65fdff94098e4a607385a60c5177c638',
542 'title': 'Hidden miracles of the natural world',
543 'uploader': 'Louie Schwartzberg',
544 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
547 # Embedded Ustream video
549 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
550 'md5': '27b99cdb639c9b12a79bca876a073417',
554 'uploader': 'AU SPA: The NSA and Privacy',
555 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
558 # nowvideo embed hidden behind percent encoding
560 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
561 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
563 'id': '06e53103ca9aa',
565 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
566 'description': 'No description',
571 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
572 'md5': '7653032cbb25bf6c80d80f217055fa43',
574 'id': '048195-004_PLUS7-F',
577 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
578 'upload_date': '20140320',
581 'skip_download': 'Requires rtmpdump'
583 'skip': 'video gone',
587 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
591 'title': 'Alcaline, le concert avec Calogero',
592 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
593 'upload_date': '20150226',
594 'timestamp': 1424989860,
599 'skip_download': True,
601 'expected_warnings': [
607 'url': 'http://www.wired.com/2014/04/honda-asimo/',
608 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
610 'id': '53501be369702d3275860000',
612 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
617 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
618 'md5': '441aeeb82eb72c422c7f14ec533999cd',
620 'id': 'k2mm4bCdJ6CQ2i7c8o2',
622 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
623 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
625 'uploader_id': 'xgditw',
626 'upload_date': '20140425',
627 'timestamp': 1398441542,
629 'add_ie': ['Dailymotion'],
633 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
637 'title': 'The NBL Auction 2014',
638 'uploader': 'BADMINTON England',
639 'uploader_id': 'BADMINTONEvents',
640 'upload_date': '20140603',
641 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
643 'add_ie': ['Youtube'],
645 'skip_download': True,
650 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
651 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
653 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
655 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
656 'description': 'Two valets share their love for movie star Liam Neesons.',
657 'timestamp': 1349922600,
658 'upload_date': '20121011',
661 # YouTube embed via <data-embed-url="">
663 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
667 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
668 'uploader': 'Gameloft',
669 'uploader_id': 'gameloft',
670 'upload_date': '20140828',
671 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
674 'skip_download': True,
679 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
681 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
683 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
684 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
689 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
691 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
692 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
698 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
703 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
704 'md5': '9d65602bf31c6e20014319c7d07fba27',
706 'id': '5123ea6d5e5a7',
709 'uploader': 'www.handjobhub.com',
710 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
713 # Multiple brightcove videos
714 # https://github.com/rg3/youtube-dl/issues/2283
716 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
718 'id': 'always-never',
719 'title': 'Always / Never - The New Yorker',
723 'extract_flat': False,
724 'skip_download': True,
729 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
730 'md5': '96f09a37e44da40dd083e12d9a683327',
734 'title': 'Ump changes call to ball',
735 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
737 'timestamp': 1401537900,
738 'upload_date': '20140531',
739 'thumbnail': 're:^https?://.*\.jpg$',
744 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
745 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
749 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
750 'description': 'a Paywall Videos video from Remilon',
752 'uploader': 'study.com',
753 'timestamp': 1459678540,
754 'upload_date': '20160403',
755 'filesize': 24687186,
759 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
760 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
764 'title': 'Conversation about Hexagonal Rails Part 1',
765 'description': 'a Martin Fowler video from ThoughtWorks',
767 'uploader': 'thoughtworks.wistia.com',
768 'timestamp': 1401832161,
769 'upload_date': '20140603',
772 # Wistia standard embed (async)
774 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
778 'title': 'Drip Brennan Dunn Workshop',
779 'description': 'a JV Webinars video from getdrip-1',
781 'timestamp': 1463607249,
782 'upload_date': '20160518',
785 'skip_download': True,
790 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
794 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
795 'uploader': 'Sophos Security',
796 'title': 'Chet Chat 171 - Oct 29, 2014',
797 'upload_date': '20141029',
800 # Soundcloud multiple embeds
802 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
805 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
807 'playlist_mincount': 7,
811 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
815 'upload_date': '20141112',
816 'title': 'Rosetta #CometLanding webcast HL 10',
819 # Another Livestream embed, without 'new.' in URL
821 'url': 'https://www.freespeech.org/',
825 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
829 'skip_download': True,
834 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
837 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
839 'playlist_mincount': 2,
843 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
847 'upload_date': '20141126',
848 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
853 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
855 'id': '730m_DandD_1901_512k',
857 'uploader': 'www.abc.net.au',
858 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
861 # embedded viddler video
863 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
867 'uploader': 'deadspin',
868 'title': 'WALL-TO-GORTAT',
869 'timestamp': 1422285291,
870 'upload_date': '20150126',
872 'add_ie': ['Viddler'],
876 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
880 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
881 'description': 'md5:601cb790edd05908957dae8aaa866465',
882 'upload_date': '20150220',
884 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
888 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
892 'upload_date': '20150212',
893 'uploader': 'The National Archives UK',
894 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
895 'uploader_id': 'NationalArchives08',
896 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
901 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
902 'playlist_mincount': 5,
904 'id': 'aanslagen-kopenhagen',
905 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
910 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
914 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
917 # Kaltura embed (different embed code)
919 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
923 'upload_date': '20150127',
924 'uploader_id': 'PremierMedia',
926 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
929 # Kaltura embed protected with referrer
931 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
935 'title': 'Violetta - Achter De Schermen - Ruggero',
936 'description': 'Achter de schermen met Ruggero',
937 'timestamp': 1435133761,
938 'upload_date': '20150624',
939 'uploader_id': 'echojecka',
942 # Kaltura embed with single quotes
944 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
949 'timestamp': 1355743100,
950 'upload_date': '20121217',
951 'uploader_id': 'batchUser',
953 'add_ie': ['Kaltura'],
956 # Kaltura embedded via quoted entry_id
957 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
961 'title': '06_matthew_brender_raj_dutt',
962 'timestamp': 1466638791,
963 'upload_date': '20160622',
965 'add_ie': ['Kaltura'],
966 'expected_warnings': [
967 'Could not send HEAD request'
970 'skip_download': True,
973 # Eagle.Platform embed (generic URL)
975 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
976 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
980 'title': 'Навальный вышел на свободу',
981 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
982 'thumbnail': 're:^https?://.*\.jpg$',
988 # ClipYou (Eagle.Platform) embed (custom URL)
990 'url': 'http://muz-tv.ru/play/7129/',
991 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
995 'title': "'O Sole Mio",
996 'thumbnail': 're:^https?://.*\.jpg$',
1003 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1007 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1008 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1009 'thumbnail': 're:^https?://.*\.jpg$',
1016 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1020 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1021 'thumbnail': 're:^https?://.*\.png$',
1027 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1028 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1032 'title': 'Facebook Creates "On This Day" | Crunch Report',
1037 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1041 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1046 # Crooks and Liars embed
1048 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1052 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1053 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1054 'timestamp': 1428207000,
1055 'upload_date': '20150405',
1056 'uploader': 'Heather',
1059 # Crooks and Liars external embed
1061 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1063 'id': 'MTE3MjUtMzQ2MzA',
1065 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1066 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1067 'timestamp': 1265032391,
1068 'upload_date': '20100201',
1069 'uploader': 'Heather',
1072 # NBC Sports vplayer embed
1074 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1076 'id': 'ln7x1qSThw4k',
1078 'title': "PFT Live: New leader in the 'new-look' defense",
1079 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1080 'uploader': 'NBCU-SPORTS',
1081 'upload_date': '20140107',
1082 'timestamp': 1389118457,
1087 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1088 'md5': '1aa589c675898ae6d37a17913cf68d66',
1090 'id': '701714499682',
1092 'title': 'PREVIEW: On Assignment: David Letterman',
1093 '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.',
1098 'url': 'https://video.udn.com/news/300346',
1099 'md5': 'fd2060e988c326991037b9aff9df21a6',
1103 'title': '中一中男師變性 全校師生力挺',
1104 'thumbnail': 're:^https?://.*\.jpg$',
1108 'skip_download': True,
1113 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1115 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1117 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1118 'title': 'This is what separates the Excel masters from the wannabes',
1119 'duration': 191.933,
1123 'skip_download': True,
1126 # Brightcove URL in single quotes
1128 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1129 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1131 'id': '4255764656001',
1133 'title': 'SN Presents: Russell Martin, World Citizen',
1134 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1135 'uploader': 'Rogers Sportsnet',
1136 'uploader_id': '1704050871',
1137 'upload_date': '20150525',
1138 'timestamp': 1432570283,
1141 # Dailymotion Cloud video
1143 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1144 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1148 'title': 'Sauvons les abeilles ! - Le débat',
1149 'description': 'md5:d9082128b1c5277987825d684939ca26',
1150 'thumbnail': 're:^https?://.*\.jpe?g$',
1151 'timestamp': 1434970506,
1152 'upload_date': '20150622',
1153 'uploader': 'Public Sénat',
1154 'uploader_id': 'xa9gza',
1157 # OnionStudios embed
1159 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1163 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1164 'thumbnail': 're:^https?://.*\.jpe?g$',
1165 'uploader': 'ClickHole',
1166 'uploader_id': 'clickhole',
1171 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1173 'id': '74849a00-85a9-11e1-9660-123139220831',
1175 'title': '#whilewewatch',
1178 # AdobeTVVideo embed
1180 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1181 'md5': '43662b577c018ad707a63766462b1e87',
1185 'title': 'New experience with Acrobat DC',
1186 'description': 'New experience with Acrobat DC',
1187 'duration': 248.667,
1190 # ScreenwaveMedia embed
1192 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1193 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1195 'id': 'cinemasnob-55d26273809dd',
1197 'title': 'cinemasnob',
1200 # BrightcoveInPageEmbed embed
1202 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1204 'id': '4238694884001',
1206 'title': 'Tabletop: Dread, Last Thoughts',
1207 'description': 'Tabletop: Dread, Last Thoughts',
1211 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1212 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1214 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1216 'id': '4785848093001',
1218 'title': 'The Cardinal Pell Interview',
1219 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1220 'uploader': 'GlobeCast Australia - GlobeStream',
1221 'uploader_id': '2733773828001',
1222 'upload_date': '20160304',
1223 'timestamp': 1457083087,
1227 'skip_download': True,
1230 # Another form of arte.tv embed
1232 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1233 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1235 'id': '030273-562_PLUS7-F',
1237 'title': 'ARTE Reportage - Nulle part, en France',
1238 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1239 'upload_date': '20160409',
1244 'url': 'http://www.wykop.pl/link/3088787/',
1245 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1247 'id': '874_1459135191',
1249 'title': 'Man shows poor quality of new apartment building',
1250 'description': 'The wall is like a sand pile.',
1251 'uploader': 'Lake8737',
1254 # Duplicated embedded video URLs
1256 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1258 'id': '149298443_480_16c25b74_2',
1260 'title': 'vs. Blue Orange Spring Game',
1261 'uploader': 'www.hudl.com',
1264 # twitter:player:stream embed
1266 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1270 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1271 'uploader': 'www.rtl.be',
1275 'skip_download': True,
1278 # twitter:player embed
1280 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1281 'md5': 'a3e0df96369831de324f0778e126653c',
1283 'id': '4909620399001',
1285 'title': 'What Do Black Holes Sound Like?',
1286 'description': 'what do black holes sound like',
1287 'upload_date': '20160524',
1288 'uploader_id': '29913724001',
1289 'timestamp': 1464107587,
1290 'uploader': 'TheAtlantic',
1292 'add_ie': ['BrightcoveLegacy'],
1294 # Facebook <iframe> embed
1296 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1297 'md5': 'fbcde74f534176ecb015849146dd3aee',
1299 'id': '599637780109885',
1301 'title': 'Facebook video #599637780109885',
1304 # Facebook API embed
1306 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1307 'md5': 'a47372ee61b39a7b90287094d447d94e',
1309 'id': '10153467542406923',
1311 'title': 'Facebook video #10153467542406923',
1314 # Wordpress "YouTube Video Importer" plugin
1316 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1317 'md5': 'd16797741b560b485194eddda8121b48',
1319 'id': 'HNTXWDXV9Is',
1321 'title': 'Blue Devils Drumline Stanford lot 2016',
1322 'upload_date': '20160627',
1323 'uploader_id': 'GENOCIDE8GENERAL10',
1324 'uploader': 'cylus cyrus',
1328 # video stored on custom kaltura server
1329 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1330 'md5': '537617d06e64dfed891fa1593c4b30cc',
1334 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1335 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1336 'uploader_id': 'videos.expansion@el-mundo.net',
1337 'upload_date': '20150429',
1338 'timestamp': 1430303472,
1340 'add_ie': ['Kaltura'],
1343 # Non-standard Vimeo embed
1344 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1345 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1349 'title': 'Understanding the web - Teaser',
1350 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1351 'upload_date': '20151214',
1352 'uploader': 'OpenClassrooms',
1353 'uploader_id': 'openclassrooms',
1355 'add_ie': ['Vimeo'],
1358 # generic vimeo embed that requires original URL passed as Referer
1359 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1360 'only_matching': True,
1363 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1364 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1366 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1368 'title': 'Big Buck Bunny',
1369 'description': 'Royalty free test video',
1370 'timestamp': 1432816365,
1371 'upload_date': '20150528',
1375 'skip_download': True,
1377 'add_ie': [ArkenaIE.ie_key()],
1380 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1384 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1387 'skip_download': True,
1389 'add_ie': [Vbox7IE.ie_key()],
1393 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1396 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1398 'playlist_mincount': 3,
1401 # # TODO: find another test
1402 # # http://schema.org/VideoObject
1403 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1404 # 'md5': '888dcf08b7ea671381f00fab74692755',
1406 # 'id': 'nyvTSJMKId',
1408 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1409 # 'description': '#love for cats.',
1410 # 'timestamp': 1461244995,
1411 # 'upload_date': '20160421',
1414 # 'force_generic_extractor': True,
1419 def report_following_redirect(self, new_url):
1420 """Report information extraction."""
1421 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1423 def _extract_rss(self, url, video_id, doc):
1424 playlist_title = doc.find('./channel/title').text
1425 playlist_desc_el = doc.find('./channel/description')
1426 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1429 for it in doc.findall('./channel/item'):
1430 next_url = xpath_text(it, 'link', fatal=False)
1432 enclosure_nodes = it.findall('./enclosure')
1433 for e in enclosure_nodes:
1434 next_url = e.attrib.get('url')
1444 'title': it.find('title').text,
1448 '_type': 'playlist',
1450 'title': playlist_title,
1451 'description': playlist_desc,
1455 def _extract_camtasia(self, url, video_id, webpage):
1456 """ Returns None if no camtasia video can be found. """
1458 camtasia_cfg = self._search_regex(
1459 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1460 webpage, 'camtasia configuration file', default=None)
1461 if camtasia_cfg is None:
1464 title = self._html_search_meta('DC.title', webpage, fatal=True)
1466 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1467 camtasia_cfg = self._download_xml(
1468 camtasia_url, video_id,
1469 note='Downloading camtasia configuration',
1470 errnote='Failed to download camtasia configuration')
1471 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1474 for n in fileset_node.getchildren():
1475 url_n = n.find('./uri')
1480 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1481 'title': '%s - %s' % (title, n.tag),
1482 'url': compat_urlparse.urljoin(url, url_n.text),
1483 'duration': float_or_none(n.find('./duration').text),
1487 '_type': 'playlist',
1492 def _real_extract(self, url):
1493 if url.startswith('//'):
1496 'url': self.http_scheme() + url,
1499 parsed_url = compat_urlparse.urlparse(url)
1500 if not parsed_url.scheme:
1501 default_search = self._downloader.params.get('default_search')
1502 if default_search is None:
1503 default_search = 'fixup_error'
1505 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1507 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1508 return self.url_result('http://' + url)
1509 elif default_search != 'fixup_error':
1510 if default_search == 'auto_warning':
1511 if re.match(r'^(?:url|URL)$', url):
1512 raise ExtractorError(
1513 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1516 self._downloader.report_warning(
1517 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1518 return self.url_result('ytsearch:' + url)
1520 if default_search in ('error', 'fixup_error'):
1521 raise ExtractorError(
1522 '%r is not a valid URL. '
1523 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1524 % (url, url), expected=True)
1526 if ':' not in default_search:
1527 default_search += ':'
1528 return self.url_result(default_search + url)
1530 url, smuggled_data = unsmuggle_url(url)
1531 force_videoid = None
1532 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1533 if smuggled_data and 'force_videoid' in smuggled_data:
1534 force_videoid = smuggled_data['force_videoid']
1535 video_id = force_videoid
1537 video_id = self._generic_id(url)
1539 self.to_screen('%s: Requesting header' % video_id)
1541 head_req = HEADRequest(url)
1542 head_response = self._request_webpage(
1544 note=False, errnote='Could not send HEAD request to %s' % url,
1547 if head_response is not False:
1548 # Check for redirect
1549 new_url = head_response.geturl()
1551 self.report_following_redirect(new_url)
1553 new_url = smuggle_url(
1554 new_url, {'force_videoid': force_videoid})
1555 return self.url_result(new_url)
1557 full_response = None
1558 if head_response is False:
1559 request = sanitized_Request(url)
1560 request.add_header('Accept-Encoding', '*')
1561 full_response = self._request_webpage(request, video_id)
1562 head_response = full_response
1566 'title': self._generic_title(url),
1567 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1570 # Check for direct link to a video
1571 content_type = head_response.headers.get('Content-Type', '').lower()
1572 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1574 format_id = m.group('format_id')
1575 if format_id.endswith('mpegurl'):
1576 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1577 elif format_id == 'f4m':
1578 formats = self._extract_f4m_formats(url, video_id)
1581 'format_id': m.group('format_id'),
1583 'vcodec': 'none' if m.group('type') == 'audio' else None
1585 info_dict['direct'] = True
1586 self._sort_formats(formats)
1587 info_dict['formats'] = formats
1590 if not self._downloader.params.get('test', False) and not is_intentional:
1591 force = self._downloader.params.get('force_generic_extractor', False)
1592 self._downloader.report_warning(
1593 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1595 if not full_response:
1596 request = sanitized_Request(url)
1597 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1598 # making it impossible to download only chunk of the file (yet we need only 512kB to
1599 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1600 # that will always result in downloading the whole file that is not desirable.
1601 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1602 # to accept raw bytes and being able to download only a chunk.
1603 # It may probably better to solve this by checking Content-Type for application/octet-stream
1604 # after HEAD request finishes, but not sure if we can rely on this.
1605 request.add_header('Accept-Encoding', '*')
1606 full_response = self._request_webpage(request, video_id)
1608 first_bytes = full_response.read(512)
1610 # Is it an M3U playlist?
1611 if first_bytes.startswith(b'#EXTM3U'):
1612 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1613 self._sort_formats(info_dict['formats'])
1616 # Maybe it's a direct link to a video?
1617 # Be careful not to download the whole thing!
1618 if not is_html(first_bytes):
1619 self._downloader.report_warning(
1620 'URL could be a direct video link, returning it as such.')
1627 webpage = self._webpage_read_content(
1628 full_response, url, video_id, prefix=first_bytes)
1630 self.report_extraction(video_id)
1632 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1634 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1635 if doc.tag == 'rss':
1636 return self._extract_rss(url, video_id, doc)
1637 elif doc.tag == 'SmoothStreamingMedia':
1638 info_dict['formats'] = self._parse_ism_formats(doc, url)
1639 self._sort_formats(info_dict['formats'])
1641 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1642 smil = self._parse_smil(doc, url, video_id)
1643 self._sort_formats(smil['formats'])
1645 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1646 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1647 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1648 info_dict['formats'] = self._parse_mpd_formats(
1650 mpd_base_url=full_response.geturl().rpartition('/')[0],
1652 self._sort_formats(info_dict['formats'])
1654 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1655 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1656 self._sort_formats(info_dict['formats'])
1658 except compat_xml_parse_error:
1661 # Is it a Camtasia project?
1662 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1663 if camtasia_res is not None:
1666 # Sometimes embedded video player is hidden behind percent encoding
1667 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1668 # Unescaping the whole page allows to handle those cases in a generic way
1669 webpage = compat_urllib_parse_unquote(webpage)
1671 # it's tempting to parse this further, but you would
1672 # have to take into account all the variations like
1673 # Video Title - Site Name
1674 # Site Name | Video Title
1675 # Video Title - Tagline | Site Name
1676 # and so on and so forth; it's just not practical
1677 video_title = self._og_search_title(
1678 webpage, default=None) or self._html_search_regex(
1679 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1682 # Try to detect age limit automatically
1683 age_limit = self._rta_search(webpage)
1684 # And then there are the jokers who advertise that they use RTA,
1685 # but actually don't.
1686 AGE_LIMIT_MARKERS = [
1687 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1689 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1692 # video uploader is domain name
1693 video_uploader = self._search_regex(
1694 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1696 video_description = self._og_search_description(webpage, default=None)
1697 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1700 def _playlist_from_matches(matches, getter=None, ie=None):
1702 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1704 return self.playlist_result(
1705 urlrs, playlist_id=video_id, playlist_title=video_title)
1707 # Look for Brightcove Legacy Studio embeds
1708 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1710 self.to_screen('Brightcove video detected.')
1713 'url': smuggle_url(bc_url, {'Referer': url}),
1714 'ie_key': 'BrightcoveLegacy'
1715 } for bc_url in bc_urls]
1718 '_type': 'playlist',
1719 'title': video_title,
1724 # Look for Brightcove New Studio embeds
1725 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1727 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1729 # Look for ThePlatform embeds
1730 tp_urls = ThePlatformIE._extract_urls(webpage)
1732 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1734 # Look for Vessel embeds
1735 vessel_urls = VesselIE._extract_urls(webpage)
1737 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1739 # Look for embedded rtl.nl player
1740 matches = re.findall(
1741 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1744 return _playlist_from_matches(matches, ie='RtlNl')
1746 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1748 return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
1750 vid_me_embed_url = self._search_regex(
1751 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1752 webpage, 'vid.me embed', default=None)
1753 if vid_me_embed_url is not None:
1754 return self.url_result(vid_me_embed_url, 'Vidme')
1756 # Look for embedded YouTube player
1757 matches = re.findall(r'''(?x)
1766 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1770 return _playlist_from_matches(
1771 matches, lambda m: unescapeHTML(m[1]))
1773 # Look for lazyYT YouTube embed
1774 matches = re.findall(
1775 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1777 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1779 # Look for Wordpress "YouTube Video Importer" plugin
1780 matches = re.findall(r'''(?x)<div[^>]+
1781 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1782 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1784 return _playlist_from_matches(matches, lambda m: m[-1])
1786 matches = DailymotionIE._extract_urls(webpage)
1788 return _playlist_from_matches(matches)
1790 # Look for embedded Dailymotion playlist player (#3822)
1792 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1794 playlists = re.findall(
1795 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1797 return _playlist_from_matches(
1798 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1800 # Look for embedded Wistia player
1802 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1804 embed_url = self._proto_relative_url(
1805 unescapeHTML(match.group('url')))
1807 '_type': 'url_transparent',
1810 'uploader': video_uploader,
1813 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1816 '_type': 'url_transparent',
1817 'url': 'wistia:%s' % match.group('id'),
1819 'uploader': video_uploader,
1824 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1825 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1828 return self.url_result(self._proto_relative_url(
1829 'wistia:%s' % match.group('id')), 'Wistia')
1831 # Look for SVT player
1832 svt_url = SVTIE._extract_url(webpage)
1834 return self.url_result(svt_url, 'SVT')
1836 # Look for embedded condenast player
1837 matches = re.findall(
1838 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1842 '_type': 'playlist',
1845 'ie_key': 'CondeNast',
1847 } for ma in matches],
1848 'title': video_title,
1852 # Look for Bandcamp pages with custom domain
1853 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1854 if mobj is not None:
1855 burl = unescapeHTML(mobj.group(1))
1856 # Don't set the extractor because it can be a track url or an album
1857 return self.url_result(burl)
1859 # Look for embedded Vevo player
1861 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1862 if mobj is not None:
1863 return self.url_result(mobj.group('url'))
1865 # Look for embedded Viddler player
1867 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1869 if mobj is not None:
1870 return self.url_result(mobj.group('url'))
1872 # Look for NYTimes player
1874 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1876 if mobj is not None:
1877 return self.url_result(mobj.group('url'))
1879 # Look for Libsyn player
1881 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1882 if mobj is not None:
1883 return self.url_result(mobj.group('url'))
1885 # Look for Ooyala videos
1886 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1887 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1888 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1889 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1890 if mobj is not None:
1891 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1893 # Look for multiple Ooyala embeds on SBN network websites
1894 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1895 if mobj is not None:
1896 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1898 return _playlist_from_matches(
1899 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1901 # Look for Aparat videos
1902 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1903 if mobj is not None:
1904 return self.url_result(mobj.group(1), 'Aparat')
1906 # Look for MPORA videos
1907 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1908 if mobj is not None:
1909 return self.url_result(mobj.group(1), 'Mpora')
1911 # Look for embedded NovaMov-based player
1913 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1914 (?P<url>http://(?:(?:embed|www)\.)?
1916 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1917 videoweed\.(?:es|com)|
1918 movshare\.(?:net|sx|ag)|
1919 divxstage\.(?:eu|net|ch|co|at|ag))
1920 /embed\.php.+?)\1''', webpage)
1921 if mobj is not None:
1922 return self.url_result(mobj.group('url'))
1924 # Look for embedded Facebook player
1925 facebook_url = FacebookIE._extract_url(webpage)
1926 if facebook_url is not None:
1927 return self.url_result(facebook_url, 'Facebook')
1929 # Look for embedded VK player
1930 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1931 if mobj is not None:
1932 return self.url_result(mobj.group('url'), 'VK')
1934 # Look for embedded Odnoklassniki player
1935 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1936 if mobj is not None:
1937 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1939 # Look for embedded ivi player
1940 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1941 if mobj is not None:
1942 return self.url_result(mobj.group('url'), 'Ivi')
1944 # Look for embedded Huffington Post player
1946 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1947 if mobj is not None:
1948 return self.url_result(mobj.group('url'), 'HuffPost')
1951 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1952 if mobj is not None:
1953 return self.url_result(mobj.group('url'))
1954 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1955 if mobj is not None:
1956 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1958 # Look for funnyordie embed
1959 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1961 return _playlist_from_matches(
1962 matches, getter=unescapeHTML, ie='FunnyOrDie')
1964 # Look for BBC iPlayer embed
1965 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1967 return _playlist_from_matches(matches, ie='BBCCoUk')
1969 # Look for embedded RUTV player
1970 rutv_url = RUTVIE._extract_url(webpage)
1972 return self.url_result(rutv_url, 'RUTV')
1974 # Look for embedded TVC player
1975 tvc_url = TVCIE._extract_url(webpage)
1977 return self.url_result(tvc_url, 'TVC')
1979 # Look for embedded SportBox player
1980 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1982 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1984 # Look for embedded PornHub player
1985 pornhub_url = PornHubIE._extract_url(webpage)
1987 return self.url_result(pornhub_url, 'PornHub')
1989 # Look for embedded XHamster player
1990 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1992 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1994 # Look for embedded TNAFlixNetwork player
1995 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1997 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1999 # Look for embedded Tvigle player
2001 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2002 if mobj is not None:
2003 return self.url_result(mobj.group('url'), 'Tvigle')
2005 # Look for embedded TED player
2007 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2008 if mobj is not None:
2009 return self.url_result(mobj.group('url'), 'TED')
2011 # Look for embedded Ustream videos
2013 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
2014 if mobj is not None:
2015 return self.url_result(mobj.group('url'), 'Ustream')
2017 # Look for embedded arte.tv player
2019 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2021 if mobj is not None:
2022 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2024 # Look for embedded francetv player
2026 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2028 if mobj is not None:
2029 return self.url_result(mobj.group('url'))
2031 # Look for embedded smotri.com player
2032 smotri_url = SmotriIE._extract_url(webpage)
2034 return self.url_result(smotri_url, 'Smotri')
2036 # Look for embedded Myvi.ru player
2037 myvi_url = MyviIE._extract_url(webpage)
2039 return self.url_result(myvi_url)
2041 # Look for embedded soundcloud player
2042 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2044 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2046 # Look for embedded mtvservices player
2047 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2049 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2051 # Look for embedded yahoo player
2053 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2055 if mobj is not None:
2056 return self.url_result(mobj.group('url'), 'Yahoo')
2058 # Look for embedded sbs.com.au player
2062 <meta\s+property="og:video"\s+content=|
2065 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2067 if mobj is not None:
2068 return self.url_result(mobj.group('url'), 'SBS')
2070 # Look for embedded Cinchcast player
2072 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2074 if mobj is not None:
2075 return self.url_result(mobj.group('url'), 'Cinchcast')
2078 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2082 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2084 if mobj is not None:
2085 return self.url_result(mobj.group('url'), 'MLB')
2088 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2090 if mobj is not None:
2091 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2094 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2096 if mobj is not None:
2097 return self.url_result(mobj.group('url'), 'Livestream')
2099 # Look for Zapiks embed
2101 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2102 if mobj is not None:
2103 return self.url_result(mobj.group('url'), 'Zapiks')
2105 # Look for Kaltura embeds
2106 kaltura_url = KalturaIE._extract_url(webpage)
2108 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2110 # Look for Eagle.Platform embeds
2111 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2112 if eagleplatform_url:
2113 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2115 # Look for ClipYou (uses Eagle.Platform) embeds
2117 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2118 if mobj is not None:
2119 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2121 # Look for Pladform embeds
2122 pladform_url = PladformIE._extract_url(webpage)
2124 return self.url_result(pladform_url)
2126 # Look for Videomore embeds
2127 videomore_url = VideomoreIE._extract_url(webpage)
2129 return self.url_result(videomore_url)
2131 # Look for Playwire embeds
2133 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2134 if mobj is not None:
2135 return self.url_result(mobj.group('url'))
2137 # Look for 5min embeds
2139 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2140 if mobj is not None:
2141 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2143 # Look for Crooks and Liars embeds
2145 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2146 if mobj is not None:
2147 return self.url_result(mobj.group('url'))
2149 # Look for NBC Sports VPlayer embeds
2150 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2152 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2154 # Look for NBC News embeds
2155 nbc_news_embed_url = re.search(
2156 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2157 if nbc_news_embed_url:
2158 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2160 # Look for Google Drive embeds
2161 google_drive_url = GoogleDriveIE._extract_url(webpage)
2162 if google_drive_url:
2163 return self.url_result(google_drive_url, 'GoogleDrive')
2165 # Look for UDN embeds
2167 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2168 if mobj is not None:
2169 return self.url_result(
2170 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2172 # Look for Senate ISVP iframe
2173 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2175 return self.url_result(senate_isvp_url, 'SenateISVP')
2177 # Look for Dailymotion Cloud videos
2178 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2180 return self.url_result(dmcloud_url, 'DailymotionCloud')
2182 # Look for OnionStudios embeds
2183 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2184 if onionstudios_url:
2185 return self.url_result(onionstudios_url)
2187 # Look for ViewLift embeds
2188 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2190 return self.url_result(viewlift_url)
2192 # Look for JWPlatform embeds
2193 jwplatform_url = JWPlatformIE._extract_url(webpage)
2195 return self.url_result(jwplatform_url, 'JWPlatform')
2197 # Look for ScreenwaveMedia embeds
2198 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2199 if mobj is not None:
2200 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2202 # Look for Digiteka embeds
2203 digiteka_url = DigitekaIE._extract_url(webpage)
2205 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2207 # Look for Arkena embeds
2208 arkena_url = ArkenaIE._extract_url(webpage)
2210 return self.url_result(arkena_url, ArkenaIE.ie_key())
2212 # Look for Limelight embeds
2213 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2217 'Channel': 'channel',
2218 'ChannelList': 'channel_list',
2220 return self.url_result('limelight:%s:%s' % (
2221 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2223 # Look for AdobeTVVideo embeds
2225 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2227 if mobj is not None:
2228 return self.url_result(
2229 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2232 # Look for Vine embeds
2234 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2236 if mobj is not None:
2237 return self.url_result(
2238 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2240 # Look for VODPlatform embeds
2242 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2244 if mobj is not None:
2245 return self.url_result(
2246 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2248 # Look for Mangomolo embeds
2250 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2252 video\?.*?\bid=(?P<video_id>\d+)|
2253 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2254 ).+?)\1''', webpage)
2255 if mobj is not None:
2257 '_type': 'url_transparent',
2258 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2259 'title': video_title,
2260 'description': video_description,
2261 'thumbnail': video_thumbnail,
2262 'uploader': video_uploader,
2264 video_id = mobj.group('video_id')
2267 'ie_key': 'MangomoloVideo',
2272 'ie_key': 'MangomoloLive',
2273 'id': mobj.group('channel_id'),
2277 # Look for Instagram embeds
2278 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2279 if instagram_embed_url is not None:
2280 return self.url_result(
2281 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2283 # Look for LiveLeak embeds
2284 liveleak_url = LiveLeakIE._extract_url(webpage)
2286 return self.url_result(liveleak_url, 'LiveLeak')
2288 # Look for 3Q SDN embeds
2289 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2292 '_type': 'url_transparent',
2293 'ie_key': ThreeQSDNIE.ie_key(),
2294 'url': self._proto_relative_url(threeqsdn_url),
2295 'title': video_title,
2296 'description': video_description,
2297 'thumbnail': video_thumbnail,
2298 'uploader': video_uploader,
2301 # Look for VBOX7 embeds
2302 vbox7_url = Vbox7IE._extract_url(webpage)
2304 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2306 # Look for DBTV embeds
2307 dbtv_urls = DBTVIE._extract_urls(webpage)
2309 return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
2311 # Looking for http://schema.org/VideoObject
2312 json_ld = self._search_json_ld(
2313 webpage, video_id, default={}, expected_type='VideoObject')
2314 if json_ld.get('url'):
2316 'title': video_title or info_dict['title'],
2317 'description': video_description,
2318 'thumbnail': video_thumbnail,
2319 'age_limit': age_limit
2321 info_dict.update(json_ld)
2324 # Look for HTML5 media
2325 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2327 for entry in entries:
2330 'title': video_title,
2332 self._sort_formats(entry['formats'])
2333 return self.playlist_result(entries)
2335 def check_video(vurl):
2336 if YoutubeIE.suitable(vurl):
2338 vpath = compat_urlparse.urlparse(vurl).path
2339 vext = determine_ext(vpath)
2340 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
2342 def filter_video(urls):
2343 return list(filter(check_video, urls))
2345 # Start with something easy: JW Player in SWFObject
2346 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2348 # Look for gorilla-vid style embedding
2349 found = filter_video(re.findall(r'''(?sx)
2353 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2356 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2358 # Broaden the search a little bit
2359 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2361 # Broaden the findall a little bit: JWPlayer JS loader
2362 found = filter_video(re.findall(
2363 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2366 found = filter_video(re.findall(r'''(?xs)
2367 flowplayer\("[^"]+",\s*
2369 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2370 ["']?url["']?\s*:\s*["']([^"']+)["']
2375 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2377 # Try to find twitter cards info
2378 # twitter:player:stream should be checked before twitter:player since
2379 # it is expected to contain a raw stream (see
2380 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2381 found = filter_video(re.findall(
2382 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2384 # We look for Open Graph info:
2385 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2386 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2387 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2388 if m_video_type is not None:
2389 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2391 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2393 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2394 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2397 # Look also in Refresh HTTP header
2398 refresh_header = head_response.headers.get('Refresh')
2400 # In python 2 response HTTP headers are bytestrings
2401 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2402 refresh_header = refresh_header.decode('iso-8859-1')
2403 found = re.search(REDIRECT_REGEX, refresh_header)
2405 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2406 self.report_following_redirect(new_url)
2413 # twitter:player is a https URL to iframe player that may or may not
2414 # be supported by youtube-dl thus this is checked the very last (see
2415 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2416 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2418 return self.url_result(embed_url)
2421 raise UnsupportedError(url)
2424 for video_url in orderedSet(found):
2425 video_url = unescapeHTML(video_url)
2426 video_url = video_url.replace('\\/', '/')
2427 video_url = compat_urlparse.urljoin(url, video_url)
2428 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2430 # Sometimes, jwplayer extraction will result in a YouTube URL
2431 if YoutubeIE.suitable(video_url):
2432 entries.append(self.url_result(video_url, 'Youtube'))
2435 # here's a fun little line of code for you:
2436 video_id = os.path.splitext(video_id)[0]
2440 'uploader': video_uploader,
2441 'title': video_title,
2442 'age_limit': age_limit,
2445 ext = determine_ext(video_url)
2447 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2449 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2451 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2453 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2455 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2456 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2457 # Just matching .ism/manifest is not enough to be reliably sure
2458 # whether it's actually an ISM manifest or some other streaming
2459 # manifest since there are various streaming URL formats
2460 # possible (see [1]) as well as some other shenanigans like
2461 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2463 # Thus the most reasonable way to solve this is to delegate
2464 # to generic extractor in order to look into the contents of
2465 # the manifest itself.
2466 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2467 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2468 entry_info_dict = self.url_result(
2469 smuggle_url(video_url, {'to_generic': True}),
2472 entry_info_dict['url'] = video_url
2474 if entry_info_dict.get('formats'):
2475 self._sort_formats(entry_info_dict['formats'])
2477 entries.append(entry_info_dict)
2479 if len(entries) == 1:
2482 for num, e in enumerate(entries, start=1):
2483 # 'url' results don't have a title
2484 if e.get('title') is not None:
2485 e['title'] = '%s (%d)' % (e['title'], num)
2487 '_type': 'playlist',