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 .commonprotocols import RtmpIE
34 from .brightcove import (
38 from .nbc import NBCSportsVPlayerIE
39 from .ooyala import OoyalaIE
40 from .rutv import RUTVIE
41 from .tvc import TVCIE
42 from .sportbox import SportBoxEmbedIE
43 from .smotri import SmotriIE
44 from .myvi import MyviIE
45 from .condenast import CondeNastIE
46 from .udn import UDNEmbedIE
47 from .senateisvp import SenateISVPIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .tnaflix import TNAFlixNetworkEmbedIE
52 from .drtuber import DrTuberIE
53 from .redtube import RedTubeIE
54 from .vimeo import VimeoIE
55 from .dailymotion import (
59 from .onionstudios import OnionStudiosIE
60 from .viewlift import ViewLiftEmbedIE
61 from .mtv import MTVServicesEmbeddedIE
62 from .pladform import PladformIE
63 from .videomore import VideomoreIE
64 from .webcaster import WebcasterFeedIE
65 from .googledrive import GoogleDriveIE
66 from .jwplatform import JWPlatformIE
67 from .digiteka import DigitekaIE
68 from .arkena import ArkenaIE
69 from .instagram import InstagramIE
70 from .liveleak import LiveLeakIE
71 from .threeqsdn import ThreeQSDNIE
72 from .theplatform import ThePlatformIE
73 from .vessel import VesselIE
74 from .kaltura import KalturaIE
75 from .eagleplatform import EaglePlatformIE
76 from .facebook import FacebookIE
77 from .soundcloud import SoundcloudIE
78 from .tunein import TuneInBaseIE
79 from .vbox7 import Vbox7IE
80 from .dbtv import DBTVIE
81 from .piksel import PikselIE
82 from .videa import VideaIE
83 from .twentymin import TwentyMinutenIE
84 from .ustream import UstreamIE
85 from .openload import OpenloadIE
86 from .videopress import VideoPressIE
87 from .rutube import RutubeIE
90 class GenericIE(InfoExtractor):
91 IE_DESC = 'Generic downloader that works on some sites'
95 # Direct link to a video
97 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
98 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
103 'upload_date': '20100513',
106 # Direct link to media delivered compressed (until Accept-Encoding is *)
108 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
109 'md5': '128c42e68b13950268b648275386fc74',
111 'id': 'FictionJunction-Parallel_Hearts',
113 'title': 'FictionJunction-Parallel_Hearts',
114 'upload_date': '20140522',
116 'expected_warnings': [
117 'URL could be a direct video link, returning it as such.'
119 'skip': 'URL invalid',
121 # Direct download with broken HEAD
123 'url': 'http://ai-radio.org:8000/radio.opus',
130 'skip_download': True, # infinite live stream
132 'expected_warnings': [
133 r'501.*Not Implemented',
137 # Direct link with incorrect MIME type
139 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
140 'md5': '4ccbebe5f36706d85221f204d7eb5913',
142 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
143 'id': '5_Lennart_Poettering_-_Systemd',
145 'title': '5_Lennart_Poettering_-_Systemd',
146 'upload_date': '20141120',
148 'expected_warnings': [
149 'URL could be a direct video link, returning it as such.'
154 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
156 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
157 'title': 'Zero Punctuation',
158 'description': 're:.*groundbreaking video review series.*'
160 'playlist_mincount': 11,
162 # RSS feed with enclosure
164 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
166 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
168 'upload_date': '20150228',
169 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
172 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
174 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
178 'title': 'Automatics, robotics and biocybernetics',
179 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
180 'upload_date': '20130627',
181 'formats': 'mincount:16',
182 'subtitles': 'mincount:1',
185 'force_generic_extractor': True,
186 'skip_download': True,
189 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
191 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
196 'formats': 'mincount:1',
199 'skip_download': True,
202 # SMIL from https://www.restudy.dk/video/play/id/1637
204 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
208 'title': 'video_1637',
209 'formats': 'mincount:3',
212 'skip_download': True,
215 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
217 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
219 'id': 'smil-service',
221 'title': 'smil-service',
222 'formats': 'mincount:1',
225 'skip_download': True,
228 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
230 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
234 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
235 'formats': 'mincount:3',
238 'skip_download': True,
241 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
243 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
245 'id': 'mZlp2ctYIUEB',
247 'title': 'Tikibad ontruimd wegens brand',
248 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
249 'thumbnail': r're:^https?://.*\.jpg$',
253 'skip_download': True,
256 # MPD from http://dash-mse-test.appspot.com/media.html
258 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
259 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
261 'id': 'car-20120827-manifest',
263 'title': 'car-20120827-manifest',
264 'formats': 'mincount:9',
265 'upload_date': '20130904',
268 'format': 'bestvideo',
271 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
273 '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',
278 'formats': 'mincount:8',
282 'skip_download': True,
284 'skip': 'video gone',
286 # m3u8 served with Content-Type: text/plain
288 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
293 'upload_date': '20140720',
294 'formats': 'mincount:11',
298 'skip_download': True,
300 'skip': 'video gone',
304 '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',
308 'upload_date': '20130224',
309 'uploader_id': 'TheVerge',
310 'description': r're:^Chris Ziegler takes a look at the\.*',
311 'uploader': 'The Verge',
312 'title': 'First Firefox OS phones side-by-side',
315 'skip_download': False,
319 # redirect in Refresh HTTP header
320 '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',
324 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
325 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
326 'upload_date': '20150917',
327 'uploader_id': 'brtvofficial',
328 'uploader': 'Boiler Room',
331 'skip_download': False,
335 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
336 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
338 'id': '13601338388002',
340 'uploader': 'www.hodiho.fr',
341 'title': 'R\u00e9gis plante sa Jeep',
344 # bandcamp page with custom domain
346 'add_ie': ['Bandcamp'],
347 'url': 'http://bronyrock.com/track/the-pony-mash',
351 'title': 'The Pony Mash',
352 'uploader': 'M_Pallante',
354 'skip': 'There is a limit of 200 free downloads / month for the test song',
357 # embedded brightcove video
358 # it also tests brightcove videos that need to set the 'Referer'
359 # in the http requests
360 'add_ie': ['BrightcoveLegacy'],
361 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
363 'id': '2765128793001',
365 'title': 'Le cours de bourse : l’analyse technique',
366 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
367 'uploader': 'BFM BUSINESS',
370 'skip_download': True,
374 # embedded with itemprop embedURL and video id spelled as `idVideo`
375 'add_id': ['BrightcoveLegacy'],
376 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
378 'id': '5255628253001',
380 'title': 'md5:37c519b1128915607601e75a87995fc0',
381 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
382 'uploader': 'BFM BUSINESS',
383 'uploader_id': '876450612001',
384 'timestamp': 1482255315,
385 'upload_date': '20161220',
388 'skip_download': True,
392 # https://github.com/rg3/youtube-dl/issues/2253
393 'url': 'http://bcove.me/i6nfkrc3',
394 'md5': '0ba9446db037002366bab3b3eb30c88c',
396 'id': '3101154703001',
398 'title': 'Still no power',
399 'uploader': 'thestar.com',
400 '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.',
402 'add_ie': ['BrightcoveLegacy'],
403 'skip': 'video gone',
406 'url': 'http://www.championat.com/video/football/v/87/87499.html',
407 'md5': 'fb973ecf6e4a78a67453647444222983',
409 'id': '3414141473001',
411 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
412 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
413 'uploader': 'Championat',
417 # https://github.com/rg3/youtube-dl/issues/3541
418 'add_ie': ['BrightcoveLegacy'],
419 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
421 'id': '3866516442001',
423 'title': 'Leer mij vrouwen kennen: Aflevering 1',
424 'description': 'Leer mij vrouwen kennen: Aflevering 1',
425 'uploader': 'SBS Broadcasting',
427 'skip': 'Restricted to Netherlands',
429 'skip_download': True, # m3u8 download
433 # Brightcove with alternative playerID key
434 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
436 'id': 'nmeth.2062_SV1',
437 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
441 'id': '2228375078001',
443 'title': 'nmeth.2062-sv1',
444 'description': 'nmeth.2062-sv1',
445 'timestamp': 1363357591,
446 'upload_date': '20130315',
447 'uploader': 'Nature Publishing Group',
448 'uploader_id': '1964492299001',
453 # Brightcove with UUID in videoPlayer
454 'url': 'http://www8.hp.com/cn/zh/home.html',
456 'id': '5255815316001',
458 'title': 'Sprocket Video - China',
459 'description': 'Sprocket Video - China',
460 'uploader': 'HP-Video Gallery',
461 'timestamp': 1482263210,
462 'upload_date': '20161220',
463 'uploader_id': '1107601872001',
466 'skip_download': True, # m3u8 download
471 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
472 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
474 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
476 'title': '2cc213299525360.mov', # that's what we get
479 'add_ie': ['Ooyala'],
482 # ooyala video embedded with http://player.ooyala.com/iframe.js
483 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
485 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
487 'title': '"Steve Jobs: Man in the Machine" trailer',
488 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
492 'skip_download': True,
494 'skip': 'movie expired',
498 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
502 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
503 'upload_date': '20140225',
504 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
505 'uploader': 'Tested',
506 'uploader_id': 'testedcom',
508 # No need to test YoutubeIE here
510 'skip_download': True,
515 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
519 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
520 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
522 # HEAD requests lead to endless 301, while GET is OK
523 'expected_warnings': ['301'],
527 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
531 'title': 'Охотское море стало целиком российским',
532 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
536 'skip_download': True,
541 '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/',
545 'title': 'Дошкольное воспитание',
550 'url': 'http://www.vestifinance.ru/articles/25753',
553 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
558 'title': 'Госзаказ. День 3',
564 'title': 'Госзаказ. День 2',
570 'title': 'Госзаказ. День 1',
576 'skip_download': True,
581 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
583 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
585 'title': 'Ужастики, русский трейлер (2015)',
586 'thumbnail': r're:^https?://.*\.jpg$',
592 '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',
595 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
597 'playlist_mincount': 7,
598 # This forum does not allow <iframe> syntaxes anymore
599 # Now HTML tags are displayed as-is
600 'skip': 'No videos on this page',
604 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
605 'md5': '65fdff94098e4a607385a60c5177c638',
609 'title': 'Hidden miracles of the natural world',
610 'uploader': 'Louie Schwartzberg',
611 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
614 # nowvideo embed hidden behind percent encoding
616 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
617 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
619 'id': '06e53103ca9aa',
621 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
622 'description': 'No description',
627 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
628 'md5': '7653032cbb25bf6c80d80f217055fa43',
630 'id': '048195-004_PLUS7-F',
633 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
634 'upload_date': '20140320',
637 'skip_download': 'Requires rtmpdump'
639 'skip': 'video gone',
643 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
647 'title': 'Alcaline, le concert avec Calogero',
648 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
649 'upload_date': '20150226',
650 'timestamp': 1424989860,
655 'skip_download': True,
657 'expected_warnings': [
663 'url': 'http://www.wired.com/2014/04/honda-asimo/',
664 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
666 'id': '53501be369702d3275860000',
668 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
673 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
674 'md5': '441aeeb82eb72c422c7f14ec533999cd',
676 'id': 'k2mm4bCdJ6CQ2i7c8o2',
678 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
679 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
681 'uploader_id': 'xgditw',
682 'upload_date': '20140425',
683 'timestamp': 1398441542,
685 'add_ie': ['Dailymotion'],
689 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
693 'title': 'The NBL Auction 2014',
694 'uploader': 'BADMINTON England',
695 'uploader_id': 'BADMINTONEvents',
696 'upload_date': '20140603',
697 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
699 'add_ie': ['Youtube'],
701 'skip_download': True,
706 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
707 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
709 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
711 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
712 'description': 'Two valets share their love for movie star Liam Neesons.',
713 'timestamp': 1349922600,
714 'upload_date': '20121011',
717 # YouTube embed via <data-embed-url="">
719 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
723 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
724 'uploader': 'Gameloft',
725 'uploader_id': 'gameloft',
726 'upload_date': '20140828',
727 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
730 'skip_download': True,
733 # YouTube <object> embed
735 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
736 'md5': '516718101ec834f74318df76259fb3cc',
740 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
741 'upload_date': '20080526',
742 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
743 'uploader': 'Christopher Sykes',
744 'uploader_id': 'ChristopherJSykes',
746 'add_ie': ['Youtube'],
750 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
752 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
754 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
755 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
760 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
762 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
763 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
769 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
774 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
775 'md5': '9d65602bf31c6e20014319c7d07fba27',
777 'id': '5123ea6d5e5a7',
780 'uploader': 'www.handjobhub.com',
781 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
784 # Multiple brightcove videos
785 # https://github.com/rg3/youtube-dl/issues/2283
787 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
789 'id': 'always-never',
790 'title': 'Always / Never - The New Yorker',
794 'extract_flat': False,
795 'skip_download': True,
800 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
801 'md5': '96f09a37e44da40dd083e12d9a683327',
805 'title': 'Ump changes call to ball',
806 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
808 'timestamp': 1401537900,
809 'upload_date': '20140531',
810 'thumbnail': r're:^https?://.*\.jpg$',
815 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
816 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
820 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
821 'description': 'a Paywall Videos video from Remilon',
823 'uploader': 'study.com',
824 'timestamp': 1459678540,
825 'upload_date': '20160403',
826 'filesize': 24687186,
830 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
831 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
835 'title': 'Conversation about Hexagonal Rails Part 1',
836 'description': 'a Martin Fowler video from ThoughtWorks',
838 'uploader': 'thoughtworks.wistia.com',
839 'timestamp': 1401832161,
840 'upload_date': '20140603',
843 # Wistia standard embed (async)
845 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
849 'title': 'Drip Brennan Dunn Workshop',
850 'description': 'a JV Webinars video from getdrip-1',
852 'timestamp': 1463607249,
853 'upload_date': '20160518',
856 'skip_download': True,
861 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
865 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
866 'uploader': 'Sophos Security',
867 'title': 'Chet Chat 171 - Oct 29, 2014',
868 'upload_date': '20141029',
871 # Soundcloud multiple embeds
873 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
876 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
878 'playlist_mincount': 7,
880 # TuneIn station embed
882 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
887 'location': 'Paris, France',
892 'skip_download': True,
897 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
901 'upload_date': '20141112',
902 'title': 'Rosetta #CometLanding webcast HL 10',
905 # Another Livestream embed, without 'new.' in URL
907 'url': 'https://www.freespeech.org/',
911 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
915 'skip_download': True,
920 'url': 'https://skiplagged.com/',
923 'title': 'Skiplagged: The smart way to find cheap flights',
925 'playlist_mincount': 1,
926 'add_ie': ['Youtube'],
930 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
934 'upload_date': '20141126',
935 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
940 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
942 'id': '730m_DandD_1901_512k',
944 'uploader': 'www.abc.net.au',
945 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
948 # embedded viddler video
950 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
954 'uploader': 'deadspin',
955 'title': 'WALL-TO-GORTAT',
956 'timestamp': 1422285291,
957 'upload_date': '20150126',
959 'add_ie': ['Viddler'],
963 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
967 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
968 'description': 'md5:601cb790edd05908957dae8aaa866465',
969 'upload_date': '20150220',
971 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
975 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
979 'upload_date': '20150212',
980 'uploader': 'The National Archives UK',
981 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
982 'uploader_id': 'NationalArchives08',
983 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
988 'url': 'http://www.suffolk.edu/sjc/',
992 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
993 'uploader': 'www.suffolk.edu',
996 'skip_download': True,
1001 'url': 'http://www.indiedb.com/games/king-machine/videos',
1005 'title': 'king machine trailer 1',
1006 'thumbnail': r're:^https?://.*\.jpg$',
1010 # JWPlayer config passed as variable
1011 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1015 'title': 'ARIELE | Tube Cup',
1016 'uploader': 'www.txxx.com',
1020 'skip_download': True,
1025 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1026 'playlist_mincount': 5,
1028 'id': 'aanslagen-kopenhagen',
1029 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1034 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1038 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1041 # Kaltura embed (different embed code)
1043 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1047 'upload_date': '20150127',
1048 'uploader_id': 'PremierMedia',
1050 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1053 # Kaltura embed with single quotes
1055 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1060 'timestamp': 1355743100,
1061 'upload_date': '20121217',
1062 'uploader_id': 'batchUser',
1064 'add_ie': ['Kaltura'],
1067 # Kaltura embedded via quoted entry_id
1068 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1072 'title': '06_matthew_brender_raj_dutt',
1073 'timestamp': 1466638791,
1074 'upload_date': '20160622',
1076 'add_ie': ['Kaltura'],
1077 'expected_warnings': [
1078 'Could not send HEAD request'
1081 'skip_download': True,
1085 # Kaltura embedded, some fileExt broken (#11480)
1086 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1090 'title': 'Our "Standard Models" of particle physics and cosmology',
1091 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1092 'timestamp': 1321158993,
1093 'upload_date': '20111113',
1094 'uploader_id': 'kps1',
1096 'add_ie': ['Kaltura'],
1099 # Kaltura iframe embed
1100 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1101 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1105 'title': 'I. M. Pei: A Centennial Celebration',
1106 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1107 'upload_date': '20170403',
1108 'uploader_id': 'batchUser',
1109 'timestamp': 1491232186,
1111 'add_ie': ['Kaltura'],
1113 # Eagle.Platform embed (generic URL)
1115 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1116 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1120 'title': 'Навальный вышел на свободу',
1121 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1122 'thumbnail': r're:^https?://.*\.jpg$',
1128 # ClipYou (Eagle.Platform) embed (custom URL)
1130 'url': 'http://muz-tv.ru/play/7129/',
1131 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1135 'title': "'O Sole Mio",
1136 'thumbnail': r're:^https?://.*\.jpg$',
1143 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1147 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1148 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1149 'thumbnail': r're:^https?://.*\.jpg$',
1156 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1160 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1161 'thumbnail': r're:^https?://.*\.png$',
1167 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1168 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1172 'title': 'Facebook Creates "On This Day" | Crunch Report',
1177 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1181 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1186 # Crooks and Liars embed
1188 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1192 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1193 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1194 'timestamp': 1428207000,
1195 'upload_date': '20150405',
1196 'uploader': 'Heather',
1199 # Crooks and Liars external embed
1201 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1203 'id': 'MTE3MjUtMzQ2MzA',
1205 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1206 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1207 'timestamp': 1265032391,
1208 'upload_date': '20100201',
1209 'uploader': 'Heather',
1212 # NBC Sports vplayer embed
1214 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1216 'id': 'ln7x1qSThw4k',
1218 'title': "PFT Live: New leader in the 'new-look' defense",
1219 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1220 'uploader': 'NBCU-SPORTS',
1221 'upload_date': '20140107',
1222 'timestamp': 1389118457,
1227 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1228 'md5': '1aa589c675898ae6d37a17913cf68d66',
1230 'id': '701714499682',
1232 'title': 'PREVIEW: On Assignment: David Letterman',
1233 '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.',
1238 'url': 'https://video.udn.com/news/300346',
1239 'md5': 'fd2060e988c326991037b9aff9df21a6',
1243 'title': '中一中男師變性 全校師生力挺',
1244 'thumbnail': r're:^https?://.*\.jpg$',
1248 'skip_download': True,
1253 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1255 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1257 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1258 'title': 'This is what separates the Excel masters from the wannabes',
1259 'duration': 191.933,
1263 'skip_download': True,
1266 # Brightcove URL in single quotes
1268 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1269 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1271 'id': '4255764656001',
1273 'title': 'SN Presents: Russell Martin, World Citizen',
1274 '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.',
1275 'uploader': 'Rogers Sportsnet',
1276 'uploader_id': '1704050871',
1277 'upload_date': '20150525',
1278 'timestamp': 1432570283,
1281 # Dailymotion Cloud video
1283 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1284 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1288 'title': 'Sauvons les abeilles ! - Le débat',
1289 'description': 'md5:d9082128b1c5277987825d684939ca26',
1290 'thumbnail': r're:^https?://.*\.jpe?g$',
1291 'timestamp': 1434970506,
1292 'upload_date': '20150622',
1293 'uploader': 'Public Sénat',
1294 'uploader_id': 'xa9gza',
1297 # OnionStudios embed
1299 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1303 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1304 'thumbnail': r're:^https?://.*\.jpe?g$',
1305 'uploader': 'ClickHole',
1306 'uploader_id': 'clickhole',
1311 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1313 'id': '74849a00-85a9-11e1-9660-123139220831',
1315 'title': '#whilewewatch',
1318 # AdobeTVVideo embed
1320 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1321 'md5': '43662b577c018ad707a63766462b1e87',
1325 'title': 'New experience with Acrobat DC',
1326 'description': 'New experience with Acrobat DC',
1327 'duration': 248.667,
1330 # BrightcoveInPageEmbed embed
1332 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1334 'id': '4238694884001',
1336 'title': 'Tabletop: Dread, Last Thoughts',
1337 'description': 'Tabletop: Dread, Last Thoughts',
1341 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1342 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1344 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1346 'id': '4785848093001',
1348 'title': 'The Cardinal Pell Interview',
1349 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1350 'uploader': 'GlobeCast Australia - GlobeStream',
1351 'uploader_id': '2733773828001',
1352 'upload_date': '20160304',
1353 'timestamp': 1457083087,
1357 'skip_download': True,
1360 # Another form of arte.tv embed
1362 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1363 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1365 'id': '030273-562_PLUS7-F',
1367 'title': 'ARTE Reportage - Nulle part, en France',
1368 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1369 'upload_date': '20160409',
1374 'url': 'http://www.wykop.pl/link/3088787/',
1375 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1377 'id': '874_1459135191',
1379 'title': 'Man shows poor quality of new apartment building',
1380 'description': 'The wall is like a sand pile.',
1381 'uploader': 'Lake8737',
1384 # Duplicated embedded video URLs
1386 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1388 'id': '149298443_480_16c25b74_2',
1390 'title': 'vs. Blue Orange Spring Game',
1391 'uploader': 'www.hudl.com',
1394 # twitter:player:stream embed
1396 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1400 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1401 'uploader': 'www.rtl.be',
1405 'skip_download': True,
1408 # twitter:player embed
1410 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1411 'md5': 'a3e0df96369831de324f0778e126653c',
1413 'id': '4909620399001',
1415 'title': 'What Do Black Holes Sound Like?',
1416 'description': 'what do black holes sound like',
1417 'upload_date': '20160524',
1418 'uploader_id': '29913724001',
1419 'timestamp': 1464107587,
1420 'uploader': 'TheAtlantic',
1422 'add_ie': ['BrightcoveLegacy'],
1424 # Facebook <iframe> embed
1426 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1427 'md5': 'fbcde74f534176ecb015849146dd3aee',
1429 'id': '599637780109885',
1431 'title': 'Facebook video #599637780109885',
1434 # Facebook API embed
1436 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1437 'md5': 'a47372ee61b39a7b90287094d447d94e',
1439 'id': '10153467542406923',
1441 'title': 'Facebook video #10153467542406923',
1444 # Wordpress "YouTube Video Importer" plugin
1446 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1447 'md5': 'd16797741b560b485194eddda8121b48',
1449 'id': 'HNTXWDXV9Is',
1451 'title': 'Blue Devils Drumline Stanford lot 2016',
1452 'upload_date': '20160627',
1453 'uploader_id': 'GENOCIDE8GENERAL10',
1454 'uploader': 'cylus cyrus',
1458 # video stored on custom kaltura server
1459 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1460 'md5': '537617d06e64dfed891fa1593c4b30cc',
1464 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1465 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1466 'uploader_id': 'videos.expansion@el-mundo.net',
1467 'upload_date': '20150429',
1468 'timestamp': 1430303472,
1470 'add_ie': ['Kaltura'],
1473 # Non-standard Vimeo embed
1474 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1475 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1479 'title': 'Understanding the web - Teaser',
1480 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1481 'upload_date': '20151214',
1482 'uploader': 'OpenClassrooms',
1483 'uploader_id': 'openclassrooms',
1485 'add_ie': ['Vimeo'],
1488 # generic vimeo embed that requires original URL passed as Referer
1489 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1490 'only_matching': True,
1493 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1494 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1496 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1498 'title': 'Big Buck Bunny',
1499 'description': 'Royalty free test video',
1500 'timestamp': 1432816365,
1501 'upload_date': '20150528',
1505 'skip_download': True,
1507 'add_ie': [ArkenaIE.ie_key()],
1510 '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/',
1514 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1517 'skip_download': True,
1519 'add_ie': [Vbox7IE.ie_key()],
1523 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1526 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1528 'playlist_mincount': 3,
1532 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1534 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1535 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1537 'playlist_mincount': 2,
1541 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1545 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1546 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1549 'skip_download': True,
1551 'add_ie': [TwentyMinutenIE.ie_key()],
1555 'url': 'https://en.support.wordpress.com/videopress/',
1559 'title': 'IMG_5786',
1560 'timestamp': 1435711927,
1561 'upload_date': '20150701',
1564 'skip_download': True,
1566 'add_ie': [VideoPressIE.ie_key()],
1570 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1572 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1574 'title': 'Магаззино: Казань 2',
1575 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1576 'uploader': 'Магаззино',
1577 'upload_date': '20170228',
1578 'uploader_id': '996642',
1581 'skip_download': True,
1583 'add_ie': [RutubeIE.ie_key()],
1586 # ThePlatform embedded with whitespaces in URLs
1587 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1588 'only_matching': True,
1591 # Senate ISVP iframe https
1592 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1593 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1595 'id': 'govtaff020316',
1597 'title': 'Integrated Senate Video Player',
1599 'add_ie': [SenateISVPIE.ie_key()],
1602 # # TODO: find another test
1603 # # http://schema.org/VideoObject
1604 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1605 # 'md5': '888dcf08b7ea671381f00fab74692755',
1607 # 'id': 'nyvTSJMKId',
1609 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1610 # 'description': '#love for cats.',
1611 # 'timestamp': 1461244995,
1612 # 'upload_date': '20160421',
1615 # 'force_generic_extractor': True,
1620 def report_following_redirect(self, new_url):
1621 """Report information extraction."""
1622 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1624 def _extract_rss(self, url, video_id, doc):
1625 playlist_title = doc.find('./channel/title').text
1626 playlist_desc_el = doc.find('./channel/description')
1627 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1630 for it in doc.findall('./channel/item'):
1631 next_url = xpath_text(it, 'link', fatal=False)
1633 enclosure_nodes = it.findall('./enclosure')
1634 for e in enclosure_nodes:
1635 next_url = e.attrib.get('url')
1645 'title': it.find('title').text,
1649 '_type': 'playlist',
1651 'title': playlist_title,
1652 'description': playlist_desc,
1656 def _extract_camtasia(self, url, video_id, webpage):
1657 """ Returns None if no camtasia video can be found. """
1659 camtasia_cfg = self._search_regex(
1660 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1661 webpage, 'camtasia configuration file', default=None)
1662 if camtasia_cfg is None:
1665 title = self._html_search_meta('DC.title', webpage, fatal=True)
1667 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1668 camtasia_cfg = self._download_xml(
1669 camtasia_url, video_id,
1670 note='Downloading camtasia configuration',
1671 errnote='Failed to download camtasia configuration')
1672 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1675 for n in fileset_node.getchildren():
1676 url_n = n.find('./uri')
1681 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1682 'title': '%s - %s' % (title, n.tag),
1683 'url': compat_urlparse.urljoin(url, url_n.text),
1684 'duration': float_or_none(n.find('./duration').text),
1688 '_type': 'playlist',
1693 def _real_extract(self, url):
1694 if url.startswith('//'):
1697 'url': self.http_scheme() + url,
1700 parsed_url = compat_urlparse.urlparse(url)
1701 if not parsed_url.scheme:
1702 default_search = self._downloader.params.get('default_search')
1703 if default_search is None:
1704 default_search = 'fixup_error'
1706 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1708 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1709 return self.url_result('http://' + url)
1710 elif default_search != 'fixup_error':
1711 if default_search == 'auto_warning':
1712 if re.match(r'^(?:url|URL)$', url):
1713 raise ExtractorError(
1714 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1717 self._downloader.report_warning(
1718 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1719 return self.url_result('ytsearch:' + url)
1721 if default_search in ('error', 'fixup_error'):
1722 raise ExtractorError(
1723 '%r is not a valid URL. '
1724 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1725 % (url, url), expected=True)
1727 if ':' not in default_search:
1728 default_search += ':'
1729 return self.url_result(default_search + url)
1731 url, smuggled_data = unsmuggle_url(url)
1732 force_videoid = None
1733 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1734 if smuggled_data and 'force_videoid' in smuggled_data:
1735 force_videoid = smuggled_data['force_videoid']
1736 video_id = force_videoid
1738 video_id = self._generic_id(url)
1740 self.to_screen('%s: Requesting header' % video_id)
1742 head_req = HEADRequest(url)
1743 head_response = self._request_webpage(
1745 note=False, errnote='Could not send HEAD request to %s' % url,
1748 if head_response is not False:
1749 # Check for redirect
1750 new_url = head_response.geturl()
1752 self.report_following_redirect(new_url)
1754 new_url = smuggle_url(
1755 new_url, {'force_videoid': force_videoid})
1756 return self.url_result(new_url)
1758 full_response = None
1759 if head_response is False:
1760 request = sanitized_Request(url)
1761 request.add_header('Accept-Encoding', '*')
1762 full_response = self._request_webpage(request, video_id)
1763 head_response = full_response
1767 'title': self._generic_title(url),
1768 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1771 # Check for direct link to a video
1772 content_type = head_response.headers.get('Content-Type', '').lower()
1773 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1775 format_id = m.group('format_id')
1776 if format_id.endswith('mpegurl'):
1777 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1778 elif format_id == 'f4m':
1779 formats = self._extract_f4m_formats(url, video_id)
1782 'format_id': m.group('format_id'),
1784 'vcodec': 'none' if m.group('type') == 'audio' else None
1786 info_dict['direct'] = True
1787 self._sort_formats(formats)
1788 info_dict['formats'] = formats
1791 if not self._downloader.params.get('test', False) and not is_intentional:
1792 force = self._downloader.params.get('force_generic_extractor', False)
1793 self._downloader.report_warning(
1794 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1796 if not full_response:
1797 request = sanitized_Request(url)
1798 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1799 # making it impossible to download only chunk of the file (yet we need only 512kB to
1800 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1801 # that will always result in downloading the whole file that is not desirable.
1802 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1803 # to accept raw bytes and being able to download only a chunk.
1804 # It may probably better to solve this by checking Content-Type for application/octet-stream
1805 # after HEAD request finishes, but not sure if we can rely on this.
1806 request.add_header('Accept-Encoding', '*')
1807 full_response = self._request_webpage(request, video_id)
1809 first_bytes = full_response.read(512)
1811 # Is it an M3U playlist?
1812 if first_bytes.startswith(b'#EXTM3U'):
1813 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1814 self._sort_formats(info_dict['formats'])
1817 # Maybe it's a direct link to a video?
1818 # Be careful not to download the whole thing!
1819 if not is_html(first_bytes):
1820 self._downloader.report_warning(
1821 'URL could be a direct video link, returning it as such.')
1828 webpage = self._webpage_read_content(
1829 full_response, url, video_id, prefix=first_bytes)
1831 self.report_extraction(video_id)
1833 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1835 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1836 if doc.tag == 'rss':
1837 return self._extract_rss(url, video_id, doc)
1838 elif doc.tag == 'SmoothStreamingMedia':
1839 info_dict['formats'] = self._parse_ism_formats(doc, url)
1840 self._sort_formats(info_dict['formats'])
1842 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1843 smil = self._parse_smil(doc, url, video_id)
1844 self._sort_formats(smil['formats'])
1846 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1847 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1848 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1849 info_dict['formats'] = self._parse_mpd_formats(
1851 mpd_base_url=full_response.geturl().rpartition('/')[0],
1853 self._sort_formats(info_dict['formats'])
1855 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1856 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1857 self._sort_formats(info_dict['formats'])
1859 except compat_xml_parse_error:
1862 # Is it a Camtasia project?
1863 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1864 if camtasia_res is not None:
1867 # Sometimes embedded video player is hidden behind percent encoding
1868 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1869 # Unescaping the whole page allows to handle those cases in a generic way
1870 webpage = compat_urllib_parse_unquote(webpage)
1872 # it's tempting to parse this further, but you would
1873 # have to take into account all the variations like
1874 # Video Title - Site Name
1875 # Site Name | Video Title
1876 # Video Title - Tagline | Site Name
1877 # and so on and so forth; it's just not practical
1878 video_title = self._og_search_title(
1879 webpage, default=None) or self._html_search_regex(
1880 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1883 # Try to detect age limit automatically
1884 age_limit = self._rta_search(webpage)
1885 # And then there are the jokers who advertise that they use RTA,
1886 # but actually don't.
1887 AGE_LIMIT_MARKERS = [
1888 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1890 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1893 # video uploader is domain name
1894 video_uploader = self._search_regex(
1895 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1897 video_description = self._og_search_description(webpage, default=None)
1898 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1900 # Look for Brightcove Legacy Studio embeds
1901 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1903 self.to_screen('Brightcove video detected.')
1906 'url': smuggle_url(bc_url, {'Referer': url}),
1907 'ie_key': 'BrightcoveLegacy'
1908 } for bc_url in bc_urls]
1911 '_type': 'playlist',
1912 'title': video_title,
1917 # Look for Brightcove New Studio embeds
1918 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1920 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
1922 # Look for ThePlatform embeds
1923 tp_urls = ThePlatformIE._extract_urls(webpage)
1925 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
1927 # Look for Vessel embeds
1928 vessel_urls = VesselIE._extract_urls(webpage)
1930 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
1932 # Look for embedded rtl.nl player
1933 matches = re.findall(
1934 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1937 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
1939 vimeo_urls = VimeoIE._extract_urls(url, webpage)
1941 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
1943 vid_me_embed_url = self._search_regex(
1944 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1945 webpage, 'vid.me embed', default=None)
1946 if vid_me_embed_url is not None:
1947 return self.url_result(vid_me_embed_url, 'Vidme')
1949 # Look for embedded YouTube player
1950 matches = re.findall(r'''(?x)
1960 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1964 return self.playlist_from_matches(
1965 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
1967 # Look for lazyYT YouTube embed
1968 matches = re.findall(
1969 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1971 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
1973 # Look for Wordpress "YouTube Video Importer" plugin
1974 matches = re.findall(r'''(?x)<div[^>]+
1975 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1976 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1978 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
1980 matches = DailymotionIE._extract_urls(webpage)
1982 return self.playlist_from_matches(matches, video_id, video_title)
1984 # Look for embedded Dailymotion playlist player (#3822)
1986 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1988 playlists = re.findall(
1989 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1991 return self.playlist_from_matches(
1992 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
1994 # Look for embedded Wistia player
1996 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1998 embed_url = self._proto_relative_url(
1999 unescapeHTML(match.group('url')))
2001 '_type': 'url_transparent',
2004 'uploader': video_uploader,
2007 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
2010 '_type': 'url_transparent',
2011 'url': 'wistia:%s' % match.group('id'),
2013 'uploader': video_uploader,
2018 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
2019 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
2022 return self.url_result(self._proto_relative_url(
2023 'wistia:%s' % match.group('id')), 'Wistia')
2025 # Look for SVT player
2026 svt_url = SVTIE._extract_url(webpage)
2028 return self.url_result(svt_url, 'SVT')
2030 # Look for embedded condenast player
2031 matches = re.findall(
2032 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
2036 '_type': 'playlist',
2039 'ie_key': 'CondeNast',
2041 } for ma in matches],
2042 'title': video_title,
2046 # Look for Bandcamp pages with custom domain
2047 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2048 if mobj is not None:
2049 burl = unescapeHTML(mobj.group(1))
2050 # Don't set the extractor because it can be a track url or an album
2051 return self.url_result(burl)
2053 # Look for embedded Vevo player
2055 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2056 if mobj is not None:
2057 return self.url_result(mobj.group('url'))
2059 # Look for embedded Viddler player
2061 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2063 if mobj is not None:
2064 return self.url_result(mobj.group('url'))
2066 # Look for NYTimes player
2068 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2070 if mobj is not None:
2071 return self.url_result(mobj.group('url'))
2073 # Look for Libsyn player
2075 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2076 if mobj is not None:
2077 return self.url_result(mobj.group('url'))
2079 # Look for Ooyala videos
2080 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2081 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2082 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2083 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2084 if mobj is not None:
2085 embed_token = self._search_regex(
2086 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2087 webpage, 'ooyala embed token', default=None)
2088 return OoyalaIE._build_url_result(smuggle_url(
2091 'embed_token': embed_token,
2094 # Look for multiple Ooyala embeds on SBN network websites
2095 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2096 if mobj is not None:
2097 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2099 return self.playlist_from_matches(
2100 embeds, video_id, video_title,
2101 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2103 # Look for Aparat videos
2104 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2105 if mobj is not None:
2106 return self.url_result(mobj.group(1), 'Aparat')
2108 # Look for MPORA videos
2109 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2110 if mobj is not None:
2111 return self.url_result(mobj.group(1), 'Mpora')
2113 # Look for embedded NovaMov-based player
2115 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2116 (?P<url>http://(?:(?:embed|www)\.)?
2118 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2119 videoweed\.(?:es|com)|
2120 movshare\.(?:net|sx|ag)|
2121 divxstage\.(?:eu|net|ch|co|at|ag))
2122 /embed\.php.+?)\1''', webpage)
2123 if mobj is not None:
2124 return self.url_result(mobj.group('url'))
2126 # Look for embedded Facebook player
2127 facebook_url = FacebookIE._extract_url(webpage)
2128 if facebook_url is not None:
2129 return self.url_result(facebook_url, 'Facebook')
2131 # Look for embedded VK player
2132 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2133 if mobj is not None:
2134 return self.url_result(mobj.group('url'), 'VK')
2136 # Look for embedded Odnoklassniki player
2137 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2138 if mobj is not None:
2139 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2141 # Look for embedded ivi player
2142 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2143 if mobj is not None:
2144 return self.url_result(mobj.group('url'), 'Ivi')
2146 # Look for embedded Huffington Post player
2148 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2149 if mobj is not None:
2150 return self.url_result(mobj.group('url'), 'HuffPost')
2153 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2154 if mobj is not None:
2155 return self.url_result(mobj.group('url'))
2156 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2157 if mobj is not None:
2158 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2160 # Look for funnyordie embed
2161 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2163 return self.playlist_from_matches(
2164 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2166 # Look for BBC iPlayer embed
2167 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2169 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2171 # Look for embedded RUTV player
2172 rutv_url = RUTVIE._extract_url(webpage)
2174 return self.url_result(rutv_url, 'RUTV')
2176 # Look for embedded TVC player
2177 tvc_url = TVCIE._extract_url(webpage)
2179 return self.url_result(tvc_url, 'TVC')
2181 # Look for embedded SportBox player
2182 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2184 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2186 # Look for embedded XHamster player
2187 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2189 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2191 # Look for embedded TNAFlixNetwork player
2192 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2194 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2196 # Look for embedded PornHub player
2197 pornhub_urls = PornHubIE._extract_urls(webpage)
2199 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2201 # Look for embedded DrTuber player
2202 drtuber_urls = DrTuberIE._extract_urls(webpage)
2204 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2206 # Look for embedded RedTube player
2207 redtube_urls = RedTubeIE._extract_urls(webpage)
2209 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2211 # Look for embedded Tvigle player
2213 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2214 if mobj is not None:
2215 return self.url_result(mobj.group('url'), 'Tvigle')
2217 # Look for embedded TED player
2219 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2220 if mobj is not None:
2221 return self.url_result(mobj.group('url'), 'TED')
2223 # Look for embedded Ustream videos
2224 ustream_url = UstreamIE._extract_url(webpage)
2226 return self.url_result(ustream_url, UstreamIE.ie_key())
2228 # Look for embedded arte.tv player
2230 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2232 if mobj is not None:
2233 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2235 # Look for embedded francetv player
2237 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2239 if mobj is not None:
2240 return self.url_result(mobj.group('url'))
2242 # Look for embedded smotri.com player
2243 smotri_url = SmotriIE._extract_url(webpage)
2245 return self.url_result(smotri_url, 'Smotri')
2247 # Look for embedded Myvi.ru player
2248 myvi_url = MyviIE._extract_url(webpage)
2250 return self.url_result(myvi_url)
2252 # Look for embedded soundcloud player
2253 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2255 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2257 # Look for tunein player
2258 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2260 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2262 # Look for embedded mtvservices player
2263 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2265 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2267 # Look for embedded yahoo player
2269 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2271 if mobj is not None:
2272 return self.url_result(mobj.group('url'), 'Yahoo')
2274 # Look for embedded sbs.com.au player
2278 <meta\s+property="og:video"\s+content=|
2281 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2283 if mobj is not None:
2284 return self.url_result(mobj.group('url'), 'SBS')
2286 # Look for embedded Cinchcast player
2288 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2290 if mobj is not None:
2291 return self.url_result(mobj.group('url'), 'Cinchcast')
2294 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2298 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2300 if mobj is not None:
2301 return self.url_result(mobj.group('url'), 'MLB')
2304 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2306 if mobj is not None:
2307 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2310 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2312 if mobj is not None:
2313 return self.url_result(mobj.group('url'), 'Livestream')
2315 # Look for Zapiks embed
2317 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2318 if mobj is not None:
2319 return self.url_result(mobj.group('url'), 'Zapiks')
2321 # Look for Kaltura embeds
2322 kaltura_url = KalturaIE._extract_url(webpage)
2324 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2326 # Look for Eagle.Platform embeds
2327 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2328 if eagleplatform_url:
2329 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2331 # Look for ClipYou (uses Eagle.Platform) embeds
2333 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2334 if mobj is not None:
2335 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2337 # Look for Pladform embeds
2338 pladform_url = PladformIE._extract_url(webpage)
2340 return self.url_result(pladform_url)
2342 # Look for Videomore embeds
2343 videomore_url = VideomoreIE._extract_url(webpage)
2345 return self.url_result(videomore_url)
2347 # Look for Webcaster embeds
2348 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2350 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2352 # Look for Playwire embeds
2354 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2355 if mobj is not None:
2356 return self.url_result(mobj.group('url'))
2358 # Look for 5min embeds
2360 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2361 if mobj is not None:
2362 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2364 # Look for Crooks and Liars embeds
2366 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2367 if mobj is not None:
2368 return self.url_result(mobj.group('url'))
2370 # Look for NBC Sports VPlayer embeds
2371 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2373 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2375 # Look for NBC News embeds
2376 nbc_news_embed_url = re.search(
2377 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2378 if nbc_news_embed_url:
2379 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2381 # Look for Google Drive embeds
2382 google_drive_url = GoogleDriveIE._extract_url(webpage)
2383 if google_drive_url:
2384 return self.url_result(google_drive_url, 'GoogleDrive')
2386 # Look for UDN embeds
2388 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2389 if mobj is not None:
2390 return self.url_result(
2391 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2393 # Look for Senate ISVP iframe
2394 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2396 return self.url_result(senate_isvp_url, 'SenateISVP')
2398 # Look for Dailymotion Cloud videos
2399 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2401 return self.url_result(dmcloud_url, 'DailymotionCloud')
2403 # Look for OnionStudios embeds
2404 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2405 if onionstudios_url:
2406 return self.url_result(onionstudios_url)
2408 # Look for ViewLift embeds
2409 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2411 return self.url_result(viewlift_url)
2413 # Look for JWPlatform embeds
2414 jwplatform_url = JWPlatformIE._extract_url(webpage)
2416 return self.url_result(jwplatform_url, 'JWPlatform')
2418 # Look for Digiteka embeds
2419 digiteka_url = DigitekaIE._extract_url(webpage)
2421 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2423 # Look for Arkena embeds
2424 arkena_url = ArkenaIE._extract_url(webpage)
2426 return self.url_result(arkena_url, ArkenaIE.ie_key())
2428 # Look for Piksel embeds
2429 piksel_url = PikselIE._extract_url(webpage)
2431 return self.url_result(piksel_url, PikselIE.ie_key())
2433 # Look for Limelight embeds
2434 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2438 'Channel': 'channel',
2439 'ChannelList': 'channel_list',
2441 return self.url_result(smuggle_url('limelight:%s:%s' % (
2442 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2443 'Limelight%s' % mobj.group(1), mobj.group(2))
2447 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2449 name=(["\'])flashVars\2[^>]+
2450 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2453 return self.url_result(smuggle_url(
2454 'limelight:media:%s' % mobj.group('id'),
2455 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2457 # Look for AdobeTVVideo embeds
2459 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2461 if mobj is not None:
2462 return self.url_result(
2463 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2466 # Look for Vine embeds
2468 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2470 if mobj is not None:
2471 return self.url_result(
2472 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2474 # Look for VODPlatform embeds
2476 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2478 if mobj is not None:
2479 return self.url_result(
2480 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2482 # Look for Mangomolo embeds
2484 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2486 video\?.*?\bid=(?P<video_id>\d+)|
2487 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2488 ).+?)\1''', webpage)
2489 if mobj is not None:
2491 '_type': 'url_transparent',
2492 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2493 'title': video_title,
2494 'description': video_description,
2495 'thumbnail': video_thumbnail,
2496 'uploader': video_uploader,
2498 video_id = mobj.group('video_id')
2501 'ie_key': 'MangomoloVideo',
2506 'ie_key': 'MangomoloLive',
2507 'id': mobj.group('channel_id'),
2511 # Look for Instagram embeds
2512 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2513 if instagram_embed_url is not None:
2514 return self.url_result(
2515 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2517 # Look for LiveLeak embeds
2518 liveleak_url = LiveLeakIE._extract_url(webpage)
2520 return self.url_result(liveleak_url, 'LiveLeak')
2522 # Look for 3Q SDN embeds
2523 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2526 '_type': 'url_transparent',
2527 'ie_key': ThreeQSDNIE.ie_key(),
2528 'url': self._proto_relative_url(threeqsdn_url),
2529 'title': video_title,
2530 'description': video_description,
2531 'thumbnail': video_thumbnail,
2532 'uploader': video_uploader,
2535 # Look for VBOX7 embeds
2536 vbox7_url = Vbox7IE._extract_url(webpage)
2538 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2540 # Look for DBTV embeds
2541 dbtv_urls = DBTVIE._extract_urls(webpage)
2543 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2545 # Look for Videa embeds
2546 videa_urls = VideaIE._extract_urls(webpage)
2548 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2550 # Look for 20 minuten embeds
2551 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2553 return self.playlist_from_matches(
2554 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2556 # Look for Openload embeds
2557 openload_urls = OpenloadIE._extract_urls(webpage)
2559 return self.playlist_from_matches(
2560 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2562 # Look for VideoPress embeds
2563 videopress_urls = VideoPressIE._extract_urls(webpage)
2565 return self.playlist_from_matches(
2566 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2568 # Look for Rutube embeds
2569 rutube_urls = RutubeIE._extract_urls(webpage)
2571 return self.playlist_from_matches(
2572 rutube_urls, ie=RutubeIE.ie_key())
2574 # Looking for http://schema.org/VideoObject
2575 json_ld = self._search_json_ld(
2576 webpage, video_id, default={}, expected_type='VideoObject')
2577 if json_ld.get('url'):
2579 'title': video_title or info_dict['title'],
2580 'description': video_description,
2581 'thumbnail': video_thumbnail,
2582 'age_limit': age_limit
2584 info_dict.update(json_ld)
2587 # Look for HTML5 media
2588 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2590 for entry in entries:
2593 'title': video_title,
2595 self._sort_formats(entry['formats'])
2596 return self.playlist_result(entries)
2598 jwplayer_data = self._find_jwplayer_data(
2599 webpage, video_id, transform_source=js_to_json)
2601 info = self._parse_jwplayer_data(
2602 jwplayer_data, video_id, require_title=False, base_url=url)
2603 if not info.get('title'):
2604 info['title'] = video_title
2607 def check_video(vurl):
2608 if YoutubeIE.suitable(vurl):
2610 if RtmpIE.suitable(vurl):
2612 vpath = compat_urlparse.urlparse(vurl).path
2613 vext = determine_ext(vpath)
2614 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2616 def filter_video(urls):
2617 return list(filter(check_video, urls))
2619 # Start with something easy: JW Player in SWFObject
2620 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2622 # Look for gorilla-vid style embedding
2623 found = filter_video(re.findall(r'''(?sx)
2627 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2630 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2632 # Broaden the search a little bit
2633 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2635 # Broaden the findall a little bit: JWPlayer JS loader
2636 found = filter_video(re.findall(
2637 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2640 found = filter_video(re.findall(r'''(?xs)
2641 flowplayer\("[^"]+",\s*
2643 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2644 ["']?url["']?\s*:\s*["']([^"']+)["']
2649 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2651 # Try to find twitter cards info
2652 # twitter:player:stream should be checked before twitter:player since
2653 # it is expected to contain a raw stream (see
2654 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2655 found = filter_video(re.findall(
2656 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2658 # We look for Open Graph info:
2659 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2660 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2661 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2662 if m_video_type is not None:
2663 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2665 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2667 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2668 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2671 # Look also in Refresh HTTP header
2672 refresh_header = head_response.headers.get('Refresh')
2674 # In python 2 response HTTP headers are bytestrings
2675 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2676 refresh_header = refresh_header.decode('iso-8859-1')
2677 found = re.search(REDIRECT_REGEX, refresh_header)
2679 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2681 self.report_following_redirect(new_url)
2690 # twitter:player is a https URL to iframe player that may or may not
2691 # be supported by youtube-dl thus this is checked the very last (see
2692 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2693 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2695 return self.url_result(embed_url)
2698 raise UnsupportedError(url)
2701 for video_url in orderedSet(found):
2702 video_url = unescapeHTML(video_url)
2703 video_url = video_url.replace('\\/', '/')
2704 video_url = compat_urlparse.urljoin(url, video_url)
2705 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2707 # Sometimes, jwplayer extraction will result in a YouTube URL
2708 if YoutubeIE.suitable(video_url):
2709 entries.append(self.url_result(video_url, 'Youtube'))
2712 # here's a fun little line of code for you:
2713 video_id = os.path.splitext(video_id)[0]
2717 'uploader': video_uploader,
2718 'title': video_title,
2719 'age_limit': age_limit,
2722 if RtmpIE.suitable(video_url):
2723 entry_info_dict.update({
2724 '_type': 'url_transparent',
2725 'ie_key': RtmpIE.ie_key(),
2728 entries.append(entry_info_dict)
2731 ext = determine_ext(video_url)
2733 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2735 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2737 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2739 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2741 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2742 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2743 # Just matching .ism/manifest is not enough to be reliably sure
2744 # whether it's actually an ISM manifest or some other streaming
2745 # manifest since there are various streaming URL formats
2746 # possible (see [1]) as well as some other shenanigans like
2747 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2749 # Thus the most reasonable way to solve this is to delegate
2750 # to generic extractor in order to look into the contents of
2751 # the manifest itself.
2752 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2753 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2754 entry_info_dict = self.url_result(
2755 smuggle_url(video_url, {'to_generic': True}),
2758 entry_info_dict['url'] = video_url
2760 if entry_info_dict.get('formats'):
2761 self._sort_formats(entry_info_dict['formats'])
2763 entries.append(entry_info_dict)
2765 if len(entries) == 1:
2768 for num, e in enumerate(entries, start=1):
2769 # 'url' results don't have a title
2770 if e.get('title') is not None:
2771 e['title'] = '%s (%d)' % (e['title'], num)
2773 '_type': 'playlist',