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
88 from .limelight import LimelightBaseIE
91 class GenericIE(InfoExtractor):
92 IE_DESC = 'Generic downloader that works on some sites'
96 # Direct link to a video
98 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
99 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
104 'upload_date': '20100513',
107 # Direct link to media delivered compressed (until Accept-Encoding is *)
109 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
110 'md5': '128c42e68b13950268b648275386fc74',
112 'id': 'FictionJunction-Parallel_Hearts',
114 'title': 'FictionJunction-Parallel_Hearts',
115 'upload_date': '20140522',
117 'expected_warnings': [
118 'URL could be a direct video link, returning it as such.'
120 'skip': 'URL invalid',
122 # Direct download with broken HEAD
124 'url': 'http://ai-radio.org:8000/radio.opus',
131 'skip_download': True, # infinite live stream
133 'expected_warnings': [
134 r'501.*Not Implemented',
138 # Direct link with incorrect MIME type
140 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
141 'md5': '4ccbebe5f36706d85221f204d7eb5913',
143 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
144 'id': '5_Lennart_Poettering_-_Systemd',
146 'title': '5_Lennart_Poettering_-_Systemd',
147 'upload_date': '20141120',
149 'expected_warnings': [
150 'URL could be a direct video link, returning it as such.'
155 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
157 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
158 'title': 'Zero Punctuation',
159 'description': 're:.*groundbreaking video review series.*'
161 'playlist_mincount': 11,
163 # RSS feed with enclosure
165 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
167 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
169 'upload_date': '20150228',
170 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
173 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
175 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
179 'title': 'Automatics, robotics and biocybernetics',
180 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
181 'upload_date': '20130627',
182 'formats': 'mincount:16',
183 'subtitles': 'mincount:1',
186 'force_generic_extractor': True,
187 'skip_download': True,
190 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
192 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
197 'formats': 'mincount:1',
200 'skip_download': True,
203 # SMIL from https://www.restudy.dk/video/play/id/1637
205 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
209 'title': 'video_1637',
210 'formats': 'mincount:3',
213 'skip_download': True,
216 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
218 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
220 'id': 'smil-service',
222 'title': 'smil-service',
223 'formats': 'mincount:1',
226 'skip_download': True,
229 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
231 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
235 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
236 'formats': 'mincount:3',
239 'skip_download': True,
242 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
244 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
246 'id': 'mZlp2ctYIUEB',
248 'title': 'Tikibad ontruimd wegens brand',
249 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
250 'thumbnail': r're:^https?://.*\.jpg$',
254 'skip_download': True,
257 # MPD from http://dash-mse-test.appspot.com/media.html
259 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
260 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
262 'id': 'car-20120827-manifest',
264 'title': 'car-20120827-manifest',
265 'formats': 'mincount:9',
266 'upload_date': '20130904',
269 'format': 'bestvideo',
272 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
274 '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',
279 'formats': 'mincount:8',
283 'skip_download': True,
285 'skip': 'video gone',
287 # m3u8 served with Content-Type: text/plain
289 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
294 'upload_date': '20140720',
295 'formats': 'mincount:11',
299 'skip_download': True,
301 'skip': 'video gone',
305 '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',
309 'upload_date': '20130224',
310 'uploader_id': 'TheVerge',
311 'description': r're:^Chris Ziegler takes a look at the\.*',
312 'uploader': 'The Verge',
313 'title': 'First Firefox OS phones side-by-side',
316 'skip_download': False,
320 # redirect in Refresh HTTP header
321 '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',
325 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
326 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
327 'upload_date': '20150917',
328 'uploader_id': 'brtvofficial',
329 'uploader': 'Boiler Room',
332 'skip_download': False,
336 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
337 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
339 'id': '13601338388002',
341 'uploader': 'www.hodiho.fr',
342 'title': 'R\u00e9gis plante sa Jeep',
345 # bandcamp page with custom domain
347 'add_ie': ['Bandcamp'],
348 'url': 'http://bronyrock.com/track/the-pony-mash',
352 'title': 'The Pony Mash',
353 'uploader': 'M_Pallante',
355 'skip': 'There is a limit of 200 free downloads / month for the test song',
358 # embedded brightcove video
359 # it also tests brightcove videos that need to set the 'Referer'
360 # in the http requests
361 'add_ie': ['BrightcoveLegacy'],
362 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
364 'id': '2765128793001',
366 'title': 'Le cours de bourse : l’analyse technique',
367 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
368 'uploader': 'BFM BUSINESS',
371 'skip_download': True,
375 # embedded with itemprop embedURL and video id spelled as `idVideo`
376 'add_id': ['BrightcoveLegacy'],
377 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
379 'id': '5255628253001',
381 'title': 'md5:37c519b1128915607601e75a87995fc0',
382 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
383 'uploader': 'BFM BUSINESS',
384 'uploader_id': '876450612001',
385 'timestamp': 1482255315,
386 'upload_date': '20161220',
389 'skip_download': True,
393 # https://github.com/rg3/youtube-dl/issues/2253
394 'url': 'http://bcove.me/i6nfkrc3',
395 'md5': '0ba9446db037002366bab3b3eb30c88c',
397 'id': '3101154703001',
399 'title': 'Still no power',
400 'uploader': 'thestar.com',
401 '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.',
403 'add_ie': ['BrightcoveLegacy'],
404 'skip': 'video gone',
407 'url': 'http://www.championat.com/video/football/v/87/87499.html',
408 'md5': 'fb973ecf6e4a78a67453647444222983',
410 'id': '3414141473001',
412 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
413 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
414 'uploader': 'Championat',
418 # https://github.com/rg3/youtube-dl/issues/3541
419 'add_ie': ['BrightcoveLegacy'],
420 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
422 'id': '3866516442001',
424 'title': 'Leer mij vrouwen kennen: Aflevering 1',
425 'description': 'Leer mij vrouwen kennen: Aflevering 1',
426 'uploader': 'SBS Broadcasting',
428 'skip': 'Restricted to Netherlands',
430 'skip_download': True, # m3u8 download
434 # Brightcove video in <iframe>
435 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
436 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
438 'id': '5360463607001',
440 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
441 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
442 'uploader': 'United Nations',
443 'uploader_id': '1362235914001',
444 'timestamp': 1489593889,
445 'upload_date': '20170315',
447 'add_ie': ['BrightcoveLegacy'],
450 # Brightcove with alternative playerID key
451 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
453 'id': 'nmeth.2062_SV1',
454 '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',
458 'id': '2228375078001',
460 'title': 'nmeth.2062-sv1',
461 'description': 'nmeth.2062-sv1',
462 'timestamp': 1363357591,
463 'upload_date': '20130315',
464 'uploader': 'Nature Publishing Group',
465 'uploader_id': '1964492299001',
470 # Brightcove with UUID in videoPlayer
471 'url': 'http://www8.hp.com/cn/zh/home.html',
473 'id': '5255815316001',
475 'title': 'Sprocket Video - China',
476 'description': 'Sprocket Video - China',
477 'uploader': 'HP-Video Gallery',
478 'timestamp': 1482263210,
479 'upload_date': '20161220',
480 'uploader_id': '1107601872001',
483 'skip_download': True, # m3u8 download
485 'skip': 'video rotates...weekly?',
488 # Brightcove:new type [2].
489 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
490 'md5': '2b35148fcf48da41c9fb4591650784f3',
492 'id': '5348741021001',
494 'upload_date': '20170306',
495 'uploader_id': '4191638492001',
496 'timestamp': 1488769918,
497 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
502 # Alternative brightcove <video> attributes
503 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
505 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
506 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
509 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
511 'id': '5311302538001',
513 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
514 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
515 'timestamp': 1486321708,
516 'upload_date': '20170205',
517 'uploader_id': '800000640001',
519 'only_matching': True,
523 # Brightcove with UUID in videoPlayer
524 'url': 'http://www8.hp.com/cn/zh/home.html',
526 'id': '5255815316001',
528 'title': 'Sprocket Video - China',
529 'description': 'Sprocket Video - China',
530 'uploader': 'HP-Video Gallery',
531 'timestamp': 1482263210,
532 'upload_date': '20161220',
533 'uploader_id': '1107601872001',
536 'skip_download': True, # m3u8 download
541 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
542 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
544 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
546 'title': '2cc213299525360.mov', # that's what we get
549 'add_ie': ['Ooyala'],
552 # ooyala video embedded with http://player.ooyala.com/iframe.js
553 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
555 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
557 'title': '"Steve Jobs: Man in the Machine" trailer',
558 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
562 'skip_download': True,
564 'skip': 'movie expired',
568 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
572 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
573 'upload_date': '20140225',
574 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
575 'uploader': 'Tested',
576 'uploader_id': 'testedcom',
578 # No need to test YoutubeIE here
580 'skip_download': True,
585 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
589 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
590 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
592 # HEAD requests lead to endless 301, while GET is OK
593 'expected_warnings': ['301'],
597 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
601 'title': 'Охотское море стало целиком российским',
602 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
606 'skip_download': True,
611 '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/',
615 'title': 'Дошкольное воспитание',
620 'url': 'http://www.vestifinance.ru/articles/25753',
623 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
628 'title': 'Госзаказ. День 3',
634 'title': 'Госзаказ. День 2',
640 'title': 'Госзаказ. День 1',
646 'skip_download': True,
651 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
653 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
655 'title': 'Ужастики, русский трейлер (2015)',
656 'thumbnail': r're:^https?://.*\.jpg$',
662 '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',
665 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
667 'playlist_mincount': 7,
668 # This forum does not allow <iframe> syntaxes anymore
669 # Now HTML tags are displayed as-is
670 'skip': 'No videos on this page',
674 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
675 'md5': '65fdff94098e4a607385a60c5177c638',
679 'title': 'Hidden miracles of the natural world',
680 'uploader': 'Louie Schwartzberg',
681 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
684 # nowvideo embed hidden behind percent encoding
686 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
687 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
689 'id': '06e53103ca9aa',
691 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
692 'description': 'No description',
697 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
698 'md5': '7653032cbb25bf6c80d80f217055fa43',
700 'id': '048195-004_PLUS7-F',
703 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
704 'upload_date': '20140320',
707 'skip_download': 'Requires rtmpdump'
709 'skip': 'video gone',
713 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
717 'title': 'Alcaline, le concert avec Calogero',
718 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
719 'upload_date': '20150226',
720 'timestamp': 1424989860,
725 'skip_download': True,
727 'expected_warnings': [
733 'url': 'http://www.wired.com/2014/04/honda-asimo/',
734 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
736 'id': '53501be369702d3275860000',
738 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
743 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
744 'md5': '441aeeb82eb72c422c7f14ec533999cd',
746 'id': 'k2mm4bCdJ6CQ2i7c8o2',
748 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
749 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
751 'uploader_id': 'xgditw',
752 'upload_date': '20140425',
753 'timestamp': 1398441542,
755 'add_ie': ['Dailymotion'],
759 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
763 'title': 'The NBL Auction 2014',
764 'uploader': 'BADMINTON England',
765 'uploader_id': 'BADMINTONEvents',
766 'upload_date': '20140603',
767 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
769 'add_ie': ['Youtube'],
771 'skip_download': True,
776 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
777 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
779 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
781 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
782 'description': 'Two valets share their love for movie star Liam Neesons.',
783 'timestamp': 1349922600,
784 'upload_date': '20121011',
787 # YouTube embed via <data-embed-url="">
789 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
793 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
794 'uploader': 'Gameloft',
795 'uploader_id': 'gameloft',
796 'upload_date': '20140828',
797 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
800 'skip_download': True,
803 # YouTube <object> embed
805 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
806 'md5': '516718101ec834f74318df76259fb3cc',
810 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
811 'upload_date': '20080526',
812 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
813 'uploader': 'Christopher Sykes',
814 'uploader_id': 'ChristopherJSykes',
816 'add_ie': ['Youtube'],
820 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
822 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
824 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
825 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
830 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
832 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
833 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
839 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
844 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
845 'md5': '9d65602bf31c6e20014319c7d07fba27',
847 'id': '5123ea6d5e5a7',
850 'uploader': 'www.handjobhub.com',
851 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
854 # Multiple brightcove videos
855 # https://github.com/rg3/youtube-dl/issues/2283
857 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
859 'id': 'always-never',
860 'title': 'Always / Never - The New Yorker',
864 'extract_flat': False,
865 'skip_download': True,
870 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
871 'md5': '96f09a37e44da40dd083e12d9a683327',
875 'title': 'Ump changes call to ball',
876 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
878 'timestamp': 1401537900,
879 'upload_date': '20140531',
880 'thumbnail': r're:^https?://.*\.jpg$',
885 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
886 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
890 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
891 'description': 'a Paywall Videos video from Remilon',
893 'uploader': 'study.com',
894 'timestamp': 1459678540,
895 'upload_date': '20160403',
896 'filesize': 24687186,
900 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
901 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
905 'title': 'Conversation about Hexagonal Rails Part 1',
906 'description': 'a Martin Fowler video from ThoughtWorks',
908 'uploader': 'thoughtworks.wistia.com',
909 'timestamp': 1401832161,
910 'upload_date': '20140603',
913 # Wistia standard embed (async)
915 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
919 'title': 'Drip Brennan Dunn Workshop',
920 'description': 'a JV Webinars video from getdrip-1',
922 'timestamp': 1463607249,
923 'upload_date': '20160518',
926 'skip_download': True,
931 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
935 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
936 'uploader': 'Sophos Security',
937 'title': 'Chet Chat 171 - Oct 29, 2014',
938 'upload_date': '20141029',
941 # Soundcloud multiple embeds
943 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
946 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
948 'playlist_mincount': 7,
950 # TuneIn station embed
952 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
957 'location': 'Paris, France',
962 'skip_download': True,
967 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
971 'upload_date': '20141112',
972 'title': 'Rosetta #CometLanding webcast HL 10',
975 # Another Livestream embed, without 'new.' in URL
977 'url': 'https://www.freespeech.org/',
981 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
985 'skip_download': True,
990 'url': 'https://skiplagged.com/',
993 'title': 'Skiplagged: The smart way to find cheap flights',
995 'playlist_mincount': 1,
996 'add_ie': ['Youtube'],
1000 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1004 'upload_date': '20141126',
1005 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1010 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1012 'id': '730m_DandD_1901_512k',
1014 'uploader': 'www.abc.net.au',
1015 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1018 # embedded viddler video
1020 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1024 'uploader': 'deadspin',
1025 'title': 'WALL-TO-GORTAT',
1026 'timestamp': 1422285291,
1027 'upload_date': '20150126',
1029 'add_ie': ['Viddler'],
1033 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1037 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1038 'description': 'md5:601cb790edd05908957dae8aaa866465',
1039 'upload_date': '20150220',
1041 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1045 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1047 'id': 'Mrj4DVp2zeA',
1049 'upload_date': '20150212',
1050 'uploader': 'The National Archives UK',
1051 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1052 'uploader_id': 'NationalArchives08',
1053 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1058 'url': 'http://www.suffolk.edu/sjc/',
1062 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1063 'uploader': 'www.suffolk.edu',
1066 'skip_download': True,
1071 'url': 'http://www.indiedb.com/games/king-machine/videos',
1075 'title': 'king machine trailer 1',
1076 'thumbnail': r're:^https?://.*\.jpg$',
1080 # JWPlayer config passed as variable
1081 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1085 'title': 'ARIELE | Tube Cup',
1086 'uploader': 'www.txxx.com',
1090 'skip_download': True,
1095 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1096 'playlist_mincount': 5,
1098 'id': 'aanslagen-kopenhagen',
1099 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1104 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1108 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1111 # Kaltura embed (different embed code)
1113 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1117 'upload_date': '20150127',
1118 'uploader_id': 'PremierMedia',
1120 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1123 # Kaltura embed with single quotes
1125 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1130 'timestamp': 1355743100,
1131 'upload_date': '20121217',
1132 'uploader_id': 'batchUser',
1134 'add_ie': ['Kaltura'],
1137 # Kaltura embedded via quoted entry_id
1138 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1142 'title': '06_matthew_brender_raj_dutt',
1143 'timestamp': 1466638791,
1144 'upload_date': '20160622',
1146 'add_ie': ['Kaltura'],
1147 'expected_warnings': [
1148 'Could not send HEAD request'
1151 'skip_download': True,
1155 # Kaltura embedded, some fileExt broken (#11480)
1156 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1160 'title': 'Our "Standard Models" of particle physics and cosmology',
1161 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1162 'timestamp': 1321158993,
1163 'upload_date': '20111113',
1164 'uploader_id': 'kps1',
1166 'add_ie': ['Kaltura'],
1169 # Kaltura iframe embed
1170 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1171 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1175 'title': 'I. M. Pei: A Centennial Celebration',
1176 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1177 'upload_date': '20170403',
1178 'uploader_id': 'batchUser',
1179 'timestamp': 1491232186,
1181 'add_ie': ['Kaltura'],
1183 # Eagle.Platform embed (generic URL)
1185 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1186 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1190 'title': 'Навальный вышел на свободу',
1191 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1192 'thumbnail': r're:^https?://.*\.jpg$',
1198 # ClipYou (Eagle.Platform) embed (custom URL)
1200 'url': 'http://muz-tv.ru/play/7129/',
1201 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1205 'title': "'O Sole Mio",
1206 'thumbnail': r're:^https?://.*\.jpg$',
1213 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1217 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1218 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1219 'thumbnail': r're:^https?://.*\.jpg$',
1226 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1230 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1231 'thumbnail': r're:^https?://.*\.png$',
1237 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1238 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1242 'title': 'Facebook Creates "On This Day" | Crunch Report',
1247 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1251 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1256 # Crooks and Liars embed
1258 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1262 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1263 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1264 'timestamp': 1428207000,
1265 'upload_date': '20150405',
1266 'uploader': 'Heather',
1269 # Crooks and Liars external embed
1271 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1273 'id': 'MTE3MjUtMzQ2MzA',
1275 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1276 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1277 'timestamp': 1265032391,
1278 'upload_date': '20100201',
1279 'uploader': 'Heather',
1282 # NBC Sports vplayer embed
1284 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1286 'id': 'ln7x1qSThw4k',
1288 'title': "PFT Live: New leader in the 'new-look' defense",
1289 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1290 'uploader': 'NBCU-SPORTS',
1291 'upload_date': '20140107',
1292 'timestamp': 1389118457,
1297 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1298 'md5': '1aa589c675898ae6d37a17913cf68d66',
1300 'id': '701714499682',
1302 'title': 'PREVIEW: On Assignment: David Letterman',
1303 '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.',
1308 'url': 'https://video.udn.com/news/300346',
1309 'md5': 'fd2060e988c326991037b9aff9df21a6',
1313 'title': '中一中男師變性 全校師生力挺',
1314 'thumbnail': r're:^https?://.*\.jpg$',
1318 'skip_download': True,
1323 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1325 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1327 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1328 'title': 'This is what separates the Excel masters from the wannabes',
1329 'duration': 191.933,
1333 'skip_download': True,
1336 # Brightcove URL in single quotes
1338 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1339 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1341 'id': '4255764656001',
1343 'title': 'SN Presents: Russell Martin, World Citizen',
1344 '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.',
1345 'uploader': 'Rogers Sportsnet',
1346 'uploader_id': '1704050871',
1347 'upload_date': '20150525',
1348 'timestamp': 1432570283,
1351 # Dailymotion Cloud video
1353 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1354 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1358 'title': 'Sauvons les abeilles ! - Le débat',
1359 'description': 'md5:d9082128b1c5277987825d684939ca26',
1360 'thumbnail': r're:^https?://.*\.jpe?g$',
1361 'timestamp': 1434970506,
1362 'upload_date': '20150622',
1363 'uploader': 'Public Sénat',
1364 'uploader_id': 'xa9gza',
1367 # OnionStudios embed
1369 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1373 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1374 'thumbnail': r're:^https?://.*\.jpe?g$',
1375 'uploader': 'ClickHole',
1376 'uploader_id': 'clickhole',
1381 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1383 'id': '74849a00-85a9-11e1-9660-123139220831',
1385 'title': '#whilewewatch',
1388 # AdobeTVVideo embed
1390 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1391 'md5': '43662b577c018ad707a63766462b1e87',
1395 'title': 'New experience with Acrobat DC',
1396 'description': 'New experience with Acrobat DC',
1397 'duration': 248.667,
1400 # BrightcoveInPageEmbed embed
1402 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1404 'id': '4238694884001',
1406 'title': 'Tabletop: Dread, Last Thoughts',
1407 'description': 'Tabletop: Dread, Last Thoughts',
1411 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1412 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1414 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1416 'id': '4785848093001',
1418 'title': 'The Cardinal Pell Interview',
1419 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1420 'uploader': 'GlobeCast Australia - GlobeStream',
1421 'uploader_id': '2733773828001',
1422 'upload_date': '20160304',
1423 'timestamp': 1457083087,
1427 'skip_download': True,
1430 # Another form of arte.tv embed
1432 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1433 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1435 'id': '030273-562_PLUS7-F',
1437 'title': 'ARTE Reportage - Nulle part, en France',
1438 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1439 'upload_date': '20160409',
1444 'url': 'http://www.wykop.pl/link/3088787/',
1445 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1447 'id': '874_1459135191',
1449 'title': 'Man shows poor quality of new apartment building',
1450 'description': 'The wall is like a sand pile.',
1451 'uploader': 'Lake8737',
1454 # Duplicated embedded video URLs
1456 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1458 'id': '149298443_480_16c25b74_2',
1460 'title': 'vs. Blue Orange Spring Game',
1461 'uploader': 'www.hudl.com',
1464 # twitter:player:stream embed
1466 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1470 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1471 'uploader': 'www.rtl.be',
1475 'skip_download': True,
1478 # twitter:player embed
1480 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1481 'md5': 'a3e0df96369831de324f0778e126653c',
1483 'id': '4909620399001',
1485 'title': 'What Do Black Holes Sound Like?',
1486 'description': 'what do black holes sound like',
1487 'upload_date': '20160524',
1488 'uploader_id': '29913724001',
1489 'timestamp': 1464107587,
1490 'uploader': 'TheAtlantic',
1492 'add_ie': ['BrightcoveLegacy'],
1494 # Facebook <iframe> embed
1496 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1497 'md5': 'fbcde74f534176ecb015849146dd3aee',
1499 'id': '599637780109885',
1501 'title': 'Facebook video #599637780109885',
1504 # Facebook API embed
1506 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1507 'md5': 'a47372ee61b39a7b90287094d447d94e',
1509 'id': '10153467542406923',
1511 'title': 'Facebook video #10153467542406923',
1514 # Wordpress "YouTube Video Importer" plugin
1516 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1517 'md5': 'd16797741b560b485194eddda8121b48',
1519 'id': 'HNTXWDXV9Is',
1521 'title': 'Blue Devils Drumline Stanford lot 2016',
1522 'upload_date': '20160627',
1523 'uploader_id': 'GENOCIDE8GENERAL10',
1524 'uploader': 'cylus cyrus',
1528 # video stored on custom kaltura server
1529 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1530 'md5': '537617d06e64dfed891fa1593c4b30cc',
1534 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1535 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1536 'uploader_id': 'videos.expansion@el-mundo.net',
1537 'upload_date': '20150429',
1538 'timestamp': 1430303472,
1540 'add_ie': ['Kaltura'],
1543 # Non-standard Vimeo embed
1544 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1545 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1549 'title': 'Understanding the web - Teaser',
1550 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1551 'upload_date': '20151214',
1552 'uploader': 'OpenClassrooms',
1553 'uploader_id': 'openclassrooms',
1555 'add_ie': ['Vimeo'],
1558 # generic vimeo embed that requires original URL passed as Referer
1559 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1560 'only_matching': True,
1563 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1564 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1566 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1568 'title': 'Big Buck Bunny',
1569 'description': 'Royalty free test video',
1570 'timestamp': 1432816365,
1571 'upload_date': '20150528',
1575 'skip_download': True,
1577 'add_ie': [ArkenaIE.ie_key()],
1580 '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/',
1584 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1587 'skip_download': True,
1589 'add_ie': [Vbox7IE.ie_key()],
1593 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1596 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1598 'playlist_mincount': 3,
1602 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1604 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1605 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1607 'playlist_mincount': 2,
1611 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1615 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1616 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1619 'skip_download': True,
1621 'add_ie': [TwentyMinutenIE.ie_key()],
1625 'url': 'https://en.support.wordpress.com/videopress/',
1629 'title': 'IMG_5786',
1630 'timestamp': 1435711927,
1631 'upload_date': '20150701',
1634 'skip_download': True,
1636 'add_ie': [VideoPressIE.ie_key()],
1640 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1642 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1644 'title': 'Магаззино: Казань 2',
1645 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1646 'uploader': 'Магаззино',
1647 'upload_date': '20170228',
1648 'uploader_id': '996642',
1651 'skip_download': True,
1653 'add_ie': [RutubeIE.ie_key()],
1656 # ThePlatform embedded with whitespaces in URLs
1657 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1658 'only_matching': True,
1661 # Senate ISVP iframe https
1662 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1663 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1665 'id': 'govtaff020316',
1667 'title': 'Integrated Senate Video Player',
1669 'add_ie': [SenateISVPIE.ie_key()],
1672 # Limelight embeds (1 channel embed + 4 media embeds)
1673 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1675 'id': 'FacilitatorTraining2017',
1676 'title': 'Facilitator Training 2017',
1678 'playlist_mincount': 5,
1681 # # TODO: find another test
1682 # # http://schema.org/VideoObject
1683 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1684 # 'md5': '888dcf08b7ea671381f00fab74692755',
1686 # 'id': 'nyvTSJMKId',
1688 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1689 # 'description': '#love for cats.',
1690 # 'timestamp': 1461244995,
1691 # 'upload_date': '20160421',
1694 # 'force_generic_extractor': True,
1699 def report_following_redirect(self, new_url):
1700 """Report information extraction."""
1701 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1703 def _extract_rss(self, url, video_id, doc):
1704 playlist_title = doc.find('./channel/title').text
1705 playlist_desc_el = doc.find('./channel/description')
1706 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1709 for it in doc.findall('./channel/item'):
1710 next_url = xpath_text(it, 'link', fatal=False)
1712 enclosure_nodes = it.findall('./enclosure')
1713 for e in enclosure_nodes:
1714 next_url = e.attrib.get('url')
1722 '_type': 'url_transparent',
1724 'title': it.find('title').text,
1728 '_type': 'playlist',
1730 'title': playlist_title,
1731 'description': playlist_desc,
1735 def _extract_camtasia(self, url, video_id, webpage):
1736 """ Returns None if no camtasia video can be found. """
1738 camtasia_cfg = self._search_regex(
1739 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1740 webpage, 'camtasia configuration file', default=None)
1741 if camtasia_cfg is None:
1744 title = self._html_search_meta('DC.title', webpage, fatal=True)
1746 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1747 camtasia_cfg = self._download_xml(
1748 camtasia_url, video_id,
1749 note='Downloading camtasia configuration',
1750 errnote='Failed to download camtasia configuration')
1751 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1754 for n in fileset_node.getchildren():
1755 url_n = n.find('./uri')
1760 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1761 'title': '%s - %s' % (title, n.tag),
1762 'url': compat_urlparse.urljoin(url, url_n.text),
1763 'duration': float_or_none(n.find('./duration').text),
1767 '_type': 'playlist',
1772 def _real_extract(self, url):
1773 if url.startswith('//'):
1776 'url': self.http_scheme() + url,
1779 parsed_url = compat_urlparse.urlparse(url)
1780 if not parsed_url.scheme:
1781 default_search = self._downloader.params.get('default_search')
1782 if default_search is None:
1783 default_search = 'fixup_error'
1785 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1787 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1788 return self.url_result('http://' + url)
1789 elif default_search != 'fixup_error':
1790 if default_search == 'auto_warning':
1791 if re.match(r'^(?:url|URL)$', url):
1792 raise ExtractorError(
1793 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1796 self._downloader.report_warning(
1797 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1798 return self.url_result('ytsearch:' + url)
1800 if default_search in ('error', 'fixup_error'):
1801 raise ExtractorError(
1802 '%r is not a valid URL. '
1803 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1804 % (url, url), expected=True)
1806 if ':' not in default_search:
1807 default_search += ':'
1808 return self.url_result(default_search + url)
1810 url, smuggled_data = unsmuggle_url(url)
1811 force_videoid = None
1812 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1813 if smuggled_data and 'force_videoid' in smuggled_data:
1814 force_videoid = smuggled_data['force_videoid']
1815 video_id = force_videoid
1817 video_id = self._generic_id(url)
1819 self.to_screen('%s: Requesting header' % video_id)
1821 head_req = HEADRequest(url)
1822 head_response = self._request_webpage(
1824 note=False, errnote='Could not send HEAD request to %s' % url,
1827 if head_response is not False:
1828 # Check for redirect
1829 new_url = head_response.geturl()
1831 self.report_following_redirect(new_url)
1833 new_url = smuggle_url(
1834 new_url, {'force_videoid': force_videoid})
1835 return self.url_result(new_url)
1837 full_response = None
1838 if head_response is False:
1839 request = sanitized_Request(url)
1840 request.add_header('Accept-Encoding', '*')
1841 full_response = self._request_webpage(request, video_id)
1842 head_response = full_response
1846 'title': self._generic_title(url),
1847 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1850 # Check for direct link to a video
1851 content_type = head_response.headers.get('Content-Type', '').lower()
1852 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1854 format_id = m.group('format_id')
1855 if format_id.endswith('mpegurl'):
1856 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1857 elif format_id == 'f4m':
1858 formats = self._extract_f4m_formats(url, video_id)
1861 'format_id': m.group('format_id'),
1863 'vcodec': 'none' if m.group('type') == 'audio' else None
1865 info_dict['direct'] = True
1866 self._sort_formats(formats)
1867 info_dict['formats'] = formats
1870 if not self._downloader.params.get('test', False) and not is_intentional:
1871 force = self._downloader.params.get('force_generic_extractor', False)
1872 self._downloader.report_warning(
1873 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1875 if not full_response:
1876 request = sanitized_Request(url)
1877 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1878 # making it impossible to download only chunk of the file (yet we need only 512kB to
1879 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1880 # that will always result in downloading the whole file that is not desirable.
1881 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1882 # to accept raw bytes and being able to download only a chunk.
1883 # It may probably better to solve this by checking Content-Type for application/octet-stream
1884 # after HEAD request finishes, but not sure if we can rely on this.
1885 request.add_header('Accept-Encoding', '*')
1886 full_response = self._request_webpage(request, video_id)
1888 first_bytes = full_response.read(512)
1890 # Is it an M3U playlist?
1891 if first_bytes.startswith(b'#EXTM3U'):
1892 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1893 self._sort_formats(info_dict['formats'])
1896 # Maybe it's a direct link to a video?
1897 # Be careful not to download the whole thing!
1898 if not is_html(first_bytes):
1899 self._downloader.report_warning(
1900 'URL could be a direct video link, returning it as such.')
1907 webpage = self._webpage_read_content(
1908 full_response, url, video_id, prefix=first_bytes)
1910 self.report_extraction(video_id)
1912 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1914 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1915 if doc.tag == 'rss':
1916 return self._extract_rss(url, video_id, doc)
1917 elif doc.tag == 'SmoothStreamingMedia':
1918 info_dict['formats'] = self._parse_ism_formats(doc, url)
1919 self._sort_formats(info_dict['formats'])
1921 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1922 smil = self._parse_smil(doc, url, video_id)
1923 self._sort_formats(smil['formats'])
1925 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1926 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1927 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1928 info_dict['formats'] = self._parse_mpd_formats(
1930 mpd_base_url=full_response.geturl().rpartition('/')[0],
1932 self._sort_formats(info_dict['formats'])
1934 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1935 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1936 self._sort_formats(info_dict['formats'])
1938 except compat_xml_parse_error:
1941 # Is it a Camtasia project?
1942 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1943 if camtasia_res is not None:
1946 # Sometimes embedded video player is hidden behind percent encoding
1947 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1948 # Unescaping the whole page allows to handle those cases in a generic way
1949 webpage = compat_urllib_parse_unquote(webpage)
1951 # it's tempting to parse this further, but you would
1952 # have to take into account all the variations like
1953 # Video Title - Site Name
1954 # Site Name | Video Title
1955 # Video Title - Tagline | Site Name
1956 # and so on and so forth; it's just not practical
1957 video_title = self._og_search_title(
1958 webpage, default=None) or self._html_search_regex(
1959 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1962 # Try to detect age limit automatically
1963 age_limit = self._rta_search(webpage)
1964 # And then there are the jokers who advertise that they use RTA,
1965 # but actually don't.
1966 AGE_LIMIT_MARKERS = [
1967 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1969 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1972 # video uploader is domain name
1973 video_uploader = self._search_regex(
1974 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1976 video_description = self._og_search_description(webpage, default=None)
1977 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1979 # Look for Brightcove Legacy Studio embeds
1980 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1984 'url': smuggle_url(bc_url, {'Referer': url}),
1985 'ie_key': 'BrightcoveLegacy'
1986 } for bc_url in bc_urls]
1989 '_type': 'playlist',
1990 'title': video_title,
1995 # Look for Brightcove New Studio embeds
1996 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
1998 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2000 # Look for ThePlatform embeds
2001 tp_urls = ThePlatformIE._extract_urls(webpage)
2003 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2005 # Look for Vessel embeds
2006 vessel_urls = VesselIE._extract_urls(webpage)
2008 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2010 # Look for embedded rtl.nl player
2011 matches = re.findall(
2012 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2015 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2017 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2019 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2021 vid_me_embed_url = self._search_regex(
2022 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2023 webpage, 'vid.me embed', default=None)
2024 if vid_me_embed_url is not None:
2025 return self.url_result(vid_me_embed_url, 'Vidme')
2027 # Look for embedded YouTube player
2028 matches = re.findall(r'''(?x)
2038 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2042 return self.playlist_from_matches(
2043 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2045 # Look for lazyYT YouTube embed
2046 matches = re.findall(
2047 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2049 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2051 # Look for Wordpress "YouTube Video Importer" plugin
2052 matches = re.findall(r'''(?x)<div[^>]+
2053 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2054 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2056 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2058 matches = DailymotionIE._extract_urls(webpage)
2060 return self.playlist_from_matches(matches, video_id, video_title)
2062 # Look for embedded Dailymotion playlist player (#3822)
2064 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2066 playlists = re.findall(
2067 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2069 return self.playlist_from_matches(
2070 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2072 # Look for embedded Wistia player
2074 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
2076 embed_url = self._proto_relative_url(
2077 unescapeHTML(match.group('url')))
2079 '_type': 'url_transparent',
2082 'uploader': video_uploader,
2085 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
2088 '_type': 'url_transparent',
2089 'url': 'wistia:%s' % match.group('id'),
2091 'uploader': video_uploader,
2096 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
2097 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
2100 return self.url_result(self._proto_relative_url(
2101 'wistia:%s' % match.group('id')), 'Wistia')
2103 # Look for SVT player
2104 svt_url = SVTIE._extract_url(webpage)
2106 return self.url_result(svt_url, 'SVT')
2108 # Look for embedded condenast player
2109 matches = re.findall(
2110 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
2114 '_type': 'playlist',
2117 'ie_key': 'CondeNast',
2119 } for ma in matches],
2120 'title': video_title,
2124 # Look for Bandcamp pages with custom domain
2125 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2126 if mobj is not None:
2127 burl = unescapeHTML(mobj.group(1))
2128 # Don't set the extractor because it can be a track url or an album
2129 return self.url_result(burl)
2131 # Look for embedded Vevo player
2133 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2134 if mobj is not None:
2135 return self.url_result(mobj.group('url'))
2137 # Look for embedded Viddler player
2139 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2141 if mobj is not None:
2142 return self.url_result(mobj.group('url'))
2144 # Look for NYTimes player
2146 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2148 if mobj is not None:
2149 return self.url_result(mobj.group('url'))
2151 # Look for Libsyn player
2153 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2154 if mobj is not None:
2155 return self.url_result(mobj.group('url'))
2157 # Look for Ooyala videos
2158 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2159 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2160 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2161 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2162 if mobj is not None:
2163 embed_token = self._search_regex(
2164 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2165 webpage, 'ooyala embed token', default=None)
2166 return OoyalaIE._build_url_result(smuggle_url(
2169 'embed_token': embed_token,
2172 # Look for multiple Ooyala embeds on SBN network websites
2173 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2174 if mobj is not None:
2175 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2177 return self.playlist_from_matches(
2178 embeds, video_id, video_title,
2179 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2181 # Look for Aparat videos
2182 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2183 if mobj is not None:
2184 return self.url_result(mobj.group(1), 'Aparat')
2186 # Look for MPORA videos
2187 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2188 if mobj is not None:
2189 return self.url_result(mobj.group(1), 'Mpora')
2191 # Look for embedded NovaMov-based player
2193 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2194 (?P<url>http://(?:(?:embed|www)\.)?
2196 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2197 videoweed\.(?:es|com)|
2198 movshare\.(?:net|sx|ag)|
2199 divxstage\.(?:eu|net|ch|co|at|ag))
2200 /embed\.php.+?)\1''', webpage)
2201 if mobj is not None:
2202 return self.url_result(mobj.group('url'))
2204 # Look for embedded Facebook player
2205 facebook_url = FacebookIE._extract_url(webpage)
2206 if facebook_url is not None:
2207 return self.url_result(facebook_url, 'Facebook')
2209 # Look for embedded VK player
2210 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2211 if mobj is not None:
2212 return self.url_result(mobj.group('url'), 'VK')
2214 # Look for embedded Odnoklassniki player
2215 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2216 if mobj is not None:
2217 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2219 # Look for embedded ivi player
2220 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2221 if mobj is not None:
2222 return self.url_result(mobj.group('url'), 'Ivi')
2224 # Look for embedded Huffington Post player
2226 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2227 if mobj is not None:
2228 return self.url_result(mobj.group('url'), 'HuffPost')
2231 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2232 if mobj is not None:
2233 return self.url_result(mobj.group('url'))
2234 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2235 if mobj is not None:
2236 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2238 # Look for funnyordie embed
2239 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2241 return self.playlist_from_matches(
2242 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2244 # Look for BBC iPlayer embed
2245 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2247 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2249 # Look for embedded RUTV player
2250 rutv_url = RUTVIE._extract_url(webpage)
2252 return self.url_result(rutv_url, 'RUTV')
2254 # Look for embedded TVC player
2255 tvc_url = TVCIE._extract_url(webpage)
2257 return self.url_result(tvc_url, 'TVC')
2259 # Look for embedded SportBox player
2260 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2262 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2264 # Look for embedded XHamster player
2265 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2267 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2269 # Look for embedded TNAFlixNetwork player
2270 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2272 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2274 # Look for embedded PornHub player
2275 pornhub_urls = PornHubIE._extract_urls(webpage)
2277 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2279 # Look for embedded DrTuber player
2280 drtuber_urls = DrTuberIE._extract_urls(webpage)
2282 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2284 # Look for embedded RedTube player
2285 redtube_urls = RedTubeIE._extract_urls(webpage)
2287 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2289 # Look for embedded Tvigle player
2291 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2292 if mobj is not None:
2293 return self.url_result(mobj.group('url'), 'Tvigle')
2295 # Look for embedded TED player
2297 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2298 if mobj is not None:
2299 return self.url_result(mobj.group('url'), 'TED')
2301 # Look for embedded Ustream videos
2302 ustream_url = UstreamIE._extract_url(webpage)
2304 return self.url_result(ustream_url, UstreamIE.ie_key())
2306 # Look for embedded arte.tv player
2308 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2310 if mobj is not None:
2311 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2313 # Look for embedded francetv player
2315 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2317 if mobj is not None:
2318 return self.url_result(mobj.group('url'))
2320 # Look for embedded smotri.com player
2321 smotri_url = SmotriIE._extract_url(webpage)
2323 return self.url_result(smotri_url, 'Smotri')
2325 # Look for embedded Myvi.ru player
2326 myvi_url = MyviIE._extract_url(webpage)
2328 return self.url_result(myvi_url)
2330 # Look for embedded soundcloud player
2331 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2333 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2335 # Look for tunein player
2336 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2338 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2340 # Look for embedded mtvservices player
2341 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2343 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2345 # Look for embedded yahoo player
2347 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2349 if mobj is not None:
2350 return self.url_result(mobj.group('url'), 'Yahoo')
2352 # Look for embedded sbs.com.au player
2356 <meta\s+property="og:video"\s+content=|
2359 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2361 if mobj is not None:
2362 return self.url_result(mobj.group('url'), 'SBS')
2364 # Look for embedded Cinchcast player
2366 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2368 if mobj is not None:
2369 return self.url_result(mobj.group('url'), 'Cinchcast')
2372 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2376 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2378 if mobj is not None:
2379 return self.url_result(mobj.group('url'), 'MLB')
2382 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2384 if mobj is not None:
2385 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2388 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2390 if mobj is not None:
2391 return self.url_result(mobj.group('url'), 'Livestream')
2393 # Look for Zapiks embed
2395 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2396 if mobj is not None:
2397 return self.url_result(mobj.group('url'), 'Zapiks')
2399 # Look for Kaltura embeds
2400 kaltura_url = KalturaIE._extract_url(webpage)
2402 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2404 # Look for Eagle.Platform embeds
2405 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2406 if eagleplatform_url:
2407 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2409 # Look for ClipYou (uses Eagle.Platform) embeds
2411 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2412 if mobj is not None:
2413 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2415 # Look for Pladform embeds
2416 pladform_url = PladformIE._extract_url(webpage)
2418 return self.url_result(pladform_url)
2420 # Look for Videomore embeds
2421 videomore_url = VideomoreIE._extract_url(webpage)
2423 return self.url_result(videomore_url)
2425 # Look for Webcaster embeds
2426 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2428 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2430 # Look for Playwire embeds
2432 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2433 if mobj is not None:
2434 return self.url_result(mobj.group('url'))
2436 # Look for 5min embeds
2438 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2439 if mobj is not None:
2440 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2442 # Look for Crooks and Liars embeds
2444 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2445 if mobj is not None:
2446 return self.url_result(mobj.group('url'))
2448 # Look for NBC Sports VPlayer embeds
2449 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2451 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2453 # Look for NBC News embeds
2454 nbc_news_embed_url = re.search(
2455 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2456 if nbc_news_embed_url:
2457 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2459 # Look for Google Drive embeds
2460 google_drive_url = GoogleDriveIE._extract_url(webpage)
2461 if google_drive_url:
2462 return self.url_result(google_drive_url, 'GoogleDrive')
2464 # Look for UDN embeds
2466 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2467 if mobj is not None:
2468 return self.url_result(
2469 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2471 # Look for Senate ISVP iframe
2472 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2474 return self.url_result(senate_isvp_url, 'SenateISVP')
2476 # Look for Dailymotion Cloud videos
2477 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2479 return self.url_result(dmcloud_url, 'DailymotionCloud')
2481 # Look for OnionStudios embeds
2482 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2483 if onionstudios_url:
2484 return self.url_result(onionstudios_url)
2486 # Look for ViewLift embeds
2487 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2489 return self.url_result(viewlift_url)
2491 # Look for JWPlatform embeds
2492 jwplatform_url = JWPlatformIE._extract_url(webpage)
2494 return self.url_result(jwplatform_url, 'JWPlatform')
2496 # Look for Digiteka embeds
2497 digiteka_url = DigitekaIE._extract_url(webpage)
2499 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2501 # Look for Arkena embeds
2502 arkena_url = ArkenaIE._extract_url(webpage)
2504 return self.url_result(arkena_url, ArkenaIE.ie_key())
2506 # Look for Piksel embeds
2507 piksel_url = PikselIE._extract_url(webpage)
2509 return self.url_result(piksel_url, PikselIE.ie_key())
2511 # Look for Limelight embeds
2512 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2514 return self.playlist_result(
2515 limelight_urls, video_id, video_title, video_description)
2517 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2521 'Channel': 'channel',
2522 'ChannelList': 'channel_list',
2524 return self.url_result(smuggle_url('limelight:%s:%s' % (
2525 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2526 'Limelight%s' % mobj.group(1), mobj.group(2))
2530 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2532 name=(["\'])flashVars\2[^>]+
2533 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2536 return self.url_result(smuggle_url(
2537 'limelight:media:%s' % mobj.group('id'),
2538 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2540 # Look for AdobeTVVideo embeds
2542 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2544 if mobj is not None:
2545 return self.url_result(
2546 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2549 # Look for Vine embeds
2551 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2553 if mobj is not None:
2554 return self.url_result(
2555 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2557 # Look for VODPlatform embeds
2559 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2561 if mobj is not None:
2562 return self.url_result(
2563 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2565 # Look for Mangomolo embeds
2567 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2569 video\?.*?\bid=(?P<video_id>\d+)|
2570 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2571 ).+?)\1''', webpage)
2572 if mobj is not None:
2574 '_type': 'url_transparent',
2575 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2576 'title': video_title,
2577 'description': video_description,
2578 'thumbnail': video_thumbnail,
2579 'uploader': video_uploader,
2581 video_id = mobj.group('video_id')
2584 'ie_key': 'MangomoloVideo',
2589 'ie_key': 'MangomoloLive',
2590 'id': mobj.group('channel_id'),
2594 # Look for Instagram embeds
2595 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2596 if instagram_embed_url is not None:
2597 return self.url_result(
2598 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2600 # Look for LiveLeak embeds
2601 liveleak_url = LiveLeakIE._extract_url(webpage)
2603 return self.url_result(liveleak_url, 'LiveLeak')
2605 # Look for 3Q SDN embeds
2606 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2609 '_type': 'url_transparent',
2610 'ie_key': ThreeQSDNIE.ie_key(),
2611 'url': self._proto_relative_url(threeqsdn_url),
2612 'title': video_title,
2613 'description': video_description,
2614 'thumbnail': video_thumbnail,
2615 'uploader': video_uploader,
2618 # Look for VBOX7 embeds
2619 vbox7_url = Vbox7IE._extract_url(webpage)
2621 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2623 # Look for DBTV embeds
2624 dbtv_urls = DBTVIE._extract_urls(webpage)
2626 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2628 # Look for Videa embeds
2629 videa_urls = VideaIE._extract_urls(webpage)
2631 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2633 # Look for 20 minuten embeds
2634 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2636 return self.playlist_from_matches(
2637 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2639 # Look for Openload embeds
2640 openload_urls = OpenloadIE._extract_urls(webpage)
2642 return self.playlist_from_matches(
2643 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2645 # Look for VideoPress embeds
2646 videopress_urls = VideoPressIE._extract_urls(webpage)
2648 return self.playlist_from_matches(
2649 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2651 # Look for Rutube embeds
2652 rutube_urls = RutubeIE._extract_urls(webpage)
2654 return self.playlist_from_matches(
2655 rutube_urls, ie=RutubeIE.ie_key())
2657 # Looking for http://schema.org/VideoObject
2658 json_ld = self._search_json_ld(
2659 webpage, video_id, default={}, expected_type='VideoObject')
2660 if json_ld.get('url'):
2662 'title': video_title or info_dict['title'],
2663 'description': video_description,
2664 'thumbnail': video_thumbnail,
2665 'age_limit': age_limit
2667 info_dict.update(json_ld)
2670 # Look for HTML5 media
2671 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2673 for entry in entries:
2676 'title': video_title,
2678 self._sort_formats(entry['formats'])
2679 return self.playlist_result(entries)
2681 jwplayer_data = self._find_jwplayer_data(
2682 webpage, video_id, transform_source=js_to_json)
2684 info = self._parse_jwplayer_data(
2685 jwplayer_data, video_id, require_title=False, base_url=url)
2686 if not info.get('title'):
2687 info['title'] = video_title
2690 def check_video(vurl):
2691 if YoutubeIE.suitable(vurl):
2693 if RtmpIE.suitable(vurl):
2695 vpath = compat_urlparse.urlparse(vurl).path
2696 vext = determine_ext(vpath)
2697 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2699 def filter_video(urls):
2700 return list(filter(check_video, urls))
2702 # Start with something easy: JW Player in SWFObject
2703 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2705 # Look for gorilla-vid style embedding
2706 found = filter_video(re.findall(r'''(?sx)
2710 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2713 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2715 # Broaden the search a little bit
2716 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2718 # Broaden the findall a little bit: JWPlayer JS loader
2719 found = filter_video(re.findall(
2720 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2723 found = filter_video(re.findall(r'''(?xs)
2724 flowplayer\("[^"]+",\s*
2726 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2727 ["']?url["']?\s*:\s*["']([^"']+)["']
2732 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2734 # Try to find twitter cards info
2735 # twitter:player:stream should be checked before twitter:player since
2736 # it is expected to contain a raw stream (see
2737 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2738 found = filter_video(re.findall(
2739 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2741 # We look for Open Graph info:
2742 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2743 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2744 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2745 if m_video_type is not None:
2746 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2748 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2750 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2751 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2754 # Look also in Refresh HTTP header
2755 refresh_header = head_response.headers.get('Refresh')
2757 # In python 2 response HTTP headers are bytestrings
2758 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2759 refresh_header = refresh_header.decode('iso-8859-1')
2760 found = re.search(REDIRECT_REGEX, refresh_header)
2762 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2764 self.report_following_redirect(new_url)
2773 # twitter:player is a https URL to iframe player that may or may not
2774 # be supported by youtube-dl thus this is checked the very last (see
2775 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2776 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2778 return self.url_result(embed_url)
2781 raise UnsupportedError(url)
2784 for video_url in orderedSet(found):
2785 video_url = unescapeHTML(video_url)
2786 video_url = video_url.replace('\\/', '/')
2787 video_url = compat_urlparse.urljoin(url, video_url)
2788 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2790 # Sometimes, jwplayer extraction will result in a YouTube URL
2791 if YoutubeIE.suitable(video_url):
2792 entries.append(self.url_result(video_url, 'Youtube'))
2795 # here's a fun little line of code for you:
2796 video_id = os.path.splitext(video_id)[0]
2800 'uploader': video_uploader,
2801 'title': video_title,
2802 'age_limit': age_limit,
2805 if RtmpIE.suitable(video_url):
2806 entry_info_dict.update({
2807 '_type': 'url_transparent',
2808 'ie_key': RtmpIE.ie_key(),
2811 entries.append(entry_info_dict)
2814 ext = determine_ext(video_url)
2816 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2818 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2820 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2822 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2824 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2825 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2826 # Just matching .ism/manifest is not enough to be reliably sure
2827 # whether it's actually an ISM manifest or some other streaming
2828 # manifest since there are various streaming URL formats
2829 # possible (see [1]) as well as some other shenanigans like
2830 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2832 # Thus the most reasonable way to solve this is to delegate
2833 # to generic extractor in order to look into the contents of
2834 # the manifest itself.
2835 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2836 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2837 entry_info_dict = self.url_result(
2838 smuggle_url(video_url, {'to_generic': True}),
2841 entry_info_dict['url'] = video_url
2843 if entry_info_dict.get('formats'):
2844 self._sort_formats(entry_info_dict['formats'])
2846 entries.append(entry_info_dict)
2848 if len(entries) == 1:
2851 for num, e in enumerate(entries, start=1):
2852 # 'url' results don't have a title
2853 if e.get('title') is not None:
2854 e['title'] = '%s (%d)' % (e['title'], num)
2856 '_type': 'playlist',