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
89 from .anvato import AnvatoIE
90 from .washingtonpost import WashingtonPostIE
91 from .wistia import WistiaIE
94 class GenericIE(InfoExtractor):
95 IE_DESC = 'Generic downloader that works on some sites'
99 # Direct link to a video
101 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
102 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
107 'upload_date': '20100513',
110 # Direct link to media delivered compressed (until Accept-Encoding is *)
112 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
113 'md5': '128c42e68b13950268b648275386fc74',
115 'id': 'FictionJunction-Parallel_Hearts',
117 'title': 'FictionJunction-Parallel_Hearts',
118 'upload_date': '20140522',
120 'expected_warnings': [
121 'URL could be a direct video link, returning it as such.'
123 'skip': 'URL invalid',
125 # Direct download with broken HEAD
127 'url': 'http://ai-radio.org:8000/radio.opus',
134 'skip_download': True, # infinite live stream
136 'expected_warnings': [
137 r'501.*Not Implemented',
141 # Direct link with incorrect MIME type
143 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
144 'md5': '4ccbebe5f36706d85221f204d7eb5913',
146 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
147 'id': '5_Lennart_Poettering_-_Systemd',
149 'title': '5_Lennart_Poettering_-_Systemd',
150 'upload_date': '20141120',
152 'expected_warnings': [
153 'URL could be a direct video link, returning it as such.'
158 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
160 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
161 'title': 'Zero Punctuation',
162 'description': 're:.*groundbreaking video review series.*'
164 'playlist_mincount': 11,
166 # RSS feed with enclosure
168 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
170 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
172 'upload_date': '20150228',
173 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
176 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
178 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
182 'title': 'Automatics, robotics and biocybernetics',
183 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
184 'upload_date': '20130627',
185 'formats': 'mincount:16',
186 'subtitles': 'mincount:1',
189 'force_generic_extractor': True,
190 'skip_download': True,
193 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
195 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
200 'formats': 'mincount:1',
203 'skip_download': True,
206 # SMIL from https://www.restudy.dk/video/play/id/1637
208 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
212 'title': 'video_1637',
213 'formats': 'mincount:3',
216 'skip_download': True,
219 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
221 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
223 'id': 'smil-service',
225 'title': 'smil-service',
226 'formats': 'mincount:1',
229 'skip_download': True,
232 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
234 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
238 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
239 'formats': 'mincount:3',
242 'skip_download': True,
245 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
247 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
249 'id': 'mZlp2ctYIUEB',
251 'title': 'Tikibad ontruimd wegens brand',
252 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
253 'thumbnail': r're:^https?://.*\.jpg$',
257 'skip_download': True,
260 # MPD from http://dash-mse-test.appspot.com/media.html
262 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
263 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
265 'id': 'car-20120827-manifest',
267 'title': 'car-20120827-manifest',
268 'formats': 'mincount:9',
269 'upload_date': '20130904',
272 'format': 'bestvideo',
275 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
277 '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',
282 'formats': 'mincount:8',
286 'skip_download': True,
288 'skip': 'video gone',
290 # m3u8 served with Content-Type: text/plain
292 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
297 'upload_date': '20140720',
298 'formats': 'mincount:11',
302 'skip_download': True,
304 'skip': 'video gone',
308 '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',
312 'upload_date': '20130224',
313 'uploader_id': 'TheVerge',
314 'description': r're:^Chris Ziegler takes a look at the\.*',
315 'uploader': 'The Verge',
316 'title': 'First Firefox OS phones side-by-side',
319 'skip_download': False,
323 # redirect in Refresh HTTP header
324 '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',
328 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
329 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
330 'upload_date': '20150917',
331 'uploader_id': 'brtvofficial',
332 'uploader': 'Boiler Room',
335 'skip_download': False,
339 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
340 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
342 'id': '13601338388002',
344 'uploader': 'www.hodiho.fr',
345 'title': 'R\u00e9gis plante sa Jeep',
348 # bandcamp page with custom domain
350 'add_ie': ['Bandcamp'],
351 'url': 'http://bronyrock.com/track/the-pony-mash',
355 'title': 'The Pony Mash',
356 'uploader': 'M_Pallante',
358 'skip': 'There is a limit of 200 free downloads / month for the test song',
361 # embedded brightcove video
362 # it also tests brightcove videos that need to set the 'Referer'
363 # in the http requests
364 'add_ie': ['BrightcoveLegacy'],
365 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
367 'id': '2765128793001',
369 'title': 'Le cours de bourse : l’analyse technique',
370 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
371 'uploader': 'BFM BUSINESS',
374 'skip_download': True,
378 # embedded with itemprop embedURL and video id spelled as `idVideo`
379 'add_id': ['BrightcoveLegacy'],
380 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
382 'id': '5255628253001',
384 'title': 'md5:37c519b1128915607601e75a87995fc0',
385 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
386 'uploader': 'BFM BUSINESS',
387 'uploader_id': '876450612001',
388 'timestamp': 1482255315,
389 'upload_date': '20161220',
392 'skip_download': True,
396 # https://github.com/rg3/youtube-dl/issues/2253
397 'url': 'http://bcove.me/i6nfkrc3',
398 'md5': '0ba9446db037002366bab3b3eb30c88c',
400 'id': '3101154703001',
402 'title': 'Still no power',
403 'uploader': 'thestar.com',
404 '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.',
406 'add_ie': ['BrightcoveLegacy'],
407 'skip': 'video gone',
410 'url': 'http://www.championat.com/video/football/v/87/87499.html',
411 'md5': 'fb973ecf6e4a78a67453647444222983',
413 'id': '3414141473001',
415 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
416 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
417 'uploader': 'Championat',
421 # https://github.com/rg3/youtube-dl/issues/3541
422 'add_ie': ['BrightcoveLegacy'],
423 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
425 'id': '3866516442001',
427 'title': 'Leer mij vrouwen kennen: Aflevering 1',
428 'description': 'Leer mij vrouwen kennen: Aflevering 1',
429 'uploader': 'SBS Broadcasting',
431 'skip': 'Restricted to Netherlands',
433 'skip_download': True, # m3u8 download
437 # Brightcove video in <iframe>
438 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
439 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
441 'id': '5360463607001',
443 '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',
444 '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。',
445 'uploader': 'United Nations',
446 'uploader_id': '1362235914001',
447 'timestamp': 1489593889,
448 'upload_date': '20170315',
450 'add_ie': ['BrightcoveLegacy'],
453 # Brightcove with alternative playerID key
454 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
456 'id': 'nmeth.2062_SV1',
457 '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',
461 'id': '2228375078001',
463 'title': 'nmeth.2062-sv1',
464 'description': 'nmeth.2062-sv1',
465 'timestamp': 1363357591,
466 'upload_date': '20130315',
467 'uploader': 'Nature Publishing Group',
468 'uploader_id': '1964492299001',
473 # Brightcove with UUID in videoPlayer
474 'url': 'http://www8.hp.com/cn/zh/home.html',
476 'id': '5255815316001',
478 'title': 'Sprocket Video - China',
479 'description': 'Sprocket Video - China',
480 'uploader': 'HP-Video Gallery',
481 'timestamp': 1482263210,
482 'upload_date': '20161220',
483 'uploader_id': '1107601872001',
486 'skip_download': True, # m3u8 download
488 'skip': 'video rotates...weekly?',
491 # Brightcove:new type [2].
492 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
493 'md5': '2b35148fcf48da41c9fb4591650784f3',
495 'id': '5348741021001',
497 'upload_date': '20170306',
498 'uploader_id': '4191638492001',
499 'timestamp': 1488769918,
500 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
505 # Alternative brightcove <video> attributes
506 '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/',
508 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
509 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
512 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
514 'id': '5311302538001',
516 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
517 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
518 'timestamp': 1486321708,
519 'upload_date': '20170205',
520 'uploader_id': '800000640001',
522 'only_matching': True,
526 # Brightcove with UUID in videoPlayer
527 'url': 'http://www8.hp.com/cn/zh/home.html',
529 'id': '5255815316001',
531 'title': 'Sprocket Video - China',
532 'description': 'Sprocket Video - China',
533 'uploader': 'HP-Video Gallery',
534 'timestamp': 1482263210,
535 'upload_date': '20161220',
536 'uploader_id': '1107601872001',
539 'skip_download': True, # m3u8 download
544 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
545 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
547 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
549 'title': '2cc213299525360.mov', # that's what we get
552 'add_ie': ['Ooyala'],
555 # ooyala video embedded with http://player.ooyala.com/iframe.js
556 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
558 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
560 'title': '"Steve Jobs: Man in the Machine" trailer',
561 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
565 'skip_download': True,
567 'skip': 'movie expired',
571 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
575 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
576 'upload_date': '20140225',
577 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
578 'uploader': 'Tested',
579 'uploader_id': 'testedcom',
581 # No need to test YoutubeIE here
583 'skip_download': True,
588 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
592 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
593 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
595 # HEAD requests lead to endless 301, while GET is OK
596 'expected_warnings': ['301'],
600 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
604 'title': 'Охотское море стало целиком российским',
605 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
609 'skip_download': True,
614 '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/',
618 'title': 'Дошкольное воспитание',
623 'url': 'http://www.vestifinance.ru/articles/25753',
626 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
631 'title': 'Госзаказ. День 3',
637 'title': 'Госзаказ. День 2',
643 'title': 'Госзаказ. День 1',
649 'skip_download': True,
654 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
656 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
658 'title': 'Ужастики, русский трейлер (2015)',
659 'thumbnail': r're:^https?://.*\.jpg$',
665 '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',
668 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
670 'playlist_mincount': 7,
671 # This forum does not allow <iframe> syntaxes anymore
672 # Now HTML tags are displayed as-is
673 'skip': 'No videos on this page',
677 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
678 'md5': '65fdff94098e4a607385a60c5177c638',
682 'title': 'Hidden miracles of the natural world',
683 'uploader': 'Louie Schwartzberg',
684 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
687 # nowvideo embed hidden behind percent encoding
689 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
690 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
692 'id': '06e53103ca9aa',
694 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
695 'description': 'No description',
700 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
701 'md5': '7653032cbb25bf6c80d80f217055fa43',
703 'id': '048195-004_PLUS7-F',
706 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
707 'upload_date': '20140320',
710 'skip_download': 'Requires rtmpdump'
712 'skip': 'video gone',
716 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
720 'title': 'Alcaline, le concert avec Calogero',
721 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
722 'upload_date': '20150226',
723 'timestamp': 1424989860,
728 'skip_download': True,
730 'expected_warnings': [
736 'url': 'http://www.wired.com/2014/04/honda-asimo/',
737 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
739 'id': '53501be369702d3275860000',
741 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
746 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
747 'md5': '441aeeb82eb72c422c7f14ec533999cd',
749 'id': 'k2mm4bCdJ6CQ2i7c8o2',
751 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
752 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
754 'uploader_id': 'xgditw',
755 'upload_date': '20140425',
756 'timestamp': 1398441542,
758 'add_ie': ['Dailymotion'],
762 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
766 'title': 'The NBL Auction 2014',
767 'uploader': 'BADMINTON England',
768 'uploader_id': 'BADMINTONEvents',
769 'upload_date': '20140603',
770 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
772 'add_ie': ['Youtube'],
774 'skip_download': True,
779 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
780 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
782 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
784 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
785 'description': 'Two valets share their love for movie star Liam Neesons.',
786 'timestamp': 1349922600,
787 'upload_date': '20121011',
790 # YouTube embed via <data-embed-url="">
792 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
796 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
797 'uploader': 'Gameloft',
798 'uploader_id': 'gameloft',
799 'upload_date': '20140828',
800 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
803 'skip_download': True,
806 # YouTube <object> embed
808 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
809 'md5': '516718101ec834f74318df76259fb3cc',
813 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
814 'upload_date': '20080526',
815 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
816 'uploader': 'Christopher Sykes',
817 'uploader_id': 'ChristopherJSykes',
819 'add_ie': ['Youtube'],
823 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
825 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
827 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
828 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
833 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
835 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
836 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
842 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
847 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
848 'md5': '9d65602bf31c6e20014319c7d07fba27',
850 'id': '5123ea6d5e5a7',
853 'uploader': 'www.handjobhub.com',
854 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
857 # Multiple brightcove videos
858 # https://github.com/rg3/youtube-dl/issues/2283
860 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
862 'id': 'always-never',
863 'title': 'Always / Never - The New Yorker',
867 'extract_flat': False,
868 'skip_download': True,
873 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
874 'md5': '96f09a37e44da40dd083e12d9a683327',
878 'title': 'Ump changes call to ball',
879 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
881 'timestamp': 1401537900,
882 'upload_date': '20140531',
883 'thumbnail': r're:^https?://.*\.jpg$',
888 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
889 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
893 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
894 'description': 'a Paywall Videos video from Remilon',
896 'uploader': 'study.com',
897 'timestamp': 1459678540,
898 'upload_date': '20160403',
899 'filesize': 24687186,
903 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
904 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
908 'title': 'Conversation about Hexagonal Rails Part 1',
909 'description': 'a Martin Fowler video from ThoughtWorks',
911 'uploader': 'thoughtworks.wistia.com',
912 'timestamp': 1401832161,
913 'upload_date': '20140603',
916 # Wistia standard embed (async)
918 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
922 'title': 'Drip Brennan Dunn Workshop',
923 'description': 'a JV Webinars video from getdrip-1',
925 'timestamp': 1463607249,
926 'upload_date': '20160518',
929 'skip_download': True,
934 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
938 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
939 'uploader': 'Sophos Security',
940 'title': 'Chet Chat 171 - Oct 29, 2014',
941 'upload_date': '20141029',
944 # Soundcloud multiple embeds
946 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
949 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
951 'playlist_mincount': 7,
953 # TuneIn station embed
955 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
960 'location': 'Paris, France',
965 'skip_download': True,
970 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
974 'upload_date': '20141112',
975 'title': 'Rosetta #CometLanding webcast HL 10',
978 # Another Livestream embed, without 'new.' in URL
980 'url': 'https://www.freespeech.org/',
984 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
988 'skip_download': True,
993 'url': 'https://skiplagged.com/',
996 'title': 'Skiplagged: The smart way to find cheap flights',
998 'playlist_mincount': 1,
999 'add_ie': ['Youtube'],
1003 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1007 'upload_date': '20141126',
1008 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1013 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1015 'id': '730m_DandD_1901_512k',
1017 'uploader': 'www.abc.net.au',
1018 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1021 # embedded viddler video
1023 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1027 'uploader': 'deadspin',
1028 'title': 'WALL-TO-GORTAT',
1029 'timestamp': 1422285291,
1030 'upload_date': '20150126',
1032 'add_ie': ['Viddler'],
1036 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1040 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1041 'description': 'md5:601cb790edd05908957dae8aaa866465',
1042 'upload_date': '20150220',
1044 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1048 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1050 'id': 'Mrj4DVp2zeA',
1052 'upload_date': '20150212',
1053 'uploader': 'The National Archives UK',
1054 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1055 'uploader_id': 'NationalArchives08',
1056 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1061 'url': 'http://www.suffolk.edu/sjc/',
1065 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1066 'uploader': 'www.suffolk.edu',
1069 'skip_download': True,
1074 'url': 'http://www.indiedb.com/games/king-machine/videos',
1078 'title': 'king machine trailer 1',
1079 'thumbnail': r're:^https?://.*\.jpg$',
1083 # JWPlayer config passed as variable
1084 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1088 'title': 'ARIELE | Tube Cup',
1089 'uploader': 'www.txxx.com',
1093 'skip_download': True,
1098 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1099 'playlist_mincount': 5,
1101 'id': 'aanslagen-kopenhagen',
1102 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1107 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1111 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1114 # Kaltura embed (different embed code)
1116 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1120 'upload_date': '20150127',
1121 'uploader_id': 'PremierMedia',
1123 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1126 # Kaltura embed with single quotes
1128 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1133 'timestamp': 1355743100,
1134 'upload_date': '20121217',
1135 'uploader_id': 'batchUser',
1137 'add_ie': ['Kaltura'],
1140 # Kaltura embedded via quoted entry_id
1141 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1145 'title': '06_matthew_brender_raj_dutt',
1146 'timestamp': 1466638791,
1147 'upload_date': '20160622',
1149 'add_ie': ['Kaltura'],
1150 'expected_warnings': [
1151 'Could not send HEAD request'
1154 'skip_download': True,
1158 # Kaltura embedded, some fileExt broken (#11480)
1159 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1163 'title': 'Our "Standard Models" of particle physics and cosmology',
1164 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1165 'timestamp': 1321158993,
1166 'upload_date': '20111113',
1167 'uploader_id': 'kps1',
1169 'add_ie': ['Kaltura'],
1172 # Kaltura iframe embed
1173 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1174 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1178 'title': 'I. M. Pei: A Centennial Celebration',
1179 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1180 'upload_date': '20170403',
1181 'uploader_id': 'batchUser',
1182 'timestamp': 1491232186,
1184 'add_ie': ['Kaltura'],
1186 # Eagle.Platform embed (generic URL)
1188 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1189 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1193 'title': 'Навальный вышел на свободу',
1194 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1195 'thumbnail': r're:^https?://.*\.jpg$',
1201 # ClipYou (Eagle.Platform) embed (custom URL)
1203 'url': 'http://muz-tv.ru/play/7129/',
1204 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1208 'title': "'O Sole Mio",
1209 'thumbnail': r're:^https?://.*\.jpg$',
1216 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1220 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1221 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1222 'thumbnail': r're:^https?://.*\.jpg$',
1229 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1233 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1234 'thumbnail': r're:^https?://.*\.png$',
1240 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1241 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1245 'title': 'Facebook Creates "On This Day" | Crunch Report',
1250 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1254 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1259 # Crooks and Liars embed
1261 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1265 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1266 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1267 'timestamp': 1428207000,
1268 'upload_date': '20150405',
1269 'uploader': 'Heather',
1272 # Crooks and Liars external embed
1274 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1276 'id': 'MTE3MjUtMzQ2MzA',
1278 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1279 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1280 'timestamp': 1265032391,
1281 'upload_date': '20100201',
1282 'uploader': 'Heather',
1285 # NBC Sports vplayer embed
1287 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1289 'id': 'ln7x1qSThw4k',
1291 'title': "PFT Live: New leader in the 'new-look' defense",
1292 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1293 'uploader': 'NBCU-SPORTS',
1294 'upload_date': '20140107',
1295 'timestamp': 1389118457,
1300 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1301 'md5': '1aa589c675898ae6d37a17913cf68d66',
1303 'id': '701714499682',
1305 'title': 'PREVIEW: On Assignment: David Letterman',
1306 '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.',
1311 'url': 'https://video.udn.com/news/300346',
1312 'md5': 'fd2060e988c326991037b9aff9df21a6',
1316 'title': '中一中男師變性 全校師生力挺',
1317 'thumbnail': r're:^https?://.*\.jpg$',
1321 'skip_download': True,
1326 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1328 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1330 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1331 'title': 'This is what separates the Excel masters from the wannabes',
1332 'duration': 191.933,
1336 'skip_download': True,
1339 # Brightcove URL in single quotes
1341 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1342 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1344 'id': '4255764656001',
1346 'title': 'SN Presents: Russell Martin, World Citizen',
1347 '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.',
1348 'uploader': 'Rogers Sportsnet',
1349 'uploader_id': '1704050871',
1350 'upload_date': '20150525',
1351 'timestamp': 1432570283,
1354 # Dailymotion Cloud video
1356 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1357 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1361 'title': 'Sauvons les abeilles ! - Le débat',
1362 'description': 'md5:d9082128b1c5277987825d684939ca26',
1363 'thumbnail': r're:^https?://.*\.jpe?g$',
1364 'timestamp': 1434970506,
1365 'upload_date': '20150622',
1366 'uploader': 'Public Sénat',
1367 'uploader_id': 'xa9gza',
1370 # OnionStudios embed
1372 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1376 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1377 'thumbnail': r're:^https?://.*\.jpe?g$',
1378 'uploader': 'ClickHole',
1379 'uploader_id': 'clickhole',
1384 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1386 'id': '74849a00-85a9-11e1-9660-123139220831',
1388 'title': '#whilewewatch',
1391 # AdobeTVVideo embed
1393 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1394 'md5': '43662b577c018ad707a63766462b1e87',
1398 'title': 'New experience with Acrobat DC',
1399 'description': 'New experience with Acrobat DC',
1400 'duration': 248.667,
1403 # BrightcoveInPageEmbed embed
1405 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1407 'id': '4238694884001',
1409 'title': 'Tabletop: Dread, Last Thoughts',
1410 'description': 'Tabletop: Dread, Last Thoughts',
1414 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1415 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1417 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1419 'id': '4785848093001',
1421 'title': 'The Cardinal Pell Interview',
1422 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1423 'uploader': 'GlobeCast Australia - GlobeStream',
1424 'uploader_id': '2733773828001',
1425 'upload_date': '20160304',
1426 'timestamp': 1457083087,
1430 'skip_download': True,
1434 # Brightcove embed with whitespace around attribute names
1435 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1437 'id': '3167554373001',
1439 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1440 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1441 'uploader_id': '1079349493',
1442 'upload_date': '20140207',
1443 'timestamp': 1391810548,
1446 'skip_download': True,
1449 # Another form of arte.tv embed
1451 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1452 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1454 'id': '030273-562_PLUS7-F',
1456 'title': 'ARTE Reportage - Nulle part, en France',
1457 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1458 'upload_date': '20160409',
1463 'url': 'http://www.wykop.pl/link/3088787/',
1464 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1466 'id': '874_1459135191',
1468 'title': 'Man shows poor quality of new apartment building',
1469 'description': 'The wall is like a sand pile.',
1470 'uploader': 'Lake8737',
1473 # Duplicated embedded video URLs
1475 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1477 'id': '149298443_480_16c25b74_2',
1479 'title': 'vs. Blue Orange Spring Game',
1480 'uploader': 'www.hudl.com',
1483 # twitter:player:stream embed
1485 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1489 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1490 'uploader': 'www.rtl.be',
1494 'skip_download': True,
1497 # twitter:player embed
1499 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1500 'md5': 'a3e0df96369831de324f0778e126653c',
1502 'id': '4909620399001',
1504 'title': 'What Do Black Holes Sound Like?',
1505 'description': 'what do black holes sound like',
1506 'upload_date': '20160524',
1507 'uploader_id': '29913724001',
1508 'timestamp': 1464107587,
1509 'uploader': 'TheAtlantic',
1511 'add_ie': ['BrightcoveLegacy'],
1513 # Facebook <iframe> embed
1515 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1516 'md5': 'fbcde74f534176ecb015849146dd3aee',
1518 'id': '599637780109885',
1520 'title': 'Facebook video #599637780109885',
1523 # Facebook API embed
1525 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1526 'md5': 'a47372ee61b39a7b90287094d447d94e',
1528 'id': '10153467542406923',
1530 'title': 'Facebook video #10153467542406923',
1533 # Wordpress "YouTube Video Importer" plugin
1535 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1536 'md5': 'd16797741b560b485194eddda8121b48',
1538 'id': 'HNTXWDXV9Is',
1540 'title': 'Blue Devils Drumline Stanford lot 2016',
1541 'upload_date': '20160627',
1542 'uploader_id': 'GENOCIDE8GENERAL10',
1543 'uploader': 'cylus cyrus',
1547 # video stored on custom kaltura server
1548 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1549 'md5': '537617d06e64dfed891fa1593c4b30cc',
1553 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1554 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1555 'uploader_id': 'videos.expansion@el-mundo.net',
1556 'upload_date': '20150429',
1557 'timestamp': 1430303472,
1559 'add_ie': ['Kaltura'],
1562 # Non-standard Vimeo embed
1563 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1564 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1568 'title': 'Understanding the web - Teaser',
1569 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1570 'upload_date': '20151214',
1571 'uploader': 'OpenClassrooms',
1572 'uploader_id': 'openclassrooms',
1574 'add_ie': ['Vimeo'],
1577 # generic vimeo embed that requires original URL passed as Referer
1578 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1579 'only_matching': True,
1582 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1583 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1585 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1587 'title': 'Big Buck Bunny',
1588 'description': 'Royalty free test video',
1589 'timestamp': 1432816365,
1590 'upload_date': '20150528',
1594 'skip_download': True,
1596 'add_ie': [ArkenaIE.ie_key()],
1599 '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/',
1603 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1606 'skip_download': True,
1608 'add_ie': [Vbox7IE.ie_key()],
1612 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1615 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1617 'playlist_mincount': 3,
1621 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1623 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1624 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1626 'playlist_mincount': 2,
1630 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1634 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1635 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1638 'skip_download': True,
1640 'add_ie': [TwentyMinutenIE.ie_key()],
1644 'url': 'https://en.support.wordpress.com/videopress/',
1648 'title': 'IMG_5786',
1649 'timestamp': 1435711927,
1650 'upload_date': '20150701',
1653 'skip_download': True,
1655 'add_ie': [VideoPressIE.ie_key()],
1659 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1661 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1663 'title': 'Магаззино: Казань 2',
1664 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1665 'uploader': 'Магаззино',
1666 'upload_date': '20170228',
1667 'uploader_id': '996642',
1670 'skip_download': True,
1672 'add_ie': [RutubeIE.ie_key()],
1675 # ThePlatform embedded with whitespaces in URLs
1676 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1677 'only_matching': True,
1680 # Senate ISVP iframe https
1681 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1682 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1684 'id': 'govtaff020316',
1686 'title': 'Integrated Senate Video Player',
1688 'add_ie': [SenateISVPIE.ie_key()],
1691 # Limelight embeds (1 channel embed + 4 media embeds)
1692 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1694 'id': 'FacilitatorTraining2017',
1695 'title': 'Facilitator Training 2017',
1697 'playlist_mincount': 5,
1700 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1702 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1703 'title': 'Standoff with Walnut Creek murder suspect ends',
1704 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1706 'playlist_mincount': 4,
1709 # WashingtonPost embed
1710 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1712 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1714 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1715 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1716 'timestamp': 1455216756,
1717 'uploader': 'The Washington Post',
1718 'upload_date': '20160211',
1720 'add_ie': [WashingtonPostIE.ie_key()],
1723 # # TODO: find another test
1724 # # http://schema.org/VideoObject
1725 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1726 # 'md5': '888dcf08b7ea671381f00fab74692755',
1728 # 'id': 'nyvTSJMKId',
1730 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1731 # 'description': '#love for cats.',
1732 # 'timestamp': 1461244995,
1733 # 'upload_date': '20160421',
1736 # 'force_generic_extractor': True,
1741 def report_following_redirect(self, new_url):
1742 """Report information extraction."""
1743 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1745 def _extract_rss(self, url, video_id, doc):
1746 playlist_title = doc.find('./channel/title').text
1747 playlist_desc_el = doc.find('./channel/description')
1748 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1751 for it in doc.findall('./channel/item'):
1752 next_url = xpath_text(it, 'link', fatal=False)
1754 enclosure_nodes = it.findall('./enclosure')
1755 for e in enclosure_nodes:
1756 next_url = e.attrib.get('url')
1764 '_type': 'url_transparent',
1766 'title': it.find('title').text,
1770 '_type': 'playlist',
1772 'title': playlist_title,
1773 'description': playlist_desc,
1777 def _extract_camtasia(self, url, video_id, webpage):
1778 """ Returns None if no camtasia video can be found. """
1780 camtasia_cfg = self._search_regex(
1781 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1782 webpage, 'camtasia configuration file', default=None)
1783 if camtasia_cfg is None:
1786 title = self._html_search_meta('DC.title', webpage, fatal=True)
1788 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1789 camtasia_cfg = self._download_xml(
1790 camtasia_url, video_id,
1791 note='Downloading camtasia configuration',
1792 errnote='Failed to download camtasia configuration')
1793 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1796 for n in fileset_node.getchildren():
1797 url_n = n.find('./uri')
1802 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1803 'title': '%s - %s' % (title, n.tag),
1804 'url': compat_urlparse.urljoin(url, url_n.text),
1805 'duration': float_or_none(n.find('./duration').text),
1809 '_type': 'playlist',
1814 def _real_extract(self, url):
1815 if url.startswith('//'):
1818 'url': self.http_scheme() + url,
1821 parsed_url = compat_urlparse.urlparse(url)
1822 if not parsed_url.scheme:
1823 default_search = self._downloader.params.get('default_search')
1824 if default_search is None:
1825 default_search = 'fixup_error'
1827 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1829 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1830 return self.url_result('http://' + url)
1831 elif default_search != 'fixup_error':
1832 if default_search == 'auto_warning':
1833 if re.match(r'^(?:url|URL)$', url):
1834 raise ExtractorError(
1835 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1838 self._downloader.report_warning(
1839 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1840 return self.url_result('ytsearch:' + url)
1842 if default_search in ('error', 'fixup_error'):
1843 raise ExtractorError(
1844 '%r is not a valid URL. '
1845 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1846 % (url, url), expected=True)
1848 if ':' not in default_search:
1849 default_search += ':'
1850 return self.url_result(default_search + url)
1852 url, smuggled_data = unsmuggle_url(url)
1853 force_videoid = None
1854 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1855 if smuggled_data and 'force_videoid' in smuggled_data:
1856 force_videoid = smuggled_data['force_videoid']
1857 video_id = force_videoid
1859 video_id = self._generic_id(url)
1861 self.to_screen('%s: Requesting header' % video_id)
1863 head_req = HEADRequest(url)
1864 head_response = self._request_webpage(
1866 note=False, errnote='Could not send HEAD request to %s' % url,
1869 if head_response is not False:
1870 # Check for redirect
1871 new_url = head_response.geturl()
1873 self.report_following_redirect(new_url)
1875 new_url = smuggle_url(
1876 new_url, {'force_videoid': force_videoid})
1877 return self.url_result(new_url)
1879 full_response = None
1880 if head_response is False:
1881 request = sanitized_Request(url)
1882 request.add_header('Accept-Encoding', '*')
1883 full_response = self._request_webpage(request, video_id)
1884 head_response = full_response
1888 'title': self._generic_title(url),
1889 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1892 # Check for direct link to a video
1893 content_type = head_response.headers.get('Content-Type', '').lower()
1894 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1896 format_id = m.group('format_id')
1897 if format_id.endswith('mpegurl'):
1898 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1899 elif format_id == 'f4m':
1900 formats = self._extract_f4m_formats(url, video_id)
1903 'format_id': m.group('format_id'),
1905 'vcodec': 'none' if m.group('type') == 'audio' else None
1907 info_dict['direct'] = True
1908 self._sort_formats(formats)
1909 info_dict['formats'] = formats
1912 if not self._downloader.params.get('test', False) and not is_intentional:
1913 force = self._downloader.params.get('force_generic_extractor', False)
1914 self._downloader.report_warning(
1915 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1917 if not full_response:
1918 request = sanitized_Request(url)
1919 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1920 # making it impossible to download only chunk of the file (yet we need only 512kB to
1921 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1922 # that will always result in downloading the whole file that is not desirable.
1923 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1924 # to accept raw bytes and being able to download only a chunk.
1925 # It may probably better to solve this by checking Content-Type for application/octet-stream
1926 # after HEAD request finishes, but not sure if we can rely on this.
1927 request.add_header('Accept-Encoding', '*')
1928 full_response = self._request_webpage(request, video_id)
1930 first_bytes = full_response.read(512)
1932 # Is it an M3U playlist?
1933 if first_bytes.startswith(b'#EXTM3U'):
1934 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1935 self._sort_formats(info_dict['formats'])
1938 # Maybe it's a direct link to a video?
1939 # Be careful not to download the whole thing!
1940 if not is_html(first_bytes):
1941 self._downloader.report_warning(
1942 'URL could be a direct video link, returning it as such.')
1949 webpage = self._webpage_read_content(
1950 full_response, url, video_id, prefix=first_bytes)
1952 self.report_extraction(video_id)
1954 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1956 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1957 if doc.tag == 'rss':
1958 return self._extract_rss(url, video_id, doc)
1959 elif doc.tag == 'SmoothStreamingMedia':
1960 info_dict['formats'] = self._parse_ism_formats(doc, url)
1961 self._sort_formats(info_dict['formats'])
1963 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1964 smil = self._parse_smil(doc, url, video_id)
1965 self._sort_formats(smil['formats'])
1967 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1968 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1969 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1970 info_dict['formats'] = self._parse_mpd_formats(
1972 mpd_base_url=full_response.geturl().rpartition('/')[0],
1974 self._sort_formats(info_dict['formats'])
1976 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1977 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1978 self._sort_formats(info_dict['formats'])
1980 except compat_xml_parse_error:
1983 # Is it a Camtasia project?
1984 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1985 if camtasia_res is not None:
1988 # Sometimes embedded video player is hidden behind percent encoding
1989 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1990 # Unescaping the whole page allows to handle those cases in a generic way
1991 webpage = compat_urllib_parse_unquote(webpage)
1993 # it's tempting to parse this further, but you would
1994 # have to take into account all the variations like
1995 # Video Title - Site Name
1996 # Site Name | Video Title
1997 # Video Title - Tagline | Site Name
1998 # and so on and so forth; it's just not practical
1999 video_title = self._og_search_title(
2000 webpage, default=None) or self._html_search_regex(
2001 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2004 # Try to detect age limit automatically
2005 age_limit = self._rta_search(webpage)
2006 # And then there are the jokers who advertise that they use RTA,
2007 # but actually don't.
2008 AGE_LIMIT_MARKERS = [
2009 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2011 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2014 # video uploader is domain name
2015 video_uploader = self._search_regex(
2016 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2018 video_description = self._og_search_description(webpage, default=None)
2019 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2021 # Look for Brightcove Legacy Studio embeds
2022 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2026 'url': smuggle_url(bc_url, {'Referer': url}),
2027 'ie_key': 'BrightcoveLegacy'
2028 } for bc_url in bc_urls]
2031 '_type': 'playlist',
2032 'title': video_title,
2037 # Look for Brightcove New Studio embeds
2038 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2040 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2042 # Look for ThePlatform embeds
2043 tp_urls = ThePlatformIE._extract_urls(webpage)
2045 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2047 # Look for Vessel embeds
2048 vessel_urls = VesselIE._extract_urls(webpage)
2050 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2052 # Look for embedded rtl.nl player
2053 matches = re.findall(
2054 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2057 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2059 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2061 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2063 vid_me_embed_url = self._search_regex(
2064 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2065 webpage, 'vid.me embed', default=None)
2066 if vid_me_embed_url is not None:
2067 return self.url_result(vid_me_embed_url, 'Vidme')
2069 # Look for embedded YouTube player
2070 matches = re.findall(r'''(?x)
2080 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2084 return self.playlist_from_matches(
2085 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2087 # Look for lazyYT YouTube embed
2088 matches = re.findall(
2089 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2091 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2093 # Look for Wordpress "YouTube Video Importer" plugin
2094 matches = re.findall(r'''(?x)<div[^>]+
2095 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2096 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2098 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2100 matches = DailymotionIE._extract_urls(webpage)
2102 return self.playlist_from_matches(matches, video_id, video_title)
2104 # Look for embedded Dailymotion playlist player (#3822)
2106 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2108 playlists = re.findall(
2109 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2111 return self.playlist_from_matches(
2112 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2114 # Look for embedded Wistia player
2115 wistia_url = WistiaIE._extract_url(webpage)
2118 '_type': 'url_transparent',
2119 'url': self._proto_relative_url(wistia_url),
2120 'ie_key': WistiaIE.ie_key(),
2121 'uploader': video_uploader,
2124 # Look for SVT player
2125 svt_url = SVTIE._extract_url(webpage)
2127 return self.url_result(svt_url, 'SVT')
2129 # Look for Bandcamp pages with custom domain
2130 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2131 if mobj is not None:
2132 burl = unescapeHTML(mobj.group(1))
2133 # Don't set the extractor because it can be a track url or an album
2134 return self.url_result(burl)
2136 # Look for embedded Vevo player
2138 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2139 if mobj is not None:
2140 return self.url_result(mobj.group('url'))
2142 # Look for embedded Viddler player
2144 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2146 if mobj is not None:
2147 return self.url_result(mobj.group('url'))
2149 # Look for NYTimes player
2151 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2153 if mobj is not None:
2154 return self.url_result(mobj.group('url'))
2156 # Look for Libsyn player
2158 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2159 if mobj is not None:
2160 return self.url_result(mobj.group('url'))
2162 # Look for Ooyala videos
2163 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2164 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2165 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2166 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2167 if mobj is not None:
2168 embed_token = self._search_regex(
2169 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2170 webpage, 'ooyala embed token', default=None)
2171 return OoyalaIE._build_url_result(smuggle_url(
2174 'embed_token': embed_token,
2177 # Look for multiple Ooyala embeds on SBN network websites
2178 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2179 if mobj is not None:
2180 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2182 return self.playlist_from_matches(
2183 embeds, video_id, video_title,
2184 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2186 # Look for Aparat videos
2187 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2188 if mobj is not None:
2189 return self.url_result(mobj.group(1), 'Aparat')
2191 # Look for MPORA videos
2192 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2193 if mobj is not None:
2194 return self.url_result(mobj.group(1), 'Mpora')
2196 # Look for embedded NovaMov-based player
2198 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2199 (?P<url>http://(?:(?:embed|www)\.)?
2201 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2202 videoweed\.(?:es|com)|
2203 movshare\.(?:net|sx|ag)|
2204 divxstage\.(?:eu|net|ch|co|at|ag))
2205 /embed\.php.+?)\1''', webpage)
2206 if mobj is not None:
2207 return self.url_result(mobj.group('url'))
2209 # Look for embedded Facebook player
2210 facebook_url = FacebookIE._extract_url(webpage)
2211 if facebook_url is not None:
2212 return self.url_result(facebook_url, 'Facebook')
2214 # Look for embedded VK player
2215 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2216 if mobj is not None:
2217 return self.url_result(mobj.group('url'), 'VK')
2219 # Look for embedded Odnoklassniki player
2220 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2221 if mobj is not None:
2222 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2224 # Look for embedded ivi player
2225 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2226 if mobj is not None:
2227 return self.url_result(mobj.group('url'), 'Ivi')
2229 # Look for embedded Huffington Post player
2231 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2232 if mobj is not None:
2233 return self.url_result(mobj.group('url'), 'HuffPost')
2236 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2237 if mobj is not None:
2238 return self.url_result(mobj.group('url'))
2239 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2240 if mobj is not None:
2241 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2243 # Look for funnyordie embed
2244 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2246 return self.playlist_from_matches(
2247 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2249 # Look for BBC iPlayer embed
2250 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2252 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2254 # Look for embedded RUTV player
2255 rutv_url = RUTVIE._extract_url(webpage)
2257 return self.url_result(rutv_url, 'RUTV')
2259 # Look for embedded TVC player
2260 tvc_url = TVCIE._extract_url(webpage)
2262 return self.url_result(tvc_url, 'TVC')
2264 # Look for embedded SportBox player
2265 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2267 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2269 # Look for embedded XHamster player
2270 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2272 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2274 # Look for embedded TNAFlixNetwork player
2275 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2277 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2279 # Look for embedded PornHub player
2280 pornhub_urls = PornHubIE._extract_urls(webpage)
2282 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2284 # Look for embedded DrTuber player
2285 drtuber_urls = DrTuberIE._extract_urls(webpage)
2287 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2289 # Look for embedded RedTube player
2290 redtube_urls = RedTubeIE._extract_urls(webpage)
2292 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2294 # Look for embedded Tvigle player
2296 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2297 if mobj is not None:
2298 return self.url_result(mobj.group('url'), 'Tvigle')
2300 # Look for embedded TED player
2302 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2303 if mobj is not None:
2304 return self.url_result(mobj.group('url'), 'TED')
2306 # Look for embedded Ustream videos
2307 ustream_url = UstreamIE._extract_url(webpage)
2309 return self.url_result(ustream_url, UstreamIE.ie_key())
2311 # Look for embedded arte.tv player
2313 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2315 if mobj is not None:
2316 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2318 # Look for embedded francetv player
2320 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2322 if mobj is not None:
2323 return self.url_result(mobj.group('url'))
2325 # Look for embedded smotri.com player
2326 smotri_url = SmotriIE._extract_url(webpage)
2328 return self.url_result(smotri_url, 'Smotri')
2330 # Look for embedded Myvi.ru player
2331 myvi_url = MyviIE._extract_url(webpage)
2333 return self.url_result(myvi_url)
2335 # Look for embedded soundcloud player
2336 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2338 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2340 # Look for tunein player
2341 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2343 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2345 # Look for embedded mtvservices player
2346 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2348 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2350 # Look for embedded yahoo player
2352 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2354 if mobj is not None:
2355 return self.url_result(mobj.group('url'), 'Yahoo')
2357 # Look for embedded sbs.com.au player
2361 <meta\s+property="og:video"\s+content=|
2364 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2366 if mobj is not None:
2367 return self.url_result(mobj.group('url'), 'SBS')
2369 # Look for embedded Cinchcast player
2371 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2373 if mobj is not None:
2374 return self.url_result(mobj.group('url'), 'Cinchcast')
2377 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2381 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2383 if mobj is not None:
2384 return self.url_result(mobj.group('url'), 'MLB')
2387 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2389 if mobj is not None:
2390 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2393 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2395 if mobj is not None:
2396 return self.url_result(mobj.group('url'), 'Livestream')
2398 # Look for Zapiks embed
2400 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2401 if mobj is not None:
2402 return self.url_result(mobj.group('url'), 'Zapiks')
2404 # Look for Kaltura embeds
2405 kaltura_url = KalturaIE._extract_url(webpage)
2407 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2409 # Look for Eagle.Platform embeds
2410 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2411 if eagleplatform_url:
2412 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2414 # Look for ClipYou (uses Eagle.Platform) embeds
2416 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2417 if mobj is not None:
2418 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2420 # Look for Pladform embeds
2421 pladform_url = PladformIE._extract_url(webpage)
2423 return self.url_result(pladform_url)
2425 # Look for Videomore embeds
2426 videomore_url = VideomoreIE._extract_url(webpage)
2428 return self.url_result(videomore_url)
2430 # Look for Webcaster embeds
2431 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2433 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2435 # Look for Playwire embeds
2437 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2438 if mobj is not None:
2439 return self.url_result(mobj.group('url'))
2441 # Look for 5min embeds
2443 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2444 if mobj is not None:
2445 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2447 # Look for Crooks and Liars embeds
2449 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2450 if mobj is not None:
2451 return self.url_result(mobj.group('url'))
2453 # Look for NBC Sports VPlayer embeds
2454 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2456 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2458 # Look for NBC News embeds
2459 nbc_news_embed_url = re.search(
2460 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2461 if nbc_news_embed_url:
2462 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2464 # Look for Google Drive embeds
2465 google_drive_url = GoogleDriveIE._extract_url(webpage)
2466 if google_drive_url:
2467 return self.url_result(google_drive_url, 'GoogleDrive')
2469 # Look for UDN embeds
2471 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2472 if mobj is not None:
2473 return self.url_result(
2474 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2476 # Look for Senate ISVP iframe
2477 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2479 return self.url_result(senate_isvp_url, 'SenateISVP')
2481 # Look for Dailymotion Cloud videos
2482 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2484 return self.url_result(dmcloud_url, 'DailymotionCloud')
2486 # Look for OnionStudios embeds
2487 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2488 if onionstudios_url:
2489 return self.url_result(onionstudios_url)
2491 # Look for ViewLift embeds
2492 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2494 return self.url_result(viewlift_url)
2496 # Look for JWPlatform embeds
2497 jwplatform_url = JWPlatformIE._extract_url(webpage)
2499 return self.url_result(jwplatform_url, 'JWPlatform')
2501 # Look for Digiteka embeds
2502 digiteka_url = DigitekaIE._extract_url(webpage)
2504 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2506 # Look for Arkena embeds
2507 arkena_url = ArkenaIE._extract_url(webpage)
2509 return self.url_result(arkena_url, ArkenaIE.ie_key())
2511 # Look for Piksel embeds
2512 piksel_url = PikselIE._extract_url(webpage)
2514 return self.url_result(piksel_url, PikselIE.ie_key())
2516 # Look for Limelight embeds
2517 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2519 return self.playlist_result(
2520 limelight_urls, video_id, video_title, video_description)
2522 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2526 'Channel': 'channel',
2527 'ChannelList': 'channel_list',
2529 return self.url_result(smuggle_url('limelight:%s:%s' % (
2530 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2531 'Limelight%s' % mobj.group(1), mobj.group(2))
2535 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2537 name=(["\'])flashVars\2[^>]+
2538 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2541 return self.url_result(smuggle_url(
2542 'limelight:media:%s' % mobj.group('id'),
2543 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2545 # Look for Anvato embeds
2546 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2548 return self.playlist_result(
2549 anvato_urls, video_id, video_title, video_description)
2551 # Look for AdobeTVVideo embeds
2553 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2555 if mobj is not None:
2556 return self.url_result(
2557 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2560 # Look for Vine embeds
2562 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2564 if mobj is not None:
2565 return self.url_result(
2566 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2568 # Look for VODPlatform embeds
2570 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2572 if mobj is not None:
2573 return self.url_result(
2574 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2576 # Look for Mangomolo embeds
2578 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2580 video\?.*?\bid=(?P<video_id>\d+)|
2581 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2582 ).+?)\1''', webpage)
2583 if mobj is not None:
2585 '_type': 'url_transparent',
2586 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2587 'title': video_title,
2588 'description': video_description,
2589 'thumbnail': video_thumbnail,
2590 'uploader': video_uploader,
2592 video_id = mobj.group('video_id')
2595 'ie_key': 'MangomoloVideo',
2600 'ie_key': 'MangomoloLive',
2601 'id': mobj.group('channel_id'),
2605 # Look for Instagram embeds
2606 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2607 if instagram_embed_url is not None:
2608 return self.url_result(
2609 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2611 # Look for LiveLeak embeds
2612 liveleak_url = LiveLeakIE._extract_url(webpage)
2614 return self.url_result(liveleak_url, 'LiveLeak')
2616 # Look for 3Q SDN embeds
2617 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2620 '_type': 'url_transparent',
2621 'ie_key': ThreeQSDNIE.ie_key(),
2622 'url': self._proto_relative_url(threeqsdn_url),
2623 'title': video_title,
2624 'description': video_description,
2625 'thumbnail': video_thumbnail,
2626 'uploader': video_uploader,
2629 # Look for VBOX7 embeds
2630 vbox7_url = Vbox7IE._extract_url(webpage)
2632 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2634 # Look for DBTV embeds
2635 dbtv_urls = DBTVIE._extract_urls(webpage)
2637 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2639 # Look for Videa embeds
2640 videa_urls = VideaIE._extract_urls(webpage)
2642 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2644 # Look for 20 minuten embeds
2645 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2647 return self.playlist_from_matches(
2648 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2650 # Look for Openload embeds
2651 openload_urls = OpenloadIE._extract_urls(webpage)
2653 return self.playlist_from_matches(
2654 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2656 # Look for VideoPress embeds
2657 videopress_urls = VideoPressIE._extract_urls(webpage)
2659 return self.playlist_from_matches(
2660 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2662 # Look for Rutube embeds
2663 rutube_urls = RutubeIE._extract_urls(webpage)
2665 return self.playlist_from_matches(
2666 rutube_urls, ie=RutubeIE.ie_key())
2668 # Look for WashingtonPost embeds
2669 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2671 return self.playlist_from_matches(
2672 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2674 # Looking for http://schema.org/VideoObject
2675 json_ld = self._search_json_ld(
2676 webpage, video_id, default={}, expected_type='VideoObject')
2677 if json_ld.get('url'):
2679 'title': video_title or info_dict['title'],
2680 'description': video_description,
2681 'thumbnail': video_thumbnail,
2682 'age_limit': age_limit
2684 info_dict.update(json_ld)
2687 # Look for HTML5 media
2688 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2690 for entry in entries:
2693 'title': video_title,
2695 self._sort_formats(entry['formats'])
2696 return self.playlist_result(entries)
2698 jwplayer_data = self._find_jwplayer_data(
2699 webpage, video_id, transform_source=js_to_json)
2701 info = self._parse_jwplayer_data(
2702 jwplayer_data, video_id, require_title=False, base_url=url)
2703 if not info.get('title'):
2704 info['title'] = video_title
2707 def check_video(vurl):
2708 if YoutubeIE.suitable(vurl):
2710 if RtmpIE.suitable(vurl):
2712 vpath = compat_urlparse.urlparse(vurl).path
2713 vext = determine_ext(vpath)
2714 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2716 def filter_video(urls):
2717 return list(filter(check_video, urls))
2719 # Start with something easy: JW Player in SWFObject
2720 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2722 # Look for gorilla-vid style embedding
2723 found = filter_video(re.findall(r'''(?sx)
2727 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2730 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2732 # Broaden the search a little bit
2733 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2735 # Broaden the findall a little bit: JWPlayer JS loader
2736 found = filter_video(re.findall(
2737 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2740 found = filter_video(re.findall(r'''(?xs)
2741 flowplayer\("[^"]+",\s*
2743 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2744 ["']?url["']?\s*:\s*["']([^"']+)["']
2749 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2751 # Try to find twitter cards info
2752 # twitter:player:stream should be checked before twitter:player since
2753 # it is expected to contain a raw stream (see
2754 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2755 found = filter_video(re.findall(
2756 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2758 # We look for Open Graph info:
2759 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2760 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2761 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2762 if m_video_type is not None:
2763 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2765 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2767 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2768 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2771 # Look also in Refresh HTTP header
2772 refresh_header = head_response.headers.get('Refresh')
2774 # In python 2 response HTTP headers are bytestrings
2775 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2776 refresh_header = refresh_header.decode('iso-8859-1')
2777 found = re.search(REDIRECT_REGEX, refresh_header)
2779 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2781 self.report_following_redirect(new_url)
2790 # twitter:player is a https URL to iframe player that may or may not
2791 # be supported by youtube-dl thus this is checked the very last (see
2792 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2793 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2795 return self.url_result(embed_url)
2798 raise UnsupportedError(url)
2801 for video_url in orderedSet(found):
2802 video_url = unescapeHTML(video_url)
2803 video_url = video_url.replace('\\/', '/')
2804 video_url = compat_urlparse.urljoin(url, video_url)
2805 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2807 # Sometimes, jwplayer extraction will result in a YouTube URL
2808 if YoutubeIE.suitable(video_url):
2809 entries.append(self.url_result(video_url, 'Youtube'))
2812 # here's a fun little line of code for you:
2813 video_id = os.path.splitext(video_id)[0]
2817 'uploader': video_uploader,
2818 'title': video_title,
2819 'age_limit': age_limit,
2822 if RtmpIE.suitable(video_url):
2823 entry_info_dict.update({
2824 '_type': 'url_transparent',
2825 'ie_key': RtmpIE.ie_key(),
2828 entries.append(entry_info_dict)
2831 ext = determine_ext(video_url)
2833 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2835 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2837 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2839 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2841 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2842 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2843 # Just matching .ism/manifest is not enough to be reliably sure
2844 # whether it's actually an ISM manifest or some other streaming
2845 # manifest since there are various streaming URL formats
2846 # possible (see [1]) as well as some other shenanigans like
2847 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2849 # Thus the most reasonable way to solve this is to delegate
2850 # to generic extractor in order to look into the contents of
2851 # the manifest itself.
2852 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2853 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2854 entry_info_dict = self.url_result(
2855 smuggle_url(video_url, {'to_generic': True}),
2858 entry_info_dict['url'] = video_url
2860 if entry_info_dict.get('formats'):
2861 self._sort_formats(entry_info_dict['formats'])
2863 entries.append(entry_info_dict)
2865 if len(entries) == 1:
2868 for num, e in enumerate(entries, start=1):
2869 # 'url' results don't have a title
2870 if e.get('title') is not None:
2871 e['title'] = '%s (%d)' % (e['title'], num)
2873 '_type': 'playlist',