3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
14 compat_urllib_parse_unquote,
16 compat_xml_parse_error,
38 from .commonprotocols import RtmpIE
39 from .brightcove import (
47 from .nbc import NBCSportsVPlayerIE
48 from .ooyala import OoyalaIE
49 from .rutv import RUTVIE
50 from .tvc import TVCIE
51 from .sportbox import SportBoxEmbedIE
52 from .smotri import SmotriIE
53 from .myvi import MyviIE
54 from .condenast import CondeNastIE
55 from .udn import UDNEmbedIE
56 from .senateisvp import SenateISVPIE
57 from .svt import SVTIE
58 from .pornhub import PornHubIE
59 from .xhamster import XHamsterEmbedIE
60 from .tnaflix import TNAFlixNetworkEmbedIE
61 from .drtuber import DrTuberIE
62 from .redtube import RedTubeIE
63 from .tube8 import Tube8IE
64 from .vimeo import VimeoIE
65 from .dailymotion import DailymotionIE
66 from .dailymail import DailyMailIE
67 from .onionstudios import OnionStudiosIE
68 from .viewlift import ViewLiftEmbedIE
69 from .mtv import MTVServicesEmbeddedIE
70 from .pladform import PladformIE
71 from .videomore import VideomoreIE
72 from .webcaster import WebcasterFeedIE
73 from .googledrive import GoogleDriveIE
74 from .jwplatform import JWPlatformIE
75 from .digiteka import DigitekaIE
76 from .arkena import ArkenaIE
77 from .instagram import InstagramIE
78 from .liveleak import LiveLeakIE
79 from .threeqsdn import ThreeQSDNIE
80 from .theplatform import ThePlatformIE
81 from .vessel import VesselIE
82 from .kaltura import KalturaIE
83 from .eagleplatform import EaglePlatformIE
84 from .facebook import FacebookIE
85 from .soundcloud import SoundcloudIE
86 from .tunein import TuneInBaseIE
87 from .vbox7 import Vbox7IE
88 from .dbtv import DBTVIE
89 from .piksel import PikselIE
90 from .videa import VideaIE
91 from .twentymin import TwentyMinutenIE
92 from .ustream import UstreamIE
93 from .openload import OpenloadIE
94 from .videopress import VideoPressIE
95 from .rutube import RutubeIE
96 from .limelight import LimelightBaseIE
97 from .anvato import AnvatoIE
98 from .washingtonpost import WashingtonPostIE
99 from .wistia import WistiaIE
100 from .mediaset import MediasetIE
101 from .joj import JojIE
102 from .megaphone import MegaphoneIE
103 from .vzaar import VzaarIE
104 from .channel9 import Channel9IE
105 from .vshare import VShareIE
106 from .mediasite import MediasiteIE
107 from .springboardplatform import SpringboardPlatformIE
108 from .yapfiles import YapFilesIE
109 from .vice import ViceIE
110 from .xfileshare import XFileShareIE
111 from .cloudflarestream import CloudflareStreamIE
112 from .peertube import PeerTubeIE
113 from .indavideo import IndavideoEmbedIE
114 from .apa import APAIE
115 from .foxnews import FoxNewsIE
116 from .viqeo import ViqeoIE
117 from .expressen import ExpressenIE
120 class GenericIE(InfoExtractor):
121 IE_DESC = 'Generic downloader that works on some sites'
125 # Direct link to a video
127 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
128 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
133 'upload_date': '20100513',
136 # Direct link to media delivered compressed (until Accept-Encoding is *)
138 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
139 'md5': '128c42e68b13950268b648275386fc74',
141 'id': 'FictionJunction-Parallel_Hearts',
143 'title': 'FictionJunction-Parallel_Hearts',
144 'upload_date': '20140522',
146 'expected_warnings': [
147 'URL could be a direct video link, returning it as such.'
149 'skip': 'URL invalid',
151 # Direct download with broken HEAD
153 'url': 'http://ai-radio.org:8000/radio.opus',
160 'skip_download': True, # infinite live stream
162 'expected_warnings': [
163 r'501.*Not Implemented',
167 # Direct link with incorrect MIME type
169 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
170 'md5': '4ccbebe5f36706d85221f204d7eb5913',
172 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
173 'id': '5_Lennart_Poettering_-_Systemd',
175 'title': '5_Lennart_Poettering_-_Systemd',
176 'upload_date': '20141120',
178 'expected_warnings': [
179 'URL could be a direct video link, returning it as such.'
184 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
186 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
187 'title': 'Zero Punctuation',
188 'description': 're:.*groundbreaking video review series.*'
190 'playlist_mincount': 11,
192 # RSS feed with enclosure
194 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
196 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
198 'upload_date': '20150228',
199 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
202 # RSS feed with enclosures and unsupported link URLs
204 'url': 'http://www.hellointernet.fm/podcast?format=rss',
206 'id': 'http://www.hellointernet.fm/podcast?format=rss',
207 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
208 'title': 'Hello Internet',
210 'playlist_mincount': 100,
212 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
214 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
218 'title': 'Automatics, robotics and biocybernetics',
219 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
220 'upload_date': '20130627',
221 'formats': 'mincount:16',
222 'subtitles': 'mincount:1',
225 'force_generic_extractor': True,
226 'skip_download': True,
229 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
231 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
236 'formats': 'mincount:1',
239 'skip_download': True,
242 # SMIL from https://www.restudy.dk/video/play/id/1637
244 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
248 'title': 'video_1637',
249 'formats': 'mincount:3',
252 'skip_download': True,
255 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
257 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
259 'id': 'smil-service',
261 'title': 'smil-service',
262 'formats': 'mincount:1',
265 'skip_download': True,
268 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
270 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
274 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
275 'formats': 'mincount:3',
278 'skip_download': True,
281 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
283 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
285 'id': 'mZlp2ctYIUEB',
287 'title': 'Tikibad ontruimd wegens brand',
288 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
289 'thumbnail': r're:^https?://.*\.jpg$',
293 'skip_download': True,
296 # MPD from http://dash-mse-test.appspot.com/media.html
298 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
299 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
301 'id': 'car-20120827-manifest',
303 'title': 'car-20120827-manifest',
304 'formats': 'mincount:9',
305 'upload_date': '20130904',
308 'format': 'bestvideo',
311 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
313 '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',
318 'formats': 'mincount:8',
322 'skip_download': True,
324 'skip': 'video gone',
326 # m3u8 served with Content-Type: text/plain
328 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
333 'upload_date': '20140720',
334 'formats': 'mincount:11',
338 'skip_download': True,
340 'skip': 'video gone',
344 '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',
348 'upload_date': '20130224',
349 'uploader_id': 'TheVerge',
350 'description': r're:^Chris Ziegler takes a look at the\.*',
351 'uploader': 'The Verge',
352 'title': 'First Firefox OS phones side-by-side',
355 'skip_download': False,
359 # redirect in Refresh HTTP header
360 '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',
364 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
365 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
366 'upload_date': '20150917',
367 'uploader_id': 'brtvofficial',
368 'uploader': 'Boiler Room',
371 'skip_download': False,
375 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
376 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
378 'id': '13601338388002',
380 'uploader': 'www.hodiho.fr',
381 'title': 'R\u00e9gis plante sa Jeep',
384 # bandcamp page with custom domain
386 'add_ie': ['Bandcamp'],
387 'url': 'http://bronyrock.com/track/the-pony-mash',
391 'title': 'The Pony Mash',
392 'uploader': 'M_Pallante',
394 'skip': 'There is a limit of 200 free downloads / month for the test song',
397 # embedded brightcove video
398 # it also tests brightcove videos that need to set the 'Referer'
399 # in the http requests
400 'add_ie': ['BrightcoveLegacy'],
401 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
403 'id': '2765128793001',
405 'title': 'Le cours de bourse : l’analyse technique',
406 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
407 'uploader': 'BFM BUSINESS',
410 'skip_download': True,
414 # embedded with itemprop embedURL and video id spelled as `idVideo`
415 'add_id': ['BrightcoveLegacy'],
416 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
418 'id': '5255628253001',
420 'title': 'md5:37c519b1128915607601e75a87995fc0',
421 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
422 'uploader': 'BFM BUSINESS',
423 'uploader_id': '876450612001',
424 'timestamp': 1482255315,
425 'upload_date': '20161220',
428 'skip_download': True,
432 # https://github.com/rg3/youtube-dl/issues/2253
433 'url': 'http://bcove.me/i6nfkrc3',
434 'md5': '0ba9446db037002366bab3b3eb30c88c',
436 'id': '3101154703001',
438 'title': 'Still no power',
439 'uploader': 'thestar.com',
440 '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.',
442 'add_ie': ['BrightcoveLegacy'],
443 'skip': 'video gone',
446 'url': 'http://www.championat.com/video/football/v/87/87499.html',
447 'md5': 'fb973ecf6e4a78a67453647444222983',
449 'id': '3414141473001',
451 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
452 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
453 'uploader': 'Championat',
457 # https://github.com/rg3/youtube-dl/issues/3541
458 'add_ie': ['BrightcoveLegacy'],
459 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
461 'id': '3866516442001',
463 'title': 'Leer mij vrouwen kennen: Aflevering 1',
464 'description': 'Leer mij vrouwen kennen: Aflevering 1',
465 'uploader': 'SBS Broadcasting',
467 'skip': 'Restricted to Netherlands',
469 'skip_download': True, # m3u8 download
473 # Brightcove video in <iframe>
474 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
475 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
477 'id': '5360463607001',
479 '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',
480 '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。',
481 'uploader': 'United Nations',
482 'uploader_id': '1362235914001',
483 'timestamp': 1489593889,
484 'upload_date': '20170315',
486 'add_ie': ['BrightcoveLegacy'],
489 # Brightcove with alternative playerID key
490 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
492 'id': 'nmeth.2062_SV1',
493 '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',
497 'id': '2228375078001',
499 'title': 'nmeth.2062-sv1',
500 'description': 'nmeth.2062-sv1',
501 'timestamp': 1363357591,
502 'upload_date': '20130315',
503 'uploader': 'Nature Publishing Group',
504 'uploader_id': '1964492299001',
509 # Brightcove with UUID in videoPlayer
510 'url': 'http://www8.hp.com/cn/zh/home.html',
512 'id': '5255815316001',
514 'title': 'Sprocket Video - China',
515 'description': 'Sprocket Video - China',
516 'uploader': 'HP-Video Gallery',
517 'timestamp': 1482263210,
518 'upload_date': '20161220',
519 'uploader_id': '1107601872001',
522 'skip_download': True, # m3u8 download
524 'skip': 'video rotates...weekly?',
527 # Brightcove:new type [2].
528 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
529 'md5': '2b35148fcf48da41c9fb4591650784f3',
531 'id': '5348741021001',
533 'upload_date': '20170306',
534 'uploader_id': '4191638492001',
535 'timestamp': 1488769918,
536 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
541 # Alternative brightcove <video> attributes
542 '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/',
544 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
545 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
548 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
550 'id': '5311302538001',
552 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
553 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
554 'timestamp': 1486321708,
555 'upload_date': '20170205',
556 'uploader_id': '800000640001',
558 'only_matching': True,
562 # Brightcove with UUID in videoPlayer
563 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'id': '5255815316001',
567 'title': 'Sprocket Video - China',
568 'description': 'Sprocket Video - China',
569 'uploader': 'HP-Video Gallery',
570 'timestamp': 1482263210,
571 'upload_date': '20161220',
572 'uploader_id': '1107601872001',
575 'skip_download': True, # m3u8 download
580 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
581 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
583 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
585 'title': '2cc213299525360.mov', # that's what we get
588 'add_ie': ['Ooyala'],
591 # ooyala video embedded with http://player.ooyala.com/iframe.js
592 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
594 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
596 'title': '"Steve Jobs: Man in the Machine" trailer',
597 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
601 'skip_download': True,
603 'skip': 'movie expired',
605 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
607 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
609 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
611 'title': 'Steampunk Fest Comes to Honesdale',
615 'skip_download': True,
620 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
624 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
625 'upload_date': '20140225',
626 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
627 'uploader': 'Tested',
628 'uploader_id': 'testedcom',
630 # No need to test YoutubeIE here
632 'skip_download': True,
637 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
641 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
642 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
644 # HEAD requests lead to endless 301, while GET is OK
645 'expected_warnings': ['301'],
649 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
653 'title': 'Охотское море стало целиком российским',
654 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
658 'skip_download': True,
663 '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/',
667 'title': 'Дошкольное воспитание',
672 'url': 'http://www.vestifinance.ru/articles/25753',
675 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
680 'title': 'Госзаказ. День 3',
686 'title': 'Госзаказ. День 2',
692 'title': 'Госзаказ. День 1',
698 'skip_download': True,
703 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
705 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
707 'title': 'Ужастики, русский трейлер (2015)',
708 'thumbnail': r're:^https?://.*\.jpg$',
714 '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',
717 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
719 'playlist_mincount': 7,
720 # This forum does not allow <iframe> syntaxes anymore
721 # Now HTML tags are displayed as-is
722 'skip': 'No videos on this page',
726 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
727 'md5': '65fdff94098e4a607385a60c5177c638',
731 'title': 'Hidden miracles of the natural world',
732 'uploader': 'Louie Schwartzberg',
733 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
736 # nowvideo embed hidden behind percent encoding
738 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
739 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
741 'id': '06e53103ca9aa',
743 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
744 'description': 'No description',
749 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
750 'md5': '7653032cbb25bf6c80d80f217055fa43',
752 'id': '048195-004_PLUS7-F',
755 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
756 'upload_date': '20140320',
759 'skip_download': 'Requires rtmpdump'
761 'skip': 'video gone',
765 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
769 'title': 'Alcaline, le concert avec Calogero',
770 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
771 'upload_date': '20150226',
772 'timestamp': 1424989860,
777 'skip_download': True,
779 'expected_warnings': [
785 'url': 'http://www.wired.com/2014/04/honda-asimo/',
786 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
788 'id': '53501be369702d3275860000',
790 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
795 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
796 'md5': '441aeeb82eb72c422c7f14ec533999cd',
798 'id': 'k2mm4bCdJ6CQ2i7c8o2',
800 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
801 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
803 'uploader_id': 'xgditw',
804 'upload_date': '20140425',
805 'timestamp': 1398441542,
807 'add_ie': ['Dailymotion'],
811 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
815 'title': 'Care worker punches elderly dementia patient in head 11 times',
816 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
818 'add_ie': ['DailyMail'],
820 'skip_download': True,
825 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
829 'title': 'The NBL Auction 2014',
830 'uploader': 'BADMINTON England',
831 'uploader_id': 'BADMINTONEvents',
832 'upload_date': '20140603',
833 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
835 'add_ie': ['Youtube'],
837 'skip_download': True,
842 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
843 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
845 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
847 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
848 'description': 'Two valets share their love for movie star Liam Neesons.',
849 'timestamp': 1349922600,
850 'upload_date': '20121011',
853 # YouTube embed via <data-embed-url="">
855 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
859 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
860 'uploader': 'Gameloft',
861 'uploader_id': 'gameloft',
862 'upload_date': '20140828',
863 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
866 'skip_download': True,
869 # YouTube <object> embed
871 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
872 'md5': '516718101ec834f74318df76259fb3cc',
876 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
877 'upload_date': '20080526',
878 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
879 'uploader': 'Christopher Sykes',
880 'uploader_id': 'ChristopherJSykes',
882 'add_ie': ['Youtube'],
886 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
888 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
890 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
891 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
896 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
898 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
899 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
905 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
910 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
911 'md5': '9d65602bf31c6e20014319c7d07fba27',
913 'id': '5123ea6d5e5a7',
916 'uploader': 'www.handjobhub.com',
917 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
920 # Multiple brightcove videos
921 # https://github.com/rg3/youtube-dl/issues/2283
923 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
925 'id': 'always-never',
926 'title': 'Always / Never - The New Yorker',
930 'extract_flat': False,
931 'skip_download': True,
936 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
937 'md5': '96f09a37e44da40dd083e12d9a683327',
941 'title': 'Ump changes call to ball',
942 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
944 'timestamp': 1401537900,
945 'upload_date': '20140531',
946 'thumbnail': r're:^https?://.*\.jpg$',
951 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
952 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
956 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
957 'description': 'a Paywall Videos video from Remilon',
959 'uploader': 'study.com',
960 'timestamp': 1459678540,
961 'upload_date': '20160403',
962 'filesize': 24687186,
966 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
967 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
971 'title': 'Conversation about Hexagonal Rails Part 1',
972 'description': 'a Martin Fowler video from ThoughtWorks',
974 'uploader': 'thoughtworks.wistia.com',
975 'timestamp': 1401832161,
976 'upload_date': '20140603',
979 # Wistia standard embed (async)
981 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
985 'title': 'Drip Brennan Dunn Workshop',
986 'description': 'a JV Webinars video from getdrip-1',
988 'timestamp': 1463607249,
989 'upload_date': '20160518',
992 'skip_download': True,
997 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1001 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1002 'uploader': 'Sophos Security',
1003 'title': 'Chet Chat 171 - Oct 29, 2014',
1004 'upload_date': '20141029',
1007 # Soundcloud multiple embeds
1009 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1012 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1014 'playlist_mincount': 7,
1016 # TuneIn station embed
1018 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1023 'location': 'Paris, France',
1028 'skip_download': True,
1033 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1037 'upload_date': '20141112',
1038 'title': 'Rosetta #CometLanding webcast HL 10',
1041 # Another Livestream embed, without 'new.' in URL
1043 'url': 'https://www.freespeech.org/',
1047 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1051 'skip_download': True,
1056 'url': 'https://skiplagged.com/',
1059 'title': 'Skiplagged: The smart way to find cheap flights',
1061 'playlist_mincount': 1,
1062 'add_ie': ['Youtube'],
1066 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1070 'upload_date': '20141126',
1071 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1076 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1078 'id': '730m_DandD_1901_512k',
1080 'uploader': 'www.abc.net.au',
1081 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1084 # embedded viddler video
1086 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1090 'uploader': 'deadspin',
1091 'title': 'WALL-TO-GORTAT',
1092 'timestamp': 1422285291,
1093 'upload_date': '20150126',
1095 'add_ie': ['Viddler'],
1099 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1103 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1104 'description': 'md5:601cb790edd05908957dae8aaa866465',
1105 'upload_date': '20150220',
1107 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1111 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1113 'id': 'Mrj4DVp2zeA',
1115 'upload_date': '20150212',
1116 'uploader': 'The National Archives UK',
1117 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1118 'uploader_id': 'NationalArchives08',
1119 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1124 'url': 'http://www.suffolk.edu/sjc/live.php',
1128 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1129 'uploader': 'www.suffolk.edu',
1132 'skip_download': True,
1134 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1138 'url': 'http://www.indiedb.com/games/king-machine/videos',
1142 'title': 'king machine trailer 1',
1143 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1144 'thumbnail': r're:^https?://.*\.jpg$',
1148 # JWPlayer config passed as variable
1149 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1153 'title': 'ARIELE | Tube Cup',
1154 'uploader': 'www.txxx.com',
1158 'skip_download': True,
1163 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1164 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1168 'upload_date': '20171122',
1169 'timestamp': 1511366290,
1170 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1172 'add_ie': [JWPlatformIE.ie_key()],
1175 # Video.js embed, multiple formats
1176 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1178 'id': 'yygqldloqIk',
1180 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1181 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1182 'upload_date': '20130314',
1183 'uploader': 'PROстое3D',
1184 'uploader_id': 'PROstoe3D',
1187 'skip_download': True,
1191 # Video.js embed, single format
1192 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1196 'title': 'Step 1 - Good Foundation',
1197 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1200 'skip_download': True,
1205 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1206 'playlist_mincount': 5,
1208 'id': 'aanslagen-kopenhagen',
1209 'title': 'Aanslagen Kopenhagen',
1214 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1218 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1221 # Kaltura embed (different embed code)
1223 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1227 'upload_date': '20150127',
1228 'uploader_id': 'PremierMedia',
1230 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1233 # Kaltura embed with single quotes
1235 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1240 'timestamp': 1355743100,
1241 'upload_date': '20121217',
1242 'uploader_id': 'cplapp@learn360.com',
1244 'add_ie': ['Kaltura'],
1247 # Kaltura embedded via quoted entry_id
1248 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1252 'title': '06_matthew_brender_raj_dutt',
1253 'timestamp': 1466638791,
1254 'upload_date': '20160622',
1256 'add_ie': ['Kaltura'],
1257 'expected_warnings': [
1258 'Could not send HEAD request'
1261 'skip_download': True,
1265 # Kaltura embedded, some fileExt broken (#11480)
1266 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1270 'title': 'Our "Standard Models" of particle physics and cosmology',
1271 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1272 'timestamp': 1321158993,
1273 'upload_date': '20111113',
1274 'uploader_id': 'kps1',
1276 'add_ie': ['Kaltura'],
1279 # Kaltura iframe embed
1280 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1281 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1285 'title': 'I. M. Pei: A Centennial Celebration',
1286 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1287 'upload_date': '20170403',
1288 'uploader_id': 'batchUser',
1289 'timestamp': 1491232186,
1291 'add_ie': ['Kaltura'],
1294 # Kaltura iframe embed, more sophisticated
1295 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1299 'title': 'lecture-05sep2017',
1300 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1301 'upload_date': '20170913',
1302 'uploader_id': 'eps2',
1303 'timestamp': 1505340777,
1306 'skip_download': True,
1308 'add_ie': ['Kaltura'],
1311 # meta twitter:player
1312 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1316 'title': 'Main Twerk (Video)',
1317 'upload_date': '20171208',
1318 'uploader_id': 'sebastian.salinas@thechive.com',
1319 'timestamp': 1512713057,
1322 'skip_download': True,
1324 'add_ie': ['Kaltura'],
1326 # referrer protected EaglePlatform embed
1328 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1332 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1333 'thumbnail': r're:^https?://.*\.jpg$',
1338 'skip_download': True,
1341 # ClipYou (EaglePlatform) embed (custom URL)
1343 'url': 'http://muz-tv.ru/play/7129/',
1344 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1348 'title': "'O Sole Mio",
1349 'thumbnail': r're:^https?://.*\.jpg$',
1354 'skip_download': True,
1356 'skip': 'This video is unavailable.',
1360 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1364 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1365 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1366 'thumbnail': r're:^https?://.*\.jpg$',
1370 'skip': 'HTTP Error 404: Not Found',
1374 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1378 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1379 'thumbnail': r're:^https?://.*\.png$',
1385 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1386 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1390 'title': 'Facebook Creates "On This Day" | Crunch Report',
1391 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1392 'timestamp': 1427237531,
1393 'uploader': 'Crunch Report',
1394 'upload_date': '20150324',
1398 'skip_download': True,
1401 # Crooks and Liars embed
1403 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1407 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1408 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1409 'timestamp': 1428207000,
1410 'upload_date': '20150405',
1411 'uploader': 'Heather',
1414 # Crooks and Liars external embed
1416 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1418 'id': 'MTE3MjUtMzQ2MzA',
1420 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1421 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1422 'timestamp': 1265032391,
1423 'upload_date': '20100201',
1424 'uploader': 'Heather',
1427 # NBC Sports vplayer embed
1429 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1431 'id': 'ln7x1qSThw4k',
1433 'title': "PFT Live: New leader in the 'new-look' defense",
1434 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1435 'uploader': 'NBCU-SPORTS',
1436 'upload_date': '20140107',
1437 'timestamp': 1389118457,
1439 'skip': 'Invalid Page URL',
1443 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1444 'md5': '1aa589c675898ae6d37a17913cf68d66',
1446 'id': 'x_dtl_oa_LettermanliftPR_160608',
1448 'title': 'David Letterman: A Preview',
1449 '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.',
1450 'upload_date': '20160609',
1451 'timestamp': 1465431544,
1452 'uploader': 'NBCU-NEWS',
1457 'url': 'https://video.udn.com/news/300346',
1458 'md5': 'fd2060e988c326991037b9aff9df21a6',
1462 'title': '中一中男師變性 全校師生力挺',
1463 'thumbnail': r're:^https?://.*\.jpg$',
1467 'skip_download': True,
1469 'expected_warnings': ['Failed to parse JSON Expecting value'],
1471 # Brightcove URL in single quotes
1473 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1474 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1476 'id': '4255764656001',
1478 'title': 'SN Presents: Russell Martin, World Citizen',
1479 '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.',
1480 'uploader': 'Rogers Sportsnet',
1481 'uploader_id': '1704050871',
1482 'upload_date': '20150525',
1483 'timestamp': 1432570283,
1486 # OnionStudios embed
1488 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1492 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1493 'thumbnail': r're:^https?://.*\.jpe?g$',
1494 'uploader': 'ClickHole',
1495 'uploader_id': 'clickhole',
1500 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1502 'id': '74849a00-85a9-11e1-9660-123139220831',
1504 'title': '#whilewewatch',
1507 # AdobeTVVideo embed
1509 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1510 'md5': '43662b577c018ad707a63766462b1e87',
1514 'title': 'New experience with Acrobat DC',
1515 'description': 'New experience with Acrobat DC',
1516 'duration': 248.667,
1519 # BrightcoveInPageEmbed embed
1521 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1523 'id': '4238694884001',
1525 'title': 'Tabletop: Dread, Last Thoughts',
1526 'description': 'Tabletop: Dread, Last Thoughts',
1530 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1531 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1533 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1535 'id': '4785848093001',
1537 'title': 'The Cardinal Pell Interview',
1538 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1539 'uploader': 'GlobeCast Australia - GlobeStream',
1540 'uploader_id': '2733773828001',
1541 'upload_date': '20160304',
1542 'timestamp': 1457083087,
1546 'skip_download': True,
1550 # Brightcove embed with whitespace around attribute names
1551 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1553 'id': '3167554373001',
1555 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1556 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1557 'uploader_id': '1079349493',
1558 'upload_date': '20140207',
1559 'timestamp': 1391810548,
1562 'skip_download': True,
1565 # Another form of arte.tv embed
1567 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1568 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1570 'id': '030273-562_PLUS7-F',
1572 'title': 'ARTE Reportage - Nulle part, en France',
1573 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1574 'upload_date': '20160409',
1579 'url': 'http://www.wykop.pl/link/3088787/',
1580 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1582 'id': '874_1459135191',
1584 'title': 'Man shows poor quality of new apartment building',
1585 'description': 'The wall is like a sand pile.',
1586 'uploader': 'Lake8737',
1588 'add_ie': [LiveLeakIE.ie_key()],
1590 # Another LiveLeak embed pattern (#13336)
1592 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1594 'id': '2eb_1496309988',
1596 'title': 'Thief robs place where everyone was armed',
1597 'description': 'md5:694d73ee79e535953cf2488562288eee',
1598 'uploader': 'brazilwtf',
1600 'add_ie': [LiveLeakIE.ie_key()],
1602 # Duplicated embedded video URLs
1604 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1606 'id': '149298443_480_16c25b74_2',
1608 'title': 'vs. Blue Orange Spring Game',
1609 'uploader': 'www.hudl.com',
1612 # twitter:player:stream embed
1614 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1618 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1619 'uploader': 'www.rtl.be',
1623 'skip_download': True,
1626 # twitter:player embed
1628 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1629 'md5': 'a3e0df96369831de324f0778e126653c',
1631 'id': '4909620399001',
1633 'title': 'What Do Black Holes Sound Like?',
1634 'description': 'what do black holes sound like',
1635 'upload_date': '20160524',
1636 'uploader_id': '29913724001',
1637 'timestamp': 1464107587,
1638 'uploader': 'TheAtlantic',
1640 'add_ie': ['BrightcoveLegacy'],
1642 # Facebook <iframe> embed
1644 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1645 'md5': 'fbcde74f534176ecb015849146dd3aee',
1647 'id': '599637780109885',
1649 'title': 'Facebook video #599637780109885',
1652 # Facebook <iframe> embed, plugin video
1654 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1656 'id': '1754168231264132',
1658 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1659 'uploader': 'Tariq Ramadan (official)',
1660 'timestamp': 1496758379,
1661 'upload_date': '20170606',
1664 'skip_download': True,
1667 # Facebook API embed
1669 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1670 'md5': 'a47372ee61b39a7b90287094d447d94e',
1672 'id': '10153467542406923',
1674 'title': 'Facebook video #10153467542406923',
1677 # Wordpress "YouTube Video Importer" plugin
1679 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1680 'md5': 'd16797741b560b485194eddda8121b48',
1682 'id': 'HNTXWDXV9Is',
1684 'title': 'Blue Devils Drumline Stanford lot 2016',
1685 'upload_date': '20160627',
1686 'uploader_id': 'GENOCIDE8GENERAL10',
1687 'uploader': 'cylus cyrus',
1691 # video stored on custom kaltura server
1692 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1693 'md5': '537617d06e64dfed891fa1593c4b30cc',
1697 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1698 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1699 'uploader_id': 'videos.expansion@el-mundo.net',
1700 'upload_date': '20150429',
1701 'timestamp': 1430303472,
1703 'add_ie': ['Kaltura'],
1706 # Non-standard Vimeo embed
1707 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1708 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1712 'title': 'Understanding the web - Teaser',
1713 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1714 'upload_date': '20151214',
1715 'uploader': 'OpenClassrooms',
1716 'uploader_id': 'openclassrooms',
1718 'add_ie': ['Vimeo'],
1721 # generic vimeo embed that requires original URL passed as Referer
1722 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1723 'only_matching': True,
1726 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1727 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1729 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1731 'title': 'Big Buck Bunny',
1732 'description': 'Royalty free test video',
1733 'timestamp': 1432816365,
1734 'upload_date': '20150528',
1738 'skip_download': True,
1740 'add_ie': [ArkenaIE.ie_key()],
1743 '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/',
1747 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1750 'skip_download': True,
1752 'add_ie': [Vbox7IE.ie_key()],
1756 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1759 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1761 'playlist_mincount': 3,
1765 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1767 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1768 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1770 'playlist_mincount': 2,
1774 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1778 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1779 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1782 'skip_download': True,
1784 'add_ie': [TwentyMinutenIE.ie_key()],
1788 'url': 'https://en.support.wordpress.com/videopress/',
1792 'title': 'IMG_5786',
1793 'timestamp': 1435711927,
1794 'upload_date': '20150701',
1797 'skip_download': True,
1799 'add_ie': [VideoPressIE.ie_key()],
1803 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1805 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1807 'title': 'Магаззино: Казань 2',
1808 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1809 'uploader': 'Магаззино',
1810 'upload_date': '20170228',
1811 'uploader_id': '996642',
1814 'skip_download': True,
1816 'add_ie': [RutubeIE.ie_key()],
1819 # ThePlatform embedded with whitespaces in URLs
1820 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1821 'only_matching': True,
1824 # Senate ISVP iframe https
1825 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1826 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1828 'id': 'govtaff020316',
1830 'title': 'Integrated Senate Video Player',
1832 'add_ie': [SenateISVPIE.ie_key()],
1835 # Limelight embeds (1 channel embed + 4 media embeds)
1836 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1838 'id': 'FacilitatorTraining2017',
1839 'title': 'Facilitator Training 2017',
1841 'playlist_mincount': 5,
1844 # Limelight embed (LimelightPlayerUtil.embed)
1845 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1847 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1849 'title': '07448641',
1850 'timestamp': 1499890639,
1851 'upload_date': '20170712',
1854 'skip_download': True,
1856 'add_ie': ['LimelightMedia'],
1859 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1861 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1862 'title': 'Standoff with Walnut Creek murder suspect ends',
1863 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1865 'playlist_mincount': 4,
1868 # WashingtonPost embed
1869 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1871 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1873 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1874 '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.',
1875 'timestamp': 1455216756,
1876 'uploader': 'The Washington Post',
1877 'upload_date': '20160211',
1879 'add_ie': [WashingtonPostIE.ie_key()],
1883 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1887 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1890 'skip_download': True,
1892 'add_ie': [MediasetIE.ie_key()],
1896 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1898 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1899 'title': 'Slovenskom sa prehnala vlna silných búrok',
1901 'playlist_mincount': 5,
1902 'add_ie': [JojIE.ie_key()],
1905 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1906 'url': 'https://tvrain.ru/amp/418921/',
1907 'md5': 'cc00413936695987e8de148b67d14f1d',
1911 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1916 'url': 'http://help.vzaar.com/article/165-embedding-video',
1917 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1921 'title': 'Building A Business Online: Principal Chairs Q & A',
1925 # multiple HTML5 videos on one page
1926 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1928 'id': 'keyscenarios',
1929 'title': 'Rescue Kit 14 Free Edition - Getting started',
1931 'playlist_count': 4,
1935 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1936 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1939 'title': 'vl14062007715967',
1944 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1945 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1947 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1949 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1950 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1951 'timestamp': 1474354800,
1952 'upload_date': '20160920',
1956 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1960 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1961 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1962 'timestamp': 1516100691,
1963 'upload_date': '20180116',
1966 'skip_download': True,
1968 'add_ie': [SpringboardPlatformIE.ie_key()],
1971 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1973 'id': 'uPDB5I9wfp8',
1975 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1976 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1977 'upload_date': '20160219',
1978 'uploader': 'Pocoyo - Português (BR)',
1979 'uploader_id': 'PocoyoBrazil',
1981 'add_ie': [YoutubeIE.ie_key()],
1983 'skip_download': True,
1987 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1989 'id': 'vMDE4NzI1Mjgt690b',
1993 'add_ie': [YapFilesIE.ie_key()],
1995 'skip_download': True,
1999 # CloudflareStream embed
2000 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2002 'id': '31c9291ab41fac05471db4e73aa11717',
2004 'title': '31c9291ab41fac05471db4e73aa11717',
2006 'add_ie': [CloudflareStreamIE.ie_key()],
2008 'skip_download': True,
2013 'url': 'https://joinpeertube.org/fr/home/',
2016 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2018 'playlist_count': 2,
2022 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2026 'title': 'Így kell otthon hamburgert sütni',
2027 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2028 'timestamp': 1426330212,
2029 'upload_date': '20150314',
2030 'uploader': 'StreetKitchen',
2031 'uploader_id': '546363',
2033 'add_ie': [IndavideoEmbedIE.ie_key()],
2035 'skip_download': True,
2039 # APA embed via JWPlatform embed
2040 'url': 'http://www.vol.at/blue-man-group/5593454',
2044 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2045 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2046 'thumbnail': r're:^https?://.*\.jpg$',
2048 'timestamp': 1519211149,
2049 'upload_date': '20180221',
2052 'skip_download': True,
2056 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2057 'md5': 'b68d276de422ab07ee1d49388103f457',
2060 'title': 'Lock up and get excited',
2063 'skip': 'TODO: fix nested playlists processing in tests',
2067 'url': 'https://viqeo.tv/',
2070 'title': 'All-new video platform',
2072 'playlist_count': 6,
2076 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2080 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2081 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2082 'thumbnail': r're:^https?://.*\.jpg$',
2085 'skip_download': True,
2087 'expected_warnings': ['Failed to download MPD manifest'],
2090 # # TODO: find another test
2091 # # http://schema.org/VideoObject
2092 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2093 # 'md5': '888dcf08b7ea671381f00fab74692755',
2095 # 'id': 'nyvTSJMKId',
2097 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2098 # 'description': '#love for cats.',
2099 # 'timestamp': 1461244995,
2100 # 'upload_date': '20160421',
2103 # 'force_generic_extractor': True,
2108 def report_following_redirect(self, new_url):
2109 """Report information extraction."""
2110 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2112 def _extract_rss(self, url, video_id, doc):
2113 playlist_title = doc.find('./channel/title').text
2114 playlist_desc_el = doc.find('./channel/description')
2115 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2118 for it in doc.findall('./channel/item'):
2120 enclosure_nodes = it.findall('./enclosure')
2121 for e in enclosure_nodes:
2122 next_url = e.attrib.get('url')
2127 next_url = xpath_text(it, 'link', fatal=False)
2133 '_type': 'url_transparent',
2135 'title': it.find('title').text,
2139 '_type': 'playlist',
2141 'title': playlist_title,
2142 'description': playlist_desc,
2146 def _extract_camtasia(self, url, video_id, webpage):
2147 """ Returns None if no camtasia video can be found. """
2149 camtasia_cfg = self._search_regex(
2150 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2151 webpage, 'camtasia configuration file', default=None)
2152 if camtasia_cfg is None:
2155 title = self._html_search_meta('DC.title', webpage, fatal=True)
2157 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2158 camtasia_cfg = self._download_xml(
2159 camtasia_url, video_id,
2160 note='Downloading camtasia configuration',
2161 errnote='Failed to download camtasia configuration')
2162 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2165 for n in fileset_node.getchildren():
2166 url_n = n.find('./uri')
2171 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2172 'title': '%s - %s' % (title, n.tag),
2173 'url': compat_urlparse.urljoin(url, url_n.text),
2174 'duration': float_or_none(n.find('./duration').text),
2178 '_type': 'playlist',
2183 def _real_extract(self, url):
2184 if url.startswith('//'):
2187 'url': self.http_scheme() + url,
2190 parsed_url = compat_urlparse.urlparse(url)
2191 if not parsed_url.scheme:
2192 default_search = self._downloader.params.get('default_search')
2193 if default_search is None:
2194 default_search = 'fixup_error'
2196 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2198 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2199 return self.url_result('http://' + url)
2200 elif default_search != 'fixup_error':
2201 if default_search == 'auto_warning':
2202 if re.match(r'^(?:url|URL)$', url):
2203 raise ExtractorError(
2204 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2207 self._downloader.report_warning(
2208 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2209 return self.url_result('ytsearch:' + url)
2211 if default_search in ('error', 'fixup_error'):
2212 raise ExtractorError(
2213 '%r is not a valid URL. '
2214 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2215 % (url, url), expected=True)
2217 if ':' not in default_search:
2218 default_search += ':'
2219 return self.url_result(default_search + url)
2221 url, smuggled_data = unsmuggle_url(url)
2222 force_videoid = None
2223 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2224 if smuggled_data and 'force_videoid' in smuggled_data:
2225 force_videoid = smuggled_data['force_videoid']
2226 video_id = force_videoid
2228 video_id = self._generic_id(url)
2230 self.to_screen('%s: Requesting header' % video_id)
2232 head_req = HEADRequest(url)
2233 head_response = self._request_webpage(
2235 note=False, errnote='Could not send HEAD request to %s' % url,
2238 if head_response is not False:
2239 # Check for redirect
2240 new_url = compat_str(head_response.geturl())
2242 self.report_following_redirect(new_url)
2244 new_url = smuggle_url(
2245 new_url, {'force_videoid': force_videoid})
2246 return self.url_result(new_url)
2248 full_response = None
2249 if head_response is False:
2250 request = sanitized_Request(url)
2251 request.add_header('Accept-Encoding', '*')
2252 full_response = self._request_webpage(request, video_id)
2253 head_response = full_response
2257 'title': self._generic_title(url),
2258 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2261 # Check for direct link to a video
2262 content_type = head_response.headers.get('Content-Type', '').lower()
2263 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2265 format_id = compat_str(m.group('format_id'))
2266 if format_id.endswith('mpegurl'):
2267 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2268 elif format_id == 'f4m':
2269 formats = self._extract_f4m_formats(url, video_id)
2272 'format_id': format_id,
2274 'vcodec': 'none' if m.group('type') == 'audio' else None
2276 info_dict['direct'] = True
2277 self._sort_formats(formats)
2278 info_dict['formats'] = formats
2281 if not self._downloader.params.get('test', False) and not is_intentional:
2282 force = self._downloader.params.get('force_generic_extractor', False)
2283 self._downloader.report_warning(
2284 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2286 if not full_response:
2287 request = sanitized_Request(url)
2288 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2289 # making it impossible to download only chunk of the file (yet we need only 512kB to
2290 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2291 # that will always result in downloading the whole file that is not desirable.
2292 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2293 # to accept raw bytes and being able to download only a chunk.
2294 # It may probably better to solve this by checking Content-Type for application/octet-stream
2295 # after HEAD request finishes, but not sure if we can rely on this.
2296 request.add_header('Accept-Encoding', '*')
2297 full_response = self._request_webpage(request, video_id)
2299 first_bytes = full_response.read(512)
2301 # Is it an M3U playlist?
2302 if first_bytes.startswith(b'#EXTM3U'):
2303 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2304 self._sort_formats(info_dict['formats'])
2307 # Maybe it's a direct link to a video?
2308 # Be careful not to download the whole thing!
2309 if not is_html(first_bytes):
2310 self._downloader.report_warning(
2311 'URL could be a direct video link, returning it as such.')
2318 webpage = self._webpage_read_content(
2319 full_response, url, video_id, prefix=first_bytes)
2321 self.report_extraction(video_id)
2323 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2325 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2326 if doc.tag == 'rss':
2327 return self._extract_rss(url, video_id, doc)
2328 elif doc.tag == 'SmoothStreamingMedia':
2329 info_dict['formats'] = self._parse_ism_formats(doc, url)
2330 self._sort_formats(info_dict['formats'])
2332 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2333 smil = self._parse_smil(doc, url, video_id)
2334 self._sort_formats(smil['formats'])
2336 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2337 return self.playlist_result(
2339 doc, video_id, xspf_url=url,
2340 xspf_base_url=compat_str(full_response.geturl())),
2342 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2343 info_dict['formats'] = self._parse_mpd_formats(
2345 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2347 self._sort_formats(info_dict['formats'])
2349 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2350 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2351 self._sort_formats(info_dict['formats'])
2353 except compat_xml_parse_error:
2356 # Is it a Camtasia project?
2357 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2358 if camtasia_res is not None:
2361 # Sometimes embedded video player is hidden behind percent encoding
2362 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2363 # Unescaping the whole page allows to handle those cases in a generic way
2364 webpage = compat_urllib_parse_unquote(webpage)
2366 # it's tempting to parse this further, but you would
2367 # have to take into account all the variations like
2368 # Video Title - Site Name
2369 # Site Name | Video Title
2370 # Video Title - Tagline | Site Name
2371 # and so on and so forth; it's just not practical
2372 video_title = self._og_search_title(
2373 webpage, default=None) or self._html_search_regex(
2374 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2377 # Try to detect age limit automatically
2378 age_limit = self._rta_search(webpage)
2379 # And then there are the jokers who advertise that they use RTA,
2380 # but actually don't.
2381 AGE_LIMIT_MARKERS = [
2382 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2384 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2387 # video uploader is domain name
2388 video_uploader = self._search_regex(
2389 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2391 video_description = self._og_search_description(webpage, default=None)
2392 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2395 'title': video_title,
2396 'description': video_description,
2397 'thumbnail': video_thumbnail,
2398 'age_limit': age_limit,
2401 # Look for Brightcove Legacy Studio embeds
2402 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2406 'url': smuggle_url(bc_url, {'Referer': url}),
2407 'ie_key': 'BrightcoveLegacy'
2408 } for bc_url in bc_urls]
2411 '_type': 'playlist',
2412 'title': video_title,
2417 # Look for Brightcove New Studio embeds
2418 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2420 return self.playlist_from_matches(
2421 bc_urls, video_id, video_title,
2422 getter=lambda x: smuggle_url(x, {'referrer': url}),
2425 # Look for Nexx embeds
2426 nexx_urls = NexxIE._extract_urls(webpage)
2428 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2430 # Look for Nexx iFrame embeds
2431 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2433 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2435 # Look for ThePlatform embeds
2436 tp_urls = ThePlatformIE._extract_urls(webpage)
2438 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2440 # Look for Vessel embeds
2441 vessel_urls = VesselIE._extract_urls(webpage)
2443 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2445 # Look for embedded rtl.nl player
2446 matches = re.findall(
2447 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2450 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2452 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2454 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2456 vid_me_embed_url = self._search_regex(
2457 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2458 webpage, 'vid.me embed', default=None)
2459 if vid_me_embed_url is not None:
2460 return self.url_result(vid_me_embed_url, 'Vidme')
2462 # Look for YouTube embeds
2463 youtube_urls = YoutubeIE._extract_urls(webpage)
2465 return self.playlist_from_matches(
2466 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2468 matches = DailymotionIE._extract_urls(webpage)
2470 return self.playlist_from_matches(matches, video_id, video_title)
2472 # Look for embedded Dailymotion playlist player (#3822)
2474 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2476 playlists = re.findall(
2477 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2479 return self.playlist_from_matches(
2480 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2482 # Look for DailyMail embeds
2483 dailymail_urls = DailyMailIE._extract_urls(webpage)
2485 return self.playlist_from_matches(
2486 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2488 # Look for embedded Wistia player
2489 wistia_url = WistiaIE._extract_url(webpage)
2492 '_type': 'url_transparent',
2493 'url': self._proto_relative_url(wistia_url),
2494 'ie_key': WistiaIE.ie_key(),
2495 'uploader': video_uploader,
2498 # Look for SVT player
2499 svt_url = SVTIE._extract_url(webpage)
2501 return self.url_result(svt_url, 'SVT')
2503 # Look for Bandcamp pages with custom domain
2504 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2505 if mobj is not None:
2506 burl = unescapeHTML(mobj.group(1))
2507 # Don't set the extractor because it can be a track url or an album
2508 return self.url_result(burl)
2510 # Look for embedded Vevo player
2512 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2513 if mobj is not None:
2514 return self.url_result(mobj.group('url'))
2516 # Look for embedded Viddler player
2518 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2520 if mobj is not None:
2521 return self.url_result(mobj.group('url'))
2523 # Look for NYTimes player
2525 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2527 if mobj is not None:
2528 return self.url_result(mobj.group('url'))
2530 # Look for Libsyn player
2532 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2533 if mobj is not None:
2534 return self.url_result(mobj.group('url'))
2536 # Look for Ooyala videos
2537 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2538 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2539 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2540 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2541 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2542 if mobj is not None:
2543 embed_token = self._search_regex(
2544 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2545 webpage, 'ooyala embed token', default=None)
2546 return OoyalaIE._build_url_result(smuggle_url(
2549 'embed_token': embed_token,
2552 # Look for multiple Ooyala embeds on SBN network websites
2553 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2554 if mobj is not None:
2555 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2557 return self.playlist_from_matches(
2558 embeds, video_id, video_title,
2559 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2561 # Look for Aparat videos
2562 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2563 if mobj is not None:
2564 return self.url_result(mobj.group(1), 'Aparat')
2566 # Look for MPORA videos
2567 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2568 if mobj is not None:
2569 return self.url_result(mobj.group(1), 'Mpora')
2571 # Look for embedded NovaMov-based player
2573 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2574 (?P<url>http://(?:(?:embed|www)\.)?
2576 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2577 videoweed\.(?:es|com)|
2578 movshare\.(?:net|sx|ag)|
2579 divxstage\.(?:eu|net|ch|co|at|ag))
2580 /embed\.php.+?)\1''', webpage)
2581 if mobj is not None:
2582 return self.url_result(mobj.group('url'))
2584 # Look for embedded Facebook player
2585 facebook_urls = FacebookIE._extract_urls(webpage)
2587 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2589 # Look for embedded VK player
2590 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2591 if mobj is not None:
2592 return self.url_result(mobj.group('url'), 'VK')
2594 # Look for embedded Odnoklassniki player
2595 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2596 if mobj is not None:
2597 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2599 # Look for embedded ivi player
2600 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2601 if mobj is not None:
2602 return self.url_result(mobj.group('url'), 'Ivi')
2604 # Look for embedded Huffington Post player
2606 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2607 if mobj is not None:
2608 return self.url_result(mobj.group('url'), 'HuffPost')
2611 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2612 if mobj is not None:
2613 return self.url_result(mobj.group('url'))
2614 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2615 if mobj is not None:
2616 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2618 # Look for funnyordie embed
2619 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2621 return self.playlist_from_matches(
2622 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2624 # Look for BBC iPlayer embed
2625 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2627 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2629 # Look for embedded RUTV player
2630 rutv_url = RUTVIE._extract_url(webpage)
2632 return self.url_result(rutv_url, 'RUTV')
2634 # Look for embedded TVC player
2635 tvc_url = TVCIE._extract_url(webpage)
2637 return self.url_result(tvc_url, 'TVC')
2639 # Look for embedded SportBox player
2640 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2642 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2644 # Look for embedded XHamster player
2645 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2647 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2649 # Look for embedded TNAFlixNetwork player
2650 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2652 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2654 # Look for embedded PornHub player
2655 pornhub_urls = PornHubIE._extract_urls(webpage)
2657 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2659 # Look for embedded DrTuber player
2660 drtuber_urls = DrTuberIE._extract_urls(webpage)
2662 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2664 # Look for embedded RedTube player
2665 redtube_urls = RedTubeIE._extract_urls(webpage)
2667 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2669 # Look for embedded Tube8 player
2670 tube8_urls = Tube8IE._extract_urls(webpage)
2672 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2674 # Look for embedded Tvigle player
2676 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2677 if mobj is not None:
2678 return self.url_result(mobj.group('url'), 'Tvigle')
2680 # Look for embedded TED player
2682 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2683 if mobj is not None:
2684 return self.url_result(mobj.group('url'), 'TED')
2686 # Look for embedded Ustream videos
2687 ustream_url = UstreamIE._extract_url(webpage)
2689 return self.url_result(ustream_url, UstreamIE.ie_key())
2691 # Look for embedded arte.tv player
2693 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2695 if mobj is not None:
2696 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2698 # Look for embedded francetv player
2700 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2702 if mobj is not None:
2703 return self.url_result(mobj.group('url'))
2705 # Look for embedded smotri.com player
2706 smotri_url = SmotriIE._extract_url(webpage)
2708 return self.url_result(smotri_url, 'Smotri')
2710 # Look for embedded Myvi.ru player
2711 myvi_url = MyviIE._extract_url(webpage)
2713 return self.url_result(myvi_url)
2715 # Look for embedded soundcloud player
2716 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2718 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2720 # Look for tunein player
2721 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2723 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2725 # Look for embedded mtvservices player
2726 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2728 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2730 # Look for embedded yahoo player
2732 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2734 if mobj is not None:
2735 return self.url_result(mobj.group('url'), 'Yahoo')
2737 # Look for embedded sbs.com.au player
2741 <meta\s+property="og:video"\s+content=|
2744 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2746 if mobj is not None:
2747 return self.url_result(mobj.group('url'), 'SBS')
2749 # Look for embedded Cinchcast player
2751 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2753 if mobj is not None:
2754 return self.url_result(mobj.group('url'), 'Cinchcast')
2757 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2761 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2763 if mobj is not None:
2764 return self.url_result(mobj.group('url'), 'MLB')
2767 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2769 if mobj is not None:
2770 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2773 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2775 if mobj is not None:
2776 return self.url_result(mobj.group('url'), 'Livestream')
2778 # Look for Zapiks embed
2780 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2781 if mobj is not None:
2782 return self.url_result(mobj.group('url'), 'Zapiks')
2784 # Look for Kaltura embeds
2785 kaltura_url = KalturaIE._extract_url(webpage)
2787 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2789 # Look for EaglePlatform embeds
2790 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2791 if eagleplatform_url:
2792 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2794 # Look for ClipYou (uses EaglePlatform) embeds
2796 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2797 if mobj is not None:
2798 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2800 # Look for Pladform embeds
2801 pladform_url = PladformIE._extract_url(webpage)
2803 return self.url_result(pladform_url)
2805 # Look for Videomore embeds
2806 videomore_url = VideomoreIE._extract_url(webpage)
2808 return self.url_result(videomore_url)
2810 # Look for Webcaster embeds
2811 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2813 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2815 # Look for Playwire embeds
2817 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2818 if mobj is not None:
2819 return self.url_result(mobj.group('url'))
2821 # Look for 5min embeds
2823 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2824 if mobj is not None:
2825 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2827 # Look for Crooks and Liars embeds
2829 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2830 if mobj is not None:
2831 return self.url_result(mobj.group('url'))
2833 # Look for NBC Sports VPlayer embeds
2834 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2836 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2838 # Look for NBC News embeds
2839 nbc_news_embed_url = re.search(
2840 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2841 if nbc_news_embed_url:
2842 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2844 # Look for Google Drive embeds
2845 google_drive_url = GoogleDriveIE._extract_url(webpage)
2846 if google_drive_url:
2847 return self.url_result(google_drive_url, 'GoogleDrive')
2849 # Look for UDN embeds
2851 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2852 if mobj is not None:
2853 return self.url_result(
2854 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2856 # Look for Senate ISVP iframe
2857 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2859 return self.url_result(senate_isvp_url, 'SenateISVP')
2861 # Look for OnionStudios embeds
2862 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2863 if onionstudios_url:
2864 return self.url_result(onionstudios_url)
2866 # Look for ViewLift embeds
2867 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2869 return self.url_result(viewlift_url)
2871 # Look for JWPlatform embeds
2872 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2874 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2876 # Look for Digiteka embeds
2877 digiteka_url = DigitekaIE._extract_url(webpage)
2879 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2881 # Look for Arkena embeds
2882 arkena_url = ArkenaIE._extract_url(webpage)
2884 return self.url_result(arkena_url, ArkenaIE.ie_key())
2886 # Look for Piksel embeds
2887 piksel_url = PikselIE._extract_url(webpage)
2889 return self.url_result(piksel_url, PikselIE.ie_key())
2891 # Look for Limelight embeds
2892 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2894 return self.playlist_result(
2895 limelight_urls, video_id, video_title, video_description)
2897 # Look for Anvato embeds
2898 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2900 return self.playlist_result(
2901 anvato_urls, video_id, video_title, video_description)
2903 # Look for AdobeTVVideo embeds
2905 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2907 if mobj is not None:
2908 return self.url_result(
2909 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2912 # Look for Vine embeds
2914 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2916 if mobj is not None:
2917 return self.url_result(
2918 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2920 # Look for VODPlatform embeds
2922 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2924 if mobj is not None:
2925 return self.url_result(
2926 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2928 # Look for Mangomolo embeds
2930 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2932 video\?.*?\bid=(?P<video_id>\d+)|
2933 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2934 ).+?)\1''', webpage)
2935 if mobj is not None:
2937 '_type': 'url_transparent',
2938 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2939 'title': video_title,
2940 'description': video_description,
2941 'thumbnail': video_thumbnail,
2942 'uploader': video_uploader,
2944 video_id = mobj.group('video_id')
2947 'ie_key': 'MangomoloVideo',
2952 'ie_key': 'MangomoloLive',
2953 'id': mobj.group('channel_id'),
2957 # Look for Instagram embeds
2958 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2959 if instagram_embed_url is not None:
2960 return self.url_result(
2961 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2963 # Look for LiveLeak embeds
2964 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2966 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2968 # Look for 3Q SDN embeds
2969 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2972 '_type': 'url_transparent',
2973 'ie_key': ThreeQSDNIE.ie_key(),
2974 'url': self._proto_relative_url(threeqsdn_url),
2975 'title': video_title,
2976 'description': video_description,
2977 'thumbnail': video_thumbnail,
2978 'uploader': video_uploader,
2981 # Look for VBOX7 embeds
2982 vbox7_url = Vbox7IE._extract_url(webpage)
2984 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2986 # Look for DBTV embeds
2987 dbtv_urls = DBTVIE._extract_urls(webpage)
2989 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2991 # Look for Videa embeds
2992 videa_urls = VideaIE._extract_urls(webpage)
2994 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2996 # Look for 20 minuten embeds
2997 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2999 return self.playlist_from_matches(
3000 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3002 # Look for Openload embeds
3003 openload_urls = OpenloadIE._extract_urls(webpage)
3005 return self.playlist_from_matches(
3006 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
3008 # Look for VideoPress embeds
3009 videopress_urls = VideoPressIE._extract_urls(webpage)
3011 return self.playlist_from_matches(
3012 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3014 # Look for Rutube embeds
3015 rutube_urls = RutubeIE._extract_urls(webpage)
3017 return self.playlist_from_matches(
3018 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3020 # Look for WashingtonPost embeds
3021 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3023 return self.playlist_from_matches(
3024 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3026 # Look for Mediaset embeds
3027 mediaset_urls = MediasetIE._extract_urls(webpage)
3029 return self.playlist_from_matches(
3030 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3032 # Look for JOJ.sk embeds
3033 joj_urls = JojIE._extract_urls(webpage)
3035 return self.playlist_from_matches(
3036 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3038 # Look for megaphone.fm embeds
3039 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3041 return self.playlist_from_matches(
3042 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3044 # Look for vzaar embeds
3045 vzaar_urls = VzaarIE._extract_urls(webpage)
3047 return self.playlist_from_matches(
3048 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3050 channel9_urls = Channel9IE._extract_urls(webpage)
3052 return self.playlist_from_matches(
3053 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3055 vshare_urls = VShareIE._extract_urls(webpage)
3057 return self.playlist_from_matches(
3058 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3060 # Look for Mediasite embeds
3061 mediasite_urls = MediasiteIE._extract_urls(webpage)
3064 self.url_result(smuggle_url(
3065 compat_urlparse.urljoin(url, mediasite_url),
3066 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3067 for mediasite_url in mediasite_urls]
3068 return self.playlist_result(entries, video_id, video_title)
3070 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3071 if springboardplatform_urls:
3072 return self.playlist_from_matches(
3073 springboardplatform_urls, video_id, video_title,
3074 ie=SpringboardPlatformIE.ie_key())
3076 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3078 return self.playlist_from_matches(
3079 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3081 vice_urls = ViceIE._extract_urls(webpage)
3083 return self.playlist_from_matches(
3084 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3086 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3088 return self.playlist_from_matches(
3089 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3091 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3092 if cloudflarestream_urls:
3093 return self.playlist_from_matches(
3094 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3096 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3098 return self.playlist_from_matches(
3099 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3101 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3103 return self.playlist_from_matches(
3104 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3106 apa_urls = APAIE._extract_urls(webpage)
3108 return self.playlist_from_matches(
3109 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3111 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3113 return self.playlist_from_matches(
3114 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3116 sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
3117 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3119 if sharevideos_urls:
3120 return self.playlist_from_matches(
3121 sharevideos_urls, video_id, video_title)
3123 viqeo_urls = ViqeoIE._extract_urls(webpage)
3125 return self.playlist_from_matches(
3126 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3128 expressen_urls = ExpressenIE._extract_urls(webpage)
3130 return self.playlist_from_matches(
3131 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3133 # Look for HTML5 media
3134 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3136 if len(entries) == 1:
3139 'title': video_title,
3142 for num, entry in enumerate(entries, start=1):
3144 'id': '%s-%s' % (video_id, num),
3145 'title': '%s (%d)' % (video_title, num),
3147 for entry in entries:
3148 self._sort_formats(entry['formats'])
3149 return self.playlist_result(entries, video_id, video_title)
3151 jwplayer_data = self._find_jwplayer_data(
3152 webpage, video_id, transform_source=js_to_json)
3154 info = self._parse_jwplayer_data(
3155 jwplayer_data, video_id, require_title=False, base_url=url)
3156 return merge_dicts(info, info_dict)
3160 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3162 if mobj is not None:
3163 sources = self._parse_json(
3164 mobj.group(1), video_id, transform_source=js_to_json,
3166 if not isinstance(sources, list):
3169 for source in sources:
3170 src = source.get('src')
3171 if not src or not isinstance(src, compat_str):
3173 src = compat_urlparse.urljoin(url, src)
3174 src_type = source.get('type')
3175 if isinstance(src_type, compat_str):
3176 src_type = src_type.lower()
3177 ext = determine_ext(src).lower()
3178 if src_type == 'video/youtube':
3179 return self.url_result(src, YoutubeIE.ie_key())
3180 if src_type == 'application/dash+xml' or ext == 'mpd':
3181 formats.extend(self._extract_mpd_formats(
3182 src, video_id, mpd_id='dash', fatal=False))
3183 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3184 formats.extend(self._extract_m3u8_formats(
3185 src, video_id, 'mp4', entry_protocol='m3u8_native',
3186 m3u8_id='hls', fatal=False))
3190 'ext': (mimetype2ext(src_type) or
3191 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3194 self._sort_formats(formats)
3195 info_dict['formats'] = formats
3198 # Looking for http://schema.org/VideoObject
3199 json_ld = self._search_json_ld(
3200 webpage, video_id, default={}, expected_type='VideoObject')
3201 if json_ld.get('url'):
3202 return merge_dicts(json_ld, info_dict)
3204 def check_video(vurl):
3205 if YoutubeIE.suitable(vurl):
3207 if RtmpIE.suitable(vurl):
3209 vpath = compat_urlparse.urlparse(vurl).path
3210 vext = determine_ext(vpath)
3211 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3213 def filter_video(urls):
3214 return list(filter(check_video, urls))
3216 # Start with something easy: JW Player in SWFObject
3217 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3219 # Look for gorilla-vid style embedding
3220 found = filter_video(re.findall(r'''(?sx)
3224 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3227 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3229 # Broaden the search a little bit
3230 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3232 # Broaden the findall a little bit: JWPlayer JS loader
3233 found = filter_video(re.findall(
3234 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3237 found = filter_video(re.findall(r'''(?xs)
3238 flowplayer\("[^"]+",\s*
3240 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3241 ["']?url["']?\s*:\s*["']([^"']+)["']
3246 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3248 # Try to find twitter cards info
3249 # twitter:player:stream should be checked before twitter:player since
3250 # it is expected to contain a raw stream (see
3251 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3252 found = filter_video(re.findall(
3253 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3255 # We look for Open Graph info:
3256 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3257 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3258 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3259 if m_video_type is not None:
3260 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3262 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3264 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3265 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3268 # Look also in Refresh HTTP header
3269 refresh_header = head_response.headers.get('Refresh')
3271 # In python 2 response HTTP headers are bytestrings
3272 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3273 refresh_header = refresh_header.decode('iso-8859-1')
3274 found = re.search(REDIRECT_REGEX, refresh_header)
3276 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3278 self.report_following_redirect(new_url)
3287 # twitter:player is a https URL to iframe player that may or may not
3288 # be supported by youtube-dl thus this is checked the very last (see
3289 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3290 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3291 if embed_url and embed_url != url:
3292 return self.url_result(embed_url)
3295 raise UnsupportedError(url)
3298 for video_url in orderedSet(found):
3299 video_url = unescapeHTML(video_url)
3300 video_url = video_url.replace('\\/', '/')
3301 video_url = compat_urlparse.urljoin(url, video_url)
3302 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3304 # Sometimes, jwplayer extraction will result in a YouTube URL
3305 if YoutubeIE.suitable(video_url):
3306 entries.append(self.url_result(video_url, 'Youtube'))
3309 # here's a fun little line of code for you:
3310 video_id = os.path.splitext(video_id)[0]
3314 'uploader': video_uploader,
3315 'title': video_title,
3316 'age_limit': age_limit,
3319 if RtmpIE.suitable(video_url):
3320 entry_info_dict.update({
3321 '_type': 'url_transparent',
3322 'ie_key': RtmpIE.ie_key(),
3325 entries.append(entry_info_dict)
3328 ext = determine_ext(video_url)
3330 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3332 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3334 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3336 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3338 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3339 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3340 # Just matching .ism/manifest is not enough to be reliably sure
3341 # whether it's actually an ISM manifest or some other streaming
3342 # manifest since there are various streaming URL formats
3343 # possible (see [1]) as well as some other shenanigans like
3344 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3346 # Thus the most reasonable way to solve this is to delegate
3347 # to generic extractor in order to look into the contents of
3348 # the manifest itself.
3349 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3350 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3351 entry_info_dict = self.url_result(
3352 smuggle_url(video_url, {'to_generic': True}),
3355 entry_info_dict['url'] = video_url
3357 if entry_info_dict.get('formats'):
3358 self._sort_formats(entry_info_dict['formats'])
3360 entries.append(entry_info_dict)
3362 if len(entries) == 1:
3365 for num, e in enumerate(entries, start=1):
3366 # 'url' results don't have a title
3367 if e.get('title') is not None:
3368 e['title'] = '%s (%d)' % (e['title'], num)
3370 '_type': 'playlist',