3 from __future__ import unicode_literals
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_urllib_parse_unquote,
15 compat_xml_parse_error,
33 from .commonprotocols import RtmpIE
34 from .brightcove import (
38 from .nbc import NBCSportsVPlayerIE
39 from .ooyala import OoyalaIE
40 from .rutv import RUTVIE
41 from .tvc import TVCIE
42 from .sportbox import SportBoxEmbedIE
43 from .smotri import SmotriIE
44 from .myvi import MyviIE
45 from .condenast import CondeNastIE
46 from .udn import UDNEmbedIE
47 from .senateisvp import SenateISVPIE
48 from .svt import SVTIE
49 from .pornhub import PornHubIE
50 from .xhamster import XHamsterEmbedIE
51 from .tnaflix import TNAFlixNetworkEmbedIE
52 from .drtuber import DrTuberIE
53 from .redtube import RedTubeIE
54 from .vimeo import VimeoIE
55 from .dailymotion import (
59 from .onionstudios import OnionStudiosIE
60 from .viewlift import ViewLiftEmbedIE
61 from .mtv import MTVServicesEmbeddedIE
62 from .pladform import PladformIE
63 from .videomore import VideomoreIE
64 from .webcaster import WebcasterFeedIE
65 from .googledrive import GoogleDriveIE
66 from .jwplatform import JWPlatformIE
67 from .digiteka import DigitekaIE
68 from .arkena import ArkenaIE
69 from .instagram import InstagramIE
70 from .liveleak import LiveLeakIE
71 from .threeqsdn import ThreeQSDNIE
72 from .theplatform import ThePlatformIE
73 from .vessel import VesselIE
74 from .kaltura import KalturaIE
75 from .eagleplatform import EaglePlatformIE
76 from .facebook import FacebookIE
77 from .soundcloud import SoundcloudIE
78 from .tunein import TuneInBaseIE
79 from .vbox7 import Vbox7IE
80 from .dbtv import DBTVIE
81 from .piksel import PikselIE
82 from .videa import VideaIE
83 from .twentymin import TwentyMinutenIE
84 from .ustream import UstreamIE
85 from .openload import OpenloadIE
86 from .videopress import VideoPressIE
87 from .rutube import RutubeIE
88 from .limelight import LimelightBaseIE
91 class GenericIE(InfoExtractor):
92 IE_DESC = 'Generic downloader that works on some sites'
96 # Direct link to a video
98 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
99 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
104 'upload_date': '20100513',
107 # Direct link to media delivered compressed (until Accept-Encoding is *)
109 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
110 'md5': '128c42e68b13950268b648275386fc74',
112 'id': 'FictionJunction-Parallel_Hearts',
114 'title': 'FictionJunction-Parallel_Hearts',
115 'upload_date': '20140522',
117 'expected_warnings': [
118 'URL could be a direct video link, returning it as such.'
120 'skip': 'URL invalid',
122 # Direct download with broken HEAD
124 'url': 'http://ai-radio.org:8000/radio.opus',
131 'skip_download': True, # infinite live stream
133 'expected_warnings': [
134 r'501.*Not Implemented',
138 # Direct link with incorrect MIME type
140 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
141 'md5': '4ccbebe5f36706d85221f204d7eb5913',
143 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
144 'id': '5_Lennart_Poettering_-_Systemd',
146 'title': '5_Lennart_Poettering_-_Systemd',
147 'upload_date': '20141120',
149 'expected_warnings': [
150 'URL could be a direct video link, returning it as such.'
155 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
157 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
158 'title': 'Zero Punctuation',
159 'description': 're:.*groundbreaking video review series.*'
161 'playlist_mincount': 11,
163 # RSS feed with enclosure
165 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
167 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
169 'upload_date': '20150228',
170 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
173 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
175 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
179 'title': 'Automatics, robotics and biocybernetics',
180 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
181 'upload_date': '20130627',
182 'formats': 'mincount:16',
183 'subtitles': 'mincount:1',
186 'force_generic_extractor': True,
187 'skip_download': True,
190 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
192 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
197 'formats': 'mincount:1',
200 'skip_download': True,
203 # SMIL from https://www.restudy.dk/video/play/id/1637
205 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
209 'title': 'video_1637',
210 'formats': 'mincount:3',
213 'skip_download': True,
216 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
218 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
220 'id': 'smil-service',
222 'title': 'smil-service',
223 'formats': 'mincount:1',
226 'skip_download': True,
229 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
231 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
235 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
236 'formats': 'mincount:3',
239 'skip_download': True,
242 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
244 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
246 'id': 'mZlp2ctYIUEB',
248 'title': 'Tikibad ontruimd wegens brand',
249 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
250 'thumbnail': r're:^https?://.*\.jpg$',
254 'skip_download': True,
257 # MPD from http://dash-mse-test.appspot.com/media.html
259 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
260 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
262 'id': 'car-20120827-manifest',
264 'title': 'car-20120827-manifest',
265 'formats': 'mincount:9',
266 'upload_date': '20130904',
269 'format': 'bestvideo',
272 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
274 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
279 'formats': 'mincount:8',
283 'skip_download': True,
285 'skip': 'video gone',
287 # m3u8 served with Content-Type: text/plain
289 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
294 'upload_date': '20140720',
295 'formats': 'mincount:11',
299 'skip_download': True,
301 'skip': 'video gone',
305 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
309 'upload_date': '20130224',
310 'uploader_id': 'TheVerge',
311 'description': r're:^Chris Ziegler takes a look at the\.*',
312 'uploader': 'The Verge',
313 'title': 'First Firefox OS phones side-by-side',
316 'skip_download': False,
320 # redirect in Refresh HTTP header
321 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
325 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
326 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
327 'upload_date': '20150917',
328 'uploader_id': 'brtvofficial',
329 'uploader': 'Boiler Room',
332 'skip_download': False,
336 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
337 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
339 'id': '13601338388002',
341 'uploader': 'www.hodiho.fr',
342 'title': 'R\u00e9gis plante sa Jeep',
345 # bandcamp page with custom domain
347 'add_ie': ['Bandcamp'],
348 'url': 'http://bronyrock.com/track/the-pony-mash',
352 'title': 'The Pony Mash',
353 'uploader': 'M_Pallante',
355 'skip': 'There is a limit of 200 free downloads / month for the test song',
358 # embedded brightcove video
359 # it also tests brightcove videos that need to set the 'Referer'
360 # in the http requests
361 'add_ie': ['BrightcoveLegacy'],
362 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
364 'id': '2765128793001',
366 'title': 'Le cours de bourse : l’analyse technique',
367 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
368 'uploader': 'BFM BUSINESS',
371 'skip_download': True,
375 # embedded with itemprop embedURL and video id spelled as `idVideo`
376 'add_id': ['BrightcoveLegacy'],
377 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
379 'id': '5255628253001',
381 'title': 'md5:37c519b1128915607601e75a87995fc0',
382 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
383 'uploader': 'BFM BUSINESS',
384 'uploader_id': '876450612001',
385 'timestamp': 1482255315,
386 'upload_date': '20161220',
389 'skip_download': True,
393 # https://github.com/rg3/youtube-dl/issues/2253
394 'url': 'http://bcove.me/i6nfkrc3',
395 'md5': '0ba9446db037002366bab3b3eb30c88c',
397 'id': '3101154703001',
399 'title': 'Still no power',
400 'uploader': 'thestar.com',
401 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
403 'add_ie': ['BrightcoveLegacy'],
404 'skip': 'video gone',
407 'url': 'http://www.championat.com/video/football/v/87/87499.html',
408 'md5': 'fb973ecf6e4a78a67453647444222983',
410 'id': '3414141473001',
412 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
413 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
414 'uploader': 'Championat',
418 # https://github.com/rg3/youtube-dl/issues/3541
419 'add_ie': ['BrightcoveLegacy'],
420 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
422 'id': '3866516442001',
424 'title': 'Leer mij vrouwen kennen: Aflevering 1',
425 'description': 'Leer mij vrouwen kennen: Aflevering 1',
426 'uploader': 'SBS Broadcasting',
428 'skip': 'Restricted to Netherlands',
430 'skip_download': True, # m3u8 download
434 # Brightcove with alternative playerID key
435 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
437 'id': 'nmeth.2062_SV1',
438 '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',
442 'id': '2228375078001',
444 'title': 'nmeth.2062-sv1',
445 'description': 'nmeth.2062-sv1',
446 'timestamp': 1363357591,
447 'upload_date': '20130315',
448 'uploader': 'Nature Publishing Group',
449 'uploader_id': '1964492299001',
454 # Brightcove with UUID in videoPlayer
455 'url': 'http://www8.hp.com/cn/zh/home.html',
457 'id': '5255815316001',
459 'title': 'Sprocket Video - China',
460 'description': 'Sprocket Video - China',
461 'uploader': 'HP-Video Gallery',
462 'timestamp': 1482263210,
463 'upload_date': '20161220',
464 'uploader_id': '1107601872001',
467 'skip_download': True, # m3u8 download
469 'skip': 'video rotates...weekly?',
472 # Brightcove:new type [2].
473 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
474 'md5': '2b35148fcf48da41c9fb4591650784f3',
476 'id': '5348741021001',
478 'upload_date': '20170306',
479 'uploader_id': '4191638492001',
480 'timestamp': 1488769918,
481 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
486 # Alternative brightcove <video> attributes
487 '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/',
489 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
490 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
493 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
495 'id': '5311302538001',
497 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
498 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
499 'timestamp': 1486321708,
500 'upload_date': '20170205',
501 'uploader_id': '800000640001',
503 'only_matching': True,
507 # Brightcove with UUID in videoPlayer
508 'url': 'http://www8.hp.com/cn/zh/home.html',
510 'id': '5255815316001',
512 'title': 'Sprocket Video - China',
513 'description': 'Sprocket Video - China',
514 'uploader': 'HP-Video Gallery',
515 'timestamp': 1482263210,
516 'upload_date': '20161220',
517 'uploader_id': '1107601872001',
520 'skip_download': True, # m3u8 download
525 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
526 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
528 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
530 'title': '2cc213299525360.mov', # that's what we get
533 'add_ie': ['Ooyala'],
536 # ooyala video embedded with http://player.ooyala.com/iframe.js
537 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
539 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
541 'title': '"Steve Jobs: Man in the Machine" trailer',
542 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
546 'skip_download': True,
548 'skip': 'movie expired',
552 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
556 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
557 'upload_date': '20140225',
558 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
559 'uploader': 'Tested',
560 'uploader_id': 'testedcom',
562 # No need to test YoutubeIE here
564 'skip_download': True,
569 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
573 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
574 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
576 # HEAD requests lead to endless 301, while GET is OK
577 'expected_warnings': ['301'],
581 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
585 'title': 'Охотское море стало целиком российским',
586 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
590 'skip_download': True,
595 '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/',
599 'title': 'Дошкольное воспитание',
604 'url': 'http://www.vestifinance.ru/articles/25753',
607 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
612 'title': 'Госзаказ. День 3',
618 'title': 'Госзаказ. День 2',
624 'title': 'Госзаказ. День 1',
630 'skip_download': True,
635 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
637 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
639 'title': 'Ужастики, русский трейлер (2015)',
640 'thumbnail': r're:^https?://.*\.jpg$',
646 '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',
649 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
651 'playlist_mincount': 7,
652 # This forum does not allow <iframe> syntaxes anymore
653 # Now HTML tags are displayed as-is
654 'skip': 'No videos on this page',
658 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
659 'md5': '65fdff94098e4a607385a60c5177c638',
663 'title': 'Hidden miracles of the natural world',
664 'uploader': 'Louie Schwartzberg',
665 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
668 # nowvideo embed hidden behind percent encoding
670 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
671 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
673 'id': '06e53103ca9aa',
675 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
676 'description': 'No description',
681 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
682 'md5': '7653032cbb25bf6c80d80f217055fa43',
684 'id': '048195-004_PLUS7-F',
687 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
688 'upload_date': '20140320',
691 'skip_download': 'Requires rtmpdump'
693 'skip': 'video gone',
697 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
701 'title': 'Alcaline, le concert avec Calogero',
702 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
703 'upload_date': '20150226',
704 'timestamp': 1424989860,
709 'skip_download': True,
711 'expected_warnings': [
717 'url': 'http://www.wired.com/2014/04/honda-asimo/',
718 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
720 'id': '53501be369702d3275860000',
722 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
727 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
728 'md5': '441aeeb82eb72c422c7f14ec533999cd',
730 'id': 'k2mm4bCdJ6CQ2i7c8o2',
732 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
733 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
735 'uploader_id': 'xgditw',
736 'upload_date': '20140425',
737 'timestamp': 1398441542,
739 'add_ie': ['Dailymotion'],
743 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
747 'title': 'The NBL Auction 2014',
748 'uploader': 'BADMINTON England',
749 'uploader_id': 'BADMINTONEvents',
750 'upload_date': '20140603',
751 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
753 'add_ie': ['Youtube'],
755 'skip_download': True,
760 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
761 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
763 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
765 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
766 'description': 'Two valets share their love for movie star Liam Neesons.',
767 'timestamp': 1349922600,
768 'upload_date': '20121011',
771 # YouTube embed via <data-embed-url="">
773 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
777 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
778 'uploader': 'Gameloft',
779 'uploader_id': 'gameloft',
780 'upload_date': '20140828',
781 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
784 'skip_download': True,
787 # YouTube <object> embed
789 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
790 'md5': '516718101ec834f74318df76259fb3cc',
794 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
795 'upload_date': '20080526',
796 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
797 'uploader': 'Christopher Sykes',
798 'uploader_id': 'ChristopherJSykes',
800 'add_ie': ['Youtube'],
804 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
806 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
808 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
809 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
814 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
816 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
817 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
823 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
828 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
829 'md5': '9d65602bf31c6e20014319c7d07fba27',
831 'id': '5123ea6d5e5a7',
834 'uploader': 'www.handjobhub.com',
835 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
838 # Multiple brightcove videos
839 # https://github.com/rg3/youtube-dl/issues/2283
841 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
843 'id': 'always-never',
844 'title': 'Always / Never - The New Yorker',
848 'extract_flat': False,
849 'skip_download': True,
854 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
855 'md5': '96f09a37e44da40dd083e12d9a683327',
859 'title': 'Ump changes call to ball',
860 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
862 'timestamp': 1401537900,
863 'upload_date': '20140531',
864 'thumbnail': r're:^https?://.*\.jpg$',
869 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
870 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
874 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
875 'description': 'a Paywall Videos video from Remilon',
877 'uploader': 'study.com',
878 'timestamp': 1459678540,
879 'upload_date': '20160403',
880 'filesize': 24687186,
884 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
885 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
889 'title': 'Conversation about Hexagonal Rails Part 1',
890 'description': 'a Martin Fowler video from ThoughtWorks',
892 'uploader': 'thoughtworks.wistia.com',
893 'timestamp': 1401832161,
894 'upload_date': '20140603',
897 # Wistia standard embed (async)
899 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
903 'title': 'Drip Brennan Dunn Workshop',
904 'description': 'a JV Webinars video from getdrip-1',
906 'timestamp': 1463607249,
907 'upload_date': '20160518',
910 'skip_download': True,
915 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
919 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
920 'uploader': 'Sophos Security',
921 'title': 'Chet Chat 171 - Oct 29, 2014',
922 'upload_date': '20141029',
925 # Soundcloud multiple embeds
927 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
930 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
932 'playlist_mincount': 7,
934 # TuneIn station embed
936 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
941 'location': 'Paris, France',
946 'skip_download': True,
951 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
955 'upload_date': '20141112',
956 'title': 'Rosetta #CometLanding webcast HL 10',
959 # Another Livestream embed, without 'new.' in URL
961 'url': 'https://www.freespeech.org/',
965 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
969 'skip_download': True,
974 'url': 'https://skiplagged.com/',
977 'title': 'Skiplagged: The smart way to find cheap flights',
979 'playlist_mincount': 1,
980 'add_ie': ['Youtube'],
984 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
988 'upload_date': '20141126',
989 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
994 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
996 'id': '730m_DandD_1901_512k',
998 'uploader': 'www.abc.net.au',
999 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1002 # embedded viddler video
1004 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1008 'uploader': 'deadspin',
1009 'title': 'WALL-TO-GORTAT',
1010 'timestamp': 1422285291,
1011 'upload_date': '20150126',
1013 'add_ie': ['Viddler'],
1017 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1021 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1022 'description': 'md5:601cb790edd05908957dae8aaa866465',
1023 'upload_date': '20150220',
1025 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1029 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1031 'id': 'Mrj4DVp2zeA',
1033 'upload_date': '20150212',
1034 'uploader': 'The National Archives UK',
1035 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1036 'uploader_id': 'NationalArchives08',
1037 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1042 'url': 'http://www.suffolk.edu/sjc/',
1046 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1047 'uploader': 'www.suffolk.edu',
1050 'skip_download': True,
1055 'url': 'http://www.indiedb.com/games/king-machine/videos',
1059 'title': 'king machine trailer 1',
1060 'thumbnail': r're:^https?://.*\.jpg$',
1064 # JWPlayer config passed as variable
1065 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1069 'title': 'ARIELE | Tube Cup',
1070 'uploader': 'www.txxx.com',
1074 'skip_download': True,
1079 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1080 'playlist_mincount': 5,
1082 'id': 'aanslagen-kopenhagen',
1083 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1088 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1092 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1095 # Kaltura embed (different embed code)
1097 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1101 'upload_date': '20150127',
1102 'uploader_id': 'PremierMedia',
1104 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1107 # Kaltura embed with single quotes
1109 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1114 'timestamp': 1355743100,
1115 'upload_date': '20121217',
1116 'uploader_id': 'batchUser',
1118 'add_ie': ['Kaltura'],
1121 # Kaltura embedded via quoted entry_id
1122 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1126 'title': '06_matthew_brender_raj_dutt',
1127 'timestamp': 1466638791,
1128 'upload_date': '20160622',
1130 'add_ie': ['Kaltura'],
1131 'expected_warnings': [
1132 'Could not send HEAD request'
1135 'skip_download': True,
1139 # Kaltura embedded, some fileExt broken (#11480)
1140 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1144 'title': 'Our "Standard Models" of particle physics and cosmology',
1145 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1146 'timestamp': 1321158993,
1147 'upload_date': '20111113',
1148 'uploader_id': 'kps1',
1150 'add_ie': ['Kaltura'],
1153 # Kaltura iframe embed
1154 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1155 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1159 'title': 'I. M. Pei: A Centennial Celebration',
1160 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1161 'upload_date': '20170403',
1162 'uploader_id': 'batchUser',
1163 'timestamp': 1491232186,
1165 'add_ie': ['Kaltura'],
1167 # Eagle.Platform embed (generic URL)
1169 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1170 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1174 'title': 'Навальный вышел на свободу',
1175 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1176 'thumbnail': r're:^https?://.*\.jpg$',
1182 # ClipYou (Eagle.Platform) embed (custom URL)
1184 'url': 'http://muz-tv.ru/play/7129/',
1185 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1189 'title': "'O Sole Mio",
1190 'thumbnail': r're:^https?://.*\.jpg$',
1197 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1201 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1202 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1203 'thumbnail': r're:^https?://.*\.jpg$',
1210 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1214 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1215 'thumbnail': r're:^https?://.*\.png$',
1221 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1222 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1226 'title': 'Facebook Creates "On This Day" | Crunch Report',
1231 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1235 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1240 # Crooks and Liars embed
1242 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1246 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1247 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1248 'timestamp': 1428207000,
1249 'upload_date': '20150405',
1250 'uploader': 'Heather',
1253 # Crooks and Liars external embed
1255 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1257 'id': 'MTE3MjUtMzQ2MzA',
1259 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1260 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1261 'timestamp': 1265032391,
1262 'upload_date': '20100201',
1263 'uploader': 'Heather',
1266 # NBC Sports vplayer embed
1268 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1270 'id': 'ln7x1qSThw4k',
1272 'title': "PFT Live: New leader in the 'new-look' defense",
1273 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1274 'uploader': 'NBCU-SPORTS',
1275 'upload_date': '20140107',
1276 'timestamp': 1389118457,
1281 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1282 'md5': '1aa589c675898ae6d37a17913cf68d66',
1284 'id': '701714499682',
1286 'title': 'PREVIEW: On Assignment: David Letterman',
1287 '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.',
1292 'url': 'https://video.udn.com/news/300346',
1293 'md5': 'fd2060e988c326991037b9aff9df21a6',
1297 'title': '中一中男師變性 全校師生力挺',
1298 'thumbnail': r're:^https?://.*\.jpg$',
1302 'skip_download': True,
1307 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1309 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1311 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1312 'title': 'This is what separates the Excel masters from the wannabes',
1313 'duration': 191.933,
1317 'skip_download': True,
1320 # Brightcove URL in single quotes
1322 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1323 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1325 'id': '4255764656001',
1327 'title': 'SN Presents: Russell Martin, World Citizen',
1328 '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.',
1329 'uploader': 'Rogers Sportsnet',
1330 'uploader_id': '1704050871',
1331 'upload_date': '20150525',
1332 'timestamp': 1432570283,
1335 # Dailymotion Cloud video
1337 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1338 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1342 'title': 'Sauvons les abeilles ! - Le débat',
1343 'description': 'md5:d9082128b1c5277987825d684939ca26',
1344 'thumbnail': r're:^https?://.*\.jpe?g$',
1345 'timestamp': 1434970506,
1346 'upload_date': '20150622',
1347 'uploader': 'Public Sénat',
1348 'uploader_id': 'xa9gza',
1351 # OnionStudios embed
1353 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1357 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1358 'thumbnail': r're:^https?://.*\.jpe?g$',
1359 'uploader': 'ClickHole',
1360 'uploader_id': 'clickhole',
1365 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1367 'id': '74849a00-85a9-11e1-9660-123139220831',
1369 'title': '#whilewewatch',
1372 # AdobeTVVideo embed
1374 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1375 'md5': '43662b577c018ad707a63766462b1e87',
1379 'title': 'New experience with Acrobat DC',
1380 'description': 'New experience with Acrobat DC',
1381 'duration': 248.667,
1384 # BrightcoveInPageEmbed embed
1386 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1388 'id': '4238694884001',
1390 'title': 'Tabletop: Dread, Last Thoughts',
1391 'description': 'Tabletop: Dread, Last Thoughts',
1395 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1396 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1398 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1400 'id': '4785848093001',
1402 'title': 'The Cardinal Pell Interview',
1403 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1404 'uploader': 'GlobeCast Australia - GlobeStream',
1405 'uploader_id': '2733773828001',
1406 'upload_date': '20160304',
1407 'timestamp': 1457083087,
1411 'skip_download': True,
1414 # Another form of arte.tv embed
1416 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1417 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1419 'id': '030273-562_PLUS7-F',
1421 'title': 'ARTE Reportage - Nulle part, en France',
1422 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1423 'upload_date': '20160409',
1428 'url': 'http://www.wykop.pl/link/3088787/',
1429 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1431 'id': '874_1459135191',
1433 'title': 'Man shows poor quality of new apartment building',
1434 'description': 'The wall is like a sand pile.',
1435 'uploader': 'Lake8737',
1438 # Duplicated embedded video URLs
1440 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1442 'id': '149298443_480_16c25b74_2',
1444 'title': 'vs. Blue Orange Spring Game',
1445 'uploader': 'www.hudl.com',
1448 # twitter:player:stream embed
1450 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1454 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1455 'uploader': 'www.rtl.be',
1459 'skip_download': True,
1462 # twitter:player embed
1464 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1465 'md5': 'a3e0df96369831de324f0778e126653c',
1467 'id': '4909620399001',
1469 'title': 'What Do Black Holes Sound Like?',
1470 'description': 'what do black holes sound like',
1471 'upload_date': '20160524',
1472 'uploader_id': '29913724001',
1473 'timestamp': 1464107587,
1474 'uploader': 'TheAtlantic',
1476 'add_ie': ['BrightcoveLegacy'],
1478 # Facebook <iframe> embed
1480 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1481 'md5': 'fbcde74f534176ecb015849146dd3aee',
1483 'id': '599637780109885',
1485 'title': 'Facebook video #599637780109885',
1488 # Facebook API embed
1490 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1491 'md5': 'a47372ee61b39a7b90287094d447d94e',
1493 'id': '10153467542406923',
1495 'title': 'Facebook video #10153467542406923',
1498 # Wordpress "YouTube Video Importer" plugin
1500 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1501 'md5': 'd16797741b560b485194eddda8121b48',
1503 'id': 'HNTXWDXV9Is',
1505 'title': 'Blue Devils Drumline Stanford lot 2016',
1506 'upload_date': '20160627',
1507 'uploader_id': 'GENOCIDE8GENERAL10',
1508 'uploader': 'cylus cyrus',
1512 # video stored on custom kaltura server
1513 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1514 'md5': '537617d06e64dfed891fa1593c4b30cc',
1518 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1519 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1520 'uploader_id': 'videos.expansion@el-mundo.net',
1521 'upload_date': '20150429',
1522 'timestamp': 1430303472,
1524 'add_ie': ['Kaltura'],
1527 # Non-standard Vimeo embed
1528 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1529 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1533 'title': 'Understanding the web - Teaser',
1534 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1535 'upload_date': '20151214',
1536 'uploader': 'OpenClassrooms',
1537 'uploader_id': 'openclassrooms',
1539 'add_ie': ['Vimeo'],
1542 # generic vimeo embed that requires original URL passed as Referer
1543 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1544 'only_matching': True,
1547 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1548 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1550 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1552 'title': 'Big Buck Bunny',
1553 'description': 'Royalty free test video',
1554 'timestamp': 1432816365,
1555 'upload_date': '20150528',
1559 'skip_download': True,
1561 'add_ie': [ArkenaIE.ie_key()],
1564 '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/',
1568 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1571 'skip_download': True,
1573 'add_ie': [Vbox7IE.ie_key()],
1577 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1580 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1582 'playlist_mincount': 3,
1586 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1588 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1589 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1591 'playlist_mincount': 2,
1595 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1599 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1600 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1603 'skip_download': True,
1605 'add_ie': [TwentyMinutenIE.ie_key()],
1609 'url': 'https://en.support.wordpress.com/videopress/',
1613 'title': 'IMG_5786',
1614 'timestamp': 1435711927,
1615 'upload_date': '20150701',
1618 'skip_download': True,
1620 'add_ie': [VideoPressIE.ie_key()],
1624 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1626 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1628 'title': 'Магаззино: Казань 2',
1629 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1630 'uploader': 'Магаззино',
1631 'upload_date': '20170228',
1632 'uploader_id': '996642',
1635 'skip_download': True,
1637 'add_ie': [RutubeIE.ie_key()],
1640 # ThePlatform embedded with whitespaces in URLs
1641 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1642 'only_matching': True,
1645 # Senate ISVP iframe https
1646 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1647 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1649 'id': 'govtaff020316',
1651 'title': 'Integrated Senate Video Player',
1653 'add_ie': [SenateISVPIE.ie_key()],
1656 # Limelight embeds (1 channel embed + 4 media embeds)
1657 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1659 'id': 'FacilitatorTraining2017',
1660 'title': 'Facilitator Training 2017',
1662 'playlist_mincount': 5,
1665 # # TODO: find another test
1666 # # http://schema.org/VideoObject
1667 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1668 # 'md5': '888dcf08b7ea671381f00fab74692755',
1670 # 'id': 'nyvTSJMKId',
1672 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1673 # 'description': '#love for cats.',
1674 # 'timestamp': 1461244995,
1675 # 'upload_date': '20160421',
1678 # 'force_generic_extractor': True,
1683 def report_following_redirect(self, new_url):
1684 """Report information extraction."""
1685 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1687 def _extract_rss(self, url, video_id, doc):
1688 playlist_title = doc.find('./channel/title').text
1689 playlist_desc_el = doc.find('./channel/description')
1690 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1693 for it in doc.findall('./channel/item'):
1694 next_url = xpath_text(it, 'link', fatal=False)
1696 enclosure_nodes = it.findall('./enclosure')
1697 for e in enclosure_nodes:
1698 next_url = e.attrib.get('url')
1706 '_type': 'url_transparent',
1708 'title': it.find('title').text,
1712 '_type': 'playlist',
1714 'title': playlist_title,
1715 'description': playlist_desc,
1719 def _extract_camtasia(self, url, video_id, webpage):
1720 """ Returns None if no camtasia video can be found. """
1722 camtasia_cfg = self._search_regex(
1723 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1724 webpage, 'camtasia configuration file', default=None)
1725 if camtasia_cfg is None:
1728 title = self._html_search_meta('DC.title', webpage, fatal=True)
1730 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1731 camtasia_cfg = self._download_xml(
1732 camtasia_url, video_id,
1733 note='Downloading camtasia configuration',
1734 errnote='Failed to download camtasia configuration')
1735 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1738 for n in fileset_node.getchildren():
1739 url_n = n.find('./uri')
1744 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1745 'title': '%s - %s' % (title, n.tag),
1746 'url': compat_urlparse.urljoin(url, url_n.text),
1747 'duration': float_or_none(n.find('./duration').text),
1751 '_type': 'playlist',
1756 def _real_extract(self, url):
1757 if url.startswith('//'):
1760 'url': self.http_scheme() + url,
1763 parsed_url = compat_urlparse.urlparse(url)
1764 if not parsed_url.scheme:
1765 default_search = self._downloader.params.get('default_search')
1766 if default_search is None:
1767 default_search = 'fixup_error'
1769 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1771 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1772 return self.url_result('http://' + url)
1773 elif default_search != 'fixup_error':
1774 if default_search == 'auto_warning':
1775 if re.match(r'^(?:url|URL)$', url):
1776 raise ExtractorError(
1777 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1780 self._downloader.report_warning(
1781 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1782 return self.url_result('ytsearch:' + url)
1784 if default_search in ('error', 'fixup_error'):
1785 raise ExtractorError(
1786 '%r is not a valid URL. '
1787 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1788 % (url, url), expected=True)
1790 if ':' not in default_search:
1791 default_search += ':'
1792 return self.url_result(default_search + url)
1794 url, smuggled_data = unsmuggle_url(url)
1795 force_videoid = None
1796 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1797 if smuggled_data and 'force_videoid' in smuggled_data:
1798 force_videoid = smuggled_data['force_videoid']
1799 video_id = force_videoid
1801 video_id = self._generic_id(url)
1803 self.to_screen('%s: Requesting header' % video_id)
1805 head_req = HEADRequest(url)
1806 head_response = self._request_webpage(
1808 note=False, errnote='Could not send HEAD request to %s' % url,
1811 if head_response is not False:
1812 # Check for redirect
1813 new_url = head_response.geturl()
1815 self.report_following_redirect(new_url)
1817 new_url = smuggle_url(
1818 new_url, {'force_videoid': force_videoid})
1819 return self.url_result(new_url)
1821 full_response = None
1822 if head_response is False:
1823 request = sanitized_Request(url)
1824 request.add_header('Accept-Encoding', '*')
1825 full_response = self._request_webpage(request, video_id)
1826 head_response = full_response
1830 'title': self._generic_title(url),
1831 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1834 # Check for direct link to a video
1835 content_type = head_response.headers.get('Content-Type', '').lower()
1836 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1838 format_id = m.group('format_id')
1839 if format_id.endswith('mpegurl'):
1840 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1841 elif format_id == 'f4m':
1842 formats = self._extract_f4m_formats(url, video_id)
1845 'format_id': m.group('format_id'),
1847 'vcodec': 'none' if m.group('type') == 'audio' else None
1849 info_dict['direct'] = True
1850 self._sort_formats(formats)
1851 info_dict['formats'] = formats
1854 if not self._downloader.params.get('test', False) and not is_intentional:
1855 force = self._downloader.params.get('force_generic_extractor', False)
1856 self._downloader.report_warning(
1857 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1859 if not full_response:
1860 request = sanitized_Request(url)
1861 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1862 # making it impossible to download only chunk of the file (yet we need only 512kB to
1863 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1864 # that will always result in downloading the whole file that is not desirable.
1865 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1866 # to accept raw bytes and being able to download only a chunk.
1867 # It may probably better to solve this by checking Content-Type for application/octet-stream
1868 # after HEAD request finishes, but not sure if we can rely on this.
1869 request.add_header('Accept-Encoding', '*')
1870 full_response = self._request_webpage(request, video_id)
1872 first_bytes = full_response.read(512)
1874 # Is it an M3U playlist?
1875 if first_bytes.startswith(b'#EXTM3U'):
1876 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1877 self._sort_formats(info_dict['formats'])
1880 # Maybe it's a direct link to a video?
1881 # Be careful not to download the whole thing!
1882 if not is_html(first_bytes):
1883 self._downloader.report_warning(
1884 'URL could be a direct video link, returning it as such.')
1891 webpage = self._webpage_read_content(
1892 full_response, url, video_id, prefix=first_bytes)
1894 self.report_extraction(video_id)
1896 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1898 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1899 if doc.tag == 'rss':
1900 return self._extract_rss(url, video_id, doc)
1901 elif doc.tag == 'SmoothStreamingMedia':
1902 info_dict['formats'] = self._parse_ism_formats(doc, url)
1903 self._sort_formats(info_dict['formats'])
1905 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1906 smil = self._parse_smil(doc, url, video_id)
1907 self._sort_formats(smil['formats'])
1909 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1910 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1911 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1912 info_dict['formats'] = self._parse_mpd_formats(
1914 mpd_base_url=full_response.geturl().rpartition('/')[0],
1916 self._sort_formats(info_dict['formats'])
1918 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1919 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1920 self._sort_formats(info_dict['formats'])
1922 except compat_xml_parse_error:
1925 # Is it a Camtasia project?
1926 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1927 if camtasia_res is not None:
1930 # Sometimes embedded video player is hidden behind percent encoding
1931 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1932 # Unescaping the whole page allows to handle those cases in a generic way
1933 webpage = compat_urllib_parse_unquote(webpage)
1935 # it's tempting to parse this further, but you would
1936 # have to take into account all the variations like
1937 # Video Title - Site Name
1938 # Site Name | Video Title
1939 # Video Title - Tagline | Site Name
1940 # and so on and so forth; it's just not practical
1941 video_title = self._og_search_title(
1942 webpage, default=None) or self._html_search_regex(
1943 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1946 # Try to detect age limit automatically
1947 age_limit = self._rta_search(webpage)
1948 # And then there are the jokers who advertise that they use RTA,
1949 # but actually don't.
1950 AGE_LIMIT_MARKERS = [
1951 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1953 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1956 # video uploader is domain name
1957 video_uploader = self._search_regex(
1958 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1960 video_description = self._og_search_description(webpage, default=None)
1961 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1963 # Look for Brightcove Legacy Studio embeds
1964 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1968 'url': smuggle_url(bc_url, {'Referer': url}),
1969 'ie_key': 'BrightcoveLegacy'
1970 } for bc_url in bc_urls]
1973 '_type': 'playlist',
1974 'title': video_title,
1979 # Look for Brightcove New Studio embeds
1980 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
1982 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
1984 # Look for ThePlatform embeds
1985 tp_urls = ThePlatformIE._extract_urls(webpage)
1987 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
1989 # Look for Vessel embeds
1990 vessel_urls = VesselIE._extract_urls(webpage)
1992 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
1994 # Look for embedded rtl.nl player
1995 matches = re.findall(
1996 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1999 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2001 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2003 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2005 vid_me_embed_url = self._search_regex(
2006 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2007 webpage, 'vid.me embed', default=None)
2008 if vid_me_embed_url is not None:
2009 return self.url_result(vid_me_embed_url, 'Vidme')
2011 # Look for embedded YouTube player
2012 matches = re.findall(r'''(?x)
2022 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2026 return self.playlist_from_matches(
2027 matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
2029 # Look for lazyYT YouTube embed
2030 matches = re.findall(
2031 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
2033 return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
2035 # Look for Wordpress "YouTube Video Importer" plugin
2036 matches = re.findall(r'''(?x)<div[^>]+
2037 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2038 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2040 return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
2042 matches = DailymotionIE._extract_urls(webpage)
2044 return self.playlist_from_matches(matches, video_id, video_title)
2046 # Look for embedded Dailymotion playlist player (#3822)
2048 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2050 playlists = re.findall(
2051 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2053 return self.playlist_from_matches(
2054 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2056 # Look for embedded Wistia player
2058 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
2060 embed_url = self._proto_relative_url(
2061 unescapeHTML(match.group('url')))
2063 '_type': 'url_transparent',
2066 'uploader': video_uploader,
2069 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
2072 '_type': 'url_transparent',
2073 'url': 'wistia:%s' % match.group('id'),
2075 'uploader': video_uploader,
2080 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
2081 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
2084 return self.url_result(self._proto_relative_url(
2085 'wistia:%s' % match.group('id')), 'Wistia')
2087 # Look for SVT player
2088 svt_url = SVTIE._extract_url(webpage)
2090 return self.url_result(svt_url, 'SVT')
2092 # Look for embedded condenast player
2093 matches = re.findall(
2094 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
2098 '_type': 'playlist',
2101 'ie_key': 'CondeNast',
2103 } for ma in matches],
2104 'title': video_title,
2108 # Look for Bandcamp pages with custom domain
2109 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2110 if mobj is not None:
2111 burl = unescapeHTML(mobj.group(1))
2112 # Don't set the extractor because it can be a track url or an album
2113 return self.url_result(burl)
2115 # Look for embedded Vevo player
2117 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2118 if mobj is not None:
2119 return self.url_result(mobj.group('url'))
2121 # Look for embedded Viddler player
2123 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2125 if mobj is not None:
2126 return self.url_result(mobj.group('url'))
2128 # Look for NYTimes player
2130 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2132 if mobj is not None:
2133 return self.url_result(mobj.group('url'))
2135 # Look for Libsyn player
2137 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2138 if mobj is not None:
2139 return self.url_result(mobj.group('url'))
2141 # Look for Ooyala videos
2142 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2143 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2144 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2145 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2146 if mobj is not None:
2147 embed_token = self._search_regex(
2148 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2149 webpage, 'ooyala embed token', default=None)
2150 return OoyalaIE._build_url_result(smuggle_url(
2153 'embed_token': embed_token,
2156 # Look for multiple Ooyala embeds on SBN network websites
2157 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2158 if mobj is not None:
2159 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2161 return self.playlist_from_matches(
2162 embeds, video_id, video_title,
2163 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2165 # Look for Aparat videos
2166 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2167 if mobj is not None:
2168 return self.url_result(mobj.group(1), 'Aparat')
2170 # Look for MPORA videos
2171 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2172 if mobj is not None:
2173 return self.url_result(mobj.group(1), 'Mpora')
2175 # Look for embedded NovaMov-based player
2177 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2178 (?P<url>http://(?:(?:embed|www)\.)?
2180 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2181 videoweed\.(?:es|com)|
2182 movshare\.(?:net|sx|ag)|
2183 divxstage\.(?:eu|net|ch|co|at|ag))
2184 /embed\.php.+?)\1''', webpage)
2185 if mobj is not None:
2186 return self.url_result(mobj.group('url'))
2188 # Look for embedded Facebook player
2189 facebook_url = FacebookIE._extract_url(webpage)
2190 if facebook_url is not None:
2191 return self.url_result(facebook_url, 'Facebook')
2193 # Look for embedded VK player
2194 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2195 if mobj is not None:
2196 return self.url_result(mobj.group('url'), 'VK')
2198 # Look for embedded Odnoklassniki player
2199 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2200 if mobj is not None:
2201 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2203 # Look for embedded ivi player
2204 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2205 if mobj is not None:
2206 return self.url_result(mobj.group('url'), 'Ivi')
2208 # Look for embedded Huffington Post player
2210 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2211 if mobj is not None:
2212 return self.url_result(mobj.group('url'), 'HuffPost')
2215 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2216 if mobj is not None:
2217 return self.url_result(mobj.group('url'))
2218 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2219 if mobj is not None:
2220 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2222 # Look for funnyordie embed
2223 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2225 return self.playlist_from_matches(
2226 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2228 # Look for BBC iPlayer embed
2229 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2231 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2233 # Look for embedded RUTV player
2234 rutv_url = RUTVIE._extract_url(webpage)
2236 return self.url_result(rutv_url, 'RUTV')
2238 # Look for embedded TVC player
2239 tvc_url = TVCIE._extract_url(webpage)
2241 return self.url_result(tvc_url, 'TVC')
2243 # Look for embedded SportBox player
2244 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2246 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2248 # Look for embedded XHamster player
2249 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2251 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2253 # Look for embedded TNAFlixNetwork player
2254 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2256 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2258 # Look for embedded PornHub player
2259 pornhub_urls = PornHubIE._extract_urls(webpage)
2261 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2263 # Look for embedded DrTuber player
2264 drtuber_urls = DrTuberIE._extract_urls(webpage)
2266 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2268 # Look for embedded RedTube player
2269 redtube_urls = RedTubeIE._extract_urls(webpage)
2271 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2273 # Look for embedded Tvigle player
2275 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2276 if mobj is not None:
2277 return self.url_result(mobj.group('url'), 'Tvigle')
2279 # Look for embedded TED player
2281 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2282 if mobj is not None:
2283 return self.url_result(mobj.group('url'), 'TED')
2285 # Look for embedded Ustream videos
2286 ustream_url = UstreamIE._extract_url(webpage)
2288 return self.url_result(ustream_url, UstreamIE.ie_key())
2290 # Look for embedded arte.tv player
2292 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2294 if mobj is not None:
2295 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2297 # Look for embedded francetv player
2299 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2301 if mobj is not None:
2302 return self.url_result(mobj.group('url'))
2304 # Look for embedded smotri.com player
2305 smotri_url = SmotriIE._extract_url(webpage)
2307 return self.url_result(smotri_url, 'Smotri')
2309 # Look for embedded Myvi.ru player
2310 myvi_url = MyviIE._extract_url(webpage)
2312 return self.url_result(myvi_url)
2314 # Look for embedded soundcloud player
2315 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2317 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2319 # Look for tunein player
2320 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2322 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2324 # Look for embedded mtvservices player
2325 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2327 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2329 # Look for embedded yahoo player
2331 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2333 if mobj is not None:
2334 return self.url_result(mobj.group('url'), 'Yahoo')
2336 # Look for embedded sbs.com.au player
2340 <meta\s+property="og:video"\s+content=|
2343 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2345 if mobj is not None:
2346 return self.url_result(mobj.group('url'), 'SBS')
2348 # Look for embedded Cinchcast player
2350 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2352 if mobj is not None:
2353 return self.url_result(mobj.group('url'), 'Cinchcast')
2356 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2360 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2362 if mobj is not None:
2363 return self.url_result(mobj.group('url'), 'MLB')
2366 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2368 if mobj is not None:
2369 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2372 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2374 if mobj is not None:
2375 return self.url_result(mobj.group('url'), 'Livestream')
2377 # Look for Zapiks embed
2379 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2380 if mobj is not None:
2381 return self.url_result(mobj.group('url'), 'Zapiks')
2383 # Look for Kaltura embeds
2384 kaltura_url = KalturaIE._extract_url(webpage)
2386 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2388 # Look for Eagle.Platform embeds
2389 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2390 if eagleplatform_url:
2391 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2393 # Look for ClipYou (uses Eagle.Platform) embeds
2395 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2396 if mobj is not None:
2397 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2399 # Look for Pladform embeds
2400 pladform_url = PladformIE._extract_url(webpage)
2402 return self.url_result(pladform_url)
2404 # Look for Videomore embeds
2405 videomore_url = VideomoreIE._extract_url(webpage)
2407 return self.url_result(videomore_url)
2409 # Look for Webcaster embeds
2410 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2412 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2414 # Look for Playwire embeds
2416 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2417 if mobj is not None:
2418 return self.url_result(mobj.group('url'))
2420 # Look for 5min embeds
2422 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2423 if mobj is not None:
2424 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2426 # Look for Crooks and Liars embeds
2428 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2429 if mobj is not None:
2430 return self.url_result(mobj.group('url'))
2432 # Look for NBC Sports VPlayer embeds
2433 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2435 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2437 # Look for NBC News embeds
2438 nbc_news_embed_url = re.search(
2439 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2440 if nbc_news_embed_url:
2441 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2443 # Look for Google Drive embeds
2444 google_drive_url = GoogleDriveIE._extract_url(webpage)
2445 if google_drive_url:
2446 return self.url_result(google_drive_url, 'GoogleDrive')
2448 # Look for UDN embeds
2450 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2451 if mobj is not None:
2452 return self.url_result(
2453 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2455 # Look for Senate ISVP iframe
2456 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2458 return self.url_result(senate_isvp_url, 'SenateISVP')
2460 # Look for Dailymotion Cloud videos
2461 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2463 return self.url_result(dmcloud_url, 'DailymotionCloud')
2465 # Look for OnionStudios embeds
2466 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2467 if onionstudios_url:
2468 return self.url_result(onionstudios_url)
2470 # Look for ViewLift embeds
2471 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2473 return self.url_result(viewlift_url)
2475 # Look for JWPlatform embeds
2476 jwplatform_url = JWPlatformIE._extract_url(webpage)
2478 return self.url_result(jwplatform_url, 'JWPlatform')
2480 # Look for Digiteka embeds
2481 digiteka_url = DigitekaIE._extract_url(webpage)
2483 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2485 # Look for Arkena embeds
2486 arkena_url = ArkenaIE._extract_url(webpage)
2488 return self.url_result(arkena_url, ArkenaIE.ie_key())
2490 # Look for Piksel embeds
2491 piksel_url = PikselIE._extract_url(webpage)
2493 return self.url_result(piksel_url, PikselIE.ie_key())
2495 # Look for Limelight embeds
2496 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2498 return self.playlist_result(
2499 limelight_urls, video_id, video_title, video_description)
2501 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2505 'Channel': 'channel',
2506 'ChannelList': 'channel_list',
2508 return self.url_result(smuggle_url('limelight:%s:%s' % (
2509 lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
2510 'Limelight%s' % mobj.group(1), mobj.group(2))
2514 <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
2516 name=(["\'])flashVars\2[^>]+
2517 value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
2520 return self.url_result(smuggle_url(
2521 'limelight:media:%s' % mobj.group('id'),
2522 {'source_url': url}), 'LimelightMedia', mobj.group('id'))
2524 # Look for AdobeTVVideo embeds
2526 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2528 if mobj is not None:
2529 return self.url_result(
2530 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2533 # Look for Vine embeds
2535 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2537 if mobj is not None:
2538 return self.url_result(
2539 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2541 # Look for VODPlatform embeds
2543 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2545 if mobj is not None:
2546 return self.url_result(
2547 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2549 # Look for Mangomolo embeds
2551 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2553 video\?.*?\bid=(?P<video_id>\d+)|
2554 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2555 ).+?)\1''', webpage)
2556 if mobj is not None:
2558 '_type': 'url_transparent',
2559 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2560 'title': video_title,
2561 'description': video_description,
2562 'thumbnail': video_thumbnail,
2563 'uploader': video_uploader,
2565 video_id = mobj.group('video_id')
2568 'ie_key': 'MangomoloVideo',
2573 'ie_key': 'MangomoloLive',
2574 'id': mobj.group('channel_id'),
2578 # Look for Instagram embeds
2579 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2580 if instagram_embed_url is not None:
2581 return self.url_result(
2582 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2584 # Look for LiveLeak embeds
2585 liveleak_url = LiveLeakIE._extract_url(webpage)
2587 return self.url_result(liveleak_url, 'LiveLeak')
2589 # Look for 3Q SDN embeds
2590 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2593 '_type': 'url_transparent',
2594 'ie_key': ThreeQSDNIE.ie_key(),
2595 'url': self._proto_relative_url(threeqsdn_url),
2596 'title': video_title,
2597 'description': video_description,
2598 'thumbnail': video_thumbnail,
2599 'uploader': video_uploader,
2602 # Look for VBOX7 embeds
2603 vbox7_url = Vbox7IE._extract_url(webpage)
2605 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2607 # Look for DBTV embeds
2608 dbtv_urls = DBTVIE._extract_urls(webpage)
2610 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2612 # Look for Videa embeds
2613 videa_urls = VideaIE._extract_urls(webpage)
2615 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2617 # Look for 20 minuten embeds
2618 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2620 return self.playlist_from_matches(
2621 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2623 # Look for Openload embeds
2624 openload_urls = OpenloadIE._extract_urls(webpage)
2626 return self.playlist_from_matches(
2627 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2629 # Look for VideoPress embeds
2630 videopress_urls = VideoPressIE._extract_urls(webpage)
2632 return self.playlist_from_matches(
2633 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2635 # Look for Rutube embeds
2636 rutube_urls = RutubeIE._extract_urls(webpage)
2638 return self.playlist_from_matches(
2639 rutube_urls, ie=RutubeIE.ie_key())
2641 # Looking for http://schema.org/VideoObject
2642 json_ld = self._search_json_ld(
2643 webpage, video_id, default={}, expected_type='VideoObject')
2644 if json_ld.get('url'):
2646 'title': video_title or info_dict['title'],
2647 'description': video_description,
2648 'thumbnail': video_thumbnail,
2649 'age_limit': age_limit
2651 info_dict.update(json_ld)
2654 # Look for HTML5 media
2655 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2657 for entry in entries:
2660 'title': video_title,
2662 self._sort_formats(entry['formats'])
2663 return self.playlist_result(entries)
2665 jwplayer_data = self._find_jwplayer_data(
2666 webpage, video_id, transform_source=js_to_json)
2668 info = self._parse_jwplayer_data(
2669 jwplayer_data, video_id, require_title=False, base_url=url)
2670 if not info.get('title'):
2671 info['title'] = video_title
2674 def check_video(vurl):
2675 if YoutubeIE.suitable(vurl):
2677 if RtmpIE.suitable(vurl):
2679 vpath = compat_urlparse.urlparse(vurl).path
2680 vext = determine_ext(vpath)
2681 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2683 def filter_video(urls):
2684 return list(filter(check_video, urls))
2686 # Start with something easy: JW Player in SWFObject
2687 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2689 # Look for gorilla-vid style embedding
2690 found = filter_video(re.findall(r'''(?sx)
2694 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2697 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2699 # Broaden the search a little bit
2700 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2702 # Broaden the findall a little bit: JWPlayer JS loader
2703 found = filter_video(re.findall(
2704 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2707 found = filter_video(re.findall(r'''(?xs)
2708 flowplayer\("[^"]+",\s*
2710 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2711 ["']?url["']?\s*:\s*["']([^"']+)["']
2716 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2718 # Try to find twitter cards info
2719 # twitter:player:stream should be checked before twitter:player since
2720 # it is expected to contain a raw stream (see
2721 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2722 found = filter_video(re.findall(
2723 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2725 # We look for Open Graph info:
2726 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2727 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2728 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2729 if m_video_type is not None:
2730 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2732 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2734 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2735 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2738 # Look also in Refresh HTTP header
2739 refresh_header = head_response.headers.get('Refresh')
2741 # In python 2 response HTTP headers are bytestrings
2742 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2743 refresh_header = refresh_header.decode('iso-8859-1')
2744 found = re.search(REDIRECT_REGEX, refresh_header)
2746 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2748 self.report_following_redirect(new_url)
2757 # twitter:player is a https URL to iframe player that may or may not
2758 # be supported by youtube-dl thus this is checked the very last (see
2759 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2760 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2762 return self.url_result(embed_url)
2765 raise UnsupportedError(url)
2768 for video_url in orderedSet(found):
2769 video_url = unescapeHTML(video_url)
2770 video_url = video_url.replace('\\/', '/')
2771 video_url = compat_urlparse.urljoin(url, video_url)
2772 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2774 # Sometimes, jwplayer extraction will result in a YouTube URL
2775 if YoutubeIE.suitable(video_url):
2776 entries.append(self.url_result(video_url, 'Youtube'))
2779 # here's a fun little line of code for you:
2780 video_id = os.path.splitext(video_id)[0]
2784 'uploader': video_uploader,
2785 'title': video_title,
2786 'age_limit': age_limit,
2789 if RtmpIE.suitable(video_url):
2790 entry_info_dict.update({
2791 '_type': 'url_transparent',
2792 'ie_key': RtmpIE.ie_key(),
2795 entries.append(entry_info_dict)
2798 ext = determine_ext(video_url)
2800 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2802 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2804 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2806 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2808 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2809 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
2810 # Just matching .ism/manifest is not enough to be reliably sure
2811 # whether it's actually an ISM manifest or some other streaming
2812 # manifest since there are various streaming URL formats
2813 # possible (see [1]) as well as some other shenanigans like
2814 # .smil/manifest URLs that actually serve an ISM (see [2]) and
2816 # Thus the most reasonable way to solve this is to delegate
2817 # to generic extractor in order to look into the contents of
2818 # the manifest itself.
2819 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
2820 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
2821 entry_info_dict = self.url_result(
2822 smuggle_url(video_url, {'to_generic': True}),
2825 entry_info_dict['url'] = video_url
2827 if entry_info_dict.get('formats'):
2828 self._sort_formats(entry_info_dict['formats'])
2830 entries.append(entry_info_dict)
2832 if len(entries) == 1:
2835 for num, e in enumerate(entries, start=1):
2836 # 'url' results don't have a title
2837 if e.get('title') is not None:
2838 e['title'] = '%s (%d)' % (e['title'], num)
2840 '_type': 'playlist',