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
,
34 from .commonprotocols
import RtmpIE
35 from .brightcove
import (
43 from .nbc
import NBCSportsVPlayerIE
44 from .ooyala
import OoyalaIE
45 from .rutv
import RUTVIE
46 from .tvc
import TVCIE
47 from .sportbox
import SportBoxEmbedIE
48 from .smotri
import SmotriIE
49 from .myvi
import MyviIE
50 from .condenast
import CondeNastIE
51 from .udn
import UDNEmbedIE
52 from .senateisvp
import SenateISVPIE
53 from .svt
import SVTIE
54 from .pornhub
import PornHubIE
55 from .xhamster
import XHamsterEmbedIE
56 from .tnaflix
import TNAFlixNetworkEmbedIE
57 from .drtuber
import DrTuberIE
58 from .redtube
import RedTubeIE
59 from .vimeo
import VimeoIE
60 from .dailymotion
import (
64 from .dailymail
import DailyMailIE
65 from .onionstudios
import OnionStudiosIE
66 from .viewlift
import ViewLiftEmbedIE
67 from .mtv
import MTVServicesEmbeddedIE
68 from .pladform
import PladformIE
69 from .videomore
import VideomoreIE
70 from .webcaster
import WebcasterFeedIE
71 from .googledrive
import GoogleDriveIE
72 from .jwplatform
import JWPlatformIE
73 from .digiteka
import DigitekaIE
74 from .arkena
import ArkenaIE
75 from .instagram
import InstagramIE
76 from .liveleak
import LiveLeakIE
77 from .threeqsdn
import ThreeQSDNIE
78 from .theplatform
import ThePlatformIE
79 from .vessel
import VesselIE
80 from .kaltura
import KalturaIE
81 from .eagleplatform
import EaglePlatformIE
82 from .facebook
import FacebookIE
83 from .soundcloud
import SoundcloudIE
84 from .tunein
import TuneInBaseIE
85 from .vbox7
import Vbox7IE
86 from .dbtv
import DBTVIE
87 from .piksel
import PikselIE
88 from .videa
import VideaIE
89 from .twentymin
import TwentyMinutenIE
90 from .ustream
import UstreamIE
91 from .openload
import OpenloadIE
92 from .videopress
import VideoPressIE
93 from .rutube
import RutubeIE
94 from .limelight
import LimelightBaseIE
95 from .anvato
import AnvatoIE
96 from .washingtonpost
import WashingtonPostIE
97 from .wistia
import WistiaIE
98 from .mediaset
import MediasetIE
99 from .joj
import JojIE
100 from .megaphone
import MegaphoneIE
101 from .vzaar
import VzaarIE
104 class GenericIE(InfoExtractor
):
105 IE_DESC
= 'Generic downloader that works on some sites'
109 # Direct link to a video
111 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
112 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
117 'upload_date': '20100513',
120 # Direct link to media delivered compressed (until Accept-Encoding is *)
122 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
123 'md5': '128c42e68b13950268b648275386fc74',
125 'id': 'FictionJunction-Parallel_Hearts',
127 'title': 'FictionJunction-Parallel_Hearts',
128 'upload_date': '20140522',
130 'expected_warnings': [
131 'URL could be a direct video link, returning it as such.'
133 'skip': 'URL invalid',
135 # Direct download with broken HEAD
137 'url': 'http://ai-radio.org:8000/radio.opus',
144 'skip_download': True, # infinite live stream
146 'expected_warnings': [
147 r
'501.*Not Implemented',
151 # Direct link with incorrect MIME type
153 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
154 'md5': '4ccbebe5f36706d85221f204d7eb5913',
156 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
157 'id': '5_Lennart_Poettering_-_Systemd',
159 'title': '5_Lennart_Poettering_-_Systemd',
160 'upload_date': '20141120',
162 'expected_warnings': [
163 'URL could be a direct video link, returning it as such.'
168 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
170 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
171 'title': 'Zero Punctuation',
172 'description': 're:.*groundbreaking video review series.*'
174 'playlist_mincount': 11,
176 # RSS feed with enclosure
178 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
180 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
182 'upload_date': '20150228',
183 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
186 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
188 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
192 'title': 'Automatics, robotics and biocybernetics',
193 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
194 'upload_date': '20130627',
195 'formats': 'mincount:16',
196 'subtitles': 'mincount:1',
199 'force_generic_extractor': True,
200 'skip_download': True,
203 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
205 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
210 'formats': 'mincount:1',
213 'skip_download': True,
216 # SMIL from https://www.restudy.dk/video/play/id/1637
218 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
222 'title': 'video_1637',
223 'formats': 'mincount:3',
226 'skip_download': True,
229 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
231 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
233 'id': 'smil-service',
235 'title': 'smil-service',
236 'formats': 'mincount:1',
239 'skip_download': True,
242 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
244 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
248 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
249 'formats': 'mincount:3',
252 'skip_download': True,
255 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
257 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
259 'id': 'mZlp2ctYIUEB',
261 'title': 'Tikibad ontruimd wegens brand',
262 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
263 'thumbnail': r
're:^https?://.*\.jpg$',
267 'skip_download': True,
270 # MPD from http://dash-mse-test.appspot.com/media.html
272 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
273 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
275 'id': 'car-20120827-manifest',
277 'title': 'car-20120827-manifest',
278 'formats': 'mincount:9',
279 'upload_date': '20130904',
282 'format': 'bestvideo',
285 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
287 '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',
292 'formats': 'mincount:8',
296 'skip_download': True,
298 'skip': 'video gone',
300 # m3u8 served with Content-Type: text/plain
302 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
307 'upload_date': '20140720',
308 'formats': 'mincount:11',
312 'skip_download': True,
314 'skip': 'video gone',
318 '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',
322 'upload_date': '20130224',
323 'uploader_id': 'TheVerge',
324 'description': r
're:^Chris Ziegler takes a look at the\.*',
325 'uploader': 'The Verge',
326 'title': 'First Firefox OS phones side-by-side',
329 'skip_download': False,
333 # redirect in Refresh HTTP header
334 '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',
338 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
339 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
340 'upload_date': '20150917',
341 'uploader_id': 'brtvofficial',
342 'uploader': 'Boiler Room',
345 'skip_download': False,
349 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
350 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
352 'id': '13601338388002',
354 'uploader': 'www.hodiho.fr',
355 'title': 'R\u00e9gis plante sa Jeep',
358 # bandcamp page with custom domain
360 'add_ie': ['Bandcamp'],
361 'url': 'http://bronyrock.com/track/the-pony-mash',
365 'title': 'The Pony Mash',
366 'uploader': 'M_Pallante',
368 'skip': 'There is a limit of 200 free downloads / month for the test song',
371 # embedded brightcove video
372 # it also tests brightcove videos that need to set the 'Referer'
373 # in the http requests
374 'add_ie': ['BrightcoveLegacy'],
375 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
377 'id': '2765128793001',
379 'title': 'Le cours de bourse : lāanalyse technique',
380 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
381 'uploader': 'BFM BUSINESS',
384 'skip_download': True,
388 # embedded with itemprop embedURL and video id spelled as `idVideo`
389 'add_id': ['BrightcoveLegacy'],
390 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
392 'id': '5255628253001',
394 'title': 'md5:37c519b1128915607601e75a87995fc0',
395 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
396 'uploader': 'BFM BUSINESS',
397 'uploader_id': '876450612001',
398 'timestamp': 1482255315,
399 'upload_date': '20161220',
402 'skip_download': True,
406 # https://github.com/rg3/youtube-dl/issues/2253
407 'url': 'http://bcove.me/i6nfkrc3',
408 'md5': '0ba9446db037002366bab3b3eb30c88c',
410 'id': '3101154703001',
412 'title': 'Still no power',
413 'uploader': 'thestar.com',
414 '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.',
416 'add_ie': ['BrightcoveLegacy'],
417 'skip': 'video gone',
420 'url': 'http://www.championat.com/video/football/v/87/87499.html',
421 'md5': 'fb973ecf6e4a78a67453647444222983',
423 'id': '3414141473001',
425 'title': 'ŠŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ ŠŠ·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠŠ)',
426 'description': 'ŠŠ½Š»Š°Š¹Š½-ŃŃŠ°Š½ŃŠ»ŃŃŠøŃ Š¼Š°ŃŃŠ° Š¦Š”ŠŠ - "ŠŠ¾Š»Š³Š°"',
427 'uploader': 'Championat',
431 # https://github.com/rg3/youtube-dl/issues/3541
432 'add_ie': ['BrightcoveLegacy'],
433 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
435 'id': '3866516442001',
437 'title': 'Leer mij vrouwen kennen: Aflevering 1',
438 'description': 'Leer mij vrouwen kennen: Aflevering 1',
439 'uploader': 'SBS Broadcasting',
441 'skip': 'Restricted to Netherlands',
443 'skip_download': True, # m3u8 download
447 # Brightcove video in <iframe>
448 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
449 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
451 'id': '5360463607001',
453 'title': 'åå©äŗ失ęåæē«„åØåŗå¢äøę¼å±ćåæč·³ć å¼åč·å¾ę£åøøē«„幓ēę“»',
454 'description': 'čåå½åæē«„åŗéä¼äøäøååéåŗå大ä½æćä½ę²å®¶ęå¾·Ā·čæŖęå°¼ļ¼Zade Diraniļ¼åØ3ę15ę„åå©äŗå²ēŖēå7åØ幓ēŗŖåæµę„ä¹é
ååøäŗäøŗåå©äŗč°±åēęę²ćåæč·³ćļ¼HEARTBEATļ¼ļ¼äøŗåå°å
幓å²ēŖå½±åēåå©äŗåæē«„ååŗå¼ŗēååļ¼å¼åäøēååŗå
±ååŖåļ¼ä½æåå©äŗåæē«„éę°č·å¾äŗ«ęę£åøøē«„幓ēę“»ēęå©ć',
455 'uploader': 'United Nations',
456 'uploader_id': '1362235914001',
457 'timestamp': 1489593889,
458 'upload_date': '20170315',
460 'add_ie': ['BrightcoveLegacy'],
463 # Brightcove with alternative playerID key
464 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
466 'id': 'nmeth.2062_SV1',
467 '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',
471 'id': '2228375078001',
473 'title': 'nmeth.2062-sv1',
474 'description': 'nmeth.2062-sv1',
475 'timestamp': 1363357591,
476 'upload_date': '20130315',
477 'uploader': 'Nature Publishing Group',
478 'uploader_id': '1964492299001',
483 # Brightcove with UUID in videoPlayer
484 'url': 'http://www8.hp.com/cn/zh/home.html',
486 'id': '5255815316001',
488 'title': 'Sprocket Video - China',
489 'description': 'Sprocket Video - China',
490 'uploader': 'HP-Video Gallery',
491 'timestamp': 1482263210,
492 'upload_date': '20161220',
493 'uploader_id': '1107601872001',
496 'skip_download': True, # m3u8 download
498 'skip': 'video rotates...weekly?',
501 # Brightcove:new type [2].
502 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
503 'md5': '2b35148fcf48da41c9fb4591650784f3',
505 'id': '5348741021001',
507 'upload_date': '20170306',
508 'uploader_id': '4191638492001',
509 'timestamp': 1488769918,
510 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
515 # Alternative brightcove <video> attributes
516 '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/',
518 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
519 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidĆ©os avec TĆ©lĆ©-Loisirs",
522 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
524 'id': '5311302538001',
526 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
527 'description': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 fĆ©vrier 2017)",
528 'timestamp': 1486321708,
529 'upload_date': '20170205',
530 'uploader_id': '800000640001',
532 'only_matching': True,
536 # Brightcove with UUID in videoPlayer
537 'url': 'http://www8.hp.com/cn/zh/home.html',
539 'id': '5255815316001',
541 'title': 'Sprocket Video - China',
542 'description': 'Sprocket Video - China',
543 'uploader': 'HP-Video Gallery',
544 'timestamp': 1482263210,
545 'upload_date': '20161220',
546 'uploader_id': '1107601872001',
549 'skip_download': True, # m3u8 download
554 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
555 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
557 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
559 'title': '2cc213299525360.mov', # that's what we get
562 'add_ie': ['Ooyala'],
565 # ooyala video embedded with http://player.ooyala.com/iframe.js
566 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
568 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
570 'title': '"Steve Jobs: Man in the Machine" trailer',
571 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
575 'skip_download': True,
577 'skip': 'movie expired',
579 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
581 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
583 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
585 'title': 'Steampunk Fest Comes to Honesdale',
589 'skip_download': True,
594 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
598 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
599 'upload_date': '20140225',
600 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
601 'uploader': 'Tested',
602 'uploader_id': 'testedcom',
604 # No need to test YoutubeIE here
606 'skip_download': True,
611 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
615 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
616 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
618 # HEAD requests lead to endless 301, while GET is OK
619 'expected_warnings': ['301'],
623 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
627 'title': 'ŠŃ
Š¾ŃŃŠŗŠ¾Šµ Š¼Š¾ŃŠµ ŃŃŠ°Š»Š¾ ŃŠµŠ»ŠøŠŗŠ¾Š¼ ŃŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
628 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
632 'skip_download': True,
637 '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/',
641 'title': 'ŠŠ¾ŃŠŗŠ¾Š»ŃŠ½Š¾Šµ Š²Š¾ŃŠæŠøŃŠ°Š½ŠøŠµ',
646 'url': 'http://www.vestifinance.ru/articles/25753',
649 'title': 'ŠŃŃŠ¼ŃŠµ ŃŃŠ°Š½ŃŠ»ŃŃŠøŠø Ń Š¤Š¾ŃŃŠ¼Š°-Š²ŃŃŃŠ°Š²ŠŗŠø "ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
654 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 3',
660 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 2',
666 'title': 'ŠŠ¾ŃŠ·Š°ŠŗŠ°Š·. ŠŠµŠ½Ń 1',
672 'skip_download': True,
677 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
679 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
681 'title': 'Š£Š¶Š°ŃŃŠøŠŗŠø, ŃŃŃŃŠŗŠøŠ¹ ŃŃŠµŠ¹Š»ŠµŃ (2015)',
682 'thumbnail': r
're:^https?://.*\.jpg$',
688 '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',
691 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
693 'playlist_mincount': 7,
694 # This forum does not allow <iframe> syntaxes anymore
695 # Now HTML tags are displayed as-is
696 'skip': 'No videos on this page',
700 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
701 'md5': '65fdff94098e4a607385a60c5177c638',
705 'title': 'Hidden miracles of the natural world',
706 'uploader': 'Louie Schwartzberg',
707 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
710 # nowvideo embed hidden behind percent encoding
712 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
713 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
715 'id': '06e53103ca9aa',
717 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
718 'description': 'No description',
723 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
724 'md5': '7653032cbb25bf6c80d80f217055fa43',
726 'id': '048195-004_PLUS7-F',
729 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
730 'upload_date': '20140320',
733 'skip_download': 'Requires rtmpdump'
735 'skip': 'video gone',
739 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
743 'title': 'Alcaline, le concert avec Calogero',
744 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
745 'upload_date': '20150226',
746 'timestamp': 1424989860,
751 'skip_download': True,
753 'expected_warnings': [
759 'url': 'http://www.wired.com/2014/04/honda-asimo/',
760 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
762 'id': '53501be369702d3275860000',
764 'title': 'Hondaās New Asimo Robot Is More Human Than Ever',
769 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
770 'md5': '441aeeb82eb72c422c7f14ec533999cd',
772 'id': 'k2mm4bCdJ6CQ2i7c8o2',
774 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
775 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
777 'uploader_id': 'xgditw',
778 'upload_date': '20140425',
779 'timestamp': 1398441542,
781 'add_ie': ['Dailymotion'],
785 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
789 'title': 'Care worker punches elderly dementia patient in head 11 times',
790 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
792 'add_ie': ['DailyMail'],
794 'skip_download': True,
799 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
803 'title': 'The NBL Auction 2014',
804 'uploader': 'BADMINTON England',
805 'uploader_id': 'BADMINTONEvents',
806 'upload_date': '20140603',
807 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
809 'add_ie': ['Youtube'],
811 'skip_download': True,
816 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
817 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
819 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
821 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
822 'description': 'Two valets share their love for movie star Liam Neesons.',
823 'timestamp': 1349922600,
824 'upload_date': '20121011',
827 # YouTube embed via <data-embed-url="">
829 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
833 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
834 'uploader': 'Gameloft',
835 'uploader_id': 'gameloft',
836 'upload_date': '20140828',
837 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
840 'skip_download': True,
843 # YouTube <object> embed
845 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
846 'md5': '516718101ec834f74318df76259fb3cc',
850 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
851 'upload_date': '20080526',
852 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
853 'uploader': 'Christopher Sykes',
854 'uploader_id': 'ChristopherJSykes',
856 'add_ie': ['Youtube'],
860 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
862 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
864 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
865 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
870 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
872 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
873 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
879 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
884 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
885 'md5': '9d65602bf31c6e20014319c7d07fba27',
887 'id': '5123ea6d5e5a7',
890 'uploader': 'www.handjobhub.com',
891 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
894 # Multiple brightcove videos
895 # https://github.com/rg3/youtube-dl/issues/2283
897 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
899 'id': 'always-never',
900 'title': 'Always / Never - The New Yorker',
904 'extract_flat': False,
905 'skip_download': True,
910 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
911 'md5': '96f09a37e44da40dd083e12d9a683327',
915 'title': 'Ump changes call to ball',
916 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
918 'timestamp': 1401537900,
919 'upload_date': '20140531',
920 'thumbnail': r
're:^https?://.*\.jpg$',
925 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
926 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
930 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
931 'description': 'a Paywall Videos video from Remilon',
933 'uploader': 'study.com',
934 'timestamp': 1459678540,
935 'upload_date': '20160403',
936 'filesize': 24687186,
940 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
941 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
945 'title': 'Conversation about Hexagonal Rails Part 1',
946 'description': 'a Martin Fowler video from ThoughtWorks',
948 'uploader': 'thoughtworks.wistia.com',
949 'timestamp': 1401832161,
950 'upload_date': '20140603',
953 # Wistia standard embed (async)
955 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
959 'title': 'Drip Brennan Dunn Workshop',
960 'description': 'a JV Webinars video from getdrip-1',
962 'timestamp': 1463607249,
963 'upload_date': '20160518',
966 'skip_download': True,
971 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
975 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
976 'uploader': 'Sophos Security',
977 'title': 'Chet Chat 171 - Oct 29, 2014',
978 'upload_date': '20141029',
981 # Soundcloud multiple embeds
983 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
986 'title': 'Guitar Essentials: Legato WorkoutāOne-Hour to Fluid Performance | TAB + AUDIO',
988 'playlist_mincount': 7,
990 # TuneIn station embed
992 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
997 'location': 'Paris, France',
1002 'skip_download': True,
1007 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1011 'upload_date': '20141112',
1012 'title': 'Rosetta #CometLanding webcast HL 10',
1015 # Another Livestream embed, without 'new.' in URL
1017 'url': 'https://www.freespeech.org/',
1021 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1025 'skip_download': True,
1030 'url': 'https://skiplagged.com/',
1033 'title': 'Skiplagged: The smart way to find cheap flights',
1035 'playlist_mincount': 1,
1036 'add_ie': ['Youtube'],
1040 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1044 'upload_date': '20141126',
1045 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1050 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1052 'id': '730m_DandD_1901_512k',
1054 'uploader': 'www.abc.net.au',
1055 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1058 # embedded viddler video
1060 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1064 'uploader': 'deadspin',
1065 'title': 'WALL-TO-GORTAT',
1066 'timestamp': 1422285291,
1067 'upload_date': '20150126',
1069 'add_ie': ['Viddler'],
1073 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1077 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1078 'description': 'md5:601cb790edd05908957dae8aaa866465',
1079 'upload_date': '20150220',
1081 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1085 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1087 'id': 'Mrj4DVp2zeA',
1089 'upload_date': '20150212',
1090 'uploader': 'The National Archives UK',
1091 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1092 'uploader_id': 'NationalArchives08',
1093 'title': 'Webinar: Using Discovery, The National Archivesā online catalogue',
1098 'url': 'http://www.suffolk.edu/sjc/',
1102 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1103 'uploader': 'www.suffolk.edu',
1106 'skip_download': True,
1111 'url': 'http://www.indiedb.com/games/king-machine/videos',
1115 'title': 'king machine trailer 1',
1116 'thumbnail': r
're:^https?://.*\.jpg$',
1120 # JWPlayer config passed as variable
1121 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1125 'title': 'ARIELE | Tube Cup',
1126 'uploader': 'www.txxx.com',
1130 'skip_download': True,
1135 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1136 'playlist_mincount': 5,
1138 'id': 'aanslagen-kopenhagen',
1139 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1144 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1148 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1151 # Kaltura embed (different embed code)
1153 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1157 'upload_date': '20150127',
1158 'uploader_id': 'PremierMedia',
1160 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1163 # Kaltura embed with single quotes
1165 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1170 'timestamp': 1355743100,
1171 'upload_date': '20121217',
1172 'uploader_id': 'batchUser',
1174 'add_ie': ['Kaltura'],
1177 # Kaltura embedded via quoted entry_id
1178 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1182 'title': '06_matthew_brender_raj_dutt',
1183 'timestamp': 1466638791,
1184 'upload_date': '20160622',
1186 'add_ie': ['Kaltura'],
1187 'expected_warnings': [
1188 'Could not send HEAD request'
1191 'skip_download': True,
1195 # Kaltura embedded, some fileExt broken (#11480)
1196 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1200 'title': 'Our "Standard Models" of particle physics and cosmology',
1201 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1202 'timestamp': 1321158993,
1203 'upload_date': '20111113',
1204 'uploader_id': 'kps1',
1206 'add_ie': ['Kaltura'],
1209 # Kaltura iframe embed
1210 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1211 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1215 'title': 'I. M. Pei: A Centennial Celebration',
1216 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1217 'upload_date': '20170403',
1218 'uploader_id': 'batchUser',
1219 'timestamp': 1491232186,
1221 'add_ie': ['Kaltura'],
1223 # EaglePlatform embed (generic URL)
1225 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1226 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1230 'title': 'ŠŠ°Š²Š°Š»ŃŠ½ŃŠ¹ Š²ŃŃŠµŠ» Š½Š° ŃŠ²Š¾Š±Š¾Š“Ń',
1231 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1232 'thumbnail': r
're:^https?://.*\.jpg$',
1238 'skip_download': True,
1241 # referrer protected EaglePlatform embed
1243 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1247 'title': 'Š”ŃŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠŃ Š½Š°ŃŃŃŠøŠ»Šø Š“ŠµŠ²ŃŃŠ²ŠµŠ½Š½Š¾ŃŃŃ ŠŃŠµŠ¼Š»ŃĀ»',
1248 'thumbnail': r
're:^https?://.*\.jpg$',
1253 'skip_download': True,
1256 # ClipYou (EaglePlatform) embed (custom URL)
1258 'url': 'http://muz-tv.ru/play/7129/',
1259 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1263 'title': "'O Sole Mio",
1264 'thumbnail': r
're:^https?://.*\.jpg$',
1269 'skip_download': True,
1274 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1278 'title': 'Š¢Š°Š¹Š½Ń ŠæŠµŃŠµŠ²Š°Š»Š° ŠŃŃŠ»Š¾Š²Š° ā¢ 1 ŃŠµŃŠøŃ 2 ŃŠ°ŃŃŃ',
1279 'description': 'ŠŠ¾ŠŗŃŠ¼ŠµŠ½ŃŠ°Š»ŃŠ½ŃŠ¹ ŃŠµŃŠøŠ°Š»-ŃŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· ŃŠ°Š¼ŃŃ
Š¶ŃŃŠŗŠøŃ
ŃŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1280 'thumbnail': r
're:^https?://.*\.jpg$',
1287 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1291 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1292 'thumbnail': r
're:^https?://.*\.png$',
1298 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1299 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1303 'title': 'Facebook Creates "On This Day" | Crunch Report',
1308 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1312 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1317 # Crooks and Liars embed
1319 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1323 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1324 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1325 'timestamp': 1428207000,
1326 'upload_date': '20150405',
1327 'uploader': 'Heather',
1330 # Crooks and Liars external embed
1332 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1334 'id': 'MTE3MjUtMzQ2MzA',
1336 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1337 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1338 'timestamp': 1265032391,
1339 'upload_date': '20100201',
1340 'uploader': 'Heather',
1343 # NBC Sports vplayer embed
1345 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1347 'id': 'ln7x1qSThw4k',
1349 'title': "PFT Live: New leader in the 'new-look' defense",
1350 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1351 'uploader': 'NBCU-SPORTS',
1352 'upload_date': '20140107',
1353 'timestamp': 1389118457,
1358 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1359 'md5': '1aa589c675898ae6d37a17913cf68d66',
1361 'id': '701714499682',
1363 'title': 'PREVIEW: On Assignment: David Letterman',
1364 '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.',
1369 'url': 'https://video.udn.com/news/300346',
1370 'md5': 'fd2060e988c326991037b9aff9df21a6',
1374 'title': 'äøäøäøē·åø«č®ę§ å
Øę ”åø«ēåęŗ',
1375 'thumbnail': r
're:^https?://.*\.jpg$',
1379 'skip_download': True,
1384 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1386 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1388 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1389 'title': 'This is what separates the Excel masters from the wannabes',
1390 'duration': 191.933,
1394 'skip_download': True,
1397 # Brightcove URL in single quotes
1399 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1400 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1402 'id': '4255764656001',
1404 'title': 'SN Presents: Russell Martin, World Citizen',
1405 'description': 'To understand why he was the Toronto Blue Jaysā top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1406 'uploader': 'Rogers Sportsnet',
1407 'uploader_id': '1704050871',
1408 'upload_date': '20150525',
1409 'timestamp': 1432570283,
1412 # Dailymotion Cloud video
1414 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1415 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1419 'title': 'Sauvons les abeilles ! - Le dƩbat',
1420 'description': 'md5:d9082128b1c5277987825d684939ca26',
1421 'thumbnail': r
're:^https?://.*\.jpe?g$',
1422 'timestamp': 1434970506,
1423 'upload_date': '20150622',
1424 'uploader': 'Public SĆ©nat',
1425 'uploader_id': 'xa9gza',
1428 # OnionStudios embed
1430 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1434 'title': 'Donāt Understand Bitcoin? This Man Will Mumble An Explanation At You',
1435 'thumbnail': r
're:^https?://.*\.jpe?g$',
1436 'uploader': 'ClickHole',
1437 'uploader_id': 'clickhole',
1442 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1444 'id': '74849a00-85a9-11e1-9660-123139220831',
1446 'title': '#whilewewatch',
1449 # AdobeTVVideo embed
1451 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1452 'md5': '43662b577c018ad707a63766462b1e87',
1456 'title': 'New experience with Acrobat DC',
1457 'description': 'New experience with Acrobat DC',
1458 'duration': 248.667,
1461 # BrightcoveInPageEmbed embed
1463 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1465 'id': '4238694884001',
1467 'title': 'Tabletop: Dread, Last Thoughts',
1468 'description': 'Tabletop: Dread, Last Thoughts',
1472 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1473 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1475 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1477 'id': '4785848093001',
1479 'title': 'The Cardinal Pell Interview',
1480 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1481 'uploader': 'GlobeCast Australia - GlobeStream',
1482 'uploader_id': '2733773828001',
1483 'upload_date': '20160304',
1484 'timestamp': 1457083087,
1488 'skip_download': True,
1492 # Brightcove embed with whitespace around attribute names
1493 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1495 'id': '3167554373001',
1497 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1498 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1499 'uploader_id': '1079349493',
1500 'upload_date': '20140207',
1501 'timestamp': 1391810548,
1504 'skip_download': True,
1507 # Another form of arte.tv embed
1509 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1510 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1512 'id': '030273-562_PLUS7-F',
1514 'title': 'ARTE Reportage - Nulle part, en France',
1515 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1516 'upload_date': '20160409',
1521 'url': 'http://www.wykop.pl/link/3088787/',
1522 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1524 'id': '874_1459135191',
1526 'title': 'Man shows poor quality of new apartment building',
1527 'description': 'The wall is like a sand pile.',
1528 'uploader': 'Lake8737',
1530 'add_ie': [LiveLeakIE
.ie_key()],
1532 # Another LiveLeak embed pattern (#13336)
1534 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1536 'id': '2eb_1496309988',
1538 'title': 'Thief robs place where everyone was armed',
1539 'description': 'md5:694d73ee79e535953cf2488562288eee',
1540 'uploader': 'brazilwtf',
1542 'add_ie': [LiveLeakIE
.ie_key()],
1544 # Duplicated embedded video URLs
1546 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1548 'id': '149298443_480_16c25b74_2',
1550 'title': 'vs. Blue Orange Spring Game',
1551 'uploader': 'www.hudl.com',
1554 # twitter:player:stream embed
1556 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1560 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1561 'uploader': 'www.rtl.be',
1565 'skip_download': True,
1568 # twitter:player embed
1570 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1571 'md5': 'a3e0df96369831de324f0778e126653c',
1573 'id': '4909620399001',
1575 'title': 'What Do Black Holes Sound Like?',
1576 'description': 'what do black holes sound like',
1577 'upload_date': '20160524',
1578 'uploader_id': '29913724001',
1579 'timestamp': 1464107587,
1580 'uploader': 'TheAtlantic',
1582 'add_ie': ['BrightcoveLegacy'],
1586 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1590 'title': "Yesterday's Jam (OV)",
1591 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1592 'timestamp': 1492594816,
1593 'upload_date': '20170419',
1596 'format': 'bestvideo',
1597 'skip_download': True,
1600 # Facebook <iframe> embed
1602 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1603 'md5': 'fbcde74f534176ecb015849146dd3aee',
1605 'id': '599637780109885',
1607 'title': 'Facebook video #599637780109885',
1610 # Facebook <iframe> embed, plugin video
1612 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1614 'id': '1754168231264132',
1616 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1617 'uploader': 'Tariq Ramadan (official)',
1618 'timestamp': 1496758379,
1619 'upload_date': '20170606',
1622 'skip_download': True,
1625 # Facebook API embed
1627 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1628 'md5': 'a47372ee61b39a7b90287094d447d94e',
1630 'id': '10153467542406923',
1632 'title': 'Facebook video #10153467542406923',
1635 # Wordpress "YouTube Video Importer" plugin
1637 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1638 'md5': 'd16797741b560b485194eddda8121b48',
1640 'id': 'HNTXWDXV9Is',
1642 'title': 'Blue Devils Drumline Stanford lot 2016',
1643 'upload_date': '20160627',
1644 'uploader_id': 'GENOCIDE8GENERAL10',
1645 'uploader': 'cylus cyrus',
1649 # video stored on custom kaltura server
1650 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1651 'md5': '537617d06e64dfed891fa1593c4b30cc',
1655 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1656 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1657 'uploader_id': 'videos.expansion@el-mundo.net',
1658 'upload_date': '20150429',
1659 'timestamp': 1430303472,
1661 'add_ie': ['Kaltura'],
1664 # Non-standard Vimeo embed
1665 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1666 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1670 'title': 'Understanding the web - Teaser',
1671 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1672 'upload_date': '20151214',
1673 'uploader': 'OpenClassrooms',
1674 'uploader_id': 'openclassrooms',
1676 'add_ie': ['Vimeo'],
1679 # generic vimeo embed that requires original URL passed as Referer
1680 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1681 'only_matching': True,
1684 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1685 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1687 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1689 'title': 'Big Buck Bunny',
1690 'description': 'Royalty free test video',
1691 'timestamp': 1432816365,
1692 'upload_date': '20150528',
1696 'skip_download': True,
1698 'add_ie': [ArkenaIE
.ie_key()],
1701 '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/',
1705 'title': 'ŠŠ ŠŠŠ”ŠŖŠ ŠŠ¢ ŠŠŠ ŠŠ: ŠŠ·ŃŠøŃŠ°Š½Šµ Š½Š° Š³Š°Š· Š½Š° Š±ŠµŠ½Š·ŠøŠ½Š¾ŃŃŠ°Š½ŃŠøŃ Š² ŠŠ»Š¾Š²Š“ŠøŠ²',
1708 'skip_download': True,
1710 'add_ie': [Vbox7IE
.ie_key()],
1714 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1717 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1719 'playlist_mincount': 3,
1723 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1725 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1726 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1728 'playlist_mincount': 2,
1732 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1736 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1737 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1740 'skip_download': True,
1742 'add_ie': [TwentyMinutenIE
.ie_key()],
1746 'url': 'https://en.support.wordpress.com/videopress/',
1750 'title': 'IMG_5786',
1751 'timestamp': 1435711927,
1752 'upload_date': '20150701',
1755 'skip_download': True,
1757 'add_ie': [VideoPressIE
.ie_key()],
1761 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1763 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1765 'title': 'ŠŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠŠ°Š·Š°Š½Ń 2',
1766 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1767 'uploader': 'ŠŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1768 'upload_date': '20170228',
1769 'uploader_id': '996642',
1772 'skip_download': True,
1774 'add_ie': [RutubeIE
.ie_key()],
1777 # ThePlatform embedded with whitespaces in URLs
1778 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1779 'only_matching': True,
1782 # Senate ISVP iframe https
1783 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1784 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1786 'id': 'govtaff020316',
1788 'title': 'Integrated Senate Video Player',
1790 'add_ie': [SenateISVPIE
.ie_key()],
1793 # Limelight embeds (1 channel embed + 4 media embeds)
1794 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1796 'id': 'FacilitatorTraining2017',
1797 'title': 'Facilitator Training 2017',
1799 'playlist_mincount': 5,
1802 # Limelight embed (LimelightPlayerUtil.embed)
1803 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1805 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1807 'title': '07448641',
1808 'timestamp': 1499890639,
1809 'upload_date': '20170712',
1812 'skip_download': True,
1814 'add_ie': ['LimelightMedia'],
1817 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1819 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1820 'title': 'Standoff with Walnut Creek murder suspect ends',
1821 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1823 'playlist_mincount': 4,
1826 # WashingtonPost embed
1827 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1829 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1831 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1832 '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 ā and enlisted actors.',
1833 'timestamp': 1455216756,
1834 'uploader': 'The Washington Post',
1835 'upload_date': '20160211',
1837 'add_ie': [WashingtonPostIE
.ie_key()],
1841 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1845 'title': 'Serracchiani: "Voglio vivere in una societĆ aperta, con tutela del patto di fiducia"',
1848 'skip_download': True,
1850 'add_ie': [MediasetIE
.ie_key()],
1854 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1856 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1857 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1859 'playlist_mincount': 5,
1860 'add_ie': [JojIE
.ie_key()],
1863 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1864 'url': 'https://tvrain.ru/amp/418921/',
1865 'md5': 'cc00413936695987e8de148b67d14f1d',
1869 'title': 'Š”ŃŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠŃ Š½Š°ŃŃŃŠøŠ»Šø Š“ŠµŠ²ŃŃŠ²ŠµŠ½Š½Š¾ŃŃŃ ŠŃŠµŠ¼Š»ŃĀ»',
1874 'url': 'http://help.vzaar.com/article/165-embedding-video',
1875 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1879 'title': 'Building A Business Online: Principal Chairs Q & A',
1883 # multiple HTML5 videos on one page
1884 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1886 'id': 'keyscenarios',
1887 'title': 'Rescue Kit 14 Free Edition - Getting started',
1889 'playlist_count': 4,
1892 # # TODO: find another test
1893 # # http://schema.org/VideoObject
1894 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1895 # 'md5': '888dcf08b7ea671381f00fab74692755',
1897 # 'id': 'nyvTSJMKId',
1899 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1900 # 'description': '#love for cats.',
1901 # 'timestamp': 1461244995,
1902 # 'upload_date': '20160421',
1905 # 'force_generic_extractor': True,
1910 def report_following_redirect(self
, new_url
):
1911 """Report information extraction."""
1912 self
._downloader
.to_screen('[redirect] Following redirect to %s' % new_url
)
1914 def _extract_rss(self
, url
, video_id
, doc
):
1915 playlist_title
= doc
.find('./channel/title').text
1916 playlist_desc_el
= doc
.find('./channel/description')
1917 playlist_desc
= None if playlist_desc_el
is None else playlist_desc_el
.text
1920 for it
in doc
.findall('./channel/item'):
1921 next_url
= xpath_text(it
, 'link', fatal
=False)
1923 enclosure_nodes
= it
.findall('./enclosure')
1924 for e
in enclosure_nodes
:
1925 next_url
= e
.attrib
.get('url')
1933 '_type': 'url_transparent',
1935 'title': it
.find('title').text
,
1939 '_type': 'playlist',
1941 'title': playlist_title
,
1942 'description': playlist_desc
,
1946 def _extract_camtasia(self
, url
, video_id
, webpage
):
1947 """ Returns None if no camtasia video can be found. """
1949 camtasia_cfg
= self
._search
_regex
(
1950 r
'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1951 webpage
, 'camtasia configuration file', default
=None)
1952 if camtasia_cfg
is None:
1955 title
= self
._html
_search
_meta
('DC.title', webpage
, fatal
=True)
1957 camtasia_url
= compat_urlparse
.urljoin(url
, camtasia_cfg
)
1958 camtasia_cfg
= self
._download
_xml
(
1959 camtasia_url
, video_id
,
1960 note
='Downloading camtasia configuration',
1961 errnote
='Failed to download camtasia configuration')
1962 fileset_node
= camtasia_cfg
.find('./playlist/array/fileset')
1965 for n
in fileset_node
.getchildren():
1966 url_n
= n
.find('./uri')
1971 'id': os
.path
.splitext(url_n
.text
.rpartition('/')[2])[0],
1972 'title': '%s - %s' % (title
, n
.tag
),
1973 'url': compat_urlparse
.urljoin(url
, url_n
.text
),
1974 'duration': float_or_none(n
.find('./duration').text
),
1978 '_type': 'playlist',
1983 def _real_extract(self
, url
):
1984 if url
.startswith('//'):
1987 'url': self
.http_scheme() + url
,
1990 parsed_url
= compat_urlparse
.urlparse(url
)
1991 if not parsed_url
.scheme
:
1992 default_search
= self
._downloader
.params
.get('default_search')
1993 if default_search
is None:
1994 default_search
= 'fixup_error'
1996 if default_search
in ('auto', 'auto_warning', 'fixup_error'):
1998 self
._downloader
.report_warning('The url doesn\'t specify the protocol, trying with http')
1999 return self
.url_result('http://' + url
)
2000 elif default_search
!= 'fixup_error':
2001 if default_search
== 'auto_warning':
2002 if re
.match(r
'^(?:url|URL)$', url
):
2003 raise ExtractorError(
2004 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url
,
2007 self
._downloader
.report_warning(
2008 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url
)
2009 return self
.url_result('ytsearch:' + url
)
2011 if default_search
in ('error', 'fixup_error'):
2012 raise ExtractorError(
2013 '%r is not a valid URL. '
2014 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2015 % (url
, url
), expected
=True)
2017 if ':' not in default_search
:
2018 default_search
+= ':'
2019 return self
.url_result(default_search
+ url
)
2021 url
, smuggled_data
= unsmuggle_url(url
)
2022 force_videoid
= None
2023 is_intentional
= smuggled_data
and smuggled_data
.get('to_generic')
2024 if smuggled_data
and 'force_videoid' in smuggled_data
:
2025 force_videoid
= smuggled_data
['force_videoid']
2026 video_id
= force_videoid
2028 video_id
= self
._generic
_id
(url
)
2030 self
.to_screen('%s: Requesting header' % video_id
)
2032 head_req
= HEADRequest(url
)
2033 head_response
= self
._request
_webpage
(
2035 note
=False, errnote
='Could not send HEAD request to %s' % url
,
2038 if head_response
is not False:
2039 # Check for redirect
2040 new_url
= compat_str(head_response
.geturl())
2042 self
.report_following_redirect(new_url
)
2044 new_url
= smuggle_url(
2045 new_url
, {'force_videoid': force_videoid
})
2046 return self
.url_result(new_url
)
2048 full_response
= None
2049 if head_response
is False:
2050 request
= sanitized_Request(url
)
2051 request
.add_header('Accept-Encoding', '*')
2052 full_response
= self
._request
_webpage
(request
, video_id
)
2053 head_response
= full_response
2057 'title': self
._generic
_title
(url
),
2058 'upload_date': unified_strdate(head_response
.headers
.get('Last-Modified'))
2061 # Check for direct link to a video
2062 content_type
= head_response
.headers
.get('Content-Type', '').lower()
2063 m
= re
.match(r
'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type
)
2065 format_id
= compat_str(m
.group('format_id'))
2066 if format_id
.endswith('mpegurl'):
2067 formats
= self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2068 elif format_id
== 'f4m':
2069 formats
= self
._extract
_f
4m
_formats
(url
, video_id
)
2072 'format_id': format_id
,
2074 'vcodec': 'none' if m
.group('type') == 'audio' else None
2076 info_dict
['direct'] = True
2077 self
._sort
_formats
(formats
)
2078 info_dict
['formats'] = formats
2081 if not self
._downloader
.params
.get('test', False) and not is_intentional
:
2082 force
= self
._downloader
.params
.get('force_generic_extractor', False)
2083 self
._downloader
.report_warning(
2084 '%s on generic information extractor.' % ('Forcing' if force
else 'Falling back'))
2086 if not full_response
:
2087 request
= sanitized_Request(url
)
2088 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2089 # making it impossible to download only chunk of the file (yet we need only 512kB to
2090 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2091 # that will always result in downloading the whole file that is not desirable.
2092 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2093 # to accept raw bytes and being able to download only a chunk.
2094 # It may probably better to solve this by checking Content-Type for application/octet-stream
2095 # after HEAD request finishes, but not sure if we can rely on this.
2096 request
.add_header('Accept-Encoding', '*')
2097 full_response
= self
._request
_webpage
(request
, video_id
)
2099 first_bytes
= full_response
.read(512)
2101 # Is it an M3U playlist?
2102 if first_bytes
.startswith(b
'#EXTM3U'):
2103 info_dict
['formats'] = self
._extract
_m
3u8_formats
(url
, video_id
, 'mp4')
2104 self
._sort
_formats
(info_dict
['formats'])
2107 # Maybe it's a direct link to a video?
2108 # Be careful not to download the whole thing!
2109 if not is_html(first_bytes
):
2110 self
._downloader
.report_warning(
2111 'URL could be a direct video link, returning it as such.')
2118 webpage
= self
._webpage
_read
_content
(
2119 full_response
, url
, video_id
, prefix
=first_bytes
)
2121 self
.report_extraction(video_id
)
2123 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2125 doc
= compat_etree_fromstring(webpage
.encode('utf-8'))
2126 if doc
.tag
== 'rss':
2127 return self
._extract
_rss
(url
, video_id
, doc
)
2128 elif doc
.tag
== 'SmoothStreamingMedia':
2129 info_dict
['formats'] = self
._parse
_ism
_formats
(doc
, url
)
2130 self
._sort
_formats
(info_dict
['formats'])
2132 elif re
.match(r
'^(?:{[^}]+})?smil$', doc
.tag
):
2133 smil
= self
._parse
_smil
(doc
, url
, video_id
)
2134 self
._sort
_formats
(smil
['formats'])
2136 elif doc
.tag
== '{http://xspf.org/ns/0/}playlist':
2137 return self
.playlist_result(self
._parse
_xspf
(doc
, video_id
), video_id
)
2138 elif re
.match(r
'(?i)^(?:{[^}]+})?MPD$', doc
.tag
):
2139 info_dict
['formats'] = self
._parse
_mpd
_formats
(
2141 mpd_base_url
=compat_str(full_response
.geturl()).rpartition('/')[0],
2143 self
._sort
_formats
(info_dict
['formats'])
2145 elif re
.match(r
'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc
.tag
):
2146 info_dict
['formats'] = self
._parse
_f
4m
_formats
(doc
, url
, video_id
)
2147 self
._sort
_formats
(info_dict
['formats'])
2149 except compat_xml_parse_error
:
2152 # Is it a Camtasia project?
2153 camtasia_res
= self
._extract
_camtasia
(url
, video_id
, webpage
)
2154 if camtasia_res
is not None:
2157 # Sometimes embedded video player is hidden behind percent encoding
2158 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2159 # Unescaping the whole page allows to handle those cases in a generic way
2160 webpage
= compat_urllib_parse_unquote(webpage
)
2162 # it's tempting to parse this further, but you would
2163 # have to take into account all the variations like
2164 # Video Title - Site Name
2165 # Site Name | Video Title
2166 # Video Title - Tagline | Site Name
2167 # and so on and so forth; it's just not practical
2168 video_title
= self
._og
_search
_title
(
2169 webpage
, default
=None) or self
._html
_search
_regex
(
2170 r
'(?s)<title>(.*?)</title>', webpage
, 'video title',
2173 # Try to detect age limit automatically
2174 age_limit
= self
._rta
_search
(webpage
)
2175 # And then there are the jokers who advertise that they use RTA,
2176 # but actually don't.
2177 AGE_LIMIT_MARKERS
= [
2178 r
'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2180 if any(re
.search(marker
, webpage
) for marker
in AGE_LIMIT_MARKERS
):
2183 # video uploader is domain name
2184 video_uploader
= self
._search
_regex
(
2185 r
'^(?:https?://)?([^/]*)/.*', url
, 'video uploader')
2187 video_description
= self
._og
_search
_description
(webpage
, default
=None)
2188 video_thumbnail
= self
._og
_search
_thumbnail
(webpage
, default
=None)
2191 'title': video_title
,
2192 'description': video_description
,
2193 'thumbnail': video_thumbnail
,
2194 'age_limit': age_limit
,
2197 # Look for Brightcove Legacy Studio embeds
2198 bc_urls
= BrightcoveLegacyIE
._extract
_brightcove
_urls
(webpage
)
2202 'url': smuggle_url(bc_url
, {'Referer': url
}),
2203 'ie_key': 'BrightcoveLegacy'
2204 } for bc_url
in bc_urls
]
2207 '_type': 'playlist',
2208 'title': video_title
,
2213 # Look for Brightcove New Studio embeds
2214 bc_urls
= BrightcoveNewIE
._extract
_urls
(self
, webpage
)
2216 return self
.playlist_from_matches(bc_urls
, video_id
, video_title
, ie
='BrightcoveNew')
2218 # Look for Nexx embeds
2219 nexx_urls
= NexxIE
._extract
_urls
(webpage
)
2221 return self
.playlist_from_matches(nexx_urls
, video_id
, video_title
, ie
=NexxIE
.ie_key())
2223 # Look for Nexx iFrame embeds
2224 nexx_embed_urls
= NexxEmbedIE
._extract
_urls
(webpage
)
2226 return self
.playlist_from_matches(nexx_embed_urls
, video_id
, video_title
, ie
=NexxEmbedIE
.ie_key())
2228 # Look for ThePlatform embeds
2229 tp_urls
= ThePlatformIE
._extract
_urls
(webpage
)
2231 return self
.playlist_from_matches(tp_urls
, video_id
, video_title
, ie
='ThePlatform')
2233 # Look for Vessel embeds
2234 vessel_urls
= VesselIE
._extract
_urls
(webpage
)
2236 return self
.playlist_from_matches(vessel_urls
, video_id
, video_title
, ie
=VesselIE
.ie_key())
2238 # Look for embedded rtl.nl player
2239 matches
= re
.findall(
2240 r
'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2243 return self
.playlist_from_matches(matches
, video_id
, video_title
, ie
='RtlNl')
2245 vimeo_urls
= VimeoIE
._extract
_urls
(url
, webpage
)
2247 return self
.playlist_from_matches(vimeo_urls
, video_id
, video_title
, ie
=VimeoIE
.ie_key())
2249 vid_me_embed_url
= self
._search
_regex
(
2250 r
'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2251 webpage, 'vid.me embed', default=None)
2252 if vid_me_embed_url is not None:
2253 return self.url_result(vid_me_embed_url, 'Vidme')
2255 # Look for YouTube embeds
2256 youtube_urls = YoutubeIE._extract_urls(webpage)
2258 return self.playlist_from_matches(
2259 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2261 matches = DailymotionIE._extract_urls(webpage)
2263 return self.playlist_from_matches(matches, video_id, video_title)
2265 # Look for embedded Dailymotion playlist player (#3822)
2267 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?dailymotion\
.[a
-z
]{2,3}/widget
/jukebox
\?.+?
)\
1', webpage)
2269 playlists = re.findall(
2270 r'list\
[\
]=/playlist
/([^
/]+)/', unescapeHTML(m.group('url
')))
2272 return self.playlist_from_matches(
2273 playlists, video_id, video_title, lambda p: '//dailymotion
.com
/playlist
/%s' % p)
2275 # Look for DailyMail embeds
2276 dailymail_urls = DailyMailIE._extract_urls(webpage)
2278 return self.playlist_from_matches(
2279 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2281 # Look for embedded Wistia player
2282 wistia_url = WistiaIE._extract_url(webpage)
2285 '_type
': 'url_transparent
',
2286 'url
': self._proto_relative_url(wistia_url),
2287 'ie_key
': WistiaIE.ie_key(),
2288 'uploader
': video_uploader,
2291 # Look for SVT player
2292 svt_url = SVTIE._extract_url(webpage)
2294 return self.url_result(svt_url, 'SVT
')
2296 # Look for Bandcamp pages with custom domain
2297 mobj = re.search(r'<meta
property="og:url"[^
>]*?content
="(.*?bandcamp\.com.*?)"', webpage)
2298 if mobj is not None:
2299 burl = unescapeHTML(mobj.group(1))
2300 # Don't
set the extractor because it can be a track url
or an album
2301 return self
.url_result(burl
)
2303 # Look for embedded Vevo player
2305 r
'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:cache\
.)?vevo\
.com
/.+?
)\
1', webpage)
2306 if mobj is not None:
2307 return self.url_result(mobj.group('url
'))
2309 # Look for embedded Viddler player
2311 r'<(?
:iframe
[^
>]+?src|param
[^
>]+?value
)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2313 if mobj is not None:
2314 return self.url_result(mobj.group('url'))
2316 # Look for NYTimes player
2318 r'<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//graphics8\
.nytimes\
.com
/bcvideo
/[^
/]+/iframe
/embed\
.html
.+?
)\
1>',
2320 if mobj is not None:
2321 return self.url_result(mobj.group('url
'))
2323 # Look for Libsyn player
2325 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2326 if mobj is not None:
2327 return self.url_result(mobj.group('url'))
2329 # Look for Ooyala videos
2330 mobj = (re.search(r'player\.ooyala\.com/[^"?
]+[?
#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2331 re
.search(r
'OO\.Player\.create\([\'"].*?[\'"],\s
*[\'"](?P<ec>.{32})[\'"]', webpage) or
2332 re.search(r'OO\
.Player\
.create\
.apply\
(\s
*OO\
.Player\s
*,\s
*op\
(\s
*\
[\s
*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage) or
2333 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P
<ec
>.{32}
)[\'"]\)', webpage) or
2334 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P
<ec
>.{32}
)[\'"]', webpage))
2335 if mobj is not None:
2336 embed_token = self._search_regex(
2337 r'embedToken[\'"]?\s
*:\s
*[\'"]([^\'"]+)',
2338 webpage, 'ooyala embed token
', default=None)
2339 return OoyalaIE._build_url_result(smuggle_url(
2342 'embed_token
': embed_token,
2345 # Look for multiple Ooyala embeds on SBN network websites
2346 mobj = re.search(r'SBN\
.VideoLinkset\
.entryGroup\
((\
[.*?\
])', webpage)
2347 if mobj is not None:
2348 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2350 return self.playlist_from_matches(
2351 embeds, video_id, video_title,
2352 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id
'], {'domain
': url})), ie='Ooyala
')
2354 # Look for Aparat videos
2355 mobj = re.search(r'<iframe
.*?src
="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2356 if mobj is not None:
2357 return self.url_result(mobj.group(1), 'Aparat')
2359 # Look for MPORA videos
2360 mobj = re.search(r'<iframe .*?src="(http
://mpora\
.(?
:com|de
)/videos
/[^
"]+)"', webpage)
2361 if mobj is not None:
2362 return self.url_result(mobj.group(1), 'Mpora
')
2364 # Look for embedded NovaMov-based player
2366 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2367 (?P<url>http://(?:(?:embed|www)\.)?
2369 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2370 videoweed\.(?:es|com)|
2371 movshare\.(?:net|sx|ag)|
2372 divxstage\.(?:eu|net|ch|co|at|ag))
2373 /embed\.php.+?)\1''', webpage)
2374 if mobj is not None:
2375 return self.url_result(mobj.group('url
'))
2377 # Look for embedded Facebook player
2378 facebook_urls = FacebookIE._extract_urls(webpage)
2380 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2382 # Look for embedded VK player
2383 mobj = re.search(r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2384 if mobj is not None:
2385 return self.url_result(mobj.group('url'), 'VK')
2387 # Look for embedded Odnoklassniki player
2388 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://(?
:odnoklassniki|ok
)\
.ru
/videoembed
/.+?
)\
1', webpage)
2389 if mobj is not None:
2390 return self.url_result(mobj.group('url
'), 'Odnoklassniki
')
2392 # Look for embedded ivi player
2393 mobj = re.search(r'<embed
[^
>]+?src
=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2394 if mobj is not None:
2395 return self.url_result(mobj.group('url'), 'Ivi')
2397 # Look for embedded Huffington Post player
2399 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://embed\
.live\
.huffingtonpost\
.com
/.+?
)\
1', webpage)
2400 if mobj is not None:
2401 return self.url_result(mobj.group('url
'), 'HuffPost
')
2404 mobj = re.search(r'class=["\']embedly-card["\'][^
>]href
=["\'](?P<url>[^"\']+)', webpage)
2405 if mobj is not None:
2406 return self.url_result(mobj.group('url
'))
2407 mobj = re.search(r'class=["\']embedly-embed["\'][^
>]src
=["\'][^"\']*url
=(?P
<url
>[^
&]+)', webpage)
2408 if mobj is not None:
2409 return self.url_result(compat_urllib_parse_unquote(mobj.group('url
')))
2411 # Look for funnyordie embed
2412 matches = re.findall(r'<iframe
[^
>]+?src
="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2414 return self.playlist_from_matches(
2415 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2417 # Look for BBC iPlayer embed
2418 matches = re.findall(r'setPlaylist\("(https?
://www\
.bbc\
.co\
.uk
/iplayer
/[^
/]+/[\da
-z
]{8}
)"\)', webpage)
2420 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2422 # Look for embedded RUTV player
2423 rutv_url = RUTVIE._extract_url(webpage)
2425 return self.url_result(rutv_url, 'RUTV')
2427 # Look for embedded TVC player
2428 tvc_url = TVCIE._extract_url(webpage)
2430 return self.url_result(tvc_url, 'TVC')
2432 # Look for embedded SportBox player
2433 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2435 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2437 # Look for embedded XHamster player
2438 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2440 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2442 # Look for embedded TNAFlixNetwork player
2443 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2445 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2447 # Look for embedded PornHub player
2448 pornhub_urls = PornHubIE._extract_urls(webpage)
2450 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2452 # Look for embedded DrTuber player
2453 drtuber_urls = DrTuberIE._extract_urls(webpage)
2455 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2457 # Look for embedded RedTube player
2458 redtube_urls = RedTubeIE._extract_urls(webpage)
2460 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2462 # Look for embedded Tvigle player
2464 r'<iframe[^>]+?src=(["\'])(?P
<url
>(?
:https?
:)?
//cloud\
.tvigle\
.ru
/video
/.+?
)\
1', webpage)
2465 if mobj is not None:
2466 return self.url_result(mobj.group('url
'), 'Tvigle
')
2468 # Look for embedded TED player
2470 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2471 if mobj is not None:
2472 return self.url_result(mobj.group('url'), 'TED')
2474 # Look for embedded Ustream videos
2475 ustream_url = UstreamIE._extract_url(webpage)
2477 return self.url_result(ustream_url, UstreamIE.ie_key())
2479 # Look for embedded arte.tv player
2481 r'<(?:script|iframe) [^>]*?src="(?P
<url
>http
://www\
.arte\
.tv
/(?
:playerv2
/embed|arte_vp
/index
)[^
"]+)"',
2483 if mobj is not None:
2484 return self.url_result(mobj.group('url
'), 'ArteTVEmbed
')
2486 # Look for embedded francetv player
2488 r'<iframe
[^
>]+?src
=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2490 if mobj is not None:
2491 return self.url_result(mobj.group('url'))
2493 # Look for embedded smotri.com player
2494 smotri_url = SmotriIE._extract_url(webpage)
2496 return self.url_result(smotri_url, 'Smotri')
2498 # Look for embedded Myvi.ru player
2499 myvi_url = MyviIE._extract_url(webpage)
2501 return self.url_result(myvi_url)
2503 # Look for embedded soundcloud player
2504 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2506 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2508 # Look for tunein player
2509 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2511 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2513 # Look for embedded mtvservices player
2514 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2516 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2518 # Look for embedded yahoo player
2520 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://(?
:screen|movies
)\
.yahoo\
.com
/.+?\
.html
\?format
=embed
)\
1',
2522 if mobj is not None:
2523 return self.url_result(mobj.group('url
'), 'Yahoo
')
2525 # Look for embedded sbs.com.au player
2529 <meta\s+property="og:video"\s+content=|
2532 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2534 if mobj is not None:
2535 return self.url_result(mobj.group('url
'), 'SBS
')
2537 # Look for embedded Cinchcast player
2539 r'<iframe
[^
>]+?src
=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2541 if mobj is not None:
2542 return self.url_result(mobj.group('url'), 'Cinchcast')
2545 r'<iframe[^>]+?src=(["\'])(?P
<url
>https?
://m(?
:lb
)?\
.mlb\
.com
/shared
/video
/embed
/embed\
.html
\?.+?
)\
1',
2549 r'data
-video
-link
=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2551 if mobj is not None:
2552 return self.url_result(mobj.group('url
'), 'MLB
')
2555 r'<(?
:iframe|script
)[^
>]+?src
=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2557 if mobj is not None:
2558 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2561 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:new\
.)?livestream\
.com
/[^
"]+/player[^"]+)"',
2563 if mobj is not None:
2564 return self.url_result(mobj.group('url'), 'Livestream')
2566 # Look for Zapiks embed
2568 r'<iframe[^>]+src="(?P
<url
>https?
://(?
:www\
.)?zapiks\
.fr
/index\
.php
\?.+?
)"', webpage)
2569 if mobj is not None:
2570 return self.url_result(mobj.group('url'), 'Zapiks')
2572 # Look for Kaltura embeds
2573 kaltura_url = KalturaIE._extract_url(webpage)
2575 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2577 # Look for EaglePlatform embeds
2578 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2579 if eagleplatform_url:
2580 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2582 # Look for ClipYou (uses EaglePlatform) embeds
2584 r'<iframe[^>]+src="https?
://(?P
<host
>media\
.clipyou\
.ru
)/index
/player
\?.*\brecord
_id
=(?P
<id>\d
+).*"', webpage)
2585 if mobj is not None:
2586 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2588 # Look for Pladform embeds
2589 pladform_url = PladformIE._extract_url(webpage)
2591 return self.url_result(pladform_url)
2593 # Look for Videomore embeds
2594 videomore_url = VideomoreIE._extract_url(webpage)
2596 return self.url_result(videomore_url)
2598 # Look for Webcaster embeds
2599 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2601 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2603 # Look for Playwire embeds
2605 r'<script[^>]+data-config=(["\'])(?P
<url
>(?
:https?
:)?
//config\
.playwire\
.com
/.+?
)\
1', webpage)
2606 if mobj is not None:
2607 return self.url_result(mobj.group('url
'))
2609 # Look for 5min embeds
2611 r'<meta
[^
>]+property="og:video"[^
>]+content
="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2612 if mobj is not None:
2613 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2615 # Look for Crooks and Liars embeds
2617 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P
<url
>(?
:https?
:)?
//embed\
.crooksandliars\
.com
/(?
:embed|v
)/.+?
)\
1', webpage)
2618 if mobj is not None:
2619 return self.url_result(mobj.group('url
'))
2621 # Look for NBC Sports VPlayer embeds
2622 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2624 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer
')
2626 # Look for NBC News embeds
2627 nbc_news_embed_url = re.search(
2628 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\
1', webpage)
2629 if nbc_news_embed_url:
2630 return self.url_result(nbc_news_embed_url.group('url
'), 'NBCNews
')
2632 # Look for Google Drive embeds
2633 google_drive_url = GoogleDriveIE._extract_url(webpage)
2634 if google_drive_url:
2635 return self.url_result(google_drive_url, 'GoogleDrive
')
2637 # Look for UDN embeds
2639 r'<iframe
[^
>]+src
="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2640 if mobj is not None:
2641 return self.url_result(
2642 compat_urlparse.urljoin(url, mobj.group('url
')), 'UDNEmbed
')
2644 # Look for Senate ISVP iframe
2645 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2647 return self.url_result(senate_isvp_url, 'SenateISVP
')
2649 # Look for Dailymotion Cloud videos
2650 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2652 return self.url_result(dmcloud_url, 'DailymotionCloud
')
2654 # Look for OnionStudios embeds
2655 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2656 if onionstudios_url:
2657 return self.url_result(onionstudios_url)
2659 # Look for ViewLift embeds
2660 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2662 return self.url_result(viewlift_url)
2664 # Look for JWPlatform embeds
2665 jwplatform_url = JWPlatformIE._extract_url(webpage)
2667 return self.url_result(jwplatform_url, 'JWPlatform
')
2669 # Look for Digiteka embeds
2670 digiteka_url = DigitekaIE._extract_url(webpage)
2672 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2674 # Look for Arkena embeds
2675 arkena_url = ArkenaIE._extract_url(webpage)
2677 return self.url_result(arkena_url, ArkenaIE.ie_key())
2679 # Look for Piksel embeds
2680 piksel_url = PikselIE._extract_url(webpage)
2682 return self.url_result(piksel_url, PikselIE.ie_key())
2684 # Look for Limelight embeds
2685 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2687 return self.playlist_result(
2688 limelight_urls, video_id, video_title, video_description)
2690 # Look for Anvato embeds
2691 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2693 return self.playlist_result(
2694 anvato_urls, video_id, video_title, video_description)
2696 # Look for AdobeTVVideo embeds
2698 r'<iframe
[^
>]+src
=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2700 if mobj is not None:
2701 return self.url_result(
2702 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2705 # Look for Vine embeds
2707 r'<iframe[^>]+src=[\'"]((?
:https?
:)?
//(?
:www\
.)?vine\
.co
/v
/[^
/]+/embed
/(?
:simple|postcard
))',
2709 if mobj is not None:
2710 return self.url_result(
2711 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine
')
2713 # Look for VODPlatform embeds
2715 r'<iframe
[^
>]+src
=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2717 if mobj is not None:
2718 return self.url_result(
2719 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2721 # Look for Mangomolo embeds
2723 r'''(?x)<iframe[^>]+src=(["\'])(?P
<url
>(?
:https?
:)?
//(?
:www\
.)?admin\
.mangomolo\
.com
/analytics
/index\
.php
/customers
/embed
/
2725 video
\?.*?
\bid
=(?P
<video_id
>\d
+)|
2726 index
\?.*?
\bchannelid
=(?P
<channel_id
>(?
:[A
-Za
-z0
-9+/=]|
%2B|
%2F|
%3D
)+)
2727 ).+?
)\
1''', webpage)
2728 if mobj is not None:
2730 '_type': 'url_transparent',
2731 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2732 'title': video_title,
2733 'description': video_description,
2734 'thumbnail': video_thumbnail,
2735 'uploader': video_uploader,
2737 video_id = mobj.group('video_id')
2740 'ie_key': 'MangomoloVideo',
2745 'ie_key': 'MangomoloLive',
2746 'id': mobj.group('channel_id'),
2750 # Look for Instagram embeds
2751 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2752 if instagram_embed_url is not None:
2753 return self.url_result(
2754 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2756 # Look for LiveLeak embeds
2757 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2759 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2761 # Look for 3Q SDN embeds
2762 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2765 '_type': 'url_transparent',
2766 'ie_key': ThreeQSDNIE.ie_key(),
2767 'url': self._proto_relative_url(threeqsdn_url),
2768 'title': video_title,
2769 'description': video_description,
2770 'thumbnail': video_thumbnail,
2771 'uploader': video_uploader,
2774 # Look for VBOX7 embeds
2775 vbox7_url = Vbox7IE._extract_url(webpage)
2777 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2779 # Look for DBTV embeds
2780 dbtv_urls = DBTVIE._extract_urls(webpage)
2782 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2784 # Look for Videa embeds
2785 videa_urls = VideaIE._extract_urls(webpage)
2787 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2789 # Look for 20 minuten embeds
2790 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2792 return self.playlist_from_matches(
2793 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2795 # Look for Openload embeds
2796 openload_urls = OpenloadIE._extract_urls(webpage)
2798 return self.playlist_from_matches(
2799 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2801 # Look for VideoPress embeds
2802 videopress_urls = VideoPressIE._extract_urls(webpage)
2804 return self.playlist_from_matches(
2805 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2807 # Look for Rutube embeds
2808 rutube_urls = RutubeIE._extract_urls(webpage)
2810 return self.playlist_from_matches(
2811 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2813 # Look for WashingtonPost embeds
2814 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2816 return self.playlist_from_matches(
2817 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2819 # Look for Mediaset embeds
2820 mediaset_urls = MediasetIE._extract_urls(webpage)
2822 return self.playlist_from_matches(
2823 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2825 # Look for JOJ.sk embeds
2826 joj_urls = JojIE._extract_urls(webpage)
2828 return self.playlist_from_matches(
2829 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2831 # Look for megaphone.fm embeds
2832 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2834 return self.playlist_from_matches(
2835 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2837 # Look for vzaar embeds
2838 vzaar_urls = VzaarIE._extract_urls(webpage)
2840 return self.playlist_from_matches(
2841 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2843 def merge_dicts(dict1, dict2):
2845 for k, v in dict1.items():
2848 for k, v in dict2.items():
2851 if (k not in merged or
2852 (isinstance(v, compat_str) and v and
2853 isinstance(merged[k], compat_str) and
2858 # Look for HTML5 media
2859 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2861 if len(entries) == 1:
2864 'title': video_title,
2867 for num, entry in enumerate(entries, start=1):
2869 'id': '%s-%s' % (video_id, num),
2870 'title': '%s (%d)' % (video_title, num),
2872 for entry in entries:
2873 self._sort_formats(entry['formats'])
2874 return self.playlist_result(entries, video_id, video_title)
2876 jwplayer_data = self._find_jwplayer_data(
2877 webpage, video_id, transform_source=js_to_json)
2879 info = self._parse_jwplayer_data(
2880 jwplayer_data, video_id, require_title=False, base_url=url)
2881 return merge_dicts(info, info_dict)
2883 # Looking for http://schema.org/VideoObject
2884 json_ld = self._search_json_ld(
2885 webpage, video_id, default={}, expected_type='VideoObject')
2886 if json_ld.get('url'):
2887 return merge_dicts(json_ld, info_dict)
2889 def check_video(vurl):
2890 if YoutubeIE.suitable(vurl):
2892 if RtmpIE.suitable(vurl):
2894 vpath = compat_urlparse.urlparse(vurl).path
2895 vext = determine_ext(vpath)
2896 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2898 def filter_video(urls):
2899 return list(filter(check_video, urls))
2901 # Start with something easy: JW Player in SWFObject
2902 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2904 # Look for gorilla-vid style embedding
2905 found = filter_video(re.findall(r'''(?sx
)
2909 jwplayer\s
*\
(\s
*["'][^'"]+["']\s*\)\s*\.setup
2912 ['"]?
file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2914 # Broaden the search a little bit
2915 found = filter_video(re.findall(r'[^A
-Za
-z0
-9]?
(?
:file|source
)=(http
[^
\'"&]*)', webpage))
2917 # Broaden the findall a little bit: JWPlayer JS loader
2918 found = filter_video(re.findall(
2919 r'[^A-Za-z0-9]?(?:file|video_url)["\']?
:\s
*["\'](http(?![^\'"]+\
.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2922 found = filter_video(re.findall(r'''(?xs)
2923 flowplayer\("[^
"]+",\s
*
2925 \s
*\
{[^
}]+?
["']?clip["']?\s*:\s*\{\s*
2926 ["']?url
["']?\s*:\s*["']([^"']+)["']
2931 r"cinerama\
.embedPlayer\
(\s
*\'[^
']+\',\s*'([^
']+)'", webpage)
2933 # Try to find twitter cards info
2934 # twitter:player:stream should be checked before twitter:player since
2935 # it is expected to contain a raw stream (see
2936 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2937 found = filter_video(re.findall(
2938 r'<meta (?:property|name)="twitter
:player
:stream
" (?:content|value)="(.+?
)"', webpage))
2940 # We look for Open Graph info:
2941 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2942 m_video_type = re.findall(r'<meta.*?property="og
:video
:type".*?content="video
/(.*?
)"', webpage)
2943 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2944 if m_video_type is not None:
2945 found = filter_video(re.findall(r'<meta.*?property="og
:video
".*?content="(.*?
)"', webpage))
2947 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2949 r'(?i
)<meta\s
+(?
=(?
:[a
-z
-]+="[^"]+"\s+)*http-equiv="refresh
")'
2950 r'(?:[a-z-]+="[^
"]+"\s
+)*?content
="%s' % REDIRECT_REGEX,
2953 # Look also in Refresh HTTP header
2954 refresh_header = head_response.headers.get('Refresh')
2956 # In python 2 response HTTP headers are bytestrings
2957 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2958 refresh_header = refresh_header.decode('iso-8859-1')
2959 found = re.search(REDIRECT_REGEX, refresh_header)
2961 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2963 self.report_following_redirect(new_url)
2972 # twitter:player is a https URL to iframe player that may or may not
2973 # be supported by youtube-dl thus this is checked the very last (see
2974 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2975 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2977 return self.url_result(embed_url)
2980 raise UnsupportedError(url)
2983 for video_url in orderedSet(found):
2984 video_url = unescapeHTML(video_url)
2985 video_url = video_url.replace('\\/', '/')
2986 video_url = compat_urlparse.urljoin(url, video_url)
2987 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2989 # Sometimes, jwplayer extraction will result in a YouTube URL
2990 if YoutubeIE.suitable(video_url):
2991 entries.append(self.url_result(video_url, 'Youtube'))
2994 # here's a fun little line of code for you:
2995 video_id = os.path.splitext(video_id)[0]
2999 'uploader': video_uploader,
3000 'title': video_title,
3001 'age_limit': age_limit,
3004 if RtmpIE.suitable(video_url):
3005 entry_info_dict.update({
3006 '_type': 'url_transparent',
3007 'ie_key': RtmpIE.ie_key(),
3010 entries.append(entry_info_dict)
3013 ext = determine_ext(video_url)
3015 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3017 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3019 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3021 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3023 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3024 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3025 # Just matching .ism/manifest is not enough to be reliably sure
3026 # whether it's actually an ISM manifest or some other streaming
3027 # manifest since there are various streaming URL formats
3028 # possible (see [1]) as well as some other shenanigans like
3029 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3031 # Thus the most reasonable way to solve this is to delegate
3032 # to generic extractor in order to look into the contents of
3033 # the manifest itself.
3034 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3035 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3036 entry_info_dict = self.url_result(
3037 smuggle_url(video_url, {'to_generic': True}),
3040 entry_info_dict['url'] = video_url
3042 if entry_info_dict.get('formats'):
3043 self._sort_formats(entry_info_dict['formats'])
3045 entries.append(entry_info_dict)
3047 if len(entries) == 1:
3050 for num, e in enumerate(entries, start=1):
3051 # 'url' results don't have a title
3052 if e.get('title') is not None:
3053 e['title'] = '%s (%d)' % (e['title'], num)
3055 '_type': 'playlist',