]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[openload] remove OpenLoad related extractors(closes #11999)(closes #15406)
[yt-dlp.git] / youtube_dl / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 is_html,
24 js_to_json,
25 KNOWN_EXTENSIONS,
26 merge_dicts,
27 mimetype2ext,
28 orderedSet,
29 sanitized_Request,
30 smuggle_url,
31 unescapeHTML,
32 unified_strdate,
33 unsmuggle_url,
34 UnsupportedError,
35 xpath_text,
36 )
37 from .commonprotocols import RtmpIE
38 from .brightcove import (
39 BrightcoveLegacyIE,
40 BrightcoveNewIE,
41 )
42 from .nexx import (
43 NexxIE,
44 NexxEmbedIE,
45 )
46 from .nbc import NBCSportsVPlayerIE
47 from .ooyala import OoyalaIE
48 from .rutv import RUTVIE
49 from .tvc import TVCIE
50 from .sportbox import SportBoxIE
51 from .smotri import SmotriIE
52 from .myvi import MyviIE
53 from .condenast import CondeNastIE
54 from .udn import UDNEmbedIE
55 from .senateisvp import SenateISVPIE
56 from .svt import SVTIE
57 from .pornhub import PornHubIE
58 from .xhamster import XHamsterEmbedIE
59 from .tnaflix import TNAFlixNetworkEmbedIE
60 from .drtuber import DrTuberIE
61 from .redtube import RedTubeIE
62 from .tube8 import Tube8IE
63 from .vimeo import VimeoIE
64 from .dailymotion import DailymotionIE
65 from .dailymail import DailyMailIE
66 from .onionstudios import OnionStudiosIE
67 from .viewlift import ViewLiftEmbedIE
68 from .mtv import MTVServicesEmbeddedIE
69 from .pladform import PladformIE
70 from .videomore import VideomoreIE
71 from .webcaster import WebcasterFeedIE
72 from .googledrive import GoogleDriveIE
73 from .jwplatform import JWPlatformIE
74 from .digiteka import DigitekaIE
75 from .arkena import ArkenaIE
76 from .instagram import InstagramIE
77 from .liveleak import LiveLeakIE
78 from .threeqsdn import ThreeQSDNIE
79 from .theplatform import ThePlatformIE
80 from .kaltura import KalturaIE
81 from .eagleplatform import EaglePlatformIE
82 from .facebook import FacebookIE
83 from .soundcloud import SoundcloudEmbedIE
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 .videopress import VideoPressIE
92 from .rutube import RutubeIE
93 from .limelight import LimelightBaseIE
94 from .anvato import AnvatoIE
95 from .washingtonpost import WashingtonPostIE
96 from .wistia import WistiaIE
97 from .mediaset import MediasetIE
98 from .joj import JojIE
99 from .megaphone import MegaphoneIE
100 from .vzaar import VzaarIE
101 from .channel9 import Channel9IE
102 from .vshare import VShareIE
103 from .mediasite import MediasiteIE
104 from .springboardplatform import SpringboardPlatformIE
105 from .yapfiles import YapFilesIE
106 from .vice import ViceIE
107 from .xfileshare import XFileShareIE
108 from .cloudflarestream import CloudflareStreamIE
109 from .peertube import PeerTubeIE
110 from .teachable import TeachableIE
111 from .indavideo import IndavideoEmbedIE
112 from .apa import APAIE
113 from .foxnews import FoxNewsIE
114 from .viqeo import ViqeoIE
115 from .expressen import ExpressenIE
116 from .zype import ZypeIE
117 from .odnoklassniki import OdnoklassnikiIE
118 from .kinja import KinjaEmbedIE
119
120
121 class GenericIE(InfoExtractor):
122 IE_DESC = 'Generic downloader that works on some sites'
123 _VALID_URL = r'.*'
124 IE_NAME = 'generic'
125 _TESTS = [
126 # Direct link to a video
127 {
128 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
129 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
130 'info_dict': {
131 'id': 'trailer',
132 'ext': 'mp4',
133 'title': 'trailer',
134 'upload_date': '20100513',
135 }
136 },
137 # Direct link to media delivered compressed (until Accept-Encoding is *)
138 {
139 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
140 'md5': '128c42e68b13950268b648275386fc74',
141 'info_dict': {
142 'id': 'FictionJunction-Parallel_Hearts',
143 'ext': 'flac',
144 'title': 'FictionJunction-Parallel_Hearts',
145 'upload_date': '20140522',
146 },
147 'expected_warnings': [
148 'URL could be a direct video link, returning it as such.'
149 ],
150 'skip': 'URL invalid',
151 },
152 # Direct download with broken HEAD
153 {
154 'url': 'http://ai-radio.org:8000/radio.opus',
155 'info_dict': {
156 'id': 'radio',
157 'ext': 'opus',
158 'title': 'radio',
159 },
160 'params': {
161 'skip_download': True, # infinite live stream
162 },
163 'expected_warnings': [
164 r'501.*Not Implemented',
165 r'400.*Bad Request',
166 ],
167 },
168 # Direct link with incorrect MIME type
169 {
170 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
171 'md5': '4ccbebe5f36706d85221f204d7eb5913',
172 'info_dict': {
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'id': '5_Lennart_Poettering_-_Systemd',
175 'ext': 'webm',
176 'title': '5_Lennart_Poettering_-_Systemd',
177 'upload_date': '20141120',
178 },
179 'expected_warnings': [
180 'URL could be a direct video link, returning it as such.'
181 ]
182 },
183 # RSS feed
184 {
185 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
186 'info_dict': {
187 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
188 'title': 'Zero Punctuation',
189 'description': 're:.*groundbreaking video review series.*'
190 },
191 'playlist_mincount': 11,
192 },
193 # RSS feed with enclosure
194 {
195 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
196 'info_dict': {
197 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
198 'ext': 'm4v',
199 'upload_date': '20150228',
200 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
201 }
202 },
203 # RSS feed with enclosures and unsupported link URLs
204 {
205 'url': 'http://www.hellointernet.fm/podcast?format=rss',
206 'info_dict': {
207 'id': 'http://www.hellointernet.fm/podcast?format=rss',
208 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
209 'title': 'Hello Internet',
210 },
211 'playlist_mincount': 100,
212 },
213 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
214 {
215 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
216 'info_dict': {
217 'id': 'smil',
218 'ext': 'mp4',
219 'title': 'Automatics, robotics and biocybernetics',
220 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
221 'upload_date': '20130627',
222 'formats': 'mincount:16',
223 'subtitles': 'mincount:1',
224 },
225 'params': {
226 'force_generic_extractor': True,
227 'skip_download': True,
228 },
229 },
230 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
231 {
232 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
233 'info_dict': {
234 'id': 'hds',
235 'ext': 'flv',
236 'title': 'hds',
237 'formats': 'mincount:1',
238 },
239 'params': {
240 'skip_download': True,
241 },
242 },
243 # SMIL from https://www.restudy.dk/video/play/id/1637
244 {
245 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
246 'info_dict': {
247 'id': 'video_1637',
248 'ext': 'flv',
249 'title': 'video_1637',
250 'formats': 'mincount:3',
251 },
252 'params': {
253 'skip_download': True,
254 },
255 },
256 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
257 {
258 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
259 'info_dict': {
260 'id': 'smil-service',
261 'ext': 'flv',
262 'title': 'smil-service',
263 'formats': 'mincount:1',
264 },
265 'params': {
266 'skip_download': True,
267 },
268 },
269 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
270 {
271 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
272 'info_dict': {
273 'id': '4719370',
274 'ext': 'mp4',
275 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
276 'formats': 'mincount:3',
277 },
278 'params': {
279 'skip_download': True,
280 },
281 },
282 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
283 {
284 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
285 'info_dict': {
286 'id': 'mZlp2ctYIUEB',
287 'ext': 'mp4',
288 'title': 'Tikibad ontruimd wegens brand',
289 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
290 'thumbnail': r're:^https?://.*\.jpg$',
291 'duration': 33,
292 },
293 'params': {
294 'skip_download': True,
295 },
296 },
297 # MPD from http://dash-mse-test.appspot.com/media.html
298 {
299 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
300 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
301 'info_dict': {
302 'id': 'car-20120827-manifest',
303 'ext': 'mp4',
304 'title': 'car-20120827-manifest',
305 'formats': 'mincount:9',
306 'upload_date': '20130904',
307 },
308 'params': {
309 'format': 'bestvideo',
310 },
311 },
312 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
313 {
314 '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',
315 'info_dict': {
316 'id': 'content',
317 'ext': 'mp4',
318 'title': 'content',
319 'formats': 'mincount:8',
320 },
321 'params': {
322 # m3u8 downloads
323 'skip_download': True,
324 },
325 'skip': 'video gone',
326 },
327 # m3u8 served with Content-Type: text/plain
328 {
329 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
330 'info_dict': {
331 'id': 'index',
332 'ext': 'mp4',
333 'title': 'index',
334 'upload_date': '20140720',
335 'formats': 'mincount:11',
336 },
337 'params': {
338 # m3u8 downloads
339 'skip_download': True,
340 },
341 'skip': 'video gone',
342 },
343 # google redirect
344 {
345 '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',
346 'info_dict': {
347 'id': 'cmQHVoWB5FY',
348 'ext': 'mp4',
349 'upload_date': '20130224',
350 'uploader_id': 'TheVerge',
351 'description': r're:^Chris Ziegler takes a look at the\.*',
352 'uploader': 'The Verge',
353 'title': 'First Firefox OS phones side-by-side',
354 },
355 'params': {
356 'skip_download': False,
357 }
358 },
359 {
360 # redirect in Refresh HTTP header
361 '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',
362 'info_dict': {
363 'id': 'pO8h3EaFRdo',
364 'ext': 'mp4',
365 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
366 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
367 'upload_date': '20150917',
368 'uploader_id': 'brtvofficial',
369 'uploader': 'Boiler Room',
370 },
371 'params': {
372 'skip_download': False,
373 },
374 },
375 {
376 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
377 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
378 'info_dict': {
379 'id': '13601338388002',
380 'ext': 'mp4',
381 'uploader': 'www.hodiho.fr',
382 'title': 'R\u00e9gis plante sa Jeep',
383 }
384 },
385 # bandcamp page with custom domain
386 {
387 'add_ie': ['Bandcamp'],
388 'url': 'http://bronyrock.com/track/the-pony-mash',
389 'info_dict': {
390 'id': '3235767654',
391 'ext': 'mp3',
392 'title': 'The Pony Mash',
393 'uploader': 'M_Pallante',
394 },
395 'skip': 'There is a limit of 200 free downloads / month for the test song',
396 },
397 {
398 # embedded brightcove video
399 # it also tests brightcove videos that need to set the 'Referer'
400 # in the http requests
401 'add_ie': ['BrightcoveLegacy'],
402 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
403 'info_dict': {
404 'id': '2765128793001',
405 'ext': 'mp4',
406 'title': 'Le cours de bourse : l’analyse technique',
407 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
408 'uploader': 'BFM BUSINESS',
409 },
410 'params': {
411 'skip_download': True,
412 },
413 },
414 {
415 # embedded with itemprop embedURL and video id spelled as `idVideo`
416 'add_id': ['BrightcoveLegacy'],
417 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
418 'info_dict': {
419 'id': '5255628253001',
420 'ext': 'mp4',
421 'title': 'md5:37c519b1128915607601e75a87995fc0',
422 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
423 'uploader': 'BFM BUSINESS',
424 'uploader_id': '876450612001',
425 'timestamp': 1482255315,
426 'upload_date': '20161220',
427 },
428 'params': {
429 'skip_download': True,
430 },
431 },
432 {
433 # https://github.com/ytdl-org/youtube-dl/issues/2253
434 'url': 'http://bcove.me/i6nfkrc3',
435 'md5': '0ba9446db037002366bab3b3eb30c88c',
436 'info_dict': {
437 'id': '3101154703001',
438 'ext': 'mp4',
439 'title': 'Still no power',
440 'uploader': 'thestar.com',
441 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
442 },
443 'add_ie': ['BrightcoveLegacy'],
444 'skip': 'video gone',
445 },
446 {
447 'url': 'http://www.championat.com/video/football/v/87/87499.html',
448 'md5': 'fb973ecf6e4a78a67453647444222983',
449 'info_dict': {
450 'id': '3414141473001',
451 'ext': 'mp4',
452 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
453 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
454 'uploader': 'Championat',
455 },
456 },
457 {
458 # https://github.com/ytdl-org/youtube-dl/issues/3541
459 'add_ie': ['BrightcoveLegacy'],
460 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
461 'info_dict': {
462 'id': '3866516442001',
463 'ext': 'mp4',
464 'title': 'Leer mij vrouwen kennen: Aflevering 1',
465 'description': 'Leer mij vrouwen kennen: Aflevering 1',
466 'uploader': 'SBS Broadcasting',
467 },
468 'skip': 'Restricted to Netherlands',
469 'params': {
470 'skip_download': True, # m3u8 download
471 },
472 },
473 {
474 # Brightcove video in <iframe>
475 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
476 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
477 'info_dict': {
478 'id': '5360463607001',
479 'ext': 'mp4',
480 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
481 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
482 'uploader': 'United Nations',
483 'uploader_id': '1362235914001',
484 'timestamp': 1489593889,
485 'upload_date': '20170315',
486 },
487 'add_ie': ['BrightcoveLegacy'],
488 },
489 {
490 # Brightcove with alternative playerID key
491 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
492 'info_dict': {
493 'id': 'nmeth.2062_SV1',
494 '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',
495 },
496 'playlist': [{
497 'info_dict': {
498 'id': '2228375078001',
499 'ext': 'mp4',
500 'title': 'nmeth.2062-sv1',
501 'description': 'nmeth.2062-sv1',
502 'timestamp': 1363357591,
503 'upload_date': '20130315',
504 'uploader': 'Nature Publishing Group',
505 'uploader_id': '1964492299001',
506 },
507 }],
508 },
509 {
510 # Brightcove with UUID in videoPlayer
511 'url': 'http://www8.hp.com/cn/zh/home.html',
512 'info_dict': {
513 'id': '5255815316001',
514 'ext': 'mp4',
515 'title': 'Sprocket Video - China',
516 'description': 'Sprocket Video - China',
517 'uploader': 'HP-Video Gallery',
518 'timestamp': 1482263210,
519 'upload_date': '20161220',
520 'uploader_id': '1107601872001',
521 },
522 'params': {
523 'skip_download': True, # m3u8 download
524 },
525 'skip': 'video rotates...weekly?',
526 },
527 {
528 # Brightcove:new type [2].
529 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
530 'md5': '2b35148fcf48da41c9fb4591650784f3',
531 'info_dict': {
532 'id': '5348741021001',
533 'ext': 'mp4',
534 'upload_date': '20170306',
535 'uploader_id': '4191638492001',
536 'timestamp': 1488769918,
537 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
538
539 },
540 },
541 {
542 # Alternative brightcove <video> attributes
543 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
544 'info_dict': {
545 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
546 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
547 },
548 'playlist': [{
549 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
550 'info_dict': {
551 'id': '5311302538001',
552 'ext': 'mp4',
553 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
554 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
555 'timestamp': 1486321708,
556 'upload_date': '20170205',
557 'uploader_id': '800000640001',
558 },
559 'only_matching': True,
560 }],
561 },
562 {
563 # Brightcove with UUID in videoPlayer
564 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'info_dict': {
566 'id': '5255815316001',
567 'ext': 'mp4',
568 'title': 'Sprocket Video - China',
569 'description': 'Sprocket Video - China',
570 'uploader': 'HP-Video Gallery',
571 'timestamp': 1482263210,
572 'upload_date': '20161220',
573 'uploader_id': '1107601872001',
574 },
575 'params': {
576 'skip_download': True, # m3u8 download
577 },
578 },
579 # ooyala video
580 {
581 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
582 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
583 'info_dict': {
584 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
585 'ext': 'mp4',
586 'title': '2cc213299525360.mov', # that's what we get
587 'duration': 238.231,
588 },
589 'add_ie': ['Ooyala'],
590 },
591 {
592 # ooyala video embedded with http://player.ooyala.com/iframe.js
593 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
594 'info_dict': {
595 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
596 'ext': 'mp4',
597 'title': '"Steve Jobs: Man in the Machine" trailer',
598 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
599 'duration': 135.427,
600 },
601 'params': {
602 'skip_download': True,
603 },
604 'skip': 'movie expired',
605 },
606 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
607 {
608 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
609 'info_dict': {
610 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
611 'ext': 'mp4',
612 'title': 'Steampunk Fest Comes to Honesdale',
613 'duration': 43.276,
614 },
615 'params': {
616 'skip_download': True,
617 }
618 },
619 # embed.ly video
620 {
621 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
622 'info_dict': {
623 'id': '9ODmcdjQcHQ',
624 'ext': 'mp4',
625 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
626 'upload_date': '20140225',
627 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
628 'uploader': 'Tested',
629 'uploader_id': 'testedcom',
630 },
631 # No need to test YoutubeIE here
632 'params': {
633 'skip_download': True,
634 },
635 },
636 # funnyordie embed
637 {
638 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
639 'info_dict': {
640 'id': '18e820ec3f',
641 'ext': 'mp4',
642 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
643 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
644 },
645 # HEAD requests lead to endless 301, while GET is OK
646 'expected_warnings': ['301'],
647 },
648 # RUTV embed
649 {
650 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
651 'info_dict': {
652 'id': '776940',
653 'ext': 'mp4',
654 'title': 'Охотское море стало целиком российским',
655 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
656 },
657 'params': {
658 # m3u8 download
659 'skip_download': True,
660 },
661 },
662 # TVC embed
663 {
664 '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/',
665 'info_dict': {
666 'id': '55304',
667 'ext': 'mp4',
668 'title': 'Дошкольное воспитание',
669 },
670 },
671 # SportBox embed
672 {
673 'url': 'http://www.vestifinance.ru/articles/25753',
674 'info_dict': {
675 'id': '25753',
676 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
677 },
678 'playlist': [{
679 'info_dict': {
680 'id': '370908',
681 'title': 'Госзаказ. День 3',
682 'ext': 'mp4',
683 }
684 }, {
685 'info_dict': {
686 'id': '370905',
687 'title': 'Госзаказ. День 2',
688 'ext': 'mp4',
689 }
690 }, {
691 'info_dict': {
692 'id': '370902',
693 'title': 'Госзаказ. День 1',
694 'ext': 'mp4',
695 }
696 }],
697 'params': {
698 # m3u8 download
699 'skip_download': True,
700 },
701 },
702 # Myvi.ru embed
703 {
704 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
705 'info_dict': {
706 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
707 'ext': 'mp4',
708 'title': 'Ужастики, русский трейлер (2015)',
709 'thumbnail': r're:^https?://.*\.jpg$',
710 'duration': 153,
711 }
712 },
713 # XHamster embed
714 {
715 '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',
716 'info_dict': {
717 'id': 'showthread',
718 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
719 },
720 'playlist_mincount': 7,
721 # This forum does not allow <iframe> syntaxes anymore
722 # Now HTML tags are displayed as-is
723 'skip': 'No videos on this page',
724 },
725 # Embedded TED video
726 {
727 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
728 'md5': '65fdff94098e4a607385a60c5177c638',
729 'info_dict': {
730 'id': '1969',
731 'ext': 'mp4',
732 'title': 'Hidden miracles of the natural world',
733 'uploader': 'Louie Schwartzberg',
734 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
735 }
736 },
737 # nowvideo embed hidden behind percent encoding
738 {
739 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
740 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
741 'info_dict': {
742 'id': '06e53103ca9aa',
743 'ext': 'flv',
744 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
745 'description': 'No description',
746 },
747 },
748 # arte embed
749 {
750 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
751 'md5': '7653032cbb25bf6c80d80f217055fa43',
752 'info_dict': {
753 'id': '048195-004_PLUS7-F',
754 'ext': 'flv',
755 'title': 'X:enius',
756 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
757 'upload_date': '20140320',
758 },
759 'params': {
760 'skip_download': 'Requires rtmpdump'
761 },
762 'skip': 'video gone',
763 },
764 # francetv embed
765 {
766 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
767 'info_dict': {
768 'id': 'EV_30231',
769 'ext': 'mp4',
770 'title': 'Alcaline, le concert avec Calogero',
771 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
772 'upload_date': '20150226',
773 'timestamp': 1424989860,
774 'duration': 5400,
775 },
776 'params': {
777 # m3u8 downloads
778 'skip_download': True,
779 },
780 'expected_warnings': [
781 'Forbidden'
782 ]
783 },
784 # Condé Nast embed
785 {
786 'url': 'http://www.wired.com/2014/04/honda-asimo/',
787 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
788 'info_dict': {
789 'id': '53501be369702d3275860000',
790 'ext': 'mp4',
791 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
792 }
793 },
794 # Dailymotion embed
795 {
796 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
797 'md5': '441aeeb82eb72c422c7f14ec533999cd',
798 'info_dict': {
799 'id': 'k2mm4bCdJ6CQ2i7c8o2',
800 'ext': 'mp4',
801 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
802 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
803 'uploader': 'Spi0n',
804 'uploader_id': 'xgditw',
805 'upload_date': '20140425',
806 'timestamp': 1398441542,
807 },
808 'add_ie': ['Dailymotion'],
809 },
810 # DailyMail embed
811 {
812 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
813 'info_dict': {
814 'id': '1495629',
815 'ext': 'mp4',
816 'title': 'Care worker punches elderly dementia patient in head 11 times',
817 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
818 },
819 'add_ie': ['DailyMail'],
820 'params': {
821 'skip_download': True,
822 },
823 },
824 # YouTube embed
825 {
826 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
827 'info_dict': {
828 'id': 'FXRb4ykk4S0',
829 'ext': 'mp4',
830 'title': 'The NBL Auction 2014',
831 'uploader': 'BADMINTON England',
832 'uploader_id': 'BADMINTONEvents',
833 'upload_date': '20140603',
834 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
835 },
836 'add_ie': ['Youtube'],
837 'params': {
838 'skip_download': True,
839 }
840 },
841 # MTVSercices embed
842 {
843 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
844 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
845 'info_dict': {
846 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
847 'ext': 'mp4',
848 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
849 'description': 'Two valets share their love for movie star Liam Neesons.',
850 'timestamp': 1349922600,
851 'upload_date': '20121011',
852 },
853 },
854 # YouTube embed via <data-embed-url="">
855 {
856 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
857 'info_dict': {
858 'id': '4vAffPZIT44',
859 'ext': 'mp4',
860 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
861 'uploader': 'Gameloft',
862 'uploader_id': 'gameloft',
863 'upload_date': '20140828',
864 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
865 },
866 'params': {
867 'skip_download': True,
868 }
869 },
870 # YouTube <object> embed
871 {
872 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
873 'md5': '516718101ec834f74318df76259fb3cc',
874 'info_dict': {
875 'id': 'msN87y-iEx0',
876 'ext': 'webm',
877 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
878 'upload_date': '20080526',
879 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
880 'uploader': 'Christopher Sykes',
881 'uploader_id': 'ChristopherJSykes',
882 },
883 'add_ie': ['Youtube'],
884 },
885 # Camtasia studio
886 {
887 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
888 'playlist': [{
889 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
890 'info_dict': {
891 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
892 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
893 'ext': 'flv',
894 'duration': 2235.90,
895 }
896 }, {
897 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
898 'info_dict': {
899 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
900 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
901 'ext': 'flv',
902 'duration': 2235.93,
903 }
904 }],
905 'info_dict': {
906 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
907 }
908 },
909 # Flowplayer
910 {
911 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
912 'md5': '9d65602bf31c6e20014319c7d07fba27',
913 'info_dict': {
914 'id': '5123ea6d5e5a7',
915 'ext': 'mp4',
916 'age_limit': 18,
917 'uploader': 'www.handjobhub.com',
918 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
919 }
920 },
921 # Multiple brightcove videos
922 # https://github.com/ytdl-org/youtube-dl/issues/2283
923 {
924 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
925 'info_dict': {
926 'id': 'always-never',
927 'title': 'Always / Never - The New Yorker',
928 },
929 'playlist_count': 3,
930 'params': {
931 'extract_flat': False,
932 'skip_download': True,
933 }
934 },
935 # MLB embed
936 {
937 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
938 'md5': '96f09a37e44da40dd083e12d9a683327',
939 'info_dict': {
940 'id': '33322633',
941 'ext': 'mp4',
942 'title': 'Ump changes call to ball',
943 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
944 'duration': 48,
945 'timestamp': 1401537900,
946 'upload_date': '20140531',
947 'thumbnail': r're:^https?://.*\.jpg$',
948 },
949 },
950 # Wistia embed
951 {
952 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
953 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
954 'info_dict': {
955 'id': '6e2wtrbdaf',
956 'ext': 'mov',
957 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
958 'description': 'a Paywall Videos video from Remilon',
959 'duration': 644.072,
960 'uploader': 'study.com',
961 'timestamp': 1459678540,
962 'upload_date': '20160403',
963 'filesize': 24687186,
964 },
965 },
966 {
967 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
968 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
969 'info_dict': {
970 'id': 'uxjb0lwrcz',
971 'ext': 'mp4',
972 'title': 'Conversation about Hexagonal Rails Part 1',
973 'description': 'a Martin Fowler video from ThoughtWorks',
974 'duration': 1715.0,
975 'uploader': 'thoughtworks.wistia.com',
976 'timestamp': 1401832161,
977 'upload_date': '20140603',
978 },
979 },
980 # Wistia standard embed (async)
981 {
982 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
983 'info_dict': {
984 'id': '807fafadvk',
985 'ext': 'mp4',
986 'title': 'Drip Brennan Dunn Workshop',
987 'description': 'a JV Webinars video from getdrip-1',
988 'duration': 4986.95,
989 'timestamp': 1463607249,
990 'upload_date': '20160518',
991 },
992 'params': {
993 'skip_download': True,
994 }
995 },
996 # Soundcloud embed
997 {
998 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
999 'info_dict': {
1000 'id': '174391317',
1001 'ext': 'mp3',
1002 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1003 'uploader': 'Sophos Security',
1004 'title': 'Chet Chat 171 - Oct 29, 2014',
1005 'upload_date': '20141029',
1006 }
1007 },
1008 # Soundcloud multiple embeds
1009 {
1010 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1011 'info_dict': {
1012 'id': '52809',
1013 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1014 },
1015 'playlist_mincount': 7,
1016 },
1017 # TuneIn station embed
1018 {
1019 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1020 'info_dict': {
1021 'id': '204146',
1022 'ext': 'mp3',
1023 'title': 'CNRV',
1024 'location': 'Paris, France',
1025 'is_live': True,
1026 },
1027 'params': {
1028 # Live stream
1029 'skip_download': True,
1030 },
1031 },
1032 # Livestream embed
1033 {
1034 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1035 'info_dict': {
1036 'id': '67864563',
1037 'ext': 'flv',
1038 'upload_date': '20141112',
1039 'title': 'Rosetta #CometLanding webcast HL 10',
1040 }
1041 },
1042 # Another Livestream embed, without 'new.' in URL
1043 {
1044 'url': 'https://www.freespeech.org/',
1045 'info_dict': {
1046 'id': '123537347',
1047 'ext': 'mp4',
1048 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1049 },
1050 'params': {
1051 # Live stream
1052 'skip_download': True,
1053 },
1054 },
1055 # LazyYT
1056 {
1057 'url': 'https://skiplagged.com/',
1058 'info_dict': {
1059 'id': 'skiplagged',
1060 'title': 'Skiplagged: The smart way to find cheap flights',
1061 },
1062 'playlist_mincount': 1,
1063 'add_ie': ['Youtube'],
1064 },
1065 # Cinchcast embed
1066 {
1067 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1068 'info_dict': {
1069 'id': '7141703',
1070 'ext': 'mp3',
1071 'upload_date': '20141126',
1072 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1073 }
1074 },
1075 # Cinerama player
1076 {
1077 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1078 'info_dict': {
1079 'id': '730m_DandD_1901_512k',
1080 'ext': 'mp4',
1081 'uploader': 'www.abc.net.au',
1082 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1083 }
1084 },
1085 # embedded viddler video
1086 {
1087 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1088 'info_dict': {
1089 'id': '4d03aad9',
1090 'ext': 'mp4',
1091 'uploader': 'deadspin',
1092 'title': 'WALL-TO-GORTAT',
1093 'timestamp': 1422285291,
1094 'upload_date': '20150126',
1095 },
1096 'add_ie': ['Viddler'],
1097 },
1098 # Libsyn embed
1099 {
1100 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1101 'info_dict': {
1102 'id': '3377616',
1103 'ext': 'mp3',
1104 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1105 'description': 'md5:601cb790edd05908957dae8aaa866465',
1106 'upload_date': '20150220',
1107 },
1108 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1109 },
1110 # jwplayer YouTube
1111 {
1112 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1113 'info_dict': {
1114 'id': 'Mrj4DVp2zeA',
1115 'ext': 'mp4',
1116 'upload_date': '20150212',
1117 'uploader': 'The National Archives UK',
1118 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1119 'uploader_id': 'NationalArchives08',
1120 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1121 },
1122 },
1123 # jwplayer rtmp
1124 {
1125 'url': 'http://www.suffolk.edu/sjc/live.php',
1126 'info_dict': {
1127 'id': 'live',
1128 'ext': 'flv',
1129 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1130 'uploader': 'www.suffolk.edu',
1131 },
1132 'params': {
1133 'skip_download': True,
1134 },
1135 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1136 },
1137 # Complex jwplayer
1138 {
1139 'url': 'http://www.indiedb.com/games/king-machine/videos',
1140 'info_dict': {
1141 'id': 'videos',
1142 'ext': 'mp4',
1143 'title': 'king machine trailer 1',
1144 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1145 'thumbnail': r're:^https?://.*\.jpg$',
1146 },
1147 },
1148 {
1149 # JWPlayer config passed as variable
1150 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1151 'info_dict': {
1152 'id': '3326530_hq',
1153 'ext': 'mp4',
1154 'title': 'ARIELE | Tube Cup',
1155 'uploader': 'www.txxx.com',
1156 'age_limit': 18,
1157 },
1158 'params': {
1159 'skip_download': True,
1160 }
1161 },
1162 {
1163 # JWPlatform iframe
1164 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1165 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1166 'info_dict': {
1167 'id': 'O0c5JcKT',
1168 'ext': 'mp4',
1169 'upload_date': '20171122',
1170 'timestamp': 1511366290,
1171 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1172 },
1173 'add_ie': [JWPlatformIE.ie_key()],
1174 },
1175 {
1176 # Video.js embed, multiple formats
1177 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1178 'info_dict': {
1179 'id': 'yygqldloqIk',
1180 'ext': 'mp4',
1181 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1182 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1183 'upload_date': '20130314',
1184 'uploader': 'PROстое3D',
1185 'uploader_id': 'PROstoe3D',
1186 },
1187 'params': {
1188 'skip_download': True,
1189 },
1190 },
1191 {
1192 # Video.js embed, single format
1193 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1194 'info_dict': {
1195 'id': 'watch',
1196 'ext': 'mp4',
1197 'title': 'Step 1 - Good Foundation',
1198 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1199 },
1200 'params': {
1201 'skip_download': True,
1202 },
1203 },
1204 # rtl.nl embed
1205 {
1206 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1207 'playlist_mincount': 5,
1208 'info_dict': {
1209 'id': 'aanslagen-kopenhagen',
1210 'title': 'Aanslagen Kopenhagen',
1211 }
1212 },
1213 # Zapiks embed
1214 {
1215 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1216 'info_dict': {
1217 'id': '118046',
1218 'ext': 'mp4',
1219 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1220 }
1221 },
1222 # Kaltura embed (different embed code)
1223 {
1224 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1225 'info_dict': {
1226 'id': '1_a52wc67y',
1227 'ext': 'flv',
1228 'upload_date': '20150127',
1229 'uploader_id': 'PremierMedia',
1230 'timestamp': int,
1231 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1232 },
1233 },
1234 # Kaltura embed with single quotes
1235 {
1236 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1237 'info_dict': {
1238 'id': '0_izeg5utt',
1239 'ext': 'mp4',
1240 'title': '35871',
1241 'timestamp': 1355743100,
1242 'upload_date': '20121217',
1243 'uploader_id': 'cplapp@learn360.com',
1244 },
1245 'add_ie': ['Kaltura'],
1246 },
1247 {
1248 # Kaltura embedded via quoted entry_id
1249 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1250 'info_dict': {
1251 'id': '0_utuok90b',
1252 'ext': 'mp4',
1253 'title': '06_matthew_brender_raj_dutt',
1254 'timestamp': 1466638791,
1255 'upload_date': '20160622',
1256 },
1257 'add_ie': ['Kaltura'],
1258 'expected_warnings': [
1259 'Could not send HEAD request'
1260 ],
1261 'params': {
1262 'skip_download': True,
1263 }
1264 },
1265 {
1266 # Kaltura embedded, some fileExt broken (#11480)
1267 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1268 'info_dict': {
1269 'id': '1_sgtvehim',
1270 'ext': 'mp4',
1271 'title': 'Our "Standard Models" of particle physics and cosmology',
1272 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1273 'timestamp': 1321158993,
1274 'upload_date': '20111113',
1275 'uploader_id': 'kps1',
1276 },
1277 'add_ie': ['Kaltura'],
1278 },
1279 {
1280 # Kaltura iframe embed
1281 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1282 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1283 'info_dict': {
1284 'id': '0_f2cfbpwy',
1285 'ext': 'mp4',
1286 'title': 'I. M. Pei: A Centennial Celebration',
1287 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1288 'upload_date': '20170403',
1289 'uploader_id': 'batchUser',
1290 'timestamp': 1491232186,
1291 },
1292 'add_ie': ['Kaltura'],
1293 },
1294 {
1295 # Kaltura iframe embed, more sophisticated
1296 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1297 'info_dict': {
1298 'id': '1_9gzouybz',
1299 'ext': 'mp4',
1300 'title': 'lecture-05sep2017',
1301 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1302 'upload_date': '20170913',
1303 'uploader_id': 'eps2',
1304 'timestamp': 1505340777,
1305 },
1306 'params': {
1307 'skip_download': True,
1308 },
1309 'add_ie': ['Kaltura'],
1310 },
1311 {
1312 # meta twitter:player
1313 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1314 'info_dict': {
1315 'id': '0_01b42zps',
1316 'ext': 'mp4',
1317 'title': 'Main Twerk (Video)',
1318 'upload_date': '20171208',
1319 'uploader_id': 'sebastian.salinas@thechive.com',
1320 'timestamp': 1512713057,
1321 },
1322 'params': {
1323 'skip_download': True,
1324 },
1325 'add_ie': ['Kaltura'],
1326 },
1327 # referrer protected EaglePlatform embed
1328 {
1329 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1330 'info_dict': {
1331 'id': '582306',
1332 'ext': 'mp4',
1333 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1334 'thumbnail': r're:^https?://.*\.jpg$',
1335 'duration': 3382,
1336 'view_count': int,
1337 },
1338 'params': {
1339 'skip_download': True,
1340 },
1341 },
1342 # ClipYou (EaglePlatform) embed (custom URL)
1343 {
1344 'url': 'http://muz-tv.ru/play/7129/',
1345 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1346 'info_dict': {
1347 'id': '12820',
1348 'ext': 'mp4',
1349 'title': "'O Sole Mio",
1350 'thumbnail': r're:^https?://.*\.jpg$',
1351 'duration': 216,
1352 'view_count': int,
1353 },
1354 'params': {
1355 'skip_download': True,
1356 },
1357 'skip': 'This video is unavailable.',
1358 },
1359 # Pladform embed
1360 {
1361 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1362 'info_dict': {
1363 'id': '100183293',
1364 'ext': 'mp4',
1365 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1366 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1367 'thumbnail': r're:^https?://.*\.jpg$',
1368 'duration': 694,
1369 'age_limit': 0,
1370 },
1371 'skip': 'HTTP Error 404: Not Found',
1372 },
1373 # Playwire embed
1374 {
1375 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1376 'info_dict': {
1377 'id': '3519514',
1378 'ext': 'mp4',
1379 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1380 'thumbnail': r're:^https?://.*\.png$',
1381 'duration': 45.115,
1382 },
1383 },
1384 # 5min embed
1385 {
1386 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1387 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1388 'info_dict': {
1389 'id': '518726732',
1390 'ext': 'mp4',
1391 'title': 'Facebook Creates "On This Day" | Crunch Report',
1392 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1393 'timestamp': 1427237531,
1394 'uploader': 'Crunch Report',
1395 'upload_date': '20150324',
1396 },
1397 'params': {
1398 # m3u8 download
1399 'skip_download': True,
1400 },
1401 },
1402 # Crooks and Liars embed
1403 {
1404 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1405 'info_dict': {
1406 'id': '8RUoRhRi',
1407 'ext': 'mp4',
1408 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1409 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1410 'timestamp': 1428207000,
1411 'upload_date': '20150405',
1412 'uploader': 'Heather',
1413 },
1414 },
1415 # Crooks and Liars external embed
1416 {
1417 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1418 'info_dict': {
1419 'id': 'MTE3MjUtMzQ2MzA',
1420 'ext': 'mp4',
1421 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1422 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1423 'timestamp': 1265032391,
1424 'upload_date': '20100201',
1425 'uploader': 'Heather',
1426 },
1427 },
1428 # NBC Sports vplayer embed
1429 {
1430 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1431 'info_dict': {
1432 'id': 'ln7x1qSThw4k',
1433 'ext': 'flv',
1434 'title': "PFT Live: New leader in the 'new-look' defense",
1435 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1436 'uploader': 'NBCU-SPORTS',
1437 'upload_date': '20140107',
1438 'timestamp': 1389118457,
1439 },
1440 'skip': 'Invalid Page URL',
1441 },
1442 # NBC News embed
1443 {
1444 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1445 'md5': '1aa589c675898ae6d37a17913cf68d66',
1446 'info_dict': {
1447 'id': 'x_dtl_oa_LettermanliftPR_160608',
1448 'ext': 'mp4',
1449 'title': 'David Letterman: A Preview',
1450 '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.',
1451 'upload_date': '20160609',
1452 'timestamp': 1465431544,
1453 'uploader': 'NBCU-NEWS',
1454 },
1455 },
1456 # UDN embed
1457 {
1458 'url': 'https://video.udn.com/news/300346',
1459 'md5': 'fd2060e988c326991037b9aff9df21a6',
1460 'info_dict': {
1461 'id': '300346',
1462 'ext': 'mp4',
1463 'title': '中一中男師變性 全校師生力挺',
1464 'thumbnail': r're:^https?://.*\.jpg$',
1465 },
1466 'params': {
1467 # m3u8 download
1468 'skip_download': True,
1469 },
1470 'expected_warnings': ['Failed to parse JSON Expecting value'],
1471 },
1472 # Brightcove URL in single quotes
1473 {
1474 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1475 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1476 'info_dict': {
1477 'id': '4255764656001',
1478 'ext': 'mp4',
1479 'title': 'SN Presents: Russell Martin, World Citizen',
1480 '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.',
1481 'uploader': 'Rogers Sportsnet',
1482 'uploader_id': '1704050871',
1483 'upload_date': '20150525',
1484 'timestamp': 1432570283,
1485 },
1486 },
1487 # Kinja embed
1488 {
1489 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1490 'info_dict': {
1491 'id': '106351',
1492 'ext': 'mp4',
1493 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1494 'description': 'Migrated from OnionStudios',
1495 'thumbnail': r're:^https?://.*\.jpe?g$',
1496 'uploader': 'clickhole',
1497 'upload_date': '20150527',
1498 'timestamp': 1432744860,
1499 }
1500 },
1501 # SnagFilms embed
1502 {
1503 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1504 'info_dict': {
1505 'id': '74849a00-85a9-11e1-9660-123139220831',
1506 'ext': 'mp4',
1507 'title': '#whilewewatch',
1508 }
1509 },
1510 # AdobeTVVideo embed
1511 {
1512 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1513 'md5': '43662b577c018ad707a63766462b1e87',
1514 'info_dict': {
1515 'id': '2456',
1516 'ext': 'mp4',
1517 'title': 'New experience with Acrobat DC',
1518 'description': 'New experience with Acrobat DC',
1519 'duration': 248.667,
1520 },
1521 },
1522 # BrightcoveInPageEmbed embed
1523 {
1524 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1525 'info_dict': {
1526 'id': '4238694884001',
1527 'ext': 'flv',
1528 'title': 'Tabletop: Dread, Last Thoughts',
1529 'description': 'Tabletop: Dread, Last Thoughts',
1530 'duration': 51690,
1531 },
1532 },
1533 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1534 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1535 {
1536 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1537 'info_dict': {
1538 'id': '4785848093001',
1539 'ext': 'mp4',
1540 'title': 'The Cardinal Pell Interview',
1541 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1542 'uploader': 'GlobeCast Australia - GlobeStream',
1543 'uploader_id': '2733773828001',
1544 'upload_date': '20160304',
1545 'timestamp': 1457083087,
1546 },
1547 'params': {
1548 # m3u8 downloads
1549 'skip_download': True,
1550 },
1551 },
1552 {
1553 # Brightcove embed with whitespace around attribute names
1554 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1555 'info_dict': {
1556 'id': '3167554373001',
1557 'ext': 'mp4',
1558 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1559 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1560 'uploader_id': '1079349493',
1561 'upload_date': '20140207',
1562 'timestamp': 1391810548,
1563 },
1564 'params': {
1565 'skip_download': True,
1566 },
1567 },
1568 # Another form of arte.tv embed
1569 {
1570 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1571 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1572 'info_dict': {
1573 'id': '030273-562_PLUS7-F',
1574 'ext': 'mp4',
1575 'title': 'ARTE Reportage - Nulle part, en France',
1576 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1577 'upload_date': '20160409',
1578 },
1579 },
1580 # LiveLeak embed
1581 {
1582 'url': 'http://www.wykop.pl/link/3088787/',
1583 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1584 'info_dict': {
1585 'id': '874_1459135191',
1586 'ext': 'mp4',
1587 'title': 'Man shows poor quality of new apartment building',
1588 'description': 'The wall is like a sand pile.',
1589 'uploader': 'Lake8737',
1590 },
1591 'add_ie': [LiveLeakIE.ie_key()],
1592 },
1593 # Another LiveLeak embed pattern (#13336)
1594 {
1595 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1596 'info_dict': {
1597 'id': '2eb_1496309988',
1598 'ext': 'mp4',
1599 'title': 'Thief robs place where everyone was armed',
1600 'description': 'md5:694d73ee79e535953cf2488562288eee',
1601 'uploader': 'brazilwtf',
1602 },
1603 'add_ie': [LiveLeakIE.ie_key()],
1604 },
1605 # Duplicated embedded video URLs
1606 {
1607 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1608 'info_dict': {
1609 'id': '149298443_480_16c25b74_2',
1610 'ext': 'mp4',
1611 'title': 'vs. Blue Orange Spring Game',
1612 'uploader': 'www.hudl.com',
1613 },
1614 },
1615 # twitter:player:stream embed
1616 {
1617 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1618 'info_dict': {
1619 'id': 'master',
1620 'ext': 'mp4',
1621 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1622 'uploader': 'www.rtl.be',
1623 },
1624 'params': {
1625 # m3u8 downloads
1626 'skip_download': True,
1627 },
1628 },
1629 # twitter:player embed
1630 {
1631 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1632 'md5': 'a3e0df96369831de324f0778e126653c',
1633 'info_dict': {
1634 'id': '4909620399001',
1635 'ext': 'mp4',
1636 'title': 'What Do Black Holes Sound Like?',
1637 'description': 'what do black holes sound like',
1638 'upload_date': '20160524',
1639 'uploader_id': '29913724001',
1640 'timestamp': 1464107587,
1641 'uploader': 'TheAtlantic',
1642 },
1643 'add_ie': ['BrightcoveLegacy'],
1644 },
1645 # Facebook <iframe> embed
1646 {
1647 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1648 'md5': 'fbcde74f534176ecb015849146dd3aee',
1649 'info_dict': {
1650 'id': '599637780109885',
1651 'ext': 'mp4',
1652 'title': 'Facebook video #599637780109885',
1653 },
1654 },
1655 # Facebook <iframe> embed, plugin video
1656 {
1657 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1658 'info_dict': {
1659 'id': '1754168231264132',
1660 'ext': 'mp4',
1661 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1662 'uploader': 'Tariq Ramadan (official)',
1663 'timestamp': 1496758379,
1664 'upload_date': '20170606',
1665 },
1666 'params': {
1667 'skip_download': True,
1668 },
1669 },
1670 # Facebook API embed
1671 {
1672 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1673 'md5': 'a47372ee61b39a7b90287094d447d94e',
1674 'info_dict': {
1675 'id': '10153467542406923',
1676 'ext': 'mp4',
1677 'title': 'Facebook video #10153467542406923',
1678 },
1679 },
1680 # Wordpress "YouTube Video Importer" plugin
1681 {
1682 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1683 'md5': 'd16797741b560b485194eddda8121b48',
1684 'info_dict': {
1685 'id': 'HNTXWDXV9Is',
1686 'ext': 'mp4',
1687 'title': 'Blue Devils Drumline Stanford lot 2016',
1688 'upload_date': '20160627',
1689 'uploader_id': 'GENOCIDE8GENERAL10',
1690 'uploader': 'cylus cyrus',
1691 },
1692 },
1693 {
1694 # video stored on custom kaltura server
1695 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1696 'md5': '537617d06e64dfed891fa1593c4b30cc',
1697 'info_dict': {
1698 'id': '0_1iotm5bh',
1699 'ext': 'mp4',
1700 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1701 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1702 'uploader_id': 'videos.expansion@el-mundo.net',
1703 'upload_date': '20150429',
1704 'timestamp': 1430303472,
1705 },
1706 'add_ie': ['Kaltura'],
1707 },
1708 {
1709 # Non-standard Vimeo embed
1710 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1711 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1712 'info_dict': {
1713 'id': '148867247',
1714 'ext': 'mp4',
1715 'title': 'Understanding the web - Teaser',
1716 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1717 'upload_date': '20151214',
1718 'uploader': 'OpenClassrooms',
1719 'uploader_id': 'openclassrooms',
1720 },
1721 'add_ie': ['Vimeo'],
1722 },
1723 {
1724 # generic vimeo embed that requires original URL passed as Referer
1725 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1726 'only_matching': True,
1727 },
1728 {
1729 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1730 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1731 'info_dict': {
1732 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1733 'ext': 'mp4',
1734 'title': 'Big Buck Bunny',
1735 'description': 'Royalty free test video',
1736 'timestamp': 1432816365,
1737 'upload_date': '20150528',
1738 'is_live': False,
1739 },
1740 'params': {
1741 'skip_download': True,
1742 },
1743 'add_ie': [ArkenaIE.ie_key()],
1744 },
1745 {
1746 'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
1747 'info_dict': {
1748 'id': '1c7141f46c',
1749 'ext': 'mp4',
1750 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1751 },
1752 'params': {
1753 'skip_download': True,
1754 },
1755 'add_ie': [Vbox7IE.ie_key()],
1756 },
1757 {
1758 # DBTV embeds
1759 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1760 'info_dict': {
1761 'id': '43254897',
1762 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1763 },
1764 'playlist_mincount': 3,
1765 },
1766 {
1767 # Videa embeds
1768 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1769 'info_dict': {
1770 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1771 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1772 },
1773 'playlist_mincount': 2,
1774 },
1775 {
1776 # 20 minuten embed
1777 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1778 'info_dict': {
1779 'id': '523629',
1780 'ext': 'mp4',
1781 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1782 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1783 },
1784 'params': {
1785 'skip_download': True,
1786 },
1787 'add_ie': [TwentyMinutenIE.ie_key()],
1788 },
1789 {
1790 # VideoPress embed
1791 'url': 'https://en.support.wordpress.com/videopress/',
1792 'info_dict': {
1793 'id': 'OcobLTqC',
1794 'ext': 'm4v',
1795 'title': 'IMG_5786',
1796 'timestamp': 1435711927,
1797 'upload_date': '20150701',
1798 },
1799 'params': {
1800 'skip_download': True,
1801 },
1802 'add_ie': [VideoPressIE.ie_key()],
1803 },
1804 {
1805 # Rutube embed
1806 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1807 'info_dict': {
1808 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1809 'ext': 'flv',
1810 'title': 'Магаззино: Казань 2',
1811 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1812 'uploader': 'Магаззино',
1813 'upload_date': '20170228',
1814 'uploader_id': '996642',
1815 },
1816 'params': {
1817 'skip_download': True,
1818 },
1819 'add_ie': [RutubeIE.ie_key()],
1820 },
1821 {
1822 # ThePlatform embedded with whitespaces in URLs
1823 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1824 'only_matching': True,
1825 },
1826 {
1827 # Senate ISVP iframe https
1828 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1829 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1830 'info_dict': {
1831 'id': 'govtaff020316',
1832 'ext': 'mp4',
1833 'title': 'Integrated Senate Video Player',
1834 },
1835 'add_ie': [SenateISVPIE.ie_key()],
1836 },
1837 {
1838 # Limelight embeds (1 channel embed + 4 media embeds)
1839 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1840 'info_dict': {
1841 'id': 'FacilitatorTraining2017',
1842 'title': 'Facilitator Training 2017',
1843 },
1844 'playlist_mincount': 5,
1845 },
1846 {
1847 # Limelight embed (LimelightPlayerUtil.embed)
1848 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1849 'info_dict': {
1850 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1851 'ext': 'mp4',
1852 'title': '07448641',
1853 'timestamp': 1499890639,
1854 'upload_date': '20170712',
1855 },
1856 'params': {
1857 'skip_download': True,
1858 },
1859 'add_ie': ['LimelightMedia'],
1860 },
1861 {
1862 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1863 'info_dict': {
1864 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1865 'title': 'Standoff with Walnut Creek murder suspect ends',
1866 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1867 },
1868 'playlist_mincount': 4,
1869 },
1870 {
1871 # WashingtonPost embed
1872 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1873 'info_dict': {
1874 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1875 'ext': 'mp4',
1876 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1877 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1878 'timestamp': 1455216756,
1879 'uploader': 'The Washington Post',
1880 'upload_date': '20160211',
1881 },
1882 'add_ie': [WashingtonPostIE.ie_key()],
1883 },
1884 {
1885 # Mediaset embed
1886 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1887 'info_dict': {
1888 'id': '720642',
1889 'ext': 'mp4',
1890 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1891 },
1892 'params': {
1893 'skip_download': True,
1894 },
1895 'add_ie': [MediasetIE.ie_key()],
1896 },
1897 {
1898 # JOJ.sk embeds
1899 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1900 'info_dict': {
1901 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1902 'title': 'Slovenskom sa prehnala vlna silných búrok',
1903 },
1904 'playlist_mincount': 5,
1905 'add_ie': [JojIE.ie_key()],
1906 },
1907 {
1908 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1909 'url': 'https://tvrain.ru/amp/418921/',
1910 'md5': 'cc00413936695987e8de148b67d14f1d',
1911 'info_dict': {
1912 'id': '418921',
1913 'ext': 'mp4',
1914 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1915 },
1916 },
1917 {
1918 # vzaar embed
1919 'url': 'http://help.vzaar.com/article/165-embedding-video',
1920 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1921 'info_dict': {
1922 'id': '8707641',
1923 'ext': 'mp4',
1924 'title': 'Building A Business Online: Principal Chairs Q & A',
1925 },
1926 },
1927 {
1928 # multiple HTML5 videos on one page
1929 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1930 'info_dict': {
1931 'id': 'keyscenarios',
1932 'title': 'Rescue Kit 14 Free Edition - Getting started',
1933 },
1934 'playlist_count': 4,
1935 },
1936 {
1937 # vshare embed
1938 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1939 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1940 'info_dict': {
1941 'id': '0f64ce6',
1942 'title': 'vl14062007715967',
1943 'ext': 'mp4',
1944 }
1945 },
1946 {
1947 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1948 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1949 'info_dict': {
1950 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1951 'ext': 'mp4',
1952 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1953 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1954 'timestamp': 1474354800,
1955 'upload_date': '20160920',
1956 }
1957 },
1958 {
1959 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1960 'info_dict': {
1961 'id': '1731611',
1962 'ext': 'mp4',
1963 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1964 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1965 'timestamp': 1516100691,
1966 'upload_date': '20180116',
1967 },
1968 'params': {
1969 'skip_download': True,
1970 },
1971 'add_ie': [SpringboardPlatformIE.ie_key()],
1972 },
1973 {
1974 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1975 'info_dict': {
1976 'id': 'uPDB5I9wfp8',
1977 'ext': 'webm',
1978 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1979 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1980 'upload_date': '20160219',
1981 'uploader': 'Pocoyo - Português (BR)',
1982 'uploader_id': 'PocoyoBrazil',
1983 },
1984 'add_ie': [YoutubeIE.ie_key()],
1985 'params': {
1986 'skip_download': True,
1987 },
1988 },
1989 {
1990 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1991 'info_dict': {
1992 'id': 'vMDE4NzI1Mjgt690b',
1993 'ext': 'mp4',
1994 'title': 'Котята',
1995 },
1996 'add_ie': [YapFilesIE.ie_key()],
1997 'params': {
1998 'skip_download': True,
1999 },
2000 },
2001 {
2002 # CloudflareStream embed
2003 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2004 'info_dict': {
2005 'id': '31c9291ab41fac05471db4e73aa11717',
2006 'ext': 'mp4',
2007 'title': '31c9291ab41fac05471db4e73aa11717',
2008 },
2009 'add_ie': [CloudflareStreamIE.ie_key()],
2010 'params': {
2011 'skip_download': True,
2012 },
2013 },
2014 {
2015 # PeerTube embed
2016 'url': 'https://joinpeertube.org/fr/home/',
2017 'info_dict': {
2018 'id': 'home',
2019 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2020 },
2021 'playlist_count': 2,
2022 },
2023 {
2024 # Indavideo embed
2025 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2026 'info_dict': {
2027 'id': '1693903',
2028 'ext': 'mp4',
2029 'title': 'Így kell otthon hamburgert sütni',
2030 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2031 'timestamp': 1426330212,
2032 'upload_date': '20150314',
2033 'uploader': 'StreetKitchen',
2034 'uploader_id': '546363',
2035 },
2036 'add_ie': [IndavideoEmbedIE.ie_key()],
2037 'params': {
2038 'skip_download': True,
2039 },
2040 },
2041 {
2042 # APA embed via JWPlatform embed
2043 'url': 'http://www.vol.at/blue-man-group/5593454',
2044 'info_dict': {
2045 'id': 'jjv85FdZ',
2046 'ext': 'mp4',
2047 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2048 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2049 'thumbnail': r're:^https?://.*\.jpg$',
2050 'duration': 254,
2051 'timestamp': 1519211149,
2052 'upload_date': '20180221',
2053 },
2054 'params': {
2055 'skip_download': True,
2056 },
2057 },
2058 {
2059 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2060 'md5': 'b68d276de422ab07ee1d49388103f457',
2061 'info_dict': {
2062 'id': '83645793',
2063 'title': 'Lock up and get excited',
2064 'ext': 'mp4'
2065 },
2066 'skip': 'TODO: fix nested playlists processing in tests',
2067 },
2068 {
2069 # Viqeo embeds
2070 'url': 'https://viqeo.tv/',
2071 'info_dict': {
2072 'id': 'viqeo',
2073 'title': 'All-new video platform',
2074 },
2075 'playlist_count': 6,
2076 },
2077 {
2078 # Squarespace video embed, 2019-08-28
2079 'url': 'http://ootboxford.com',
2080 'info_dict': {
2081 'id': 'Tc7b_JGdZfw',
2082 'title': 'Out of the Blue, at Childish Things 10',
2083 'ext': 'mp4',
2084 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
2085 'uploader_id': 'helendouglashouse',
2086 'uploader': 'Helen & Douglas House',
2087 'upload_date': '20140328',
2088 },
2089 'params': {
2090 'skip_download': True,
2091 },
2092 },
2093 {
2094 # Zype embed
2095 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2096 'info_dict': {
2097 'id': '5b400b834b32992a310622b9',
2098 'ext': 'mp4',
2099 'title': 'Smoky Barbecue Favorites',
2100 'thumbnail': r're:^https?://.*\.jpe?g',
2101 },
2102 'add_ie': [ZypeIE.ie_key()],
2103 'params': {
2104 'skip_download': True,
2105 },
2106 },
2107 {
2108 # videojs embed
2109 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2110 'info_dict': {
2111 'id': 'shell',
2112 'ext': 'mp4',
2113 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2114 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2115 'thumbnail': r're:^https?://.*\.jpg$',
2116 },
2117 'params': {
2118 'skip_download': True,
2119 },
2120 'expected_warnings': ['Failed to download MPD manifest'],
2121 },
2122 {
2123 # DailyMotion embed with DM.player
2124 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
2125 'info_dict': {
2126 'id': 'k6aKkGHd9FJs4mtJN39',
2127 'ext': 'mp4',
2128 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
2129 'description': 'This video is private.',
2130 'uploader_id': 'x1jf30l',
2131 'uploader': 'beIN SPORTS USA',
2132 'upload_date': '20190528',
2133 'timestamp': 1559062971,
2134 },
2135 'params': {
2136 'skip_download': True,
2137 },
2138 },
2139 # {
2140 # # TODO: find another test
2141 # # http://schema.org/VideoObject
2142 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2143 # 'md5': '888dcf08b7ea671381f00fab74692755',
2144 # 'info_dict': {
2145 # 'id': 'nyvTSJMKId',
2146 # 'ext': 'mp4',
2147 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2148 # 'description': '#love for cats.',
2149 # 'timestamp': 1461244995,
2150 # 'upload_date': '20160421',
2151 # },
2152 # 'params': {
2153 # 'force_generic_extractor': True,
2154 # },
2155 # }
2156 ]
2157
2158 def report_following_redirect(self, new_url):
2159 """Report information extraction."""
2160 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2161
2162 def _extract_rss(self, url, video_id, doc):
2163 playlist_title = doc.find('./channel/title').text
2164 playlist_desc_el = doc.find('./channel/description')
2165 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2166
2167 entries = []
2168 for it in doc.findall('./channel/item'):
2169 next_url = None
2170 enclosure_nodes = it.findall('./enclosure')
2171 for e in enclosure_nodes:
2172 next_url = e.attrib.get('url')
2173 if next_url:
2174 break
2175
2176 if not next_url:
2177 next_url = xpath_text(it, 'link', fatal=False)
2178
2179 if not next_url:
2180 continue
2181
2182 entries.append({
2183 '_type': 'url_transparent',
2184 'url': next_url,
2185 'title': it.find('title').text,
2186 })
2187
2188 return {
2189 '_type': 'playlist',
2190 'id': url,
2191 'title': playlist_title,
2192 'description': playlist_desc,
2193 'entries': entries,
2194 }
2195
2196 def _extract_camtasia(self, url, video_id, webpage):
2197 """ Returns None if no camtasia video can be found. """
2198
2199 camtasia_cfg = self._search_regex(
2200 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2201 webpage, 'camtasia configuration file', default=None)
2202 if camtasia_cfg is None:
2203 return None
2204
2205 title = self._html_search_meta('DC.title', webpage, fatal=True)
2206
2207 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2208 camtasia_cfg = self._download_xml(
2209 camtasia_url, video_id,
2210 note='Downloading camtasia configuration',
2211 errnote='Failed to download camtasia configuration')
2212 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2213
2214 entries = []
2215 for n in fileset_node.getchildren():
2216 url_n = n.find('./uri')
2217 if url_n is None:
2218 continue
2219
2220 entries.append({
2221 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2222 'title': '%s - %s' % (title, n.tag),
2223 'url': compat_urlparse.urljoin(url, url_n.text),
2224 'duration': float_or_none(n.find('./duration').text),
2225 })
2226
2227 return {
2228 '_type': 'playlist',
2229 'entries': entries,
2230 'title': title,
2231 }
2232
2233 def _real_extract(self, url):
2234 if url.startswith('//'):
2235 return self.url_result(self.http_scheme() + url)
2236
2237 parsed_url = compat_urlparse.urlparse(url)
2238 if not parsed_url.scheme:
2239 default_search = self._downloader.params.get('default_search')
2240 if default_search is None:
2241 default_search = 'fixup_error'
2242
2243 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2244 if re.match(r'^[^\s/]+\.[^\s/]+/', url):
2245 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2246 return self.url_result('http://' + url)
2247 elif default_search != 'fixup_error':
2248 if default_search == 'auto_warning':
2249 if re.match(r'^(?:url|URL)$', url):
2250 raise ExtractorError(
2251 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2252 expected=True)
2253 else:
2254 self._downloader.report_warning(
2255 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2256 return self.url_result('ytsearch:' + url)
2257
2258 if default_search in ('error', 'fixup_error'):
2259 raise ExtractorError(
2260 '%r is not a valid URL. '
2261 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2262 % (url, url), expected=True)
2263 else:
2264 if ':' not in default_search:
2265 default_search += ':'
2266 return self.url_result(default_search + url)
2267
2268 url, smuggled_data = unsmuggle_url(url)
2269 force_videoid = None
2270 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2271 if smuggled_data and 'force_videoid' in smuggled_data:
2272 force_videoid = smuggled_data['force_videoid']
2273 video_id = force_videoid
2274 else:
2275 video_id = self._generic_id(url)
2276
2277 self.to_screen('%s: Requesting header' % video_id)
2278
2279 head_req = HEADRequest(url)
2280 head_response = self._request_webpage(
2281 head_req, video_id,
2282 note=False, errnote='Could not send HEAD request to %s' % url,
2283 fatal=False)
2284
2285 if head_response is not False:
2286 # Check for redirect
2287 new_url = compat_str(head_response.geturl())
2288 if url != new_url:
2289 self.report_following_redirect(new_url)
2290 if force_videoid:
2291 new_url = smuggle_url(
2292 new_url, {'force_videoid': force_videoid})
2293 return self.url_result(new_url)
2294
2295 full_response = None
2296 if head_response is False:
2297 request = sanitized_Request(url)
2298 request.add_header('Accept-Encoding', '*')
2299 full_response = self._request_webpage(request, video_id)
2300 head_response = full_response
2301
2302 info_dict = {
2303 'id': video_id,
2304 'title': self._generic_title(url),
2305 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2306 }
2307
2308 # Check for direct link to a video
2309 content_type = head_response.headers.get('Content-Type', '').lower()
2310 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2311 if m:
2312 format_id = compat_str(m.group('format_id'))
2313 if format_id.endswith('mpegurl'):
2314 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2315 elif format_id == 'f4m':
2316 formats = self._extract_f4m_formats(url, video_id)
2317 else:
2318 formats = [{
2319 'format_id': format_id,
2320 'url': url,
2321 'vcodec': 'none' if m.group('type') == 'audio' else None
2322 }]
2323 info_dict['direct'] = True
2324 self._sort_formats(formats)
2325 info_dict['formats'] = formats
2326 return info_dict
2327
2328 if not self._downloader.params.get('test', False) and not is_intentional:
2329 force = self._downloader.params.get('force_generic_extractor', False)
2330 self._downloader.report_warning(
2331 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2332
2333 if not full_response:
2334 request = sanitized_Request(url)
2335 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2336 # making it impossible to download only chunk of the file (yet we need only 512kB to
2337 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2338 # that will always result in downloading the whole file that is not desirable.
2339 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2340 # to accept raw bytes and being able to download only a chunk.
2341 # It may probably better to solve this by checking Content-Type for application/octet-stream
2342 # after HEAD request finishes, but not sure if we can rely on this.
2343 request.add_header('Accept-Encoding', '*')
2344 full_response = self._request_webpage(request, video_id)
2345
2346 first_bytes = full_response.read(512)
2347
2348 # Is it an M3U playlist?
2349 if first_bytes.startswith(b'#EXTM3U'):
2350 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2351 self._sort_formats(info_dict['formats'])
2352 return info_dict
2353
2354 # Maybe it's a direct link to a video?
2355 # Be careful not to download the whole thing!
2356 if not is_html(first_bytes):
2357 self._downloader.report_warning(
2358 'URL could be a direct video link, returning it as such.')
2359 info_dict.update({
2360 'direct': True,
2361 'url': url,
2362 })
2363 return info_dict
2364
2365 webpage = self._webpage_read_content(
2366 full_response, url, video_id, prefix=first_bytes)
2367
2368 self.report_extraction(video_id)
2369
2370 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2371 try:
2372 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2373 if doc.tag == 'rss':
2374 return self._extract_rss(url, video_id, doc)
2375 elif doc.tag == 'SmoothStreamingMedia':
2376 info_dict['formats'] = self._parse_ism_formats(doc, url)
2377 self._sort_formats(info_dict['formats'])
2378 return info_dict
2379 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2380 smil = self._parse_smil(doc, url, video_id)
2381 self._sort_formats(smil['formats'])
2382 return smil
2383 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2384 return self.playlist_result(
2385 self._parse_xspf(
2386 doc, video_id, xspf_url=url,
2387 xspf_base_url=compat_str(full_response.geturl())),
2388 video_id)
2389 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2390 info_dict['formats'] = self._parse_mpd_formats(
2391 doc,
2392 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2393 mpd_url=url)
2394 self._sort_formats(info_dict['formats'])
2395 return info_dict
2396 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2397 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2398 self._sort_formats(info_dict['formats'])
2399 return info_dict
2400 except compat_xml_parse_error:
2401 pass
2402
2403 # Is it a Camtasia project?
2404 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2405 if camtasia_res is not None:
2406 return camtasia_res
2407
2408 # Sometimes embedded video player is hidden behind percent encoding
2409 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2410 # Unescaping the whole page allows to handle those cases in a generic way
2411 webpage = compat_urllib_parse_unquote(webpage)
2412
2413 # Unescape squarespace embeds to be detected by generic extractor,
2414 # see https://github.com/ytdl-org/youtube-dl/issues/21294
2415 webpage = re.sub(
2416 r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
2417 lambda x: unescapeHTML(x.group(0)), webpage)
2418
2419 # it's tempting to parse this further, but you would
2420 # have to take into account all the variations like
2421 # Video Title - Site Name
2422 # Site Name | Video Title
2423 # Video Title - Tagline | Site Name
2424 # and so on and so forth; it's just not practical
2425 video_title = self._og_search_title(
2426 webpage, default=None) or self._html_search_regex(
2427 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2428 default='video')
2429
2430 # Try to detect age limit automatically
2431 age_limit = self._rta_search(webpage)
2432 # And then there are the jokers who advertise that they use RTA,
2433 # but actually don't.
2434 AGE_LIMIT_MARKERS = [
2435 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2436 ]
2437 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2438 age_limit = 18
2439
2440 # video uploader is domain name
2441 video_uploader = self._search_regex(
2442 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2443
2444 video_description = self._og_search_description(webpage, default=None)
2445 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2446
2447 info_dict.update({
2448 'title': video_title,
2449 'description': video_description,
2450 'thumbnail': video_thumbnail,
2451 'age_limit': age_limit,
2452 })
2453
2454 # Look for Brightcove Legacy Studio embeds
2455 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2456 if bc_urls:
2457 entries = [{
2458 '_type': 'url',
2459 'url': smuggle_url(bc_url, {'Referer': url}),
2460 'ie_key': 'BrightcoveLegacy'
2461 } for bc_url in bc_urls]
2462
2463 return {
2464 '_type': 'playlist',
2465 'title': video_title,
2466 'id': video_id,
2467 'entries': entries,
2468 }
2469
2470 # Look for Brightcove New Studio embeds
2471 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2472 if bc_urls:
2473 return self.playlist_from_matches(
2474 bc_urls, video_id, video_title,
2475 getter=lambda x: smuggle_url(x, {'referrer': url}),
2476 ie='BrightcoveNew')
2477
2478 # Look for Nexx embeds
2479 nexx_urls = NexxIE._extract_urls(webpage)
2480 if nexx_urls:
2481 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2482
2483 # Look for Nexx iFrame embeds
2484 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2485 if nexx_embed_urls:
2486 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2487
2488 # Look for ThePlatform embeds
2489 tp_urls = ThePlatformIE._extract_urls(webpage)
2490 if tp_urls:
2491 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2492
2493 # Look for embedded rtl.nl player
2494 matches = re.findall(
2495 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2496 webpage)
2497 if matches:
2498 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2499
2500 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2501 if vimeo_urls:
2502 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2503
2504 vid_me_embed_url = self._search_regex(
2505 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2506 webpage, 'vid.me embed', default=None)
2507 if vid_me_embed_url is not None:
2508 return self.url_result(vid_me_embed_url, 'Vidme')
2509
2510 # Look for YouTube embeds
2511 youtube_urls = YoutubeIE._extract_urls(webpage)
2512 if youtube_urls:
2513 return self.playlist_from_matches(
2514 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2515
2516 matches = DailymotionIE._extract_urls(webpage)
2517 if matches:
2518 return self.playlist_from_matches(matches, video_id, video_title)
2519
2520 # Look for embedded Dailymotion playlist player (#3822)
2521 m = re.search(
2522 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2523 if m:
2524 playlists = re.findall(
2525 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2526 if playlists:
2527 return self.playlist_from_matches(
2528 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2529
2530 # Look for DailyMail embeds
2531 dailymail_urls = DailyMailIE._extract_urls(webpage)
2532 if dailymail_urls:
2533 return self.playlist_from_matches(
2534 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2535
2536 # Look for embedded Wistia player
2537 wistia_url = WistiaIE._extract_url(webpage)
2538 if wistia_url:
2539 return {
2540 '_type': 'url_transparent',
2541 'url': self._proto_relative_url(wistia_url),
2542 'ie_key': WistiaIE.ie_key(),
2543 'uploader': video_uploader,
2544 }
2545
2546 # Look for SVT player
2547 svt_url = SVTIE._extract_url(webpage)
2548 if svt_url:
2549 return self.url_result(svt_url, 'SVT')
2550
2551 # Look for Bandcamp pages with custom domain
2552 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2553 if mobj is not None:
2554 burl = unescapeHTML(mobj.group(1))
2555 # Don't set the extractor because it can be a track url or an album
2556 return self.url_result(burl)
2557
2558 # Look for embedded Vevo player
2559 mobj = re.search(
2560 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2561 if mobj is not None:
2562 return self.url_result(mobj.group('url'))
2563
2564 # Look for embedded Viddler player
2565 mobj = re.search(
2566 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2567 webpage)
2568 if mobj is not None:
2569 return self.url_result(mobj.group('url'))
2570
2571 # Look for NYTimes player
2572 mobj = re.search(
2573 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2574 webpage)
2575 if mobj is not None:
2576 return self.url_result(mobj.group('url'))
2577
2578 # Look for Libsyn player
2579 mobj = re.search(
2580 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2581 if mobj is not None:
2582 return self.url_result(mobj.group('url'))
2583
2584 # Look for Ooyala videos
2585 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
2586 or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2587 or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
2588 or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
2589 or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2590 if mobj is not None:
2591 embed_token = self._search_regex(
2592 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2593 webpage, 'ooyala embed token', default=None)
2594 return OoyalaIE._build_url_result(smuggle_url(
2595 mobj.group('ec'), {
2596 'domain': url,
2597 'embed_token': embed_token,
2598 }))
2599
2600 # Look for multiple Ooyala embeds on SBN network websites
2601 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2602 if mobj is not None:
2603 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2604 if embeds:
2605 return self.playlist_from_matches(
2606 embeds, video_id, video_title,
2607 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2608
2609 # Look for Aparat videos
2610 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2611 if mobj is not None:
2612 return self.url_result(mobj.group(1), 'Aparat')
2613
2614 # Look for MPORA videos
2615 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2616 if mobj is not None:
2617 return self.url_result(mobj.group(1), 'Mpora')
2618
2619 # Look for embedded Facebook player
2620 facebook_urls = FacebookIE._extract_urls(webpage)
2621 if facebook_urls:
2622 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2623
2624 # Look for embedded VK player
2625 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2626 if mobj is not None:
2627 return self.url_result(mobj.group('url'), 'VK')
2628
2629 # Look for embedded Odnoklassniki player
2630 odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
2631 if odnoklassniki_url:
2632 return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
2633
2634 # Look for embedded ivi player
2635 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2636 if mobj is not None:
2637 return self.url_result(mobj.group('url'), 'Ivi')
2638
2639 # Look for embedded Huffington Post player
2640 mobj = re.search(
2641 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2642 if mobj is not None:
2643 return self.url_result(mobj.group('url'), 'HuffPost')
2644
2645 # Look for embed.ly
2646 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2647 if mobj is not None:
2648 return self.url_result(mobj.group('url'))
2649 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2650 if mobj is not None:
2651 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2652
2653 # Look for funnyordie embed
2654 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2655 if matches:
2656 return self.playlist_from_matches(
2657 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2658
2659 # Look for BBC iPlayer embed
2660 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2661 if matches:
2662 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2663
2664 # Look for embedded RUTV player
2665 rutv_url = RUTVIE._extract_url(webpage)
2666 if rutv_url:
2667 return self.url_result(rutv_url, 'RUTV')
2668
2669 # Look for embedded TVC player
2670 tvc_url = TVCIE._extract_url(webpage)
2671 if tvc_url:
2672 return self.url_result(tvc_url, 'TVC')
2673
2674 # Look for embedded SportBox player
2675 sportbox_urls = SportBoxIE._extract_urls(webpage)
2676 if sportbox_urls:
2677 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2678
2679 # Look for embedded XHamster player
2680 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2681 if xhamster_urls:
2682 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2683
2684 # Look for embedded TNAFlixNetwork player
2685 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2686 if tnaflix_urls:
2687 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2688
2689 # Look for embedded PornHub player
2690 pornhub_urls = PornHubIE._extract_urls(webpage)
2691 if pornhub_urls:
2692 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2693
2694 # Look for embedded DrTuber player
2695 drtuber_urls = DrTuberIE._extract_urls(webpage)
2696 if drtuber_urls:
2697 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2698
2699 # Look for embedded RedTube player
2700 redtube_urls = RedTubeIE._extract_urls(webpage)
2701 if redtube_urls:
2702 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2703
2704 # Look for embedded Tube8 player
2705 tube8_urls = Tube8IE._extract_urls(webpage)
2706 if tube8_urls:
2707 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2708
2709 # Look for embedded Tvigle player
2710 mobj = re.search(
2711 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2712 if mobj is not None:
2713 return self.url_result(mobj.group('url'), 'Tvigle')
2714
2715 # Look for embedded TED player
2716 mobj = re.search(
2717 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2718 if mobj is not None:
2719 return self.url_result(mobj.group('url'), 'TED')
2720
2721 # Look for embedded Ustream videos
2722 ustream_url = UstreamIE._extract_url(webpage)
2723 if ustream_url:
2724 return self.url_result(ustream_url, UstreamIE.ie_key())
2725
2726 # Look for embedded arte.tv player
2727 mobj = re.search(
2728 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2729 webpage)
2730 if mobj is not None:
2731 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2732
2733 # Look for embedded francetv player
2734 mobj = re.search(
2735 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2736 webpage)
2737 if mobj is not None:
2738 return self.url_result(mobj.group('url'))
2739
2740 # Look for embedded smotri.com player
2741 smotri_url = SmotriIE._extract_url(webpage)
2742 if smotri_url:
2743 return self.url_result(smotri_url, 'Smotri')
2744
2745 # Look for embedded Myvi.ru player
2746 myvi_url = MyviIE._extract_url(webpage)
2747 if myvi_url:
2748 return self.url_result(myvi_url)
2749
2750 # Look for embedded soundcloud player
2751 soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
2752 if soundcloud_urls:
2753 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
2754
2755 # Look for tunein player
2756 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2757 if tunein_urls:
2758 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2759
2760 # Look for embedded mtvservices player
2761 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2762 if mtvservices_url:
2763 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2764
2765 # Look for embedded yahoo player
2766 mobj = re.search(
2767 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2768 webpage)
2769 if mobj is not None:
2770 return self.url_result(mobj.group('url'), 'Yahoo')
2771
2772 # Look for embedded sbs.com.au player
2773 mobj = re.search(
2774 r'''(?x)
2775 (?:
2776 <meta\s+property="og:video"\s+content=|
2777 <iframe[^>]+?src=
2778 )
2779 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2780 webpage)
2781 if mobj is not None:
2782 return self.url_result(mobj.group('url'), 'SBS')
2783
2784 # Look for embedded Cinchcast player
2785 mobj = re.search(
2786 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2787 webpage)
2788 if mobj is not None:
2789 return self.url_result(mobj.group('url'), 'Cinchcast')
2790
2791 mobj = re.search(
2792 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2793 webpage)
2794 if not mobj:
2795 mobj = re.search(
2796 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2797 webpage)
2798 if mobj is not None:
2799 return self.url_result(mobj.group('url'), 'MLB')
2800
2801 mobj = re.search(
2802 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2803 webpage)
2804 if mobj is not None:
2805 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2806
2807 mobj = re.search(
2808 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2809 webpage)
2810 if mobj is not None:
2811 return self.url_result(mobj.group('url'), 'Livestream')
2812
2813 # Look for Zapiks embed
2814 mobj = re.search(
2815 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2816 if mobj is not None:
2817 return self.url_result(mobj.group('url'), 'Zapiks')
2818
2819 # Look for Kaltura embeds
2820 kaltura_url = KalturaIE._extract_url(webpage)
2821 if kaltura_url:
2822 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2823
2824 # Look for EaglePlatform embeds
2825 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2826 if eagleplatform_url:
2827 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2828
2829 # Look for ClipYou (uses EaglePlatform) embeds
2830 mobj = re.search(
2831 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2832 if mobj is not None:
2833 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2834
2835 # Look for Pladform embeds
2836 pladform_url = PladformIE._extract_url(webpage)
2837 if pladform_url:
2838 return self.url_result(pladform_url)
2839
2840 # Look for Videomore embeds
2841 videomore_url = VideomoreIE._extract_url(webpage)
2842 if videomore_url:
2843 return self.url_result(videomore_url)
2844
2845 # Look for Webcaster embeds
2846 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2847 if webcaster_url:
2848 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2849
2850 # Look for Playwire embeds
2851 mobj = re.search(
2852 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2853 if mobj is not None:
2854 return self.url_result(mobj.group('url'))
2855
2856 # Look for 5min embeds
2857 mobj = re.search(
2858 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2859 if mobj is not None:
2860 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2861
2862 # Look for Crooks and Liars embeds
2863 mobj = re.search(
2864 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2865 if mobj is not None:
2866 return self.url_result(mobj.group('url'))
2867
2868 # Look for NBC Sports VPlayer embeds
2869 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2870 if nbc_sports_url:
2871 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2872
2873 # Look for NBC News embeds
2874 nbc_news_embed_url = re.search(
2875 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2876 if nbc_news_embed_url:
2877 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2878
2879 # Look for Google Drive embeds
2880 google_drive_url = GoogleDriveIE._extract_url(webpage)
2881 if google_drive_url:
2882 return self.url_result(google_drive_url, 'GoogleDrive')
2883
2884 # Look for UDN embeds
2885 mobj = re.search(
2886 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2887 if mobj is not None:
2888 return self.url_result(
2889 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2890
2891 # Look for Senate ISVP iframe
2892 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2893 if senate_isvp_url:
2894 return self.url_result(senate_isvp_url, 'SenateISVP')
2895
2896 # Look for Kinja embeds
2897 kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
2898 if kinja_embed_urls:
2899 return self.playlist_from_matches(
2900 kinja_embed_urls, video_id, video_title)
2901
2902 # Look for OnionStudios embeds
2903 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2904 if onionstudios_url:
2905 return self.url_result(onionstudios_url)
2906
2907 # Look for ViewLift embeds
2908 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2909 if viewlift_url:
2910 return self.url_result(viewlift_url)
2911
2912 # Look for JWPlatform embeds
2913 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2914 if jwplatform_urls:
2915 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2916
2917 # Look for Digiteka embeds
2918 digiteka_url = DigitekaIE._extract_url(webpage)
2919 if digiteka_url:
2920 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2921
2922 # Look for Arkena embeds
2923 arkena_url = ArkenaIE._extract_url(webpage)
2924 if arkena_url:
2925 return self.url_result(arkena_url, ArkenaIE.ie_key())
2926
2927 # Look for Piksel embeds
2928 piksel_url = PikselIE._extract_url(webpage)
2929 if piksel_url:
2930 return self.url_result(piksel_url, PikselIE.ie_key())
2931
2932 # Look for Limelight embeds
2933 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2934 if limelight_urls:
2935 return self.playlist_result(
2936 limelight_urls, video_id, video_title, video_description)
2937
2938 # Look for Anvato embeds
2939 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2940 if anvato_urls:
2941 return self.playlist_result(
2942 anvato_urls, video_id, video_title, video_description)
2943
2944 # Look for AdobeTVVideo embeds
2945 mobj = re.search(
2946 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2947 webpage)
2948 if mobj is not None:
2949 return self.url_result(
2950 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2951 'AdobeTVVideo')
2952
2953 # Look for Vine embeds
2954 mobj = re.search(
2955 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2956 webpage)
2957 if mobj is not None:
2958 return self.url_result(
2959 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2960
2961 # Look for VODPlatform embeds
2962 mobj = re.search(
2963 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2964 webpage)
2965 if mobj is not None:
2966 return self.url_result(
2967 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2968
2969 # Look for Mangomolo embeds
2970 mobj = re.search(
2971 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
2972 (?:
2973 admin\.mangomolo\.com/analytics/index\.php/customers/embed|
2974 player\.mangomolo\.com/v1
2975 )/
2976 (?:
2977 video\?.*?\bid=(?P<video_id>\d+)|
2978 (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2979 ).+?)\1''', webpage)
2980 if mobj is not None:
2981 info = {
2982 '_type': 'url_transparent',
2983 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2984 'title': video_title,
2985 'description': video_description,
2986 'thumbnail': video_thumbnail,
2987 'uploader': video_uploader,
2988 }
2989 video_id = mobj.group('video_id')
2990 if video_id:
2991 info.update({
2992 'ie_key': 'MangomoloVideo',
2993 'id': video_id,
2994 })
2995 else:
2996 info.update({
2997 'ie_key': 'MangomoloLive',
2998 'id': mobj.group('channel_id'),
2999 })
3000 return info
3001
3002 # Look for Instagram embeds
3003 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
3004 if instagram_embed_url is not None:
3005 return self.url_result(
3006 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
3007
3008 # Look for LiveLeak embeds
3009 liveleak_urls = LiveLeakIE._extract_urls(webpage)
3010 if liveleak_urls:
3011 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
3012
3013 # Look for 3Q SDN embeds
3014 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
3015 if threeqsdn_url:
3016 return {
3017 '_type': 'url_transparent',
3018 'ie_key': ThreeQSDNIE.ie_key(),
3019 'url': self._proto_relative_url(threeqsdn_url),
3020 'title': video_title,
3021 'description': video_description,
3022 'thumbnail': video_thumbnail,
3023 'uploader': video_uploader,
3024 }
3025
3026 # Look for VBOX7 embeds
3027 vbox7_url = Vbox7IE._extract_url(webpage)
3028 if vbox7_url:
3029 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3030
3031 # Look for DBTV embeds
3032 dbtv_urls = DBTVIE._extract_urls(webpage)
3033 if dbtv_urls:
3034 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3035
3036 # Look for Videa embeds
3037 videa_urls = VideaIE._extract_urls(webpage)
3038 if videa_urls:
3039 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3040
3041 # Look for 20 minuten embeds
3042 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3043 if twentymin_urls:
3044 return self.playlist_from_matches(
3045 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3046
3047 # Look for VideoPress embeds
3048 videopress_urls = VideoPressIE._extract_urls(webpage)
3049 if videopress_urls:
3050 return self.playlist_from_matches(
3051 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3052
3053 # Look for Rutube embeds
3054 rutube_urls = RutubeIE._extract_urls(webpage)
3055 if rutube_urls:
3056 return self.playlist_from_matches(
3057 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3058
3059 # Look for WashingtonPost embeds
3060 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3061 if wapo_urls:
3062 return self.playlist_from_matches(
3063 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3064
3065 # Look for Mediaset embeds
3066 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3067 if mediaset_urls:
3068 return self.playlist_from_matches(
3069 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3070
3071 # Look for JOJ.sk embeds
3072 joj_urls = JojIE._extract_urls(webpage)
3073 if joj_urls:
3074 return self.playlist_from_matches(
3075 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3076
3077 # Look for megaphone.fm embeds
3078 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3079 if mpfn_urls:
3080 return self.playlist_from_matches(
3081 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3082
3083 # Look for vzaar embeds
3084 vzaar_urls = VzaarIE._extract_urls(webpage)
3085 if vzaar_urls:
3086 return self.playlist_from_matches(
3087 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3088
3089 channel9_urls = Channel9IE._extract_urls(webpage)
3090 if channel9_urls:
3091 return self.playlist_from_matches(
3092 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3093
3094 vshare_urls = VShareIE._extract_urls(webpage)
3095 if vshare_urls:
3096 return self.playlist_from_matches(
3097 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3098
3099 # Look for Mediasite embeds
3100 mediasite_urls = MediasiteIE._extract_urls(webpage)
3101 if mediasite_urls:
3102 entries = [
3103 self.url_result(smuggle_url(
3104 compat_urlparse.urljoin(url, mediasite_url),
3105 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3106 for mediasite_url in mediasite_urls]
3107 return self.playlist_result(entries, video_id, video_title)
3108
3109 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3110 if springboardplatform_urls:
3111 return self.playlist_from_matches(
3112 springboardplatform_urls, video_id, video_title,
3113 ie=SpringboardPlatformIE.ie_key())
3114
3115 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3116 if yapfiles_urls:
3117 return self.playlist_from_matches(
3118 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3119
3120 vice_urls = ViceIE._extract_urls(webpage)
3121 if vice_urls:
3122 return self.playlist_from_matches(
3123 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3124
3125 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3126 if xfileshare_urls:
3127 return self.playlist_from_matches(
3128 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3129
3130 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3131 if cloudflarestream_urls:
3132 return self.playlist_from_matches(
3133 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3134
3135 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3136 if peertube_urls:
3137 return self.playlist_from_matches(
3138 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3139
3140 teachable_url = TeachableIE._extract_url(webpage, url)
3141 if teachable_url:
3142 return self.url_result(teachable_url)
3143
3144 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3145 if indavideo_urls:
3146 return self.playlist_from_matches(
3147 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3148
3149 apa_urls = APAIE._extract_urls(webpage)
3150 if apa_urls:
3151 return self.playlist_from_matches(
3152 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3153
3154 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3155 if foxnews_urls:
3156 return self.playlist_from_matches(
3157 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3158
3159 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3160 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3161 webpage)]
3162 if sharevideos_urls:
3163 return self.playlist_from_matches(
3164 sharevideos_urls, video_id, video_title)
3165
3166 viqeo_urls = ViqeoIE._extract_urls(webpage)
3167 if viqeo_urls:
3168 return self.playlist_from_matches(
3169 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3170
3171 expressen_urls = ExpressenIE._extract_urls(webpage)
3172 if expressen_urls:
3173 return self.playlist_from_matches(
3174 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3175
3176 zype_urls = ZypeIE._extract_urls(webpage)
3177 if zype_urls:
3178 return self.playlist_from_matches(
3179 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3180
3181 # Look for HTML5 media
3182 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3183 if entries:
3184 if len(entries) == 1:
3185 entries[0].update({
3186 'id': video_id,
3187 'title': video_title,
3188 })
3189 else:
3190 for num, entry in enumerate(entries, start=1):
3191 entry.update({
3192 'id': '%s-%s' % (video_id, num),
3193 'title': '%s (%d)' % (video_title, num),
3194 })
3195 for entry in entries:
3196 self._sort_formats(entry['formats'])
3197 return self.playlist_result(entries, video_id, video_title)
3198
3199 jwplayer_data = self._find_jwplayer_data(
3200 webpage, video_id, transform_source=js_to_json)
3201 if jwplayer_data:
3202 try:
3203 info = self._parse_jwplayer_data(
3204 jwplayer_data, video_id, require_title=False, base_url=url)
3205 return merge_dicts(info, info_dict)
3206 except ExtractorError:
3207 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3208 pass
3209
3210 # Video.js embed
3211 mobj = re.search(
3212 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3213 webpage)
3214 if mobj is not None:
3215 sources = self._parse_json(
3216 mobj.group(1), video_id, transform_source=js_to_json,
3217 fatal=False) or []
3218 if not isinstance(sources, list):
3219 sources = [sources]
3220 formats = []
3221 for source in sources:
3222 src = source.get('src')
3223 if not src or not isinstance(src, compat_str):
3224 continue
3225 src = compat_urlparse.urljoin(url, src)
3226 src_type = source.get('type')
3227 if isinstance(src_type, compat_str):
3228 src_type = src_type.lower()
3229 ext = determine_ext(src).lower()
3230 if src_type == 'video/youtube':
3231 return self.url_result(src, YoutubeIE.ie_key())
3232 if src_type == 'application/dash+xml' or ext == 'mpd':
3233 formats.extend(self._extract_mpd_formats(
3234 src, video_id, mpd_id='dash', fatal=False))
3235 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3236 formats.extend(self._extract_m3u8_formats(
3237 src, video_id, 'mp4', entry_protocol='m3u8_native',
3238 m3u8_id='hls', fatal=False))
3239 else:
3240 formats.append({
3241 'url': src,
3242 'ext': (mimetype2ext(src_type)
3243 or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3244 })
3245 if formats:
3246 self._sort_formats(formats)
3247 info_dict['formats'] = formats
3248 return info_dict
3249
3250 # Looking for http://schema.org/VideoObject
3251 json_ld = self._search_json_ld(
3252 webpage, video_id, default={}, expected_type='VideoObject')
3253 if json_ld.get('url'):
3254 return merge_dicts(json_ld, info_dict)
3255
3256 def check_video(vurl):
3257 if YoutubeIE.suitable(vurl):
3258 return True
3259 if RtmpIE.suitable(vurl):
3260 return True
3261 vpath = compat_urlparse.urlparse(vurl).path
3262 vext = determine_ext(vpath)
3263 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3264
3265 def filter_video(urls):
3266 return list(filter(check_video, urls))
3267
3268 # Start with something easy: JW Player in SWFObject
3269 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3270 if not found:
3271 # Look for gorilla-vid style embedding
3272 found = filter_video(re.findall(r'''(?sx)
3273 (?:
3274 jw_plugins|
3275 JWPlayerOptions|
3276 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3277 )
3278 .*?
3279 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3280 if not found:
3281 # Broaden the search a little bit
3282 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3283 if not found:
3284 # Broaden the findall a little bit: JWPlayer JS loader
3285 found = filter_video(re.findall(
3286 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3287 if not found:
3288 # Flow player
3289 found = filter_video(re.findall(r'''(?xs)
3290 flowplayer\("[^"]+",\s*
3291 \{[^}]+?\}\s*,
3292 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3293 ["']?url["']?\s*:\s*["']([^"']+)["']
3294 ''', webpage))
3295 if not found:
3296 # Cinerama player
3297 found = re.findall(
3298 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3299 if not found:
3300 # Try to find twitter cards info
3301 # twitter:player:stream should be checked before twitter:player since
3302 # it is expected to contain a raw stream (see
3303 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3304 found = filter_video(re.findall(
3305 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3306 if not found:
3307 # We look for Open Graph info:
3308 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3309 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3310 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3311 if m_video_type is not None:
3312 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3313 if not found:
3314 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3315 found = re.search(
3316 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3317 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3318 webpage)
3319 if not found:
3320 # Look also in Refresh HTTP header
3321 refresh_header = head_response.headers.get('Refresh')
3322 if refresh_header:
3323 # In python 2 response HTTP headers are bytestrings
3324 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3325 refresh_header = refresh_header.decode('iso-8859-1')
3326 found = re.search(REDIRECT_REGEX, refresh_header)
3327 if found:
3328 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3329 if new_url != url:
3330 self.report_following_redirect(new_url)
3331 return {
3332 '_type': 'url',
3333 'url': new_url,
3334 }
3335 else:
3336 found = None
3337
3338 if not found:
3339 # twitter:player is a https URL to iframe player that may or may not
3340 # be supported by youtube-dl thus this is checked the very last (see
3341 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3342 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3343 if embed_url and embed_url != url:
3344 return self.url_result(embed_url)
3345
3346 if not found:
3347 raise UnsupportedError(url)
3348
3349 entries = []
3350 for video_url in orderedSet(found):
3351 video_url = unescapeHTML(video_url)
3352 video_url = video_url.replace('\\/', '/')
3353 video_url = compat_urlparse.urljoin(url, video_url)
3354 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3355
3356 # Sometimes, jwplayer extraction will result in a YouTube URL
3357 if YoutubeIE.suitable(video_url):
3358 entries.append(self.url_result(video_url, 'Youtube'))
3359 continue
3360
3361 # here's a fun little line of code for you:
3362 video_id = os.path.splitext(video_id)[0]
3363
3364 entry_info_dict = {
3365 'id': video_id,
3366 'uploader': video_uploader,
3367 'title': video_title,
3368 'age_limit': age_limit,
3369 }
3370
3371 if RtmpIE.suitable(video_url):
3372 entry_info_dict.update({
3373 '_type': 'url_transparent',
3374 'ie_key': RtmpIE.ie_key(),
3375 'url': video_url,
3376 })
3377 entries.append(entry_info_dict)
3378 continue
3379
3380 ext = determine_ext(video_url)
3381 if ext == 'smil':
3382 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3383 elif ext == 'xspf':
3384 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3385 elif ext == 'm3u8':
3386 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3387 elif ext == 'mpd':
3388 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3389 elif ext == 'f4m':
3390 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3391 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3392 # Just matching .ism/manifest is not enough to be reliably sure
3393 # whether it's actually an ISM manifest or some other streaming
3394 # manifest since there are various streaming URL formats
3395 # possible (see [1]) as well as some other shenanigans like
3396 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3397 # so on.
3398 # Thus the most reasonable way to solve this is to delegate
3399 # to generic extractor in order to look into the contents of
3400 # the manifest itself.
3401 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3402 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3403 entry_info_dict = self.url_result(
3404 smuggle_url(video_url, {'to_generic': True}),
3405 GenericIE.ie_key())
3406 else:
3407 entry_info_dict['url'] = video_url
3408
3409 if entry_info_dict.get('formats'):
3410 self._sort_formats(entry_info_dict['formats'])
3411
3412 entries.append(entry_info_dict)
3413
3414 if len(entries) == 1:
3415 return entries[0]
3416 else:
3417 for num, e in enumerate(entries, start=1):
3418 # 'url' results don't have a title
3419 if e.get('title') is not None:
3420 e['title'] = '%s (%d)' % (e['title'], num)
3421 return {
3422 '_type': 'playlist',
3423 'entries': entries,
3424 }