]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
495fa497544ba4e2a61aa905a69e717b472c003d
[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 .vessel import VesselIE
81 from .kaltura import KalturaIE
82 from .eagleplatform import EaglePlatformIE
83 from .facebook import FacebookIE
84 from .soundcloud import SoundcloudIE
85 from .tunein import TuneInBaseIE
86 from .vbox7 import Vbox7IE
87 from .dbtv import DBTVIE
88 from .piksel import PikselIE
89 from .videa import VideaIE
90 from .twentymin import TwentyMinutenIE
91 from .ustream import UstreamIE
92 from .openload import (
93 OpenloadIE,
94 VerystreamIE,
95 )
96 from .videopress import VideoPressIE
97 from .rutube import RutubeIE
98 from .limelight import LimelightBaseIE
99 from .anvato import AnvatoIE
100 from .washingtonpost import WashingtonPostIE
101 from .wistia import WistiaIE
102 from .mediaset import MediasetIE
103 from .joj import JojIE
104 from .megaphone import MegaphoneIE
105 from .vzaar import VzaarIE
106 from .channel9 import Channel9IE
107 from .vshare import VShareIE
108 from .mediasite import MediasiteIE
109 from .springboardplatform import SpringboardPlatformIE
110 from .yapfiles import YapFilesIE
111 from .vice import ViceIE
112 from .xfileshare import XFileShareIE
113 from .cloudflarestream import CloudflareStreamIE
114 from .peertube import PeerTubeIE
115 from .teachable import TeachableIE
116 from .indavideo import IndavideoEmbedIE
117 from .apa import APAIE
118 from .foxnews import FoxNewsIE
119 from .viqeo import ViqeoIE
120 from .expressen import ExpressenIE
121 from .zype import ZypeIE
122
123
124 class GenericIE(InfoExtractor):
125 IE_DESC = 'Generic downloader that works on some sites'
126 _VALID_URL = r'.*'
127 IE_NAME = 'generic'
128 _TESTS = [
129 # Direct link to a video
130 {
131 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
132 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
133 'info_dict': {
134 'id': 'trailer',
135 'ext': 'mp4',
136 'title': 'trailer',
137 'upload_date': '20100513',
138 }
139 },
140 # Direct link to media delivered compressed (until Accept-Encoding is *)
141 {
142 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
143 'md5': '128c42e68b13950268b648275386fc74',
144 'info_dict': {
145 'id': 'FictionJunction-Parallel_Hearts',
146 'ext': 'flac',
147 'title': 'FictionJunction-Parallel_Hearts',
148 'upload_date': '20140522',
149 },
150 'expected_warnings': [
151 'URL could be a direct video link, returning it as such.'
152 ],
153 'skip': 'URL invalid',
154 },
155 # Direct download with broken HEAD
156 {
157 'url': 'http://ai-radio.org:8000/radio.opus',
158 'info_dict': {
159 'id': 'radio',
160 'ext': 'opus',
161 'title': 'radio',
162 },
163 'params': {
164 'skip_download': True, # infinite live stream
165 },
166 'expected_warnings': [
167 r'501.*Not Implemented',
168 r'400.*Bad Request',
169 ],
170 },
171 # Direct link with incorrect MIME type
172 {
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'md5': '4ccbebe5f36706d85221f204d7eb5913',
175 'info_dict': {
176 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
177 'id': '5_Lennart_Poettering_-_Systemd',
178 'ext': 'webm',
179 'title': '5_Lennart_Poettering_-_Systemd',
180 'upload_date': '20141120',
181 },
182 'expected_warnings': [
183 'URL could be a direct video link, returning it as such.'
184 ]
185 },
186 # RSS feed
187 {
188 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
189 'info_dict': {
190 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
191 'title': 'Zero Punctuation',
192 'description': 're:.*groundbreaking video review series.*'
193 },
194 'playlist_mincount': 11,
195 },
196 # RSS feed with enclosure
197 {
198 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
199 'info_dict': {
200 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
201 'ext': 'm4v',
202 'upload_date': '20150228',
203 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
204 }
205 },
206 # RSS feed with enclosures and unsupported link URLs
207 {
208 'url': 'http://www.hellointernet.fm/podcast?format=rss',
209 'info_dict': {
210 'id': 'http://www.hellointernet.fm/podcast?format=rss',
211 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
212 'title': 'Hello Internet',
213 },
214 'playlist_mincount': 100,
215 },
216 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
217 {
218 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
219 'info_dict': {
220 'id': 'smil',
221 'ext': 'mp4',
222 'title': 'Automatics, robotics and biocybernetics',
223 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
224 'upload_date': '20130627',
225 'formats': 'mincount:16',
226 'subtitles': 'mincount:1',
227 },
228 'params': {
229 'force_generic_extractor': True,
230 'skip_download': True,
231 },
232 },
233 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
234 {
235 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
236 'info_dict': {
237 'id': 'hds',
238 'ext': 'flv',
239 'title': 'hds',
240 'formats': 'mincount:1',
241 },
242 'params': {
243 'skip_download': True,
244 },
245 },
246 # SMIL from https://www.restudy.dk/video/play/id/1637
247 {
248 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
249 'info_dict': {
250 'id': 'video_1637',
251 'ext': 'flv',
252 'title': 'video_1637',
253 'formats': 'mincount:3',
254 },
255 'params': {
256 'skip_download': True,
257 },
258 },
259 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
260 {
261 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
262 'info_dict': {
263 'id': 'smil-service',
264 'ext': 'flv',
265 'title': 'smil-service',
266 'formats': 'mincount:1',
267 },
268 'params': {
269 'skip_download': True,
270 },
271 },
272 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
273 {
274 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
275 'info_dict': {
276 'id': '4719370',
277 'ext': 'mp4',
278 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
279 'formats': 'mincount:3',
280 },
281 'params': {
282 'skip_download': True,
283 },
284 },
285 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
286 {
287 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
288 'info_dict': {
289 'id': 'mZlp2ctYIUEB',
290 'ext': 'mp4',
291 'title': 'Tikibad ontruimd wegens brand',
292 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
293 'thumbnail': r're:^https?://.*\.jpg$',
294 'duration': 33,
295 },
296 'params': {
297 'skip_download': True,
298 },
299 },
300 # MPD from http://dash-mse-test.appspot.com/media.html
301 {
302 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
303 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
304 'info_dict': {
305 'id': 'car-20120827-manifest',
306 'ext': 'mp4',
307 'title': 'car-20120827-manifest',
308 'formats': 'mincount:9',
309 'upload_date': '20130904',
310 },
311 'params': {
312 'format': 'bestvideo',
313 },
314 },
315 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
316 {
317 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
318 'info_dict': {
319 'id': 'content',
320 'ext': 'mp4',
321 'title': 'content',
322 'formats': 'mincount:8',
323 },
324 'params': {
325 # m3u8 downloads
326 'skip_download': True,
327 },
328 'skip': 'video gone',
329 },
330 # m3u8 served with Content-Type: text/plain
331 {
332 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
333 'info_dict': {
334 'id': 'index',
335 'ext': 'mp4',
336 'title': 'index',
337 'upload_date': '20140720',
338 'formats': 'mincount:11',
339 },
340 'params': {
341 # m3u8 downloads
342 'skip_download': True,
343 },
344 'skip': 'video gone',
345 },
346 # google redirect
347 {
348 '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',
349 'info_dict': {
350 'id': 'cmQHVoWB5FY',
351 'ext': 'mp4',
352 'upload_date': '20130224',
353 'uploader_id': 'TheVerge',
354 'description': r're:^Chris Ziegler takes a look at the\.*',
355 'uploader': 'The Verge',
356 'title': 'First Firefox OS phones side-by-side',
357 },
358 'params': {
359 'skip_download': False,
360 }
361 },
362 {
363 # redirect in Refresh HTTP header
364 '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',
365 'info_dict': {
366 'id': 'pO8h3EaFRdo',
367 'ext': 'mp4',
368 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
369 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
370 'upload_date': '20150917',
371 'uploader_id': 'brtvofficial',
372 'uploader': 'Boiler Room',
373 },
374 'params': {
375 'skip_download': False,
376 },
377 },
378 {
379 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
380 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
381 'info_dict': {
382 'id': '13601338388002',
383 'ext': 'mp4',
384 'uploader': 'www.hodiho.fr',
385 'title': 'R\u00e9gis plante sa Jeep',
386 }
387 },
388 # bandcamp page with custom domain
389 {
390 'add_ie': ['Bandcamp'],
391 'url': 'http://bronyrock.com/track/the-pony-mash',
392 'info_dict': {
393 'id': '3235767654',
394 'ext': 'mp3',
395 'title': 'The Pony Mash',
396 'uploader': 'M_Pallante',
397 },
398 'skip': 'There is a limit of 200 free downloads / month for the test song',
399 },
400 {
401 # embedded brightcove video
402 # it also tests brightcove videos that need to set the 'Referer'
403 # in the http requests
404 'add_ie': ['BrightcoveLegacy'],
405 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
406 'info_dict': {
407 'id': '2765128793001',
408 'ext': 'mp4',
409 'title': 'Le cours de bourse : l’analyse technique',
410 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
411 'uploader': 'BFM BUSINESS',
412 },
413 'params': {
414 'skip_download': True,
415 },
416 },
417 {
418 # embedded with itemprop embedURL and video id spelled as `idVideo`
419 'add_id': ['BrightcoveLegacy'],
420 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
421 'info_dict': {
422 'id': '5255628253001',
423 'ext': 'mp4',
424 'title': 'md5:37c519b1128915607601e75a87995fc0',
425 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
426 'uploader': 'BFM BUSINESS',
427 'uploader_id': '876450612001',
428 'timestamp': 1482255315,
429 'upload_date': '20161220',
430 },
431 'params': {
432 'skip_download': True,
433 },
434 },
435 {
436 # https://github.com/ytdl-org/youtube-dl/issues/2253
437 'url': 'http://bcove.me/i6nfkrc3',
438 'md5': '0ba9446db037002366bab3b3eb30c88c',
439 'info_dict': {
440 'id': '3101154703001',
441 'ext': 'mp4',
442 'title': 'Still no power',
443 'uploader': 'thestar.com',
444 '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.',
445 },
446 'add_ie': ['BrightcoveLegacy'],
447 'skip': 'video gone',
448 },
449 {
450 'url': 'http://www.championat.com/video/football/v/87/87499.html',
451 'md5': 'fb973ecf6e4a78a67453647444222983',
452 'info_dict': {
453 'id': '3414141473001',
454 'ext': 'mp4',
455 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
456 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
457 'uploader': 'Championat',
458 },
459 },
460 {
461 # https://github.com/ytdl-org/youtube-dl/issues/3541
462 'add_ie': ['BrightcoveLegacy'],
463 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
464 'info_dict': {
465 'id': '3866516442001',
466 'ext': 'mp4',
467 'title': 'Leer mij vrouwen kennen: Aflevering 1',
468 'description': 'Leer mij vrouwen kennen: Aflevering 1',
469 'uploader': 'SBS Broadcasting',
470 },
471 'skip': 'Restricted to Netherlands',
472 'params': {
473 'skip_download': True, # m3u8 download
474 },
475 },
476 {
477 # Brightcove video in <iframe>
478 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
479 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
480 'info_dict': {
481 'id': '5360463607001',
482 'ext': 'mp4',
483 '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',
484 '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。',
485 'uploader': 'United Nations',
486 'uploader_id': '1362235914001',
487 'timestamp': 1489593889,
488 'upload_date': '20170315',
489 },
490 'add_ie': ['BrightcoveLegacy'],
491 },
492 {
493 # Brightcove with alternative playerID key
494 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
495 'info_dict': {
496 'id': 'nmeth.2062_SV1',
497 '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',
498 },
499 'playlist': [{
500 'info_dict': {
501 'id': '2228375078001',
502 'ext': 'mp4',
503 'title': 'nmeth.2062-sv1',
504 'description': 'nmeth.2062-sv1',
505 'timestamp': 1363357591,
506 'upload_date': '20130315',
507 'uploader': 'Nature Publishing Group',
508 'uploader_id': '1964492299001',
509 },
510 }],
511 },
512 {
513 # Brightcove with UUID in videoPlayer
514 'url': 'http://www8.hp.com/cn/zh/home.html',
515 'info_dict': {
516 'id': '5255815316001',
517 'ext': 'mp4',
518 'title': 'Sprocket Video - China',
519 'description': 'Sprocket Video - China',
520 'uploader': 'HP-Video Gallery',
521 'timestamp': 1482263210,
522 'upload_date': '20161220',
523 'uploader_id': '1107601872001',
524 },
525 'params': {
526 'skip_download': True, # m3u8 download
527 },
528 'skip': 'video rotates...weekly?',
529 },
530 {
531 # Brightcove:new type [2].
532 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
533 'md5': '2b35148fcf48da41c9fb4591650784f3',
534 'info_dict': {
535 'id': '5348741021001',
536 'ext': 'mp4',
537 'upload_date': '20170306',
538 'uploader_id': '4191638492001',
539 'timestamp': 1488769918,
540 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
541
542 },
543 },
544 {
545 # Alternative brightcove <video> attributes
546 '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/',
547 'info_dict': {
548 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
549 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
550 },
551 'playlist': [{
552 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
553 'info_dict': {
554 'id': '5311302538001',
555 'ext': 'mp4',
556 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
557 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
558 'timestamp': 1486321708,
559 'upload_date': '20170205',
560 'uploader_id': '800000640001',
561 },
562 'only_matching': True,
563 }],
564 },
565 {
566 # Brightcove with UUID in videoPlayer
567 'url': 'http://www8.hp.com/cn/zh/home.html',
568 'info_dict': {
569 'id': '5255815316001',
570 'ext': 'mp4',
571 'title': 'Sprocket Video - China',
572 'description': 'Sprocket Video - China',
573 'uploader': 'HP-Video Gallery',
574 'timestamp': 1482263210,
575 'upload_date': '20161220',
576 'uploader_id': '1107601872001',
577 },
578 'params': {
579 'skip_download': True, # m3u8 download
580 },
581 },
582 # ooyala video
583 {
584 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
585 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
586 'info_dict': {
587 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
588 'ext': 'mp4',
589 'title': '2cc213299525360.mov', # that's what we get
590 'duration': 238.231,
591 },
592 'add_ie': ['Ooyala'],
593 },
594 {
595 # ooyala video embedded with http://player.ooyala.com/iframe.js
596 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
597 'info_dict': {
598 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
599 'ext': 'mp4',
600 'title': '"Steve Jobs: Man in the Machine" trailer',
601 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
602 'duration': 135.427,
603 },
604 'params': {
605 'skip_download': True,
606 },
607 'skip': 'movie expired',
608 },
609 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
610 {
611 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
612 'info_dict': {
613 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
614 'ext': 'mp4',
615 'title': 'Steampunk Fest Comes to Honesdale',
616 'duration': 43.276,
617 },
618 'params': {
619 'skip_download': True,
620 }
621 },
622 # embed.ly video
623 {
624 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
625 'info_dict': {
626 'id': '9ODmcdjQcHQ',
627 'ext': 'mp4',
628 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
629 'upload_date': '20140225',
630 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
631 'uploader': 'Tested',
632 'uploader_id': 'testedcom',
633 },
634 # No need to test YoutubeIE here
635 'params': {
636 'skip_download': True,
637 },
638 },
639 # funnyordie embed
640 {
641 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
642 'info_dict': {
643 'id': '18e820ec3f',
644 'ext': 'mp4',
645 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
646 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
647 },
648 # HEAD requests lead to endless 301, while GET is OK
649 'expected_warnings': ['301'],
650 },
651 # RUTV embed
652 {
653 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
654 'info_dict': {
655 'id': '776940',
656 'ext': 'mp4',
657 'title': 'Охотское море стало целиком российским',
658 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
659 },
660 'params': {
661 # m3u8 download
662 'skip_download': True,
663 },
664 },
665 # TVC embed
666 {
667 '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/',
668 'info_dict': {
669 'id': '55304',
670 'ext': 'mp4',
671 'title': 'Дошкольное воспитание',
672 },
673 },
674 # SportBox embed
675 {
676 'url': 'http://www.vestifinance.ru/articles/25753',
677 'info_dict': {
678 'id': '25753',
679 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
680 },
681 'playlist': [{
682 'info_dict': {
683 'id': '370908',
684 'title': 'Госзаказ. День 3',
685 'ext': 'mp4',
686 }
687 }, {
688 'info_dict': {
689 'id': '370905',
690 'title': 'Госзаказ. День 2',
691 'ext': 'mp4',
692 }
693 }, {
694 'info_dict': {
695 'id': '370902',
696 'title': 'Госзаказ. День 1',
697 'ext': 'mp4',
698 }
699 }],
700 'params': {
701 # m3u8 download
702 'skip_download': True,
703 },
704 },
705 # Myvi.ru embed
706 {
707 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
708 'info_dict': {
709 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
710 'ext': 'mp4',
711 'title': 'Ужастики, русский трейлер (2015)',
712 'thumbnail': r're:^https?://.*\.jpg$',
713 'duration': 153,
714 }
715 },
716 # XHamster embed
717 {
718 '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',
719 'info_dict': {
720 'id': 'showthread',
721 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
722 },
723 'playlist_mincount': 7,
724 # This forum does not allow <iframe> syntaxes anymore
725 # Now HTML tags are displayed as-is
726 'skip': 'No videos on this page',
727 },
728 # Embedded TED video
729 {
730 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
731 'md5': '65fdff94098e4a607385a60c5177c638',
732 'info_dict': {
733 'id': '1969',
734 'ext': 'mp4',
735 'title': 'Hidden miracles of the natural world',
736 'uploader': 'Louie Schwartzberg',
737 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
738 }
739 },
740 # nowvideo embed hidden behind percent encoding
741 {
742 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
743 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
744 'info_dict': {
745 'id': '06e53103ca9aa',
746 'ext': 'flv',
747 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
748 'description': 'No description',
749 },
750 },
751 # arte embed
752 {
753 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
754 'md5': '7653032cbb25bf6c80d80f217055fa43',
755 'info_dict': {
756 'id': '048195-004_PLUS7-F',
757 'ext': 'flv',
758 'title': 'X:enius',
759 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
760 'upload_date': '20140320',
761 },
762 'params': {
763 'skip_download': 'Requires rtmpdump'
764 },
765 'skip': 'video gone',
766 },
767 # francetv embed
768 {
769 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
770 'info_dict': {
771 'id': 'EV_30231',
772 'ext': 'mp4',
773 'title': 'Alcaline, le concert avec Calogero',
774 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
775 'upload_date': '20150226',
776 'timestamp': 1424989860,
777 'duration': 5400,
778 },
779 'params': {
780 # m3u8 downloads
781 'skip_download': True,
782 },
783 'expected_warnings': [
784 'Forbidden'
785 ]
786 },
787 # Condé Nast embed
788 {
789 'url': 'http://www.wired.com/2014/04/honda-asimo/',
790 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
791 'info_dict': {
792 'id': '53501be369702d3275860000',
793 'ext': 'mp4',
794 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
795 }
796 },
797 # Dailymotion embed
798 {
799 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
800 'md5': '441aeeb82eb72c422c7f14ec533999cd',
801 'info_dict': {
802 'id': 'k2mm4bCdJ6CQ2i7c8o2',
803 'ext': 'mp4',
804 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
805 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
806 'uploader': 'Spi0n',
807 'uploader_id': 'xgditw',
808 'upload_date': '20140425',
809 'timestamp': 1398441542,
810 },
811 'add_ie': ['Dailymotion'],
812 },
813 # DailyMail embed
814 {
815 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
816 'info_dict': {
817 'id': '1495629',
818 'ext': 'mp4',
819 'title': 'Care worker punches elderly dementia patient in head 11 times',
820 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
821 },
822 'add_ie': ['DailyMail'],
823 'params': {
824 'skip_download': True,
825 },
826 },
827 # YouTube embed
828 {
829 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
830 'info_dict': {
831 'id': 'FXRb4ykk4S0',
832 'ext': 'mp4',
833 'title': 'The NBL Auction 2014',
834 'uploader': 'BADMINTON England',
835 'uploader_id': 'BADMINTONEvents',
836 'upload_date': '20140603',
837 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
838 },
839 'add_ie': ['Youtube'],
840 'params': {
841 'skip_download': True,
842 }
843 },
844 # MTVSercices embed
845 {
846 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
847 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
848 'info_dict': {
849 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
850 'ext': 'mp4',
851 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
852 'description': 'Two valets share their love for movie star Liam Neesons.',
853 'timestamp': 1349922600,
854 'upload_date': '20121011',
855 },
856 },
857 # YouTube embed via <data-embed-url="">
858 {
859 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
860 'info_dict': {
861 'id': '4vAffPZIT44',
862 'ext': 'mp4',
863 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
864 'uploader': 'Gameloft',
865 'uploader_id': 'gameloft',
866 'upload_date': '20140828',
867 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
868 },
869 'params': {
870 'skip_download': True,
871 }
872 },
873 # YouTube <object> embed
874 {
875 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
876 'md5': '516718101ec834f74318df76259fb3cc',
877 'info_dict': {
878 'id': 'msN87y-iEx0',
879 'ext': 'webm',
880 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
881 'upload_date': '20080526',
882 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
883 'uploader': 'Christopher Sykes',
884 'uploader_id': 'ChristopherJSykes',
885 },
886 'add_ie': ['Youtube'],
887 },
888 # Camtasia studio
889 {
890 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
891 'playlist': [{
892 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
893 'info_dict': {
894 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
895 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
896 'ext': 'flv',
897 'duration': 2235.90,
898 }
899 }, {
900 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
901 'info_dict': {
902 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
903 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
904 'ext': 'flv',
905 'duration': 2235.93,
906 }
907 }],
908 'info_dict': {
909 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
910 }
911 },
912 # Flowplayer
913 {
914 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
915 'md5': '9d65602bf31c6e20014319c7d07fba27',
916 'info_dict': {
917 'id': '5123ea6d5e5a7',
918 'ext': 'mp4',
919 'age_limit': 18,
920 'uploader': 'www.handjobhub.com',
921 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
922 }
923 },
924 # Multiple brightcove videos
925 # https://github.com/ytdl-org/youtube-dl/issues/2283
926 {
927 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
928 'info_dict': {
929 'id': 'always-never',
930 'title': 'Always / Never - The New Yorker',
931 },
932 'playlist_count': 3,
933 'params': {
934 'extract_flat': False,
935 'skip_download': True,
936 }
937 },
938 # MLB embed
939 {
940 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
941 'md5': '96f09a37e44da40dd083e12d9a683327',
942 'info_dict': {
943 'id': '33322633',
944 'ext': 'mp4',
945 'title': 'Ump changes call to ball',
946 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
947 'duration': 48,
948 'timestamp': 1401537900,
949 'upload_date': '20140531',
950 'thumbnail': r're:^https?://.*\.jpg$',
951 },
952 },
953 # Wistia embed
954 {
955 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
956 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
957 'info_dict': {
958 'id': '6e2wtrbdaf',
959 'ext': 'mov',
960 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
961 'description': 'a Paywall Videos video from Remilon',
962 'duration': 644.072,
963 'uploader': 'study.com',
964 'timestamp': 1459678540,
965 'upload_date': '20160403',
966 'filesize': 24687186,
967 },
968 },
969 {
970 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
971 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
972 'info_dict': {
973 'id': 'uxjb0lwrcz',
974 'ext': 'mp4',
975 'title': 'Conversation about Hexagonal Rails Part 1',
976 'description': 'a Martin Fowler video from ThoughtWorks',
977 'duration': 1715.0,
978 'uploader': 'thoughtworks.wistia.com',
979 'timestamp': 1401832161,
980 'upload_date': '20140603',
981 },
982 },
983 # Wistia standard embed (async)
984 {
985 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
986 'info_dict': {
987 'id': '807fafadvk',
988 'ext': 'mp4',
989 'title': 'Drip Brennan Dunn Workshop',
990 'description': 'a JV Webinars video from getdrip-1',
991 'duration': 4986.95,
992 'timestamp': 1463607249,
993 'upload_date': '20160518',
994 },
995 'params': {
996 'skip_download': True,
997 }
998 },
999 # Soundcloud embed
1000 {
1001 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
1002 'info_dict': {
1003 'id': '174391317',
1004 'ext': 'mp3',
1005 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1006 'uploader': 'Sophos Security',
1007 'title': 'Chet Chat 171 - Oct 29, 2014',
1008 'upload_date': '20141029',
1009 }
1010 },
1011 # Soundcloud multiple embeds
1012 {
1013 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1014 'info_dict': {
1015 'id': '52809',
1016 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1017 },
1018 'playlist_mincount': 7,
1019 },
1020 # TuneIn station embed
1021 {
1022 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1023 'info_dict': {
1024 'id': '204146',
1025 'ext': 'mp3',
1026 'title': 'CNRV',
1027 'location': 'Paris, France',
1028 'is_live': True,
1029 },
1030 'params': {
1031 # Live stream
1032 'skip_download': True,
1033 },
1034 },
1035 # Livestream embed
1036 {
1037 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1038 'info_dict': {
1039 'id': '67864563',
1040 'ext': 'flv',
1041 'upload_date': '20141112',
1042 'title': 'Rosetta #CometLanding webcast HL 10',
1043 }
1044 },
1045 # Another Livestream embed, without 'new.' in URL
1046 {
1047 'url': 'https://www.freespeech.org/',
1048 'info_dict': {
1049 'id': '123537347',
1050 'ext': 'mp4',
1051 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1052 },
1053 'params': {
1054 # Live stream
1055 'skip_download': True,
1056 },
1057 },
1058 # LazyYT
1059 {
1060 'url': 'https://skiplagged.com/',
1061 'info_dict': {
1062 'id': 'skiplagged',
1063 'title': 'Skiplagged: The smart way to find cheap flights',
1064 },
1065 'playlist_mincount': 1,
1066 'add_ie': ['Youtube'],
1067 },
1068 # Cinchcast embed
1069 {
1070 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1071 'info_dict': {
1072 'id': '7141703',
1073 'ext': 'mp3',
1074 'upload_date': '20141126',
1075 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1076 }
1077 },
1078 # Cinerama player
1079 {
1080 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1081 'info_dict': {
1082 'id': '730m_DandD_1901_512k',
1083 'ext': 'mp4',
1084 'uploader': 'www.abc.net.au',
1085 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1086 }
1087 },
1088 # embedded viddler video
1089 {
1090 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1091 'info_dict': {
1092 'id': '4d03aad9',
1093 'ext': 'mp4',
1094 'uploader': 'deadspin',
1095 'title': 'WALL-TO-GORTAT',
1096 'timestamp': 1422285291,
1097 'upload_date': '20150126',
1098 },
1099 'add_ie': ['Viddler'],
1100 },
1101 # Libsyn embed
1102 {
1103 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1104 'info_dict': {
1105 'id': '3377616',
1106 'ext': 'mp3',
1107 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1108 'description': 'md5:601cb790edd05908957dae8aaa866465',
1109 'upload_date': '20150220',
1110 },
1111 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1112 },
1113 # jwplayer YouTube
1114 {
1115 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1116 'info_dict': {
1117 'id': 'Mrj4DVp2zeA',
1118 'ext': 'mp4',
1119 'upload_date': '20150212',
1120 'uploader': 'The National Archives UK',
1121 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1122 'uploader_id': 'NationalArchives08',
1123 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1124 },
1125 },
1126 # jwplayer rtmp
1127 {
1128 'url': 'http://www.suffolk.edu/sjc/live.php',
1129 'info_dict': {
1130 'id': 'live',
1131 'ext': 'flv',
1132 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1133 'uploader': 'www.suffolk.edu',
1134 },
1135 'params': {
1136 'skip_download': True,
1137 },
1138 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1139 },
1140 # Complex jwplayer
1141 {
1142 'url': 'http://www.indiedb.com/games/king-machine/videos',
1143 'info_dict': {
1144 'id': 'videos',
1145 'ext': 'mp4',
1146 'title': 'king machine trailer 1',
1147 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1148 'thumbnail': r're:^https?://.*\.jpg$',
1149 },
1150 },
1151 {
1152 # JWPlayer config passed as variable
1153 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1154 'info_dict': {
1155 'id': '3326530_hq',
1156 'ext': 'mp4',
1157 'title': 'ARIELE | Tube Cup',
1158 'uploader': 'www.txxx.com',
1159 'age_limit': 18,
1160 },
1161 'params': {
1162 'skip_download': True,
1163 }
1164 },
1165 {
1166 # JWPlatform iframe
1167 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1168 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1169 'info_dict': {
1170 'id': 'O0c5JcKT',
1171 'ext': 'mp4',
1172 'upload_date': '20171122',
1173 'timestamp': 1511366290,
1174 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1175 },
1176 'add_ie': [JWPlatformIE.ie_key()],
1177 },
1178 {
1179 # Video.js embed, multiple formats
1180 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1181 'info_dict': {
1182 'id': 'yygqldloqIk',
1183 'ext': 'mp4',
1184 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1185 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1186 'upload_date': '20130314',
1187 'uploader': 'PROстое3D',
1188 'uploader_id': 'PROstoe3D',
1189 },
1190 'params': {
1191 'skip_download': True,
1192 },
1193 },
1194 {
1195 # Video.js embed, single format
1196 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1197 'info_dict': {
1198 'id': 'watch',
1199 'ext': 'mp4',
1200 'title': 'Step 1 - Good Foundation',
1201 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1202 },
1203 'params': {
1204 'skip_download': True,
1205 },
1206 },
1207 # rtl.nl embed
1208 {
1209 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1210 'playlist_mincount': 5,
1211 'info_dict': {
1212 'id': 'aanslagen-kopenhagen',
1213 'title': 'Aanslagen Kopenhagen',
1214 }
1215 },
1216 # Zapiks embed
1217 {
1218 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1219 'info_dict': {
1220 'id': '118046',
1221 'ext': 'mp4',
1222 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1223 }
1224 },
1225 # Kaltura embed (different embed code)
1226 {
1227 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1228 'info_dict': {
1229 'id': '1_a52wc67y',
1230 'ext': 'flv',
1231 'upload_date': '20150127',
1232 'uploader_id': 'PremierMedia',
1233 'timestamp': int,
1234 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1235 },
1236 },
1237 # Kaltura embed with single quotes
1238 {
1239 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1240 'info_dict': {
1241 'id': '0_izeg5utt',
1242 'ext': 'mp4',
1243 'title': '35871',
1244 'timestamp': 1355743100,
1245 'upload_date': '20121217',
1246 'uploader_id': 'cplapp@learn360.com',
1247 },
1248 'add_ie': ['Kaltura'],
1249 },
1250 {
1251 # Kaltura embedded via quoted entry_id
1252 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1253 'info_dict': {
1254 'id': '0_utuok90b',
1255 'ext': 'mp4',
1256 'title': '06_matthew_brender_raj_dutt',
1257 'timestamp': 1466638791,
1258 'upload_date': '20160622',
1259 },
1260 'add_ie': ['Kaltura'],
1261 'expected_warnings': [
1262 'Could not send HEAD request'
1263 ],
1264 'params': {
1265 'skip_download': True,
1266 }
1267 },
1268 {
1269 # Kaltura embedded, some fileExt broken (#11480)
1270 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1271 'info_dict': {
1272 'id': '1_sgtvehim',
1273 'ext': 'mp4',
1274 'title': 'Our "Standard Models" of particle physics and cosmology',
1275 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1276 'timestamp': 1321158993,
1277 'upload_date': '20111113',
1278 'uploader_id': 'kps1',
1279 },
1280 'add_ie': ['Kaltura'],
1281 },
1282 {
1283 # Kaltura iframe embed
1284 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1285 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1286 'info_dict': {
1287 'id': '0_f2cfbpwy',
1288 'ext': 'mp4',
1289 'title': 'I. M. Pei: A Centennial Celebration',
1290 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1291 'upload_date': '20170403',
1292 'uploader_id': 'batchUser',
1293 'timestamp': 1491232186,
1294 },
1295 'add_ie': ['Kaltura'],
1296 },
1297 {
1298 # Kaltura iframe embed, more sophisticated
1299 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1300 'info_dict': {
1301 'id': '1_9gzouybz',
1302 'ext': 'mp4',
1303 'title': 'lecture-05sep2017',
1304 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1305 'upload_date': '20170913',
1306 'uploader_id': 'eps2',
1307 'timestamp': 1505340777,
1308 },
1309 'params': {
1310 'skip_download': True,
1311 },
1312 'add_ie': ['Kaltura'],
1313 },
1314 {
1315 # meta twitter:player
1316 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1317 'info_dict': {
1318 'id': '0_01b42zps',
1319 'ext': 'mp4',
1320 'title': 'Main Twerk (Video)',
1321 'upload_date': '20171208',
1322 'uploader_id': 'sebastian.salinas@thechive.com',
1323 'timestamp': 1512713057,
1324 },
1325 'params': {
1326 'skip_download': True,
1327 },
1328 'add_ie': ['Kaltura'],
1329 },
1330 # referrer protected EaglePlatform embed
1331 {
1332 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1333 'info_dict': {
1334 'id': '582306',
1335 'ext': 'mp4',
1336 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1337 'thumbnail': r're:^https?://.*\.jpg$',
1338 'duration': 3382,
1339 'view_count': int,
1340 },
1341 'params': {
1342 'skip_download': True,
1343 },
1344 },
1345 # ClipYou (EaglePlatform) embed (custom URL)
1346 {
1347 'url': 'http://muz-tv.ru/play/7129/',
1348 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1349 'info_dict': {
1350 'id': '12820',
1351 'ext': 'mp4',
1352 'title': "'O Sole Mio",
1353 'thumbnail': r're:^https?://.*\.jpg$',
1354 'duration': 216,
1355 'view_count': int,
1356 },
1357 'params': {
1358 'skip_download': True,
1359 },
1360 'skip': 'This video is unavailable.',
1361 },
1362 # Pladform embed
1363 {
1364 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1365 'info_dict': {
1366 'id': '100183293',
1367 'ext': 'mp4',
1368 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1369 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1370 'thumbnail': r're:^https?://.*\.jpg$',
1371 'duration': 694,
1372 'age_limit': 0,
1373 },
1374 'skip': 'HTTP Error 404: Not Found',
1375 },
1376 # Playwire embed
1377 {
1378 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1379 'info_dict': {
1380 'id': '3519514',
1381 'ext': 'mp4',
1382 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1383 'thumbnail': r're:^https?://.*\.png$',
1384 'duration': 45.115,
1385 },
1386 },
1387 # 5min embed
1388 {
1389 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1390 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1391 'info_dict': {
1392 'id': '518726732',
1393 'ext': 'mp4',
1394 'title': 'Facebook Creates "On This Day" | Crunch Report',
1395 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1396 'timestamp': 1427237531,
1397 'uploader': 'Crunch Report',
1398 'upload_date': '20150324',
1399 },
1400 'params': {
1401 # m3u8 download
1402 'skip_download': True,
1403 },
1404 },
1405 # Crooks and Liars embed
1406 {
1407 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1408 'info_dict': {
1409 'id': '8RUoRhRi',
1410 'ext': 'mp4',
1411 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1412 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1413 'timestamp': 1428207000,
1414 'upload_date': '20150405',
1415 'uploader': 'Heather',
1416 },
1417 },
1418 # Crooks and Liars external embed
1419 {
1420 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1421 'info_dict': {
1422 'id': 'MTE3MjUtMzQ2MzA',
1423 'ext': 'mp4',
1424 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1425 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1426 'timestamp': 1265032391,
1427 'upload_date': '20100201',
1428 'uploader': 'Heather',
1429 },
1430 },
1431 # NBC Sports vplayer embed
1432 {
1433 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1434 'info_dict': {
1435 'id': 'ln7x1qSThw4k',
1436 'ext': 'flv',
1437 'title': "PFT Live: New leader in the 'new-look' defense",
1438 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1439 'uploader': 'NBCU-SPORTS',
1440 'upload_date': '20140107',
1441 'timestamp': 1389118457,
1442 },
1443 'skip': 'Invalid Page URL',
1444 },
1445 # NBC News embed
1446 {
1447 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1448 'md5': '1aa589c675898ae6d37a17913cf68d66',
1449 'info_dict': {
1450 'id': 'x_dtl_oa_LettermanliftPR_160608',
1451 'ext': 'mp4',
1452 'title': 'David Letterman: A Preview',
1453 '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.',
1454 'upload_date': '20160609',
1455 'timestamp': 1465431544,
1456 'uploader': 'NBCU-NEWS',
1457 },
1458 },
1459 # UDN embed
1460 {
1461 'url': 'https://video.udn.com/news/300346',
1462 'md5': 'fd2060e988c326991037b9aff9df21a6',
1463 'info_dict': {
1464 'id': '300346',
1465 'ext': 'mp4',
1466 'title': '中一中男師變性 全校師生力挺',
1467 'thumbnail': r're:^https?://.*\.jpg$',
1468 },
1469 'params': {
1470 # m3u8 download
1471 'skip_download': True,
1472 },
1473 'expected_warnings': ['Failed to parse JSON Expecting value'],
1474 },
1475 # Brightcove URL in single quotes
1476 {
1477 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1478 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1479 'info_dict': {
1480 'id': '4255764656001',
1481 'ext': 'mp4',
1482 'title': 'SN Presents: Russell Martin, World Citizen',
1483 '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.',
1484 'uploader': 'Rogers Sportsnet',
1485 'uploader_id': '1704050871',
1486 'upload_date': '20150525',
1487 'timestamp': 1432570283,
1488 },
1489 },
1490 # OnionStudios embed
1491 {
1492 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1493 'info_dict': {
1494 'id': '2855',
1495 'ext': 'mp4',
1496 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1497 'thumbnail': r're:^https?://.*\.jpe?g$',
1498 'uploader': 'ClickHole',
1499 'uploader_id': 'clickhole',
1500 }
1501 },
1502 # SnagFilms embed
1503 {
1504 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1505 'info_dict': {
1506 'id': '74849a00-85a9-11e1-9660-123139220831',
1507 'ext': 'mp4',
1508 'title': '#whilewewatch',
1509 }
1510 },
1511 # AdobeTVVideo embed
1512 {
1513 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1514 'md5': '43662b577c018ad707a63766462b1e87',
1515 'info_dict': {
1516 'id': '2456',
1517 'ext': 'mp4',
1518 'title': 'New experience with Acrobat DC',
1519 'description': 'New experience with Acrobat DC',
1520 'duration': 248.667,
1521 },
1522 },
1523 # BrightcoveInPageEmbed embed
1524 {
1525 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1526 'info_dict': {
1527 'id': '4238694884001',
1528 'ext': 'flv',
1529 'title': 'Tabletop: Dread, Last Thoughts',
1530 'description': 'Tabletop: Dread, Last Thoughts',
1531 'duration': 51690,
1532 },
1533 },
1534 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1535 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1536 {
1537 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1538 'info_dict': {
1539 'id': '4785848093001',
1540 'ext': 'mp4',
1541 'title': 'The Cardinal Pell Interview',
1542 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1543 'uploader': 'GlobeCast Australia - GlobeStream',
1544 'uploader_id': '2733773828001',
1545 'upload_date': '20160304',
1546 'timestamp': 1457083087,
1547 },
1548 'params': {
1549 # m3u8 downloads
1550 'skip_download': True,
1551 },
1552 },
1553 {
1554 # Brightcove embed with whitespace around attribute names
1555 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1556 'info_dict': {
1557 'id': '3167554373001',
1558 'ext': 'mp4',
1559 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1560 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1561 'uploader_id': '1079349493',
1562 'upload_date': '20140207',
1563 'timestamp': 1391810548,
1564 },
1565 'params': {
1566 'skip_download': True,
1567 },
1568 },
1569 # Another form of arte.tv embed
1570 {
1571 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1572 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1573 'info_dict': {
1574 'id': '030273-562_PLUS7-F',
1575 'ext': 'mp4',
1576 'title': 'ARTE Reportage - Nulle part, en France',
1577 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1578 'upload_date': '20160409',
1579 },
1580 },
1581 # LiveLeak embed
1582 {
1583 'url': 'http://www.wykop.pl/link/3088787/',
1584 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1585 'info_dict': {
1586 'id': '874_1459135191',
1587 'ext': 'mp4',
1588 'title': 'Man shows poor quality of new apartment building',
1589 'description': 'The wall is like a sand pile.',
1590 'uploader': 'Lake8737',
1591 },
1592 'add_ie': [LiveLeakIE.ie_key()],
1593 },
1594 # Another LiveLeak embed pattern (#13336)
1595 {
1596 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1597 'info_dict': {
1598 'id': '2eb_1496309988',
1599 'ext': 'mp4',
1600 'title': 'Thief robs place where everyone was armed',
1601 'description': 'md5:694d73ee79e535953cf2488562288eee',
1602 'uploader': 'brazilwtf',
1603 },
1604 'add_ie': [LiveLeakIE.ie_key()],
1605 },
1606 # Duplicated embedded video URLs
1607 {
1608 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1609 'info_dict': {
1610 'id': '149298443_480_16c25b74_2',
1611 'ext': 'mp4',
1612 'title': 'vs. Blue Orange Spring Game',
1613 'uploader': 'www.hudl.com',
1614 },
1615 },
1616 # twitter:player:stream embed
1617 {
1618 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1619 'info_dict': {
1620 'id': 'master',
1621 'ext': 'mp4',
1622 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1623 'uploader': 'www.rtl.be',
1624 },
1625 'params': {
1626 # m3u8 downloads
1627 'skip_download': True,
1628 },
1629 },
1630 # twitter:player embed
1631 {
1632 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1633 'md5': 'a3e0df96369831de324f0778e126653c',
1634 'info_dict': {
1635 'id': '4909620399001',
1636 'ext': 'mp4',
1637 'title': 'What Do Black Holes Sound Like?',
1638 'description': 'what do black holes sound like',
1639 'upload_date': '20160524',
1640 'uploader_id': '29913724001',
1641 'timestamp': 1464107587,
1642 'uploader': 'TheAtlantic',
1643 },
1644 'add_ie': ['BrightcoveLegacy'],
1645 },
1646 # Facebook <iframe> embed
1647 {
1648 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1649 'md5': 'fbcde74f534176ecb015849146dd3aee',
1650 'info_dict': {
1651 'id': '599637780109885',
1652 'ext': 'mp4',
1653 'title': 'Facebook video #599637780109885',
1654 },
1655 },
1656 # Facebook <iframe> embed, plugin video
1657 {
1658 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1659 'info_dict': {
1660 'id': '1754168231264132',
1661 'ext': 'mp4',
1662 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1663 'uploader': 'Tariq Ramadan (official)',
1664 'timestamp': 1496758379,
1665 'upload_date': '20170606',
1666 },
1667 'params': {
1668 'skip_download': True,
1669 },
1670 },
1671 # Facebook API embed
1672 {
1673 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1674 'md5': 'a47372ee61b39a7b90287094d447d94e',
1675 'info_dict': {
1676 'id': '10153467542406923',
1677 'ext': 'mp4',
1678 'title': 'Facebook video #10153467542406923',
1679 },
1680 },
1681 # Wordpress "YouTube Video Importer" plugin
1682 {
1683 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1684 'md5': 'd16797741b560b485194eddda8121b48',
1685 'info_dict': {
1686 'id': 'HNTXWDXV9Is',
1687 'ext': 'mp4',
1688 'title': 'Blue Devils Drumline Stanford lot 2016',
1689 'upload_date': '20160627',
1690 'uploader_id': 'GENOCIDE8GENERAL10',
1691 'uploader': 'cylus cyrus',
1692 },
1693 },
1694 {
1695 # video stored on custom kaltura server
1696 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1697 'md5': '537617d06e64dfed891fa1593c4b30cc',
1698 'info_dict': {
1699 'id': '0_1iotm5bh',
1700 'ext': 'mp4',
1701 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1702 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1703 'uploader_id': 'videos.expansion@el-mundo.net',
1704 'upload_date': '20150429',
1705 'timestamp': 1430303472,
1706 },
1707 'add_ie': ['Kaltura'],
1708 },
1709 {
1710 # Non-standard Vimeo embed
1711 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1712 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1713 'info_dict': {
1714 'id': '148867247',
1715 'ext': 'mp4',
1716 'title': 'Understanding the web - Teaser',
1717 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1718 'upload_date': '20151214',
1719 'uploader': 'OpenClassrooms',
1720 'uploader_id': 'openclassrooms',
1721 },
1722 'add_ie': ['Vimeo'],
1723 },
1724 {
1725 # generic vimeo embed that requires original URL passed as Referer
1726 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1727 'only_matching': True,
1728 },
1729 {
1730 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1731 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1732 'info_dict': {
1733 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1734 'ext': 'mp4',
1735 'title': 'Big Buck Bunny',
1736 'description': 'Royalty free test video',
1737 'timestamp': 1432816365,
1738 'upload_date': '20150528',
1739 'is_live': False,
1740 },
1741 'params': {
1742 'skip_download': True,
1743 },
1744 'add_ie': [ArkenaIE.ie_key()],
1745 },
1746 {
1747 '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/',
1748 'info_dict': {
1749 'id': '1c7141f46c',
1750 'ext': 'mp4',
1751 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1752 },
1753 'params': {
1754 'skip_download': True,
1755 },
1756 'add_ie': [Vbox7IE.ie_key()],
1757 },
1758 {
1759 # DBTV embeds
1760 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1761 'info_dict': {
1762 'id': '43254897',
1763 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1764 },
1765 'playlist_mincount': 3,
1766 },
1767 {
1768 # Videa embeds
1769 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1770 'info_dict': {
1771 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1772 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1773 },
1774 'playlist_mincount': 2,
1775 },
1776 {
1777 # 20 minuten embed
1778 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1779 'info_dict': {
1780 'id': '523629',
1781 'ext': 'mp4',
1782 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1783 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1784 },
1785 'params': {
1786 'skip_download': True,
1787 },
1788 'add_ie': [TwentyMinutenIE.ie_key()],
1789 },
1790 {
1791 # VideoPress embed
1792 'url': 'https://en.support.wordpress.com/videopress/',
1793 'info_dict': {
1794 'id': 'OcobLTqC',
1795 'ext': 'm4v',
1796 'title': 'IMG_5786',
1797 'timestamp': 1435711927,
1798 'upload_date': '20150701',
1799 },
1800 'params': {
1801 'skip_download': True,
1802 },
1803 'add_ie': [VideoPressIE.ie_key()],
1804 },
1805 {
1806 # Rutube embed
1807 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1808 'info_dict': {
1809 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1810 'ext': 'flv',
1811 'title': 'Магаззино: Казань 2',
1812 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1813 'uploader': 'Магаззино',
1814 'upload_date': '20170228',
1815 'uploader_id': '996642',
1816 },
1817 'params': {
1818 'skip_download': True,
1819 },
1820 'add_ie': [RutubeIE.ie_key()],
1821 },
1822 {
1823 # ThePlatform embedded with whitespaces in URLs
1824 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1825 'only_matching': True,
1826 },
1827 {
1828 # Senate ISVP iframe https
1829 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1830 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1831 'info_dict': {
1832 'id': 'govtaff020316',
1833 'ext': 'mp4',
1834 'title': 'Integrated Senate Video Player',
1835 },
1836 'add_ie': [SenateISVPIE.ie_key()],
1837 },
1838 {
1839 # Limelight embeds (1 channel embed + 4 media embeds)
1840 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1841 'info_dict': {
1842 'id': 'FacilitatorTraining2017',
1843 'title': 'Facilitator Training 2017',
1844 },
1845 'playlist_mincount': 5,
1846 },
1847 {
1848 # Limelight embed (LimelightPlayerUtil.embed)
1849 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1850 'info_dict': {
1851 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1852 'ext': 'mp4',
1853 'title': '07448641',
1854 'timestamp': 1499890639,
1855 'upload_date': '20170712',
1856 },
1857 'params': {
1858 'skip_download': True,
1859 },
1860 'add_ie': ['LimelightMedia'],
1861 },
1862 {
1863 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1864 'info_dict': {
1865 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1866 'title': 'Standoff with Walnut Creek murder suspect ends',
1867 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1868 },
1869 'playlist_mincount': 4,
1870 },
1871 {
1872 # WashingtonPost embed
1873 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1874 'info_dict': {
1875 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1876 'ext': 'mp4',
1877 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1878 '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.',
1879 'timestamp': 1455216756,
1880 'uploader': 'The Washington Post',
1881 'upload_date': '20160211',
1882 },
1883 'add_ie': [WashingtonPostIE.ie_key()],
1884 },
1885 {
1886 # Mediaset embed
1887 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1888 'info_dict': {
1889 'id': '720642',
1890 'ext': 'mp4',
1891 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 'add_ie': [MediasetIE.ie_key()],
1897 },
1898 {
1899 # JOJ.sk embeds
1900 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1901 'info_dict': {
1902 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1903 'title': 'Slovenskom sa prehnala vlna silných búrok',
1904 },
1905 'playlist_mincount': 5,
1906 'add_ie': [JojIE.ie_key()],
1907 },
1908 {
1909 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1910 'url': 'https://tvrain.ru/amp/418921/',
1911 'md5': 'cc00413936695987e8de148b67d14f1d',
1912 'info_dict': {
1913 'id': '418921',
1914 'ext': 'mp4',
1915 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1916 },
1917 },
1918 {
1919 # vzaar embed
1920 'url': 'http://help.vzaar.com/article/165-embedding-video',
1921 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1922 'info_dict': {
1923 'id': '8707641',
1924 'ext': 'mp4',
1925 'title': 'Building A Business Online: Principal Chairs Q & A',
1926 },
1927 },
1928 {
1929 # multiple HTML5 videos on one page
1930 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1931 'info_dict': {
1932 'id': 'keyscenarios',
1933 'title': 'Rescue Kit 14 Free Edition - Getting started',
1934 },
1935 'playlist_count': 4,
1936 },
1937 {
1938 # vshare embed
1939 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1940 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1941 'info_dict': {
1942 'id': '0f64ce6',
1943 'title': 'vl14062007715967',
1944 'ext': 'mp4',
1945 }
1946 },
1947 {
1948 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1949 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1950 'info_dict': {
1951 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1952 'ext': 'mp4',
1953 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1954 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1955 'timestamp': 1474354800,
1956 'upload_date': '20160920',
1957 }
1958 },
1959 {
1960 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1961 'info_dict': {
1962 'id': '1731611',
1963 'ext': 'mp4',
1964 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1965 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1966 'timestamp': 1516100691,
1967 'upload_date': '20180116',
1968 },
1969 'params': {
1970 'skip_download': True,
1971 },
1972 'add_ie': [SpringboardPlatformIE.ie_key()],
1973 },
1974 {
1975 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1976 'info_dict': {
1977 'id': 'uPDB5I9wfp8',
1978 'ext': 'webm',
1979 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1980 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1981 'upload_date': '20160219',
1982 'uploader': 'Pocoyo - Português (BR)',
1983 'uploader_id': 'PocoyoBrazil',
1984 },
1985 'add_ie': [YoutubeIE.ie_key()],
1986 'params': {
1987 'skip_download': True,
1988 },
1989 },
1990 {
1991 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1992 'info_dict': {
1993 'id': 'vMDE4NzI1Mjgt690b',
1994 'ext': 'mp4',
1995 'title': 'Котята',
1996 },
1997 'add_ie': [YapFilesIE.ie_key()],
1998 'params': {
1999 'skip_download': True,
2000 },
2001 },
2002 {
2003 # CloudflareStream embed
2004 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2005 'info_dict': {
2006 'id': '31c9291ab41fac05471db4e73aa11717',
2007 'ext': 'mp4',
2008 'title': '31c9291ab41fac05471db4e73aa11717',
2009 },
2010 'add_ie': [CloudflareStreamIE.ie_key()],
2011 'params': {
2012 'skip_download': True,
2013 },
2014 },
2015 {
2016 # PeerTube embed
2017 'url': 'https://joinpeertube.org/fr/home/',
2018 'info_dict': {
2019 'id': 'home',
2020 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2021 },
2022 'playlist_count': 2,
2023 },
2024 {
2025 # Indavideo embed
2026 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2027 'info_dict': {
2028 'id': '1693903',
2029 'ext': 'mp4',
2030 'title': 'Így kell otthon hamburgert sütni',
2031 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2032 'timestamp': 1426330212,
2033 'upload_date': '20150314',
2034 'uploader': 'StreetKitchen',
2035 'uploader_id': '546363',
2036 },
2037 'add_ie': [IndavideoEmbedIE.ie_key()],
2038 'params': {
2039 'skip_download': True,
2040 },
2041 },
2042 {
2043 # APA embed via JWPlatform embed
2044 'url': 'http://www.vol.at/blue-man-group/5593454',
2045 'info_dict': {
2046 'id': 'jjv85FdZ',
2047 'ext': 'mp4',
2048 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2049 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2050 'thumbnail': r're:^https?://.*\.jpg$',
2051 'duration': 254,
2052 'timestamp': 1519211149,
2053 'upload_date': '20180221',
2054 },
2055 'params': {
2056 'skip_download': True,
2057 },
2058 },
2059 {
2060 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2061 'md5': 'b68d276de422ab07ee1d49388103f457',
2062 'info_dict': {
2063 'id': '83645793',
2064 'title': 'Lock up and get excited',
2065 'ext': 'mp4'
2066 },
2067 'skip': 'TODO: fix nested playlists processing in tests',
2068 },
2069 {
2070 # Viqeo embeds
2071 'url': 'https://viqeo.tv/',
2072 'info_dict': {
2073 'id': 'viqeo',
2074 'title': 'All-new video platform',
2075 },
2076 'playlist_count': 6,
2077 },
2078 {
2079 # Zype embed
2080 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2081 'info_dict': {
2082 'id': '5b400b834b32992a310622b9',
2083 'ext': 'mp4',
2084 'title': 'Smoky Barbecue Favorites',
2085 'thumbnail': r're:^https?://.*\.jpe?g',
2086 },
2087 'add_ie': [ZypeIE.ie_key()],
2088 'params': {
2089 'skip_download': True,
2090 },
2091 },
2092 {
2093 # videojs embed
2094 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2095 'info_dict': {
2096 'id': 'shell',
2097 'ext': 'mp4',
2098 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2099 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2100 'thumbnail': r're:^https?://.*\.jpg$',
2101 },
2102 'params': {
2103 'skip_download': True,
2104 },
2105 'expected_warnings': ['Failed to download MPD manifest'],
2106 },
2107 # {
2108 # # TODO: find another test
2109 # # http://schema.org/VideoObject
2110 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2111 # 'md5': '888dcf08b7ea671381f00fab74692755',
2112 # 'info_dict': {
2113 # 'id': 'nyvTSJMKId',
2114 # 'ext': 'mp4',
2115 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2116 # 'description': '#love for cats.',
2117 # 'timestamp': 1461244995,
2118 # 'upload_date': '20160421',
2119 # },
2120 # 'params': {
2121 # 'force_generic_extractor': True,
2122 # },
2123 # }
2124 ]
2125
2126 def report_following_redirect(self, new_url):
2127 """Report information extraction."""
2128 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2129
2130 def _extract_rss(self, url, video_id, doc):
2131 playlist_title = doc.find('./channel/title').text
2132 playlist_desc_el = doc.find('./channel/description')
2133 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2134
2135 entries = []
2136 for it in doc.findall('./channel/item'):
2137 next_url = None
2138 enclosure_nodes = it.findall('./enclosure')
2139 for e in enclosure_nodes:
2140 next_url = e.attrib.get('url')
2141 if next_url:
2142 break
2143
2144 if not next_url:
2145 next_url = xpath_text(it, 'link', fatal=False)
2146
2147 if not next_url:
2148 continue
2149
2150 entries.append({
2151 '_type': 'url_transparent',
2152 'url': next_url,
2153 'title': it.find('title').text,
2154 })
2155
2156 return {
2157 '_type': 'playlist',
2158 'id': url,
2159 'title': playlist_title,
2160 'description': playlist_desc,
2161 'entries': entries,
2162 }
2163
2164 def _extract_camtasia(self, url, video_id, webpage):
2165 """ Returns None if no camtasia video can be found. """
2166
2167 camtasia_cfg = self._search_regex(
2168 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2169 webpage, 'camtasia configuration file', default=None)
2170 if camtasia_cfg is None:
2171 return None
2172
2173 title = self._html_search_meta('DC.title', webpage, fatal=True)
2174
2175 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2176 camtasia_cfg = self._download_xml(
2177 camtasia_url, video_id,
2178 note='Downloading camtasia configuration',
2179 errnote='Failed to download camtasia configuration')
2180 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2181
2182 entries = []
2183 for n in fileset_node.getchildren():
2184 url_n = n.find('./uri')
2185 if url_n is None:
2186 continue
2187
2188 entries.append({
2189 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2190 'title': '%s - %s' % (title, n.tag),
2191 'url': compat_urlparse.urljoin(url, url_n.text),
2192 'duration': float_or_none(n.find('./duration').text),
2193 })
2194
2195 return {
2196 '_type': 'playlist',
2197 'entries': entries,
2198 'title': title,
2199 }
2200
2201 def _real_extract(self, url):
2202 if url.startswith('//'):
2203 return self.url_result(self.http_scheme() + url)
2204
2205 parsed_url = compat_urlparse.urlparse(url)
2206 if not parsed_url.scheme:
2207 default_search = self._downloader.params.get('default_search')
2208 if default_search is None:
2209 default_search = 'fixup_error'
2210
2211 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2212 if '/' in url:
2213 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2214 return self.url_result('http://' + url)
2215 elif default_search != 'fixup_error':
2216 if default_search == 'auto_warning':
2217 if re.match(r'^(?:url|URL)$', url):
2218 raise ExtractorError(
2219 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2220 expected=True)
2221 else:
2222 self._downloader.report_warning(
2223 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2224 return self.url_result('ytsearch:' + url)
2225
2226 if default_search in ('error', 'fixup_error'):
2227 raise ExtractorError(
2228 '%r is not a valid URL. '
2229 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2230 % (url, url), expected=True)
2231 else:
2232 if ':' not in default_search:
2233 default_search += ':'
2234 return self.url_result(default_search + url)
2235
2236 url, smuggled_data = unsmuggle_url(url)
2237 force_videoid = None
2238 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2239 if smuggled_data and 'force_videoid' in smuggled_data:
2240 force_videoid = smuggled_data['force_videoid']
2241 video_id = force_videoid
2242 else:
2243 video_id = self._generic_id(url)
2244
2245 self.to_screen('%s: Requesting header' % video_id)
2246
2247 head_req = HEADRequest(url)
2248 head_response = self._request_webpage(
2249 head_req, video_id,
2250 note=False, errnote='Could not send HEAD request to %s' % url,
2251 fatal=False)
2252
2253 if head_response is not False:
2254 # Check for redirect
2255 new_url = compat_str(head_response.geturl())
2256 if url != new_url:
2257 self.report_following_redirect(new_url)
2258 if force_videoid:
2259 new_url = smuggle_url(
2260 new_url, {'force_videoid': force_videoid})
2261 return self.url_result(new_url)
2262
2263 full_response = None
2264 if head_response is False:
2265 request = sanitized_Request(url)
2266 request.add_header('Accept-Encoding', '*')
2267 full_response = self._request_webpage(request, video_id)
2268 head_response = full_response
2269
2270 info_dict = {
2271 'id': video_id,
2272 'title': self._generic_title(url),
2273 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2274 }
2275
2276 # Check for direct link to a video
2277 content_type = head_response.headers.get('Content-Type', '').lower()
2278 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2279 if m:
2280 format_id = compat_str(m.group('format_id'))
2281 if format_id.endswith('mpegurl'):
2282 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2283 elif format_id == 'f4m':
2284 formats = self._extract_f4m_formats(url, video_id)
2285 else:
2286 formats = [{
2287 'format_id': format_id,
2288 'url': url,
2289 'vcodec': 'none' if m.group('type') == 'audio' else None
2290 }]
2291 info_dict['direct'] = True
2292 self._sort_formats(formats)
2293 info_dict['formats'] = formats
2294 return info_dict
2295
2296 if not self._downloader.params.get('test', False) and not is_intentional:
2297 force = self._downloader.params.get('force_generic_extractor', False)
2298 self._downloader.report_warning(
2299 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2300
2301 if not full_response:
2302 request = sanitized_Request(url)
2303 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2304 # making it impossible to download only chunk of the file (yet we need only 512kB to
2305 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2306 # that will always result in downloading the whole file that is not desirable.
2307 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2308 # to accept raw bytes and being able to download only a chunk.
2309 # It may probably better to solve this by checking Content-Type for application/octet-stream
2310 # after HEAD request finishes, but not sure if we can rely on this.
2311 request.add_header('Accept-Encoding', '*')
2312 full_response = self._request_webpage(request, video_id)
2313
2314 first_bytes = full_response.read(512)
2315
2316 # Is it an M3U playlist?
2317 if first_bytes.startswith(b'#EXTM3U'):
2318 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2319 self._sort_formats(info_dict['formats'])
2320 return info_dict
2321
2322 # Maybe it's a direct link to a video?
2323 # Be careful not to download the whole thing!
2324 if not is_html(first_bytes):
2325 self._downloader.report_warning(
2326 'URL could be a direct video link, returning it as such.')
2327 info_dict.update({
2328 'direct': True,
2329 'url': url,
2330 })
2331 return info_dict
2332
2333 webpage = self._webpage_read_content(
2334 full_response, url, video_id, prefix=first_bytes)
2335
2336 self.report_extraction(video_id)
2337
2338 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2339 try:
2340 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2341 if doc.tag == 'rss':
2342 return self._extract_rss(url, video_id, doc)
2343 elif doc.tag == 'SmoothStreamingMedia':
2344 info_dict['formats'] = self._parse_ism_formats(doc, url)
2345 self._sort_formats(info_dict['formats'])
2346 return info_dict
2347 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2348 smil = self._parse_smil(doc, url, video_id)
2349 self._sort_formats(smil['formats'])
2350 return smil
2351 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2352 return self.playlist_result(
2353 self._parse_xspf(
2354 doc, video_id, xspf_url=url,
2355 xspf_base_url=compat_str(full_response.geturl())),
2356 video_id)
2357 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2358 info_dict['formats'] = self._parse_mpd_formats(
2359 doc,
2360 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2361 mpd_url=url)
2362 self._sort_formats(info_dict['formats'])
2363 return info_dict
2364 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2365 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2366 self._sort_formats(info_dict['formats'])
2367 return info_dict
2368 except compat_xml_parse_error:
2369 pass
2370
2371 # Is it a Camtasia project?
2372 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2373 if camtasia_res is not None:
2374 return camtasia_res
2375
2376 # Sometimes embedded video player is hidden behind percent encoding
2377 # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
2378 # Unescaping the whole page allows to handle those cases in a generic way
2379 webpage = compat_urllib_parse_unquote(webpage)
2380
2381 # it's tempting to parse this further, but you would
2382 # have to take into account all the variations like
2383 # Video Title - Site Name
2384 # Site Name | Video Title
2385 # Video Title - Tagline | Site Name
2386 # and so on and so forth; it's just not practical
2387 video_title = self._og_search_title(
2388 webpage, default=None) or self._html_search_regex(
2389 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2390 default='video')
2391
2392 # Try to detect age limit automatically
2393 age_limit = self._rta_search(webpage)
2394 # And then there are the jokers who advertise that they use RTA,
2395 # but actually don't.
2396 AGE_LIMIT_MARKERS = [
2397 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2398 ]
2399 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2400 age_limit = 18
2401
2402 # video uploader is domain name
2403 video_uploader = self._search_regex(
2404 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2405
2406 video_description = self._og_search_description(webpage, default=None)
2407 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2408
2409 info_dict.update({
2410 'title': video_title,
2411 'description': video_description,
2412 'thumbnail': video_thumbnail,
2413 'age_limit': age_limit,
2414 })
2415
2416 # Look for Brightcove Legacy Studio embeds
2417 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2418 if bc_urls:
2419 entries = [{
2420 '_type': 'url',
2421 'url': smuggle_url(bc_url, {'Referer': url}),
2422 'ie_key': 'BrightcoveLegacy'
2423 } for bc_url in bc_urls]
2424
2425 return {
2426 '_type': 'playlist',
2427 'title': video_title,
2428 'id': video_id,
2429 'entries': entries,
2430 }
2431
2432 # Look for Brightcove New Studio embeds
2433 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2434 if bc_urls:
2435 return self.playlist_from_matches(
2436 bc_urls, video_id, video_title,
2437 getter=lambda x: smuggle_url(x, {'referrer': url}),
2438 ie='BrightcoveNew')
2439
2440 # Look for Nexx embeds
2441 nexx_urls = NexxIE._extract_urls(webpage)
2442 if nexx_urls:
2443 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2444
2445 # Look for Nexx iFrame embeds
2446 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2447 if nexx_embed_urls:
2448 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2449
2450 # Look for ThePlatform embeds
2451 tp_urls = ThePlatformIE._extract_urls(webpage)
2452 if tp_urls:
2453 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2454
2455 # Look for Vessel embeds
2456 vessel_urls = VesselIE._extract_urls(webpage)
2457 if vessel_urls:
2458 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2459
2460 # Look for embedded rtl.nl player
2461 matches = re.findall(
2462 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2463 webpage)
2464 if matches:
2465 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2466
2467 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2468 if vimeo_urls:
2469 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2470
2471 vid_me_embed_url = self._search_regex(
2472 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2473 webpage, 'vid.me embed', default=None)
2474 if vid_me_embed_url is not None:
2475 return self.url_result(vid_me_embed_url, 'Vidme')
2476
2477 # Look for YouTube embeds
2478 youtube_urls = YoutubeIE._extract_urls(webpage)
2479 if youtube_urls:
2480 return self.playlist_from_matches(
2481 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2482
2483 matches = DailymotionIE._extract_urls(webpage)
2484 if matches:
2485 return self.playlist_from_matches(matches, video_id, video_title)
2486
2487 # Look for embedded Dailymotion playlist player (#3822)
2488 m = re.search(
2489 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2490 if m:
2491 playlists = re.findall(
2492 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2493 if playlists:
2494 return self.playlist_from_matches(
2495 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2496
2497 # Look for DailyMail embeds
2498 dailymail_urls = DailyMailIE._extract_urls(webpage)
2499 if dailymail_urls:
2500 return self.playlist_from_matches(
2501 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2502
2503 # Look for embedded Wistia player
2504 wistia_url = WistiaIE._extract_url(webpage)
2505 if wistia_url:
2506 return {
2507 '_type': 'url_transparent',
2508 'url': self._proto_relative_url(wistia_url),
2509 'ie_key': WistiaIE.ie_key(),
2510 'uploader': video_uploader,
2511 }
2512
2513 # Look for SVT player
2514 svt_url = SVTIE._extract_url(webpage)
2515 if svt_url:
2516 return self.url_result(svt_url, 'SVT')
2517
2518 # Look for Bandcamp pages with custom domain
2519 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2520 if mobj is not None:
2521 burl = unescapeHTML(mobj.group(1))
2522 # Don't set the extractor because it can be a track url or an album
2523 return self.url_result(burl)
2524
2525 # Look for embedded Vevo player
2526 mobj = re.search(
2527 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2528 if mobj is not None:
2529 return self.url_result(mobj.group('url'))
2530
2531 # Look for embedded Viddler player
2532 mobj = re.search(
2533 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2534 webpage)
2535 if mobj is not None:
2536 return self.url_result(mobj.group('url'))
2537
2538 # Look for NYTimes player
2539 mobj = re.search(
2540 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2541 webpage)
2542 if mobj is not None:
2543 return self.url_result(mobj.group('url'))
2544
2545 # Look for Libsyn player
2546 mobj = re.search(
2547 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2548 if mobj is not None:
2549 return self.url_result(mobj.group('url'))
2550
2551 # Look for Ooyala videos
2552 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2553 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2554 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2555 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2556 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2557 if mobj is not None:
2558 embed_token = self._search_regex(
2559 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2560 webpage, 'ooyala embed token', default=None)
2561 return OoyalaIE._build_url_result(smuggle_url(
2562 mobj.group('ec'), {
2563 'domain': url,
2564 'embed_token': embed_token,
2565 }))
2566
2567 # Look for multiple Ooyala embeds on SBN network websites
2568 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2569 if mobj is not None:
2570 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2571 if embeds:
2572 return self.playlist_from_matches(
2573 embeds, video_id, video_title,
2574 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2575
2576 # Look for Aparat videos
2577 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2578 if mobj is not None:
2579 return self.url_result(mobj.group(1), 'Aparat')
2580
2581 # Look for MPORA videos
2582 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2583 if mobj is not None:
2584 return self.url_result(mobj.group(1), 'Mpora')
2585
2586 # Look for embedded NovaMov-based player
2587 mobj = re.search(
2588 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2589 (?P<url>http://(?:(?:embed|www)\.)?
2590 (?:novamov\.com|
2591 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2592 videoweed\.(?:es|com)|
2593 movshare\.(?:net|sx|ag)|
2594 divxstage\.(?:eu|net|ch|co|at|ag))
2595 /embed\.php.+?)\1''', webpage)
2596 if mobj is not None:
2597 return self.url_result(mobj.group('url'))
2598
2599 # Look for embedded Facebook player
2600 facebook_urls = FacebookIE._extract_urls(webpage)
2601 if facebook_urls:
2602 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2603
2604 # Look for embedded VK player
2605 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2606 if mobj is not None:
2607 return self.url_result(mobj.group('url'), 'VK')
2608
2609 # Look for embedded Odnoklassniki player
2610 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2611 if mobj is not None:
2612 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2613
2614 # Look for embedded ivi player
2615 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2616 if mobj is not None:
2617 return self.url_result(mobj.group('url'), 'Ivi')
2618
2619 # Look for embedded Huffington Post player
2620 mobj = re.search(
2621 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2622 if mobj is not None:
2623 return self.url_result(mobj.group('url'), 'HuffPost')
2624
2625 # Look for embed.ly
2626 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2627 if mobj is not None:
2628 return self.url_result(mobj.group('url'))
2629 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2630 if mobj is not None:
2631 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2632
2633 # Look for funnyordie embed
2634 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2635 if matches:
2636 return self.playlist_from_matches(
2637 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2638
2639 # Look for BBC iPlayer embed
2640 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2641 if matches:
2642 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2643
2644 # Look for embedded RUTV player
2645 rutv_url = RUTVIE._extract_url(webpage)
2646 if rutv_url:
2647 return self.url_result(rutv_url, 'RUTV')
2648
2649 # Look for embedded TVC player
2650 tvc_url = TVCIE._extract_url(webpage)
2651 if tvc_url:
2652 return self.url_result(tvc_url, 'TVC')
2653
2654 # Look for embedded SportBox player
2655 sportbox_urls = SportBoxIE._extract_urls(webpage)
2656 if sportbox_urls:
2657 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
2658
2659 # Look for embedded XHamster player
2660 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2661 if xhamster_urls:
2662 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2663
2664 # Look for embedded TNAFlixNetwork player
2665 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2666 if tnaflix_urls:
2667 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2668
2669 # Look for embedded PornHub player
2670 pornhub_urls = PornHubIE._extract_urls(webpage)
2671 if pornhub_urls:
2672 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2673
2674 # Look for embedded DrTuber player
2675 drtuber_urls = DrTuberIE._extract_urls(webpage)
2676 if drtuber_urls:
2677 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2678
2679 # Look for embedded RedTube player
2680 redtube_urls = RedTubeIE._extract_urls(webpage)
2681 if redtube_urls:
2682 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2683
2684 # Look for embedded Tube8 player
2685 tube8_urls = Tube8IE._extract_urls(webpage)
2686 if tube8_urls:
2687 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2688
2689 # Look for embedded Tvigle player
2690 mobj = re.search(
2691 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2692 if mobj is not None:
2693 return self.url_result(mobj.group('url'), 'Tvigle')
2694
2695 # Look for embedded TED player
2696 mobj = re.search(
2697 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2698 if mobj is not None:
2699 return self.url_result(mobj.group('url'), 'TED')
2700
2701 # Look for embedded Ustream videos
2702 ustream_url = UstreamIE._extract_url(webpage)
2703 if ustream_url:
2704 return self.url_result(ustream_url, UstreamIE.ie_key())
2705
2706 # Look for embedded arte.tv player
2707 mobj = re.search(
2708 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2709 webpage)
2710 if mobj is not None:
2711 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2712
2713 # Look for embedded francetv player
2714 mobj = re.search(
2715 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2716 webpage)
2717 if mobj is not None:
2718 return self.url_result(mobj.group('url'))
2719
2720 # Look for embedded smotri.com player
2721 smotri_url = SmotriIE._extract_url(webpage)
2722 if smotri_url:
2723 return self.url_result(smotri_url, 'Smotri')
2724
2725 # Look for embedded Myvi.ru player
2726 myvi_url = MyviIE._extract_url(webpage)
2727 if myvi_url:
2728 return self.url_result(myvi_url)
2729
2730 # Look for embedded soundcloud player
2731 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2732 if soundcloud_urls:
2733 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2734
2735 # Look for tunein player
2736 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2737 if tunein_urls:
2738 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2739
2740 # Look for embedded mtvservices player
2741 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2742 if mtvservices_url:
2743 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2744
2745 # Look for embedded yahoo player
2746 mobj = re.search(
2747 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2748 webpage)
2749 if mobj is not None:
2750 return self.url_result(mobj.group('url'), 'Yahoo')
2751
2752 # Look for embedded sbs.com.au player
2753 mobj = re.search(
2754 r'''(?x)
2755 (?:
2756 <meta\s+property="og:video"\s+content=|
2757 <iframe[^>]+?src=
2758 )
2759 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2760 webpage)
2761 if mobj is not None:
2762 return self.url_result(mobj.group('url'), 'SBS')
2763
2764 # Look for embedded Cinchcast player
2765 mobj = re.search(
2766 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2767 webpage)
2768 if mobj is not None:
2769 return self.url_result(mobj.group('url'), 'Cinchcast')
2770
2771 mobj = re.search(
2772 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2773 webpage)
2774 if not mobj:
2775 mobj = re.search(
2776 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2777 webpage)
2778 if mobj is not None:
2779 return self.url_result(mobj.group('url'), 'MLB')
2780
2781 mobj = re.search(
2782 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2783 webpage)
2784 if mobj is not None:
2785 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2786
2787 mobj = re.search(
2788 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2789 webpage)
2790 if mobj is not None:
2791 return self.url_result(mobj.group('url'), 'Livestream')
2792
2793 # Look for Zapiks embed
2794 mobj = re.search(
2795 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2796 if mobj is not None:
2797 return self.url_result(mobj.group('url'), 'Zapiks')
2798
2799 # Look for Kaltura embeds
2800 kaltura_url = KalturaIE._extract_url(webpage)
2801 if kaltura_url:
2802 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2803
2804 # Look for EaglePlatform embeds
2805 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2806 if eagleplatform_url:
2807 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2808
2809 # Look for ClipYou (uses EaglePlatform) embeds
2810 mobj = re.search(
2811 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2812 if mobj is not None:
2813 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2814
2815 # Look for Pladform embeds
2816 pladform_url = PladformIE._extract_url(webpage)
2817 if pladform_url:
2818 return self.url_result(pladform_url)
2819
2820 # Look for Videomore embeds
2821 videomore_url = VideomoreIE._extract_url(webpage)
2822 if videomore_url:
2823 return self.url_result(videomore_url)
2824
2825 # Look for Webcaster embeds
2826 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2827 if webcaster_url:
2828 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2829
2830 # Look for Playwire embeds
2831 mobj = re.search(
2832 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2833 if mobj is not None:
2834 return self.url_result(mobj.group('url'))
2835
2836 # Look for 5min embeds
2837 mobj = re.search(
2838 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2839 if mobj is not None:
2840 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2841
2842 # Look for Crooks and Liars embeds
2843 mobj = re.search(
2844 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2845 if mobj is not None:
2846 return self.url_result(mobj.group('url'))
2847
2848 # Look for NBC Sports VPlayer embeds
2849 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2850 if nbc_sports_url:
2851 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2852
2853 # Look for NBC News embeds
2854 nbc_news_embed_url = re.search(
2855 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2856 if nbc_news_embed_url:
2857 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2858
2859 # Look for Google Drive embeds
2860 google_drive_url = GoogleDriveIE._extract_url(webpage)
2861 if google_drive_url:
2862 return self.url_result(google_drive_url, 'GoogleDrive')
2863
2864 # Look for UDN embeds
2865 mobj = re.search(
2866 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2867 if mobj is not None:
2868 return self.url_result(
2869 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2870
2871 # Look for Senate ISVP iframe
2872 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2873 if senate_isvp_url:
2874 return self.url_result(senate_isvp_url, 'SenateISVP')
2875
2876 # Look for OnionStudios embeds
2877 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2878 if onionstudios_url:
2879 return self.url_result(onionstudios_url)
2880
2881 # Look for ViewLift embeds
2882 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2883 if viewlift_url:
2884 return self.url_result(viewlift_url)
2885
2886 # Look for JWPlatform embeds
2887 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2888 if jwplatform_urls:
2889 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2890
2891 # Look for Digiteka embeds
2892 digiteka_url = DigitekaIE._extract_url(webpage)
2893 if digiteka_url:
2894 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2895
2896 # Look for Arkena embeds
2897 arkena_url = ArkenaIE._extract_url(webpage)
2898 if arkena_url:
2899 return self.url_result(arkena_url, ArkenaIE.ie_key())
2900
2901 # Look for Piksel embeds
2902 piksel_url = PikselIE._extract_url(webpage)
2903 if piksel_url:
2904 return self.url_result(piksel_url, PikselIE.ie_key())
2905
2906 # Look for Limelight embeds
2907 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2908 if limelight_urls:
2909 return self.playlist_result(
2910 limelight_urls, video_id, video_title, video_description)
2911
2912 # Look for Anvato embeds
2913 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2914 if anvato_urls:
2915 return self.playlist_result(
2916 anvato_urls, video_id, video_title, video_description)
2917
2918 # Look for AdobeTVVideo embeds
2919 mobj = re.search(
2920 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2921 webpage)
2922 if mobj is not None:
2923 return self.url_result(
2924 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2925 'AdobeTVVideo')
2926
2927 # Look for Vine embeds
2928 mobj = re.search(
2929 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2930 webpage)
2931 if mobj is not None:
2932 return self.url_result(
2933 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2934
2935 # Look for VODPlatform embeds
2936 mobj = re.search(
2937 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2938 webpage)
2939 if mobj is not None:
2940 return self.url_result(
2941 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2942
2943 # Look for Mangomolo embeds
2944 mobj = re.search(
2945 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2946 (?:
2947 video\?.*?\bid=(?P<video_id>\d+)|
2948 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2949 ).+?)\1''', webpage)
2950 if mobj is not None:
2951 info = {
2952 '_type': 'url_transparent',
2953 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2954 'title': video_title,
2955 'description': video_description,
2956 'thumbnail': video_thumbnail,
2957 'uploader': video_uploader,
2958 }
2959 video_id = mobj.group('video_id')
2960 if video_id:
2961 info.update({
2962 'ie_key': 'MangomoloVideo',
2963 'id': video_id,
2964 })
2965 else:
2966 info.update({
2967 'ie_key': 'MangomoloLive',
2968 'id': mobj.group('channel_id'),
2969 })
2970 return info
2971
2972 # Look for Instagram embeds
2973 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2974 if instagram_embed_url is not None:
2975 return self.url_result(
2976 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2977
2978 # Look for LiveLeak embeds
2979 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2980 if liveleak_urls:
2981 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2982
2983 # Look for 3Q SDN embeds
2984 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2985 if threeqsdn_url:
2986 return {
2987 '_type': 'url_transparent',
2988 'ie_key': ThreeQSDNIE.ie_key(),
2989 'url': self._proto_relative_url(threeqsdn_url),
2990 'title': video_title,
2991 'description': video_description,
2992 'thumbnail': video_thumbnail,
2993 'uploader': video_uploader,
2994 }
2995
2996 # Look for VBOX7 embeds
2997 vbox7_url = Vbox7IE._extract_url(webpage)
2998 if vbox7_url:
2999 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3000
3001 # Look for DBTV embeds
3002 dbtv_urls = DBTVIE._extract_urls(webpage)
3003 if dbtv_urls:
3004 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
3005
3006 # Look for Videa embeds
3007 videa_urls = VideaIE._extract_urls(webpage)
3008 if videa_urls:
3009 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
3010
3011 # Look for 20 minuten embeds
3012 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3013 if twentymin_urls:
3014 return self.playlist_from_matches(
3015 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
3016
3017 # Look for Openload embeds
3018 openload_urls = OpenloadIE._extract_urls(webpage)
3019 if openload_urls:
3020 return self.playlist_from_matches(
3021 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
3022
3023 # Look for Verystream embeds
3024 verystream_urls = VerystreamIE._extract_urls(webpage)
3025 if verystream_urls:
3026 return self.playlist_from_matches(
3027 verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key())
3028
3029 # Look for VideoPress embeds
3030 videopress_urls = VideoPressIE._extract_urls(webpage)
3031 if videopress_urls:
3032 return self.playlist_from_matches(
3033 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
3034
3035 # Look for Rutube embeds
3036 rutube_urls = RutubeIE._extract_urls(webpage)
3037 if rutube_urls:
3038 return self.playlist_from_matches(
3039 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
3040
3041 # Look for WashingtonPost embeds
3042 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3043 if wapo_urls:
3044 return self.playlist_from_matches(
3045 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3046
3047 # Look for Mediaset embeds
3048 mediaset_urls = MediasetIE._extract_urls(self, webpage)
3049 if mediaset_urls:
3050 return self.playlist_from_matches(
3051 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3052
3053 # Look for JOJ.sk embeds
3054 joj_urls = JojIE._extract_urls(webpage)
3055 if joj_urls:
3056 return self.playlist_from_matches(
3057 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3058
3059 # Look for megaphone.fm embeds
3060 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3061 if mpfn_urls:
3062 return self.playlist_from_matches(
3063 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3064
3065 # Look for vzaar embeds
3066 vzaar_urls = VzaarIE._extract_urls(webpage)
3067 if vzaar_urls:
3068 return self.playlist_from_matches(
3069 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3070
3071 channel9_urls = Channel9IE._extract_urls(webpage)
3072 if channel9_urls:
3073 return self.playlist_from_matches(
3074 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3075
3076 vshare_urls = VShareIE._extract_urls(webpage)
3077 if vshare_urls:
3078 return self.playlist_from_matches(
3079 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3080
3081 # Look for Mediasite embeds
3082 mediasite_urls = MediasiteIE._extract_urls(webpage)
3083 if mediasite_urls:
3084 entries = [
3085 self.url_result(smuggle_url(
3086 compat_urlparse.urljoin(url, mediasite_url),
3087 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3088 for mediasite_url in mediasite_urls]
3089 return self.playlist_result(entries, video_id, video_title)
3090
3091 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3092 if springboardplatform_urls:
3093 return self.playlist_from_matches(
3094 springboardplatform_urls, video_id, video_title,
3095 ie=SpringboardPlatformIE.ie_key())
3096
3097 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3098 if yapfiles_urls:
3099 return self.playlist_from_matches(
3100 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3101
3102 vice_urls = ViceIE._extract_urls(webpage)
3103 if vice_urls:
3104 return self.playlist_from_matches(
3105 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3106
3107 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3108 if xfileshare_urls:
3109 return self.playlist_from_matches(
3110 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3111
3112 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3113 if cloudflarestream_urls:
3114 return self.playlist_from_matches(
3115 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3116
3117 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
3118 if peertube_urls:
3119 return self.playlist_from_matches(
3120 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3121
3122 teachable_url = TeachableIE._extract_url(webpage, url)
3123 if teachable_url:
3124 return self.url_result(teachable_url)
3125
3126 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3127 if indavideo_urls:
3128 return self.playlist_from_matches(
3129 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3130
3131 apa_urls = APAIE._extract_urls(webpage)
3132 if apa_urls:
3133 return self.playlist_from_matches(
3134 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3135
3136 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3137 if foxnews_urls:
3138 return self.playlist_from_matches(
3139 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3140
3141 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
3142 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3143 webpage)]
3144 if sharevideos_urls:
3145 return self.playlist_from_matches(
3146 sharevideos_urls, video_id, video_title)
3147
3148 viqeo_urls = ViqeoIE._extract_urls(webpage)
3149 if viqeo_urls:
3150 return self.playlist_from_matches(
3151 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
3152
3153 expressen_urls = ExpressenIE._extract_urls(webpage)
3154 if expressen_urls:
3155 return self.playlist_from_matches(
3156 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
3157
3158 zype_urls = ZypeIE._extract_urls(webpage)
3159 if zype_urls:
3160 return self.playlist_from_matches(
3161 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3162
3163 # Look for HTML5 media
3164 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3165 if entries:
3166 if len(entries) == 1:
3167 entries[0].update({
3168 'id': video_id,
3169 'title': video_title,
3170 })
3171 else:
3172 for num, entry in enumerate(entries, start=1):
3173 entry.update({
3174 'id': '%s-%s' % (video_id, num),
3175 'title': '%s (%d)' % (video_title, num),
3176 })
3177 for entry in entries:
3178 self._sort_formats(entry['formats'])
3179 return self.playlist_result(entries, video_id, video_title)
3180
3181 jwplayer_data = self._find_jwplayer_data(
3182 webpage, video_id, transform_source=js_to_json)
3183 if jwplayer_data:
3184 try:
3185 info = self._parse_jwplayer_data(
3186 jwplayer_data, video_id, require_title=False, base_url=url)
3187 return merge_dicts(info, info_dict)
3188 except ExtractorError:
3189 # See https://github.com/ytdl-org/youtube-dl/pull/16735
3190 pass
3191
3192 # Video.js embed
3193 mobj = re.search(
3194 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3195 webpage)
3196 if mobj is not None:
3197 sources = self._parse_json(
3198 mobj.group(1), video_id, transform_source=js_to_json,
3199 fatal=False) or []
3200 if not isinstance(sources, list):
3201 sources = [sources]
3202 formats = []
3203 for source in sources:
3204 src = source.get('src')
3205 if not src or not isinstance(src, compat_str):
3206 continue
3207 src = compat_urlparse.urljoin(url, src)
3208 src_type = source.get('type')
3209 if isinstance(src_type, compat_str):
3210 src_type = src_type.lower()
3211 ext = determine_ext(src).lower()
3212 if src_type == 'video/youtube':
3213 return self.url_result(src, YoutubeIE.ie_key())
3214 if src_type == 'application/dash+xml' or ext == 'mpd':
3215 formats.extend(self._extract_mpd_formats(
3216 src, video_id, mpd_id='dash', fatal=False))
3217 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3218 formats.extend(self._extract_m3u8_formats(
3219 src, video_id, 'mp4', entry_protocol='m3u8_native',
3220 m3u8_id='hls', fatal=False))
3221 else:
3222 formats.append({
3223 'url': src,
3224 'ext': (mimetype2ext(src_type) or
3225 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3226 })
3227 if formats:
3228 self._sort_formats(formats)
3229 info_dict['formats'] = formats
3230 return info_dict
3231
3232 # Looking for http://schema.org/VideoObject
3233 json_ld = self._search_json_ld(
3234 webpage, video_id, default={}, expected_type='VideoObject')
3235 if json_ld.get('url'):
3236 return merge_dicts(json_ld, info_dict)
3237
3238 def check_video(vurl):
3239 if YoutubeIE.suitable(vurl):
3240 return True
3241 if RtmpIE.suitable(vurl):
3242 return True
3243 vpath = compat_urlparse.urlparse(vurl).path
3244 vext = determine_ext(vpath)
3245 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3246
3247 def filter_video(urls):
3248 return list(filter(check_video, urls))
3249
3250 # Start with something easy: JW Player in SWFObject
3251 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3252 if not found:
3253 # Look for gorilla-vid style embedding
3254 found = filter_video(re.findall(r'''(?sx)
3255 (?:
3256 jw_plugins|
3257 JWPlayerOptions|
3258 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3259 )
3260 .*?
3261 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3262 if not found:
3263 # Broaden the search a little bit
3264 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3265 if not found:
3266 # Broaden the findall a little bit: JWPlayer JS loader
3267 found = filter_video(re.findall(
3268 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3269 if not found:
3270 # Flow player
3271 found = filter_video(re.findall(r'''(?xs)
3272 flowplayer\("[^"]+",\s*
3273 \{[^}]+?\}\s*,
3274 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3275 ["']?url["']?\s*:\s*["']([^"']+)["']
3276 ''', webpage))
3277 if not found:
3278 # Cinerama player
3279 found = re.findall(
3280 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3281 if not found:
3282 # Try to find twitter cards info
3283 # twitter:player:stream should be checked before twitter:player since
3284 # it is expected to contain a raw stream (see
3285 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3286 found = filter_video(re.findall(
3287 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3288 if not found:
3289 # We look for Open Graph info:
3290 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3291 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3292 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3293 if m_video_type is not None:
3294 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3295 if not found:
3296 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3297 found = re.search(
3298 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3299 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3300 webpage)
3301 if not found:
3302 # Look also in Refresh HTTP header
3303 refresh_header = head_response.headers.get('Refresh')
3304 if refresh_header:
3305 # In python 2 response HTTP headers are bytestrings
3306 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3307 refresh_header = refresh_header.decode('iso-8859-1')
3308 found = re.search(REDIRECT_REGEX, refresh_header)
3309 if found:
3310 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3311 if new_url != url:
3312 self.report_following_redirect(new_url)
3313 return {
3314 '_type': 'url',
3315 'url': new_url,
3316 }
3317 else:
3318 found = None
3319
3320 if not found:
3321 # twitter:player is a https URL to iframe player that may or may not
3322 # be supported by youtube-dl thus this is checked the very last (see
3323 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3324 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3325 if embed_url and embed_url != url:
3326 return self.url_result(embed_url)
3327
3328 if not found:
3329 raise UnsupportedError(url)
3330
3331 entries = []
3332 for video_url in orderedSet(found):
3333 video_url = unescapeHTML(video_url)
3334 video_url = video_url.replace('\\/', '/')
3335 video_url = compat_urlparse.urljoin(url, video_url)
3336 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3337
3338 # Sometimes, jwplayer extraction will result in a YouTube URL
3339 if YoutubeIE.suitable(video_url):
3340 entries.append(self.url_result(video_url, 'Youtube'))
3341 continue
3342
3343 # here's a fun little line of code for you:
3344 video_id = os.path.splitext(video_id)[0]
3345
3346 entry_info_dict = {
3347 'id': video_id,
3348 'uploader': video_uploader,
3349 'title': video_title,
3350 'age_limit': age_limit,
3351 }
3352
3353 if RtmpIE.suitable(video_url):
3354 entry_info_dict.update({
3355 '_type': 'url_transparent',
3356 'ie_key': RtmpIE.ie_key(),
3357 'url': video_url,
3358 })
3359 entries.append(entry_info_dict)
3360 continue
3361
3362 ext = determine_ext(video_url)
3363 if ext == 'smil':
3364 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3365 elif ext == 'xspf':
3366 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3367 elif ext == 'm3u8':
3368 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3369 elif ext == 'mpd':
3370 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3371 elif ext == 'f4m':
3372 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3373 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3374 # Just matching .ism/manifest is not enough to be reliably sure
3375 # whether it's actually an ISM manifest or some other streaming
3376 # manifest since there are various streaming URL formats
3377 # possible (see [1]) as well as some other shenanigans like
3378 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3379 # so on.
3380 # Thus the most reasonable way to solve this is to delegate
3381 # to generic extractor in order to look into the contents of
3382 # the manifest itself.
3383 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3384 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3385 entry_info_dict = self.url_result(
3386 smuggle_url(video_url, {'to_generic': True}),
3387 GenericIE.ie_key())
3388 else:
3389 entry_info_dict['url'] = video_url
3390
3391 if entry_info_dict.get('formats'):
3392 self._sort_formats(entry_info_dict['formats'])
3393
3394 entries.append(entry_info_dict)
3395
3396 if len(entries) == 1:
3397 return entries[0]
3398 else:
3399 for num, e in enumerate(entries, start=1):
3400 # 'url' results don't have a title
3401 if e.get('title') is not None:
3402 e['title'] = '%s (%d)' % (e['title'], num)
3403 return {
3404 '_type': 'playlist',
3405 'entries': entries,
3406 }