]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[mediasite] Add extractor, subsume sandia and collegerama extractors
[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 mimetype2ext,
27 orderedSet,
28 sanitized_Request,
29 smuggle_url,
30 unescapeHTML,
31 unified_strdate,
32 unsmuggle_url,
33 UnsupportedError,
34 xpath_text,
35 )
36 from .commonprotocols import RtmpIE
37 from .brightcove import (
38 BrightcoveLegacyIE,
39 BrightcoveNewIE,
40 )
41 from .nexx import (
42 NexxIE,
43 NexxEmbedIE,
44 )
45 from .nbc import NBCSportsVPlayerIE
46 from .ooyala import OoyalaIE
47 from .rutv import RUTVIE
48 from .tvc import TVCIE
49 from .sportbox import SportBoxEmbedIE
50 from .smotri import SmotriIE
51 from .myvi import MyviIE
52 from .condenast import CondeNastIE
53 from .udn import UDNEmbedIE
54 from .senateisvp import SenateISVPIE
55 from .svt import SVTIE
56 from .pornhub import PornHubIE
57 from .xhamster import XHamsterEmbedIE
58 from .tnaflix import TNAFlixNetworkEmbedIE
59 from .drtuber import DrTuberIE
60 from .redtube import RedTubeIE
61 from .vimeo import VimeoIE
62 from .dailymotion import DailymotionIE
63 from .dailymail import DailyMailIE
64 from .onionstudios import OnionStudiosIE
65 from .viewlift import ViewLiftEmbedIE
66 from .mtv import MTVServicesEmbeddedIE
67 from .pladform import PladformIE
68 from .videomore import VideomoreIE
69 from .webcaster import WebcasterFeedIE
70 from .googledrive import GoogleDriveIE
71 from .jwplatform import JWPlatformIE
72 from .digiteka import DigitekaIE
73 from .arkena import ArkenaIE
74 from .instagram import InstagramIE
75 from .liveleak import LiveLeakIE
76 from .threeqsdn import ThreeQSDNIE
77 from .theplatform import ThePlatformIE
78 from .vessel import VesselIE
79 from .kaltura import KalturaIE
80 from .eagleplatform import EaglePlatformIE
81 from .facebook import FacebookIE
82 from .soundcloud import SoundcloudIE
83 from .tunein import TuneInBaseIE
84 from .vbox7 import Vbox7IE
85 from .dbtv import DBTVIE
86 from .piksel import PikselIE
87 from .videa import VideaIE
88 from .twentymin import TwentyMinutenIE
89 from .ustream import UstreamIE
90 from .openload import OpenloadIE
91 from .videopress import VideoPressIE
92 from .rutube import RutubeIE
93 from .limelight import LimelightBaseIE
94 from .anvato import AnvatoIE
95 from .washingtonpost import WashingtonPostIE
96 from .wistia import WistiaIE
97 from .mediaset import MediasetIE
98 from .joj import JojIE
99 from .megaphone import MegaphoneIE
100 from .vzaar import VzaarIE
101 from .channel9 import Channel9IE
102 from .vshare import VShareIE
103
104
105 class GenericIE(InfoExtractor):
106 IE_DESC = 'Generic downloader that works on some sites'
107 _VALID_URL = r'.*'
108 IE_NAME = 'generic'
109 _TESTS = [
110 # Direct link to a video
111 {
112 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
113 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
114 'info_dict': {
115 'id': 'trailer',
116 'ext': 'mp4',
117 'title': 'trailer',
118 'upload_date': '20100513',
119 }
120 },
121 # Direct link to media delivered compressed (until Accept-Encoding is *)
122 {
123 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
124 'md5': '128c42e68b13950268b648275386fc74',
125 'info_dict': {
126 'id': 'FictionJunction-Parallel_Hearts',
127 'ext': 'flac',
128 'title': 'FictionJunction-Parallel_Hearts',
129 'upload_date': '20140522',
130 },
131 'expected_warnings': [
132 'URL could be a direct video link, returning it as such.'
133 ],
134 'skip': 'URL invalid',
135 },
136 # Direct download with broken HEAD
137 {
138 'url': 'http://ai-radio.org:8000/radio.opus',
139 'info_dict': {
140 'id': 'radio',
141 'ext': 'opus',
142 'title': 'radio',
143 },
144 'params': {
145 'skip_download': True, # infinite live stream
146 },
147 'expected_warnings': [
148 r'501.*Not Implemented',
149 r'400.*Bad Request',
150 ],
151 },
152 # Direct link with incorrect MIME type
153 {
154 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
155 'md5': '4ccbebe5f36706d85221f204d7eb5913',
156 'info_dict': {
157 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
158 'id': '5_Lennart_Poettering_-_Systemd',
159 'ext': 'webm',
160 'title': '5_Lennart_Poettering_-_Systemd',
161 'upload_date': '20141120',
162 },
163 'expected_warnings': [
164 'URL could be a direct video link, returning it as such.'
165 ]
166 },
167 # RSS feed
168 {
169 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
170 'info_dict': {
171 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
172 'title': 'Zero Punctuation',
173 'description': 're:.*groundbreaking video review series.*'
174 },
175 'playlist_mincount': 11,
176 },
177 # RSS feed with enclosure
178 {
179 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
180 'info_dict': {
181 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
182 'ext': 'm4v',
183 'upload_date': '20150228',
184 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
185 }
186 },
187 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
188 {
189 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
190 'info_dict': {
191 'id': 'smil',
192 'ext': 'mp4',
193 'title': 'Automatics, robotics and biocybernetics',
194 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
195 'upload_date': '20130627',
196 'formats': 'mincount:16',
197 'subtitles': 'mincount:1',
198 },
199 'params': {
200 'force_generic_extractor': True,
201 'skip_download': True,
202 },
203 },
204 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
205 {
206 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
207 'info_dict': {
208 'id': 'hds',
209 'ext': 'flv',
210 'title': 'hds',
211 'formats': 'mincount:1',
212 },
213 'params': {
214 'skip_download': True,
215 },
216 },
217 # SMIL from https://www.restudy.dk/video/play/id/1637
218 {
219 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
220 'info_dict': {
221 'id': 'video_1637',
222 'ext': 'flv',
223 'title': 'video_1637',
224 'formats': 'mincount:3',
225 },
226 'params': {
227 'skip_download': True,
228 },
229 },
230 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
231 {
232 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
233 'info_dict': {
234 'id': 'smil-service',
235 'ext': 'flv',
236 'title': 'smil-service',
237 'formats': 'mincount:1',
238 },
239 'params': {
240 'skip_download': True,
241 },
242 },
243 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
244 {
245 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
246 'info_dict': {
247 'id': '4719370',
248 'ext': 'mp4',
249 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
250 'formats': 'mincount:3',
251 },
252 'params': {
253 'skip_download': True,
254 },
255 },
256 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
257 {
258 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
259 'info_dict': {
260 'id': 'mZlp2ctYIUEB',
261 'ext': 'mp4',
262 'title': 'Tikibad ontruimd wegens brand',
263 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
264 'thumbnail': r're:^https?://.*\.jpg$',
265 'duration': 33,
266 },
267 'params': {
268 'skip_download': True,
269 },
270 },
271 # MPD from http://dash-mse-test.appspot.com/media.html
272 {
273 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
274 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
275 'info_dict': {
276 'id': 'car-20120827-manifest',
277 'ext': 'mp4',
278 'title': 'car-20120827-manifest',
279 'formats': 'mincount:9',
280 'upload_date': '20130904',
281 },
282 'params': {
283 'format': 'bestvideo',
284 },
285 },
286 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
287 {
288 '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',
289 'info_dict': {
290 'id': 'content',
291 'ext': 'mp4',
292 'title': 'content',
293 'formats': 'mincount:8',
294 },
295 'params': {
296 # m3u8 downloads
297 'skip_download': True,
298 },
299 'skip': 'video gone',
300 },
301 # m3u8 served with Content-Type: text/plain
302 {
303 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
304 'info_dict': {
305 'id': 'index',
306 'ext': 'mp4',
307 'title': 'index',
308 'upload_date': '20140720',
309 'formats': 'mincount:11',
310 },
311 'params': {
312 # m3u8 downloads
313 'skip_download': True,
314 },
315 'skip': 'video gone',
316 },
317 # google redirect
318 {
319 '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',
320 'info_dict': {
321 'id': 'cmQHVoWB5FY',
322 'ext': 'mp4',
323 'upload_date': '20130224',
324 'uploader_id': 'TheVerge',
325 'description': r're:^Chris Ziegler takes a look at the\.*',
326 'uploader': 'The Verge',
327 'title': 'First Firefox OS phones side-by-side',
328 },
329 'params': {
330 'skip_download': False,
331 }
332 },
333 {
334 # redirect in Refresh HTTP header
335 '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',
336 'info_dict': {
337 'id': 'pO8h3EaFRdo',
338 'ext': 'mp4',
339 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
340 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
341 'upload_date': '20150917',
342 'uploader_id': 'brtvofficial',
343 'uploader': 'Boiler Room',
344 },
345 'params': {
346 'skip_download': False,
347 },
348 },
349 {
350 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
351 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
352 'info_dict': {
353 'id': '13601338388002',
354 'ext': 'mp4',
355 'uploader': 'www.hodiho.fr',
356 'title': 'R\u00e9gis plante sa Jeep',
357 }
358 },
359 # bandcamp page with custom domain
360 {
361 'add_ie': ['Bandcamp'],
362 'url': 'http://bronyrock.com/track/the-pony-mash',
363 'info_dict': {
364 'id': '3235767654',
365 'ext': 'mp3',
366 'title': 'The Pony Mash',
367 'uploader': 'M_Pallante',
368 },
369 'skip': 'There is a limit of 200 free downloads / month for the test song',
370 },
371 {
372 # embedded brightcove video
373 # it also tests brightcove videos that need to set the 'Referer'
374 # in the http requests
375 'add_ie': ['BrightcoveLegacy'],
376 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
377 'info_dict': {
378 'id': '2765128793001',
379 'ext': 'mp4',
380 'title': 'Le cours de bourse : l’analyse technique',
381 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
382 'uploader': 'BFM BUSINESS',
383 },
384 'params': {
385 'skip_download': True,
386 },
387 },
388 {
389 # embedded with itemprop embedURL and video id spelled as `idVideo`
390 'add_id': ['BrightcoveLegacy'],
391 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
392 'info_dict': {
393 'id': '5255628253001',
394 'ext': 'mp4',
395 'title': 'md5:37c519b1128915607601e75a87995fc0',
396 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
397 'uploader': 'BFM BUSINESS',
398 'uploader_id': '876450612001',
399 'timestamp': 1482255315,
400 'upload_date': '20161220',
401 },
402 'params': {
403 'skip_download': True,
404 },
405 },
406 {
407 # https://github.com/rg3/youtube-dl/issues/2253
408 'url': 'http://bcove.me/i6nfkrc3',
409 'md5': '0ba9446db037002366bab3b3eb30c88c',
410 'info_dict': {
411 'id': '3101154703001',
412 'ext': 'mp4',
413 'title': 'Still no power',
414 'uploader': 'thestar.com',
415 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
416 },
417 'add_ie': ['BrightcoveLegacy'],
418 'skip': 'video gone',
419 },
420 {
421 'url': 'http://www.championat.com/video/football/v/87/87499.html',
422 'md5': 'fb973ecf6e4a78a67453647444222983',
423 'info_dict': {
424 'id': '3414141473001',
425 'ext': 'mp4',
426 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
427 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
428 'uploader': 'Championat',
429 },
430 },
431 {
432 # https://github.com/rg3/youtube-dl/issues/3541
433 'add_ie': ['BrightcoveLegacy'],
434 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
435 'info_dict': {
436 'id': '3866516442001',
437 'ext': 'mp4',
438 'title': 'Leer mij vrouwen kennen: Aflevering 1',
439 'description': 'Leer mij vrouwen kennen: Aflevering 1',
440 'uploader': 'SBS Broadcasting',
441 },
442 'skip': 'Restricted to Netherlands',
443 'params': {
444 'skip_download': True, # m3u8 download
445 },
446 },
447 {
448 # Brightcove video in <iframe>
449 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
450 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
451 'info_dict': {
452 'id': '5360463607001',
453 'ext': 'mp4',
454 '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',
455 '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。',
456 'uploader': 'United Nations',
457 'uploader_id': '1362235914001',
458 'timestamp': 1489593889,
459 'upload_date': '20170315',
460 },
461 'add_ie': ['BrightcoveLegacy'],
462 },
463 {
464 # Brightcove with alternative playerID key
465 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
466 'info_dict': {
467 'id': 'nmeth.2062_SV1',
468 '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',
469 },
470 'playlist': [{
471 'info_dict': {
472 'id': '2228375078001',
473 'ext': 'mp4',
474 'title': 'nmeth.2062-sv1',
475 'description': 'nmeth.2062-sv1',
476 'timestamp': 1363357591,
477 'upload_date': '20130315',
478 'uploader': 'Nature Publishing Group',
479 'uploader_id': '1964492299001',
480 },
481 }],
482 },
483 {
484 # Brightcove with UUID in videoPlayer
485 'url': 'http://www8.hp.com/cn/zh/home.html',
486 'info_dict': {
487 'id': '5255815316001',
488 'ext': 'mp4',
489 'title': 'Sprocket Video - China',
490 'description': 'Sprocket Video - China',
491 'uploader': 'HP-Video Gallery',
492 'timestamp': 1482263210,
493 'upload_date': '20161220',
494 'uploader_id': '1107601872001',
495 },
496 'params': {
497 'skip_download': True, # m3u8 download
498 },
499 'skip': 'video rotates...weekly?',
500 },
501 {
502 # Brightcove:new type [2].
503 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
504 'md5': '2b35148fcf48da41c9fb4591650784f3',
505 'info_dict': {
506 'id': '5348741021001',
507 'ext': 'mp4',
508 'upload_date': '20170306',
509 'uploader_id': '4191638492001',
510 'timestamp': 1488769918,
511 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
512
513 },
514 },
515 {
516 # Alternative brightcove <video> attributes
517 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
518 'info_dict': {
519 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
520 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
521 },
522 'playlist': [{
523 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
524 'info_dict': {
525 'id': '5311302538001',
526 'ext': 'mp4',
527 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
528 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
529 'timestamp': 1486321708,
530 'upload_date': '20170205',
531 'uploader_id': '800000640001',
532 },
533 'only_matching': True,
534 }],
535 },
536 {
537 # Brightcove with UUID in videoPlayer
538 'url': 'http://www8.hp.com/cn/zh/home.html',
539 'info_dict': {
540 'id': '5255815316001',
541 'ext': 'mp4',
542 'title': 'Sprocket Video - China',
543 'description': 'Sprocket Video - China',
544 'uploader': 'HP-Video Gallery',
545 'timestamp': 1482263210,
546 'upload_date': '20161220',
547 'uploader_id': '1107601872001',
548 },
549 'params': {
550 'skip_download': True, # m3u8 download
551 },
552 },
553 # ooyala video
554 {
555 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
556 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
557 'info_dict': {
558 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
559 'ext': 'mp4',
560 'title': '2cc213299525360.mov', # that's what we get
561 'duration': 238.231,
562 },
563 'add_ie': ['Ooyala'],
564 },
565 {
566 # ooyala video embedded with http://player.ooyala.com/iframe.js
567 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
568 'info_dict': {
569 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
570 'ext': 'mp4',
571 'title': '"Steve Jobs: Man in the Machine" trailer',
572 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
573 'duration': 135.427,
574 },
575 'params': {
576 'skip_download': True,
577 },
578 'skip': 'movie expired',
579 },
580 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
581 {
582 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
583 'info_dict': {
584 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
585 'ext': 'mp4',
586 'title': 'Steampunk Fest Comes to Honesdale',
587 'duration': 43.276,
588 },
589 'params': {
590 'skip_download': True,
591 }
592 },
593 # embed.ly video
594 {
595 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
596 'info_dict': {
597 'id': '9ODmcdjQcHQ',
598 'ext': 'mp4',
599 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
600 'upload_date': '20140225',
601 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
602 'uploader': 'Tested',
603 'uploader_id': 'testedcom',
604 },
605 # No need to test YoutubeIE here
606 'params': {
607 'skip_download': True,
608 },
609 },
610 # funnyordie embed
611 {
612 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
613 'info_dict': {
614 'id': '18e820ec3f',
615 'ext': 'mp4',
616 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
617 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
618 },
619 # HEAD requests lead to endless 301, while GET is OK
620 'expected_warnings': ['301'],
621 },
622 # RUTV embed
623 {
624 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
625 'info_dict': {
626 'id': '776940',
627 'ext': 'mp4',
628 'title': 'Охотское море стало целиком российским',
629 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
630 },
631 'params': {
632 # m3u8 download
633 'skip_download': True,
634 },
635 },
636 # TVC embed
637 {
638 '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/',
639 'info_dict': {
640 'id': '55304',
641 'ext': 'mp4',
642 'title': 'Дошкольное воспитание',
643 },
644 },
645 # SportBox embed
646 {
647 'url': 'http://www.vestifinance.ru/articles/25753',
648 'info_dict': {
649 'id': '25753',
650 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
651 },
652 'playlist': [{
653 'info_dict': {
654 'id': '370908',
655 'title': 'Госзаказ. День 3',
656 'ext': 'mp4',
657 }
658 }, {
659 'info_dict': {
660 'id': '370905',
661 'title': 'Госзаказ. День 2',
662 'ext': 'mp4',
663 }
664 }, {
665 'info_dict': {
666 'id': '370902',
667 'title': 'Госзаказ. День 1',
668 'ext': 'mp4',
669 }
670 }],
671 'params': {
672 # m3u8 download
673 'skip_download': True,
674 },
675 },
676 # Myvi.ru embed
677 {
678 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
679 'info_dict': {
680 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
681 'ext': 'mp4',
682 'title': 'Ужастики, русский трейлер (2015)',
683 'thumbnail': r're:^https?://.*\.jpg$',
684 'duration': 153,
685 }
686 },
687 # XHamster embed
688 {
689 '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',
690 'info_dict': {
691 'id': 'showthread',
692 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
693 },
694 'playlist_mincount': 7,
695 # This forum does not allow <iframe> syntaxes anymore
696 # Now HTML tags are displayed as-is
697 'skip': 'No videos on this page',
698 },
699 # Embedded TED video
700 {
701 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
702 'md5': '65fdff94098e4a607385a60c5177c638',
703 'info_dict': {
704 'id': '1969',
705 'ext': 'mp4',
706 'title': 'Hidden miracles of the natural world',
707 'uploader': 'Louie Schwartzberg',
708 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
709 }
710 },
711 # nowvideo embed hidden behind percent encoding
712 {
713 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
714 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
715 'info_dict': {
716 'id': '06e53103ca9aa',
717 'ext': 'flv',
718 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
719 'description': 'No description',
720 },
721 },
722 # arte embed
723 {
724 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
725 'md5': '7653032cbb25bf6c80d80f217055fa43',
726 'info_dict': {
727 'id': '048195-004_PLUS7-F',
728 'ext': 'flv',
729 'title': 'X:enius',
730 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
731 'upload_date': '20140320',
732 },
733 'params': {
734 'skip_download': 'Requires rtmpdump'
735 },
736 'skip': 'video gone',
737 },
738 # francetv embed
739 {
740 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
741 'info_dict': {
742 'id': 'EV_30231',
743 'ext': 'mp4',
744 'title': 'Alcaline, le concert avec Calogero',
745 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
746 'upload_date': '20150226',
747 'timestamp': 1424989860,
748 'duration': 5400,
749 },
750 'params': {
751 # m3u8 downloads
752 'skip_download': True,
753 },
754 'expected_warnings': [
755 'Forbidden'
756 ]
757 },
758 # Condé Nast embed
759 {
760 'url': 'http://www.wired.com/2014/04/honda-asimo/',
761 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
762 'info_dict': {
763 'id': '53501be369702d3275860000',
764 'ext': 'mp4',
765 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
766 }
767 },
768 # Dailymotion embed
769 {
770 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
771 'md5': '441aeeb82eb72c422c7f14ec533999cd',
772 'info_dict': {
773 'id': 'k2mm4bCdJ6CQ2i7c8o2',
774 'ext': 'mp4',
775 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
776 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
777 'uploader': 'Spi0n',
778 'uploader_id': 'xgditw',
779 'upload_date': '20140425',
780 'timestamp': 1398441542,
781 },
782 'add_ie': ['Dailymotion'],
783 },
784 # DailyMail embed
785 {
786 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
787 'info_dict': {
788 'id': '1495629',
789 'ext': 'mp4',
790 'title': 'Care worker punches elderly dementia patient in head 11 times',
791 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
792 },
793 'add_ie': ['DailyMail'],
794 'params': {
795 'skip_download': True,
796 },
797 },
798 # YouTube embed
799 {
800 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
801 'info_dict': {
802 'id': 'FXRb4ykk4S0',
803 'ext': 'mp4',
804 'title': 'The NBL Auction 2014',
805 'uploader': 'BADMINTON England',
806 'uploader_id': 'BADMINTONEvents',
807 'upload_date': '20140603',
808 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
809 },
810 'add_ie': ['Youtube'],
811 'params': {
812 'skip_download': True,
813 }
814 },
815 # MTVSercices embed
816 {
817 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
818 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
819 'info_dict': {
820 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
821 'ext': 'mp4',
822 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
823 'description': 'Two valets share their love for movie star Liam Neesons.',
824 'timestamp': 1349922600,
825 'upload_date': '20121011',
826 },
827 },
828 # YouTube embed via <data-embed-url="">
829 {
830 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
831 'info_dict': {
832 'id': '4vAffPZIT44',
833 'ext': 'mp4',
834 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
835 'uploader': 'Gameloft',
836 'uploader_id': 'gameloft',
837 'upload_date': '20140828',
838 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
839 },
840 'params': {
841 'skip_download': True,
842 }
843 },
844 # YouTube <object> embed
845 {
846 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
847 'md5': '516718101ec834f74318df76259fb3cc',
848 'info_dict': {
849 'id': 'msN87y-iEx0',
850 'ext': 'webm',
851 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
852 'upload_date': '20080526',
853 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
854 'uploader': 'Christopher Sykes',
855 'uploader_id': 'ChristopherJSykes',
856 },
857 'add_ie': ['Youtube'],
858 },
859 # Camtasia studio
860 {
861 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
862 'playlist': [{
863 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
864 'info_dict': {
865 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
866 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
867 'ext': 'flv',
868 'duration': 2235.90,
869 }
870 }, {
871 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
872 'info_dict': {
873 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
874 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
875 'ext': 'flv',
876 'duration': 2235.93,
877 }
878 }],
879 'info_dict': {
880 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
881 }
882 },
883 # Flowplayer
884 {
885 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
886 'md5': '9d65602bf31c6e20014319c7d07fba27',
887 'info_dict': {
888 'id': '5123ea6d5e5a7',
889 'ext': 'mp4',
890 'age_limit': 18,
891 'uploader': 'www.handjobhub.com',
892 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
893 }
894 },
895 # Multiple brightcove videos
896 # https://github.com/rg3/youtube-dl/issues/2283
897 {
898 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
899 'info_dict': {
900 'id': 'always-never',
901 'title': 'Always / Never - The New Yorker',
902 },
903 'playlist_count': 3,
904 'params': {
905 'extract_flat': False,
906 'skip_download': True,
907 }
908 },
909 # MLB embed
910 {
911 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
912 'md5': '96f09a37e44da40dd083e12d9a683327',
913 'info_dict': {
914 'id': '33322633',
915 'ext': 'mp4',
916 'title': 'Ump changes call to ball',
917 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
918 'duration': 48,
919 'timestamp': 1401537900,
920 'upload_date': '20140531',
921 'thumbnail': r're:^https?://.*\.jpg$',
922 },
923 },
924 # Wistia embed
925 {
926 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
927 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
928 'info_dict': {
929 'id': '6e2wtrbdaf',
930 'ext': 'mov',
931 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
932 'description': 'a Paywall Videos video from Remilon',
933 'duration': 644.072,
934 'uploader': 'study.com',
935 'timestamp': 1459678540,
936 'upload_date': '20160403',
937 'filesize': 24687186,
938 },
939 },
940 {
941 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
942 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
943 'info_dict': {
944 'id': 'uxjb0lwrcz',
945 'ext': 'mp4',
946 'title': 'Conversation about Hexagonal Rails Part 1',
947 'description': 'a Martin Fowler video from ThoughtWorks',
948 'duration': 1715.0,
949 'uploader': 'thoughtworks.wistia.com',
950 'timestamp': 1401832161,
951 'upload_date': '20140603',
952 },
953 },
954 # Wistia standard embed (async)
955 {
956 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
957 'info_dict': {
958 'id': '807fafadvk',
959 'ext': 'mp4',
960 'title': 'Drip Brennan Dunn Workshop',
961 'description': 'a JV Webinars video from getdrip-1',
962 'duration': 4986.95,
963 'timestamp': 1463607249,
964 'upload_date': '20160518',
965 },
966 'params': {
967 'skip_download': True,
968 }
969 },
970 # Soundcloud embed
971 {
972 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
973 'info_dict': {
974 'id': '174391317',
975 'ext': 'mp3',
976 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
977 'uploader': 'Sophos Security',
978 'title': 'Chet Chat 171 - Oct 29, 2014',
979 'upload_date': '20141029',
980 }
981 },
982 # Soundcloud multiple embeds
983 {
984 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
985 'info_dict': {
986 'id': '52809',
987 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
988 },
989 'playlist_mincount': 7,
990 },
991 # TuneIn station embed
992 {
993 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
994 'info_dict': {
995 'id': '204146',
996 'ext': 'mp3',
997 'title': 'CNRV',
998 'location': 'Paris, France',
999 'is_live': True,
1000 },
1001 'params': {
1002 # Live stream
1003 'skip_download': True,
1004 },
1005 },
1006 # Livestream embed
1007 {
1008 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1009 'info_dict': {
1010 'id': '67864563',
1011 'ext': 'flv',
1012 'upload_date': '20141112',
1013 'title': 'Rosetta #CometLanding webcast HL 10',
1014 }
1015 },
1016 # Another Livestream embed, without 'new.' in URL
1017 {
1018 'url': 'https://www.freespeech.org/',
1019 'info_dict': {
1020 'id': '123537347',
1021 'ext': 'mp4',
1022 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1023 },
1024 'params': {
1025 # Live stream
1026 'skip_download': True,
1027 },
1028 },
1029 # LazyYT
1030 {
1031 'url': 'https://skiplagged.com/',
1032 'info_dict': {
1033 'id': 'skiplagged',
1034 'title': 'Skiplagged: The smart way to find cheap flights',
1035 },
1036 'playlist_mincount': 1,
1037 'add_ie': ['Youtube'],
1038 },
1039 # Cinchcast embed
1040 {
1041 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1042 'info_dict': {
1043 'id': '7141703',
1044 'ext': 'mp3',
1045 'upload_date': '20141126',
1046 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1047 }
1048 },
1049 # Cinerama player
1050 {
1051 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1052 'info_dict': {
1053 'id': '730m_DandD_1901_512k',
1054 'ext': 'mp4',
1055 'uploader': 'www.abc.net.au',
1056 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1057 }
1058 },
1059 # embedded viddler video
1060 {
1061 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1062 'info_dict': {
1063 'id': '4d03aad9',
1064 'ext': 'mp4',
1065 'uploader': 'deadspin',
1066 'title': 'WALL-TO-GORTAT',
1067 'timestamp': 1422285291,
1068 'upload_date': '20150126',
1069 },
1070 'add_ie': ['Viddler'],
1071 },
1072 # Libsyn embed
1073 {
1074 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1075 'info_dict': {
1076 'id': '3377616',
1077 'ext': 'mp3',
1078 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1079 'description': 'md5:601cb790edd05908957dae8aaa866465',
1080 'upload_date': '20150220',
1081 },
1082 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1083 },
1084 # jwplayer YouTube
1085 {
1086 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1087 'info_dict': {
1088 'id': 'Mrj4DVp2zeA',
1089 'ext': 'mp4',
1090 'upload_date': '20150212',
1091 'uploader': 'The National Archives UK',
1092 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1093 'uploader_id': 'NationalArchives08',
1094 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1095 },
1096 },
1097 # jwplayer rtmp
1098 {
1099 'url': 'http://www.suffolk.edu/sjc/live.php',
1100 'info_dict': {
1101 'id': 'live',
1102 'ext': 'flv',
1103 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1104 'uploader': 'www.suffolk.edu',
1105 },
1106 'params': {
1107 'skip_download': True,
1108 },
1109 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1110 },
1111 # Complex jwplayer
1112 {
1113 'url': 'http://www.indiedb.com/games/king-machine/videos',
1114 'info_dict': {
1115 'id': 'videos',
1116 'ext': 'mp4',
1117 'title': 'king machine trailer 1',
1118 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1119 'thumbnail': r're:^https?://.*\.jpg$',
1120 },
1121 },
1122 {
1123 # JWPlayer config passed as variable
1124 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1125 'info_dict': {
1126 'id': '3326530_hq',
1127 'ext': 'mp4',
1128 'title': 'ARIELE | Tube Cup',
1129 'uploader': 'www.txxx.com',
1130 'age_limit': 18,
1131 },
1132 'params': {
1133 'skip_download': True,
1134 }
1135 },
1136 {
1137 # JWPlatform iframe
1138 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1139 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1140 'info_dict': {
1141 'id': 'O0c5JcKT',
1142 'ext': 'mp4',
1143 'upload_date': '20171122',
1144 'timestamp': 1511366290,
1145 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1146 },
1147 'add_ie': [JWPlatformIE.ie_key()],
1148 },
1149 {
1150 # Video.js embed, multiple formats
1151 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1152 'info_dict': {
1153 'id': 'yygqldloqIk',
1154 'ext': 'mp4',
1155 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1156 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1157 'upload_date': '20130314',
1158 'uploader': 'PROстое3D',
1159 'uploader_id': 'PROstoe3D',
1160 },
1161 'params': {
1162 'skip_download': True,
1163 },
1164 },
1165 {
1166 # Video.js embed, single format
1167 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1168 'info_dict': {
1169 'id': 'watch',
1170 'ext': 'mp4',
1171 'title': 'Step 1 - Good Foundation',
1172 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1173 },
1174 'params': {
1175 'skip_download': True,
1176 },
1177 },
1178 # rtl.nl embed
1179 {
1180 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1181 'playlist_mincount': 5,
1182 'info_dict': {
1183 'id': 'aanslagen-kopenhagen',
1184 'title': 'Aanslagen Kopenhagen',
1185 }
1186 },
1187 # Zapiks embed
1188 {
1189 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1190 'info_dict': {
1191 'id': '118046',
1192 'ext': 'mp4',
1193 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1194 }
1195 },
1196 # Kaltura embed (different embed code)
1197 {
1198 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1199 'info_dict': {
1200 'id': '1_a52wc67y',
1201 'ext': 'flv',
1202 'upload_date': '20150127',
1203 'uploader_id': 'PremierMedia',
1204 'timestamp': int,
1205 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1206 },
1207 },
1208 # Kaltura embed with single quotes
1209 {
1210 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1211 'info_dict': {
1212 'id': '0_izeg5utt',
1213 'ext': 'mp4',
1214 'title': '35871',
1215 'timestamp': 1355743100,
1216 'upload_date': '20121217',
1217 'uploader_id': 'batchUser',
1218 },
1219 'add_ie': ['Kaltura'],
1220 },
1221 {
1222 # Kaltura embedded via quoted entry_id
1223 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1224 'info_dict': {
1225 'id': '0_utuok90b',
1226 'ext': 'mp4',
1227 'title': '06_matthew_brender_raj_dutt',
1228 'timestamp': 1466638791,
1229 'upload_date': '20160622',
1230 },
1231 'add_ie': ['Kaltura'],
1232 'expected_warnings': [
1233 'Could not send HEAD request'
1234 ],
1235 'params': {
1236 'skip_download': True,
1237 }
1238 },
1239 {
1240 # Kaltura embedded, some fileExt broken (#11480)
1241 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1242 'info_dict': {
1243 'id': '1_sgtvehim',
1244 'ext': 'mp4',
1245 'title': 'Our "Standard Models" of particle physics and cosmology',
1246 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1247 'timestamp': 1321158993,
1248 'upload_date': '20111113',
1249 'uploader_id': 'kps1',
1250 },
1251 'add_ie': ['Kaltura'],
1252 },
1253 {
1254 # Kaltura iframe embed
1255 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1256 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1257 'info_dict': {
1258 'id': '0_f2cfbpwy',
1259 'ext': 'mp4',
1260 'title': 'I. M. Pei: A Centennial Celebration',
1261 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1262 'upload_date': '20170403',
1263 'uploader_id': 'batchUser',
1264 'timestamp': 1491232186,
1265 },
1266 'add_ie': ['Kaltura'],
1267 },
1268 # EaglePlatform embed (generic URL)
1269 {
1270 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1271 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1272 'info_dict': {
1273 'id': '227304',
1274 'ext': 'mp4',
1275 'title': 'Навальный вышел на свободу',
1276 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1277 'thumbnail': r're:^https?://.*\.jpg$',
1278 'duration': 87,
1279 'view_count': int,
1280 'age_limit': 0,
1281 },
1282 'params': {
1283 'skip_download': True,
1284 },
1285 },
1286 # referrer protected EaglePlatform embed
1287 {
1288 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1289 'info_dict': {
1290 'id': '582306',
1291 'ext': 'mp4',
1292 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1293 'thumbnail': r're:^https?://.*\.jpg$',
1294 'duration': 3382,
1295 'view_count': int,
1296 },
1297 'params': {
1298 'skip_download': True,
1299 },
1300 },
1301 # ClipYou (EaglePlatform) embed (custom URL)
1302 {
1303 'url': 'http://muz-tv.ru/play/7129/',
1304 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1305 'info_dict': {
1306 'id': '12820',
1307 'ext': 'mp4',
1308 'title': "'O Sole Mio",
1309 'thumbnail': r're:^https?://.*\.jpg$',
1310 'duration': 216,
1311 'view_count': int,
1312 },
1313 'params': {
1314 'skip_download': True,
1315 },
1316 'skip': 'This video is unavailable.',
1317 },
1318 # Pladform embed
1319 {
1320 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1321 'info_dict': {
1322 'id': '100183293',
1323 'ext': 'mp4',
1324 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1325 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1326 'thumbnail': r're:^https?://.*\.jpg$',
1327 'duration': 694,
1328 'age_limit': 0,
1329 },
1330 'skip': 'HTTP Error 404: Not Found',
1331 },
1332 # Playwire embed
1333 {
1334 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1335 'info_dict': {
1336 'id': '3519514',
1337 'ext': 'mp4',
1338 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1339 'thumbnail': r're:^https?://.*\.png$',
1340 'duration': 45.115,
1341 },
1342 },
1343 # 5min embed
1344 {
1345 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1346 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1347 'info_dict': {
1348 'id': '518726732',
1349 'ext': 'mp4',
1350 'title': 'Facebook Creates "On This Day" | Crunch Report',
1351 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1352 'timestamp': 1427237531,
1353 'uploader': 'Crunch Report',
1354 'upload_date': '20150324',
1355 },
1356 'params': {
1357 # m3u8 download
1358 'skip_download': True,
1359 },
1360 },
1361 # SVT embed
1362 {
1363 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1364 'info_dict': {
1365 'id': '2900353',
1366 'ext': 'flv',
1367 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1368 'duration': 27,
1369 'age_limit': 0,
1370 },
1371 },
1372 # Crooks and Liars embed
1373 {
1374 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1375 'info_dict': {
1376 'id': '8RUoRhRi',
1377 'ext': 'mp4',
1378 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1379 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1380 'timestamp': 1428207000,
1381 'upload_date': '20150405',
1382 'uploader': 'Heather',
1383 },
1384 },
1385 # Crooks and Liars external embed
1386 {
1387 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1388 'info_dict': {
1389 'id': 'MTE3MjUtMzQ2MzA',
1390 'ext': 'mp4',
1391 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1392 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1393 'timestamp': 1265032391,
1394 'upload_date': '20100201',
1395 'uploader': 'Heather',
1396 },
1397 },
1398 # NBC Sports vplayer embed
1399 {
1400 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1401 'info_dict': {
1402 'id': 'ln7x1qSThw4k',
1403 'ext': 'flv',
1404 'title': "PFT Live: New leader in the 'new-look' defense",
1405 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1406 'uploader': 'NBCU-SPORTS',
1407 'upload_date': '20140107',
1408 'timestamp': 1389118457,
1409 },
1410 'skip': 'Invalid Page URL',
1411 },
1412 # NBC News embed
1413 {
1414 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1415 'md5': '1aa589c675898ae6d37a17913cf68d66',
1416 'info_dict': {
1417 'id': 'x_dtl_oa_LettermanliftPR_160608',
1418 'ext': 'mp4',
1419 'title': 'David Letterman: A Preview',
1420 '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.',
1421 'upload_date': '20160609',
1422 'timestamp': 1465431544,
1423 'uploader': 'NBCU-NEWS',
1424 },
1425 },
1426 # UDN embed
1427 {
1428 'url': 'https://video.udn.com/news/300346',
1429 'md5': 'fd2060e988c326991037b9aff9df21a6',
1430 'info_dict': {
1431 'id': '300346',
1432 'ext': 'mp4',
1433 'title': '中一中男師變性 全校師生力挺',
1434 'thumbnail': r're:^https?://.*\.jpg$',
1435 },
1436 'params': {
1437 # m3u8 download
1438 'skip_download': True,
1439 },
1440 'expected_warnings': ['Failed to parse JSON Expecting value'],
1441 },
1442 # Ooyala embed
1443 {
1444 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1445 'info_dict': {
1446 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1447 'ext': 'mp4',
1448 'description': 'Index/Match versus VLOOKUP.',
1449 'title': 'This is what separates the Excel masters from the wannabes',
1450 'duration': 191.933,
1451 },
1452 'params': {
1453 # m3u8 downloads
1454 'skip_download': True,
1455 }
1456 },
1457 # Brightcove URL in single quotes
1458 {
1459 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1460 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1461 'info_dict': {
1462 'id': '4255764656001',
1463 'ext': 'mp4',
1464 'title': 'SN Presents: Russell Martin, World Citizen',
1465 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1466 'uploader': 'Rogers Sportsnet',
1467 'uploader_id': '1704050871',
1468 'upload_date': '20150525',
1469 'timestamp': 1432570283,
1470 },
1471 },
1472 # OnionStudios embed
1473 {
1474 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1475 'info_dict': {
1476 'id': '2855',
1477 'ext': 'mp4',
1478 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1479 'thumbnail': r're:^https?://.*\.jpe?g$',
1480 'uploader': 'ClickHole',
1481 'uploader_id': 'clickhole',
1482 }
1483 },
1484 # SnagFilms embed
1485 {
1486 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1487 'info_dict': {
1488 'id': '74849a00-85a9-11e1-9660-123139220831',
1489 'ext': 'mp4',
1490 'title': '#whilewewatch',
1491 }
1492 },
1493 # AdobeTVVideo embed
1494 {
1495 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1496 'md5': '43662b577c018ad707a63766462b1e87',
1497 'info_dict': {
1498 'id': '2456',
1499 'ext': 'mp4',
1500 'title': 'New experience with Acrobat DC',
1501 'description': 'New experience with Acrobat DC',
1502 'duration': 248.667,
1503 },
1504 },
1505 # BrightcoveInPageEmbed embed
1506 {
1507 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1508 'info_dict': {
1509 'id': '4238694884001',
1510 'ext': 'flv',
1511 'title': 'Tabletop: Dread, Last Thoughts',
1512 'description': 'Tabletop: Dread, Last Thoughts',
1513 'duration': 51690,
1514 },
1515 },
1516 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1517 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1518 {
1519 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1520 'info_dict': {
1521 'id': '4785848093001',
1522 'ext': 'mp4',
1523 'title': 'The Cardinal Pell Interview',
1524 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1525 'uploader': 'GlobeCast Australia - GlobeStream',
1526 'uploader_id': '2733773828001',
1527 'upload_date': '20160304',
1528 'timestamp': 1457083087,
1529 },
1530 'params': {
1531 # m3u8 downloads
1532 'skip_download': True,
1533 },
1534 },
1535 {
1536 # Brightcove embed with whitespace around attribute names
1537 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1538 'info_dict': {
1539 'id': '3167554373001',
1540 'ext': 'mp4',
1541 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1542 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1543 'uploader_id': '1079349493',
1544 'upload_date': '20140207',
1545 'timestamp': 1391810548,
1546 },
1547 'params': {
1548 'skip_download': True,
1549 },
1550 },
1551 # Another form of arte.tv embed
1552 {
1553 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1554 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1555 'info_dict': {
1556 'id': '030273-562_PLUS7-F',
1557 'ext': 'mp4',
1558 'title': 'ARTE Reportage - Nulle part, en France',
1559 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1560 'upload_date': '20160409',
1561 },
1562 },
1563 # LiveLeak embed
1564 {
1565 'url': 'http://www.wykop.pl/link/3088787/',
1566 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1567 'info_dict': {
1568 'id': '874_1459135191',
1569 'ext': 'mp4',
1570 'title': 'Man shows poor quality of new apartment building',
1571 'description': 'The wall is like a sand pile.',
1572 'uploader': 'Lake8737',
1573 },
1574 'add_ie': [LiveLeakIE.ie_key()],
1575 },
1576 # Another LiveLeak embed pattern (#13336)
1577 {
1578 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1579 'info_dict': {
1580 'id': '2eb_1496309988',
1581 'ext': 'mp4',
1582 'title': 'Thief robs place where everyone was armed',
1583 'description': 'md5:694d73ee79e535953cf2488562288eee',
1584 'uploader': 'brazilwtf',
1585 },
1586 'add_ie': [LiveLeakIE.ie_key()],
1587 },
1588 # Duplicated embedded video URLs
1589 {
1590 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1591 'info_dict': {
1592 'id': '149298443_480_16c25b74_2',
1593 'ext': 'mp4',
1594 'title': 'vs. Blue Orange Spring Game',
1595 'uploader': 'www.hudl.com',
1596 },
1597 },
1598 # twitter:player:stream embed
1599 {
1600 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1601 'info_dict': {
1602 'id': 'master',
1603 'ext': 'mp4',
1604 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1605 'uploader': 'www.rtl.be',
1606 },
1607 'params': {
1608 # m3u8 downloads
1609 'skip_download': True,
1610 },
1611 },
1612 # twitter:player embed
1613 {
1614 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1615 'md5': 'a3e0df96369831de324f0778e126653c',
1616 'info_dict': {
1617 'id': '4909620399001',
1618 'ext': 'mp4',
1619 'title': 'What Do Black Holes Sound Like?',
1620 'description': 'what do black holes sound like',
1621 'upload_date': '20160524',
1622 'uploader_id': '29913724001',
1623 'timestamp': 1464107587,
1624 'uploader': 'TheAtlantic',
1625 },
1626 'add_ie': ['BrightcoveLegacy'],
1627 },
1628 # Facebook <iframe> embed
1629 {
1630 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1631 'md5': 'fbcde74f534176ecb015849146dd3aee',
1632 'info_dict': {
1633 'id': '599637780109885',
1634 'ext': 'mp4',
1635 'title': 'Facebook video #599637780109885',
1636 },
1637 },
1638 # Facebook <iframe> embed, plugin video
1639 {
1640 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1641 'info_dict': {
1642 'id': '1754168231264132',
1643 'ext': 'mp4',
1644 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1645 'uploader': 'Tariq Ramadan (official)',
1646 'timestamp': 1496758379,
1647 'upload_date': '20170606',
1648 },
1649 'params': {
1650 'skip_download': True,
1651 },
1652 },
1653 # Facebook API embed
1654 {
1655 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1656 'md5': 'a47372ee61b39a7b90287094d447d94e',
1657 'info_dict': {
1658 'id': '10153467542406923',
1659 'ext': 'mp4',
1660 'title': 'Facebook video #10153467542406923',
1661 },
1662 },
1663 # Wordpress "YouTube Video Importer" plugin
1664 {
1665 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1666 'md5': 'd16797741b560b485194eddda8121b48',
1667 'info_dict': {
1668 'id': 'HNTXWDXV9Is',
1669 'ext': 'mp4',
1670 'title': 'Blue Devils Drumline Stanford lot 2016',
1671 'upload_date': '20160627',
1672 'uploader_id': 'GENOCIDE8GENERAL10',
1673 'uploader': 'cylus cyrus',
1674 },
1675 },
1676 {
1677 # video stored on custom kaltura server
1678 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1679 'md5': '537617d06e64dfed891fa1593c4b30cc',
1680 'info_dict': {
1681 'id': '0_1iotm5bh',
1682 'ext': 'mp4',
1683 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1684 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1685 'uploader_id': 'videos.expansion@el-mundo.net',
1686 'upload_date': '20150429',
1687 'timestamp': 1430303472,
1688 },
1689 'add_ie': ['Kaltura'],
1690 },
1691 {
1692 # Non-standard Vimeo embed
1693 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1694 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1695 'info_dict': {
1696 'id': '148867247',
1697 'ext': 'mp4',
1698 'title': 'Understanding the web - Teaser',
1699 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1700 'upload_date': '20151214',
1701 'uploader': 'OpenClassrooms',
1702 'uploader_id': 'openclassrooms',
1703 },
1704 'add_ie': ['Vimeo'],
1705 },
1706 {
1707 # generic vimeo embed that requires original URL passed as Referer
1708 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1709 'only_matching': True,
1710 },
1711 {
1712 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1713 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1714 'info_dict': {
1715 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1716 'ext': 'mp4',
1717 'title': 'Big Buck Bunny',
1718 'description': 'Royalty free test video',
1719 'timestamp': 1432816365,
1720 'upload_date': '20150528',
1721 'is_live': False,
1722 },
1723 'params': {
1724 'skip_download': True,
1725 },
1726 'add_ie': [ArkenaIE.ie_key()],
1727 },
1728 {
1729 '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/',
1730 'info_dict': {
1731 'id': '1c7141f46c',
1732 'ext': 'mp4',
1733 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1734 },
1735 'params': {
1736 'skip_download': True,
1737 },
1738 'add_ie': [Vbox7IE.ie_key()],
1739 },
1740 {
1741 # DBTV embeds
1742 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1743 'info_dict': {
1744 'id': '43254897',
1745 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1746 },
1747 'playlist_mincount': 3,
1748 },
1749 {
1750 # Videa embeds
1751 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1752 'info_dict': {
1753 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1754 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1755 },
1756 'playlist_mincount': 2,
1757 },
1758 {
1759 # 20 minuten embed
1760 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1761 'info_dict': {
1762 'id': '523629',
1763 'ext': 'mp4',
1764 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1765 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1766 },
1767 'params': {
1768 'skip_download': True,
1769 },
1770 'add_ie': [TwentyMinutenIE.ie_key()],
1771 },
1772 {
1773 # VideoPress embed
1774 'url': 'https://en.support.wordpress.com/videopress/',
1775 'info_dict': {
1776 'id': 'OcobLTqC',
1777 'ext': 'm4v',
1778 'title': 'IMG_5786',
1779 'timestamp': 1435711927,
1780 'upload_date': '20150701',
1781 },
1782 'params': {
1783 'skip_download': True,
1784 },
1785 'add_ie': [VideoPressIE.ie_key()],
1786 },
1787 {
1788 # Rutube embed
1789 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1790 'info_dict': {
1791 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1792 'ext': 'flv',
1793 'title': 'Магаззино: Казань 2',
1794 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1795 'uploader': 'Магаззино',
1796 'upload_date': '20170228',
1797 'uploader_id': '996642',
1798 },
1799 'params': {
1800 'skip_download': True,
1801 },
1802 'add_ie': [RutubeIE.ie_key()],
1803 },
1804 {
1805 # ThePlatform embedded with whitespaces in URLs
1806 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1807 'only_matching': True,
1808 },
1809 {
1810 # Senate ISVP iframe https
1811 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1812 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1813 'info_dict': {
1814 'id': 'govtaff020316',
1815 'ext': 'mp4',
1816 'title': 'Integrated Senate Video Player',
1817 },
1818 'add_ie': [SenateISVPIE.ie_key()],
1819 },
1820 {
1821 # Limelight embeds (1 channel embed + 4 media embeds)
1822 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1823 'info_dict': {
1824 'id': 'FacilitatorTraining2017',
1825 'title': 'Facilitator Training 2017',
1826 },
1827 'playlist_mincount': 5,
1828 },
1829 {
1830 # Limelight embed (LimelightPlayerUtil.embed)
1831 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1832 'info_dict': {
1833 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1834 'ext': 'mp4',
1835 'title': '07448641',
1836 'timestamp': 1499890639,
1837 'upload_date': '20170712',
1838 },
1839 'params': {
1840 'skip_download': True,
1841 },
1842 'add_ie': ['LimelightMedia'],
1843 },
1844 {
1845 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1846 'info_dict': {
1847 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1848 'title': 'Standoff with Walnut Creek murder suspect ends',
1849 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1850 },
1851 'playlist_mincount': 4,
1852 },
1853 {
1854 # WashingtonPost embed
1855 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1856 'info_dict': {
1857 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1858 'ext': 'mp4',
1859 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1860 '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.',
1861 'timestamp': 1455216756,
1862 'uploader': 'The Washington Post',
1863 'upload_date': '20160211',
1864 },
1865 'add_ie': [WashingtonPostIE.ie_key()],
1866 },
1867 {
1868 # Mediaset embed
1869 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1870 'info_dict': {
1871 'id': '720642',
1872 'ext': 'mp4',
1873 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1874 },
1875 'params': {
1876 'skip_download': True,
1877 },
1878 'add_ie': [MediasetIE.ie_key()],
1879 },
1880 {
1881 # JOJ.sk embeds
1882 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1883 'info_dict': {
1884 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1885 'title': 'Slovenskom sa prehnala vlna silných búrok',
1886 },
1887 'playlist_mincount': 5,
1888 'add_ie': [JojIE.ie_key()],
1889 },
1890 {
1891 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1892 'url': 'https://tvrain.ru/amp/418921/',
1893 'md5': 'cc00413936695987e8de148b67d14f1d',
1894 'info_dict': {
1895 'id': '418921',
1896 'ext': 'mp4',
1897 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1898 },
1899 },
1900 {
1901 # vzaar embed
1902 'url': 'http://help.vzaar.com/article/165-embedding-video',
1903 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1904 'info_dict': {
1905 'id': '8707641',
1906 'ext': 'mp4',
1907 'title': 'Building A Business Online: Principal Chairs Q & A',
1908 },
1909 },
1910 {
1911 # multiple HTML5 videos on one page
1912 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1913 'info_dict': {
1914 'id': 'keyscenarios',
1915 'title': 'Rescue Kit 14 Free Edition - Getting started',
1916 },
1917 'playlist_count': 4,
1918 },
1919 {
1920 # vshare embed
1921 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1922 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1923 'info_dict': {
1924 'id': '0f64ce6',
1925 'title': 'vl14062007715967',
1926 'ext': 'mp4',
1927 }
1928 }
1929 # {
1930 # # TODO: find another test
1931 # # http://schema.org/VideoObject
1932 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1933 # 'md5': '888dcf08b7ea671381f00fab74692755',
1934 # 'info_dict': {
1935 # 'id': 'nyvTSJMKId',
1936 # 'ext': 'mp4',
1937 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1938 # 'description': '#love for cats.',
1939 # 'timestamp': 1461244995,
1940 # 'upload_date': '20160421',
1941 # },
1942 # 'params': {
1943 # 'force_generic_extractor': True,
1944 # },
1945 # }
1946 ]
1947
1948 def report_following_redirect(self, new_url):
1949 """Report information extraction."""
1950 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1951
1952 def _extract_rss(self, url, video_id, doc):
1953 playlist_title = doc.find('./channel/title').text
1954 playlist_desc_el = doc.find('./channel/description')
1955 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1956
1957 entries = []
1958 for it in doc.findall('./channel/item'):
1959 next_url = xpath_text(it, 'link', fatal=False)
1960 if not next_url:
1961 enclosure_nodes = it.findall('./enclosure')
1962 for e in enclosure_nodes:
1963 next_url = e.attrib.get('url')
1964 if next_url:
1965 break
1966
1967 if not next_url:
1968 continue
1969
1970 entries.append({
1971 '_type': 'url_transparent',
1972 'url': next_url,
1973 'title': it.find('title').text,
1974 })
1975
1976 return {
1977 '_type': 'playlist',
1978 'id': url,
1979 'title': playlist_title,
1980 'description': playlist_desc,
1981 'entries': entries,
1982 }
1983
1984 def _extract_camtasia(self, url, video_id, webpage):
1985 """ Returns None if no camtasia video can be found. """
1986
1987 camtasia_cfg = self._search_regex(
1988 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1989 webpage, 'camtasia configuration file', default=None)
1990 if camtasia_cfg is None:
1991 return None
1992
1993 title = self._html_search_meta('DC.title', webpage, fatal=True)
1994
1995 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1996 camtasia_cfg = self._download_xml(
1997 camtasia_url, video_id,
1998 note='Downloading camtasia configuration',
1999 errnote='Failed to download camtasia configuration')
2000 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2001
2002 entries = []
2003 for n in fileset_node.getchildren():
2004 url_n = n.find('./uri')
2005 if url_n is None:
2006 continue
2007
2008 entries.append({
2009 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2010 'title': '%s - %s' % (title, n.tag),
2011 'url': compat_urlparse.urljoin(url, url_n.text),
2012 'duration': float_or_none(n.find('./duration').text),
2013 })
2014
2015 return {
2016 '_type': 'playlist',
2017 'entries': entries,
2018 'title': title,
2019 }
2020
2021 def _real_extract(self, url):
2022 if url.startswith('//'):
2023 return {
2024 '_type': 'url',
2025 'url': self.http_scheme() + url,
2026 }
2027
2028 parsed_url = compat_urlparse.urlparse(url)
2029 if not parsed_url.scheme:
2030 default_search = self._downloader.params.get('default_search')
2031 if default_search is None:
2032 default_search = 'fixup_error'
2033
2034 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2035 if '/' in url:
2036 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2037 return self.url_result('http://' + url)
2038 elif default_search != 'fixup_error':
2039 if default_search == 'auto_warning':
2040 if re.match(r'^(?:url|URL)$', url):
2041 raise ExtractorError(
2042 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2043 expected=True)
2044 else:
2045 self._downloader.report_warning(
2046 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2047 return self.url_result('ytsearch:' + url)
2048
2049 if default_search in ('error', 'fixup_error'):
2050 raise ExtractorError(
2051 '%r is not a valid URL. '
2052 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2053 % (url, url), expected=True)
2054 else:
2055 if ':' not in default_search:
2056 default_search += ':'
2057 return self.url_result(default_search + url)
2058
2059 url, smuggled_data = unsmuggle_url(url)
2060 force_videoid = None
2061 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2062 if smuggled_data and 'force_videoid' in smuggled_data:
2063 force_videoid = smuggled_data['force_videoid']
2064 video_id = force_videoid
2065 else:
2066 video_id = self._generic_id(url)
2067
2068 self.to_screen('%s: Requesting header' % video_id)
2069
2070 head_req = HEADRequest(url)
2071 head_response = self._request_webpage(
2072 head_req, video_id,
2073 note=False, errnote='Could not send HEAD request to %s' % url,
2074 fatal=False)
2075
2076 if head_response is not False:
2077 # Check for redirect
2078 new_url = compat_str(head_response.geturl())
2079 if url != new_url:
2080 self.report_following_redirect(new_url)
2081 if force_videoid:
2082 new_url = smuggle_url(
2083 new_url, {'force_videoid': force_videoid})
2084 return self.url_result(new_url)
2085
2086 full_response = None
2087 if head_response is False:
2088 request = sanitized_Request(url)
2089 request.add_header('Accept-Encoding', '*')
2090 full_response = self._request_webpage(request, video_id)
2091 head_response = full_response
2092
2093 info_dict = {
2094 'id': video_id,
2095 'title': self._generic_title(url),
2096 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2097 }
2098
2099 # Check for direct link to a video
2100 content_type = head_response.headers.get('Content-Type', '').lower()
2101 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2102 if m:
2103 format_id = compat_str(m.group('format_id'))
2104 if format_id.endswith('mpegurl'):
2105 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2106 elif format_id == 'f4m':
2107 formats = self._extract_f4m_formats(url, video_id)
2108 else:
2109 formats = [{
2110 'format_id': format_id,
2111 'url': url,
2112 'vcodec': 'none' if m.group('type') == 'audio' else None
2113 }]
2114 info_dict['direct'] = True
2115 self._sort_formats(formats)
2116 info_dict['formats'] = formats
2117 return info_dict
2118
2119 if not self._downloader.params.get('test', False) and not is_intentional:
2120 force = self._downloader.params.get('force_generic_extractor', False)
2121 self._downloader.report_warning(
2122 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2123
2124 if not full_response:
2125 request = sanitized_Request(url)
2126 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2127 # making it impossible to download only chunk of the file (yet we need only 512kB to
2128 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2129 # that will always result in downloading the whole file that is not desirable.
2130 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2131 # to accept raw bytes and being able to download only a chunk.
2132 # It may probably better to solve this by checking Content-Type for application/octet-stream
2133 # after HEAD request finishes, but not sure if we can rely on this.
2134 request.add_header('Accept-Encoding', '*')
2135 full_response = self._request_webpage(request, video_id)
2136
2137 first_bytes = full_response.read(512)
2138
2139 # Is it an M3U playlist?
2140 if first_bytes.startswith(b'#EXTM3U'):
2141 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2142 self._sort_formats(info_dict['formats'])
2143 return info_dict
2144
2145 # Maybe it's a direct link to a video?
2146 # Be careful not to download the whole thing!
2147 if not is_html(first_bytes):
2148 self._downloader.report_warning(
2149 'URL could be a direct video link, returning it as such.')
2150 info_dict.update({
2151 'direct': True,
2152 'url': url,
2153 })
2154 return info_dict
2155
2156 webpage = self._webpage_read_content(
2157 full_response, url, video_id, prefix=first_bytes)
2158
2159 self.report_extraction(video_id)
2160
2161 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2162 try:
2163 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2164 if doc.tag == 'rss':
2165 return self._extract_rss(url, video_id, doc)
2166 elif doc.tag == 'SmoothStreamingMedia':
2167 info_dict['formats'] = self._parse_ism_formats(doc, url)
2168 self._sort_formats(info_dict['formats'])
2169 return info_dict
2170 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2171 smil = self._parse_smil(doc, url, video_id)
2172 self._sort_formats(smil['formats'])
2173 return smil
2174 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2175 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2176 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2177 info_dict['formats'] = self._parse_mpd_formats(
2178 doc,
2179 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2180 mpd_url=url)
2181 self._sort_formats(info_dict['formats'])
2182 return info_dict
2183 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2184 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2185 self._sort_formats(info_dict['formats'])
2186 return info_dict
2187 except compat_xml_parse_error:
2188 pass
2189
2190 # Is it a Camtasia project?
2191 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2192 if camtasia_res is not None:
2193 return camtasia_res
2194
2195 # Sometimes embedded video player is hidden behind percent encoding
2196 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2197 # Unescaping the whole page allows to handle those cases in a generic way
2198 webpage = compat_urllib_parse_unquote(webpage)
2199
2200 # it's tempting to parse this further, but you would
2201 # have to take into account all the variations like
2202 # Video Title - Site Name
2203 # Site Name | Video Title
2204 # Video Title - Tagline | Site Name
2205 # and so on and so forth; it's just not practical
2206 video_title = self._og_search_title(
2207 webpage, default=None) or self._html_search_regex(
2208 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2209 default='video')
2210
2211 # Try to detect age limit automatically
2212 age_limit = self._rta_search(webpage)
2213 # And then there are the jokers who advertise that they use RTA,
2214 # but actually don't.
2215 AGE_LIMIT_MARKERS = [
2216 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2217 ]
2218 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2219 age_limit = 18
2220
2221 # video uploader is domain name
2222 video_uploader = self._search_regex(
2223 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2224
2225 video_description = self._og_search_description(webpage, default=None)
2226 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2227
2228 info_dict.update({
2229 'title': video_title,
2230 'description': video_description,
2231 'thumbnail': video_thumbnail,
2232 'age_limit': age_limit,
2233 })
2234
2235 # Look for Brightcove Legacy Studio embeds
2236 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2237 if bc_urls:
2238 entries = [{
2239 '_type': 'url',
2240 'url': smuggle_url(bc_url, {'Referer': url}),
2241 'ie_key': 'BrightcoveLegacy'
2242 } for bc_url in bc_urls]
2243
2244 return {
2245 '_type': 'playlist',
2246 'title': video_title,
2247 'id': video_id,
2248 'entries': entries,
2249 }
2250
2251 # Look for Brightcove New Studio embeds
2252 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2253 if bc_urls:
2254 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2255
2256 # Look for Nexx embeds
2257 nexx_urls = NexxIE._extract_urls(webpage)
2258 if nexx_urls:
2259 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2260
2261 # Look for Nexx iFrame embeds
2262 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2263 if nexx_embed_urls:
2264 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2265
2266 # Look for ThePlatform embeds
2267 tp_urls = ThePlatformIE._extract_urls(webpage)
2268 if tp_urls:
2269 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2270
2271 # Look for Vessel embeds
2272 vessel_urls = VesselIE._extract_urls(webpage)
2273 if vessel_urls:
2274 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2275
2276 # Look for embedded rtl.nl player
2277 matches = re.findall(
2278 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2279 webpage)
2280 if matches:
2281 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2282
2283 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2284 if vimeo_urls:
2285 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2286
2287 vid_me_embed_url = self._search_regex(
2288 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2289 webpage, 'vid.me embed', default=None)
2290 if vid_me_embed_url is not None:
2291 return self.url_result(vid_me_embed_url, 'Vidme')
2292
2293 # Look for YouTube embeds
2294 youtube_urls = YoutubeIE._extract_urls(webpage)
2295 if youtube_urls:
2296 return self.playlist_from_matches(
2297 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2298
2299 matches = DailymotionIE._extract_urls(webpage)
2300 if matches:
2301 return self.playlist_from_matches(matches, video_id, video_title)
2302
2303 # Look for embedded Dailymotion playlist player (#3822)
2304 m = re.search(
2305 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2306 if m:
2307 playlists = re.findall(
2308 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2309 if playlists:
2310 return self.playlist_from_matches(
2311 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2312
2313 # Look for DailyMail embeds
2314 dailymail_urls = DailyMailIE._extract_urls(webpage)
2315 if dailymail_urls:
2316 return self.playlist_from_matches(
2317 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2318
2319 # Look for embedded Wistia player
2320 wistia_url = WistiaIE._extract_url(webpage)
2321 if wistia_url:
2322 return {
2323 '_type': 'url_transparent',
2324 'url': self._proto_relative_url(wistia_url),
2325 'ie_key': WistiaIE.ie_key(),
2326 'uploader': video_uploader,
2327 }
2328
2329 # Look for SVT player
2330 svt_url = SVTIE._extract_url(webpage)
2331 if svt_url:
2332 return self.url_result(svt_url, 'SVT')
2333
2334 # Look for Bandcamp pages with custom domain
2335 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2336 if mobj is not None:
2337 burl = unescapeHTML(mobj.group(1))
2338 # Don't set the extractor because it can be a track url or an album
2339 return self.url_result(burl)
2340
2341 # Look for embedded Vevo player
2342 mobj = re.search(
2343 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2344 if mobj is not None:
2345 return self.url_result(mobj.group('url'))
2346
2347 # Look for embedded Viddler player
2348 mobj = re.search(
2349 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2350 webpage)
2351 if mobj is not None:
2352 return self.url_result(mobj.group('url'))
2353
2354 # Look for NYTimes player
2355 mobj = re.search(
2356 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2357 webpage)
2358 if mobj is not None:
2359 return self.url_result(mobj.group('url'))
2360
2361 # Look for Libsyn player
2362 mobj = re.search(
2363 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2364 if mobj is not None:
2365 return self.url_result(mobj.group('url'))
2366
2367 # Look for Ooyala videos
2368 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2369 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2370 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2371 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2372 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2373 if mobj is not None:
2374 embed_token = self._search_regex(
2375 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2376 webpage, 'ooyala embed token', default=None)
2377 return OoyalaIE._build_url_result(smuggle_url(
2378 mobj.group('ec'), {
2379 'domain': url,
2380 'embed_token': embed_token,
2381 }))
2382
2383 # Look for multiple Ooyala embeds on SBN network websites
2384 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2385 if mobj is not None:
2386 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2387 if embeds:
2388 return self.playlist_from_matches(
2389 embeds, video_id, video_title,
2390 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2391
2392 # Look for Aparat videos
2393 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2394 if mobj is not None:
2395 return self.url_result(mobj.group(1), 'Aparat')
2396
2397 # Look for MPORA videos
2398 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2399 if mobj is not None:
2400 return self.url_result(mobj.group(1), 'Mpora')
2401
2402 # Look for embedded NovaMov-based player
2403 mobj = re.search(
2404 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2405 (?P<url>http://(?:(?:embed|www)\.)?
2406 (?:novamov\.com|
2407 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2408 videoweed\.(?:es|com)|
2409 movshare\.(?:net|sx|ag)|
2410 divxstage\.(?:eu|net|ch|co|at|ag))
2411 /embed\.php.+?)\1''', webpage)
2412 if mobj is not None:
2413 return self.url_result(mobj.group('url'))
2414
2415 # Look for embedded Facebook player
2416 facebook_urls = FacebookIE._extract_urls(webpage)
2417 if facebook_urls:
2418 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2419
2420 # Look for embedded VK player
2421 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2422 if mobj is not None:
2423 return self.url_result(mobj.group('url'), 'VK')
2424
2425 # Look for embedded Odnoklassniki player
2426 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2427 if mobj is not None:
2428 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2429
2430 # Look for embedded ivi player
2431 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2432 if mobj is not None:
2433 return self.url_result(mobj.group('url'), 'Ivi')
2434
2435 # Look for embedded Huffington Post player
2436 mobj = re.search(
2437 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2438 if mobj is not None:
2439 return self.url_result(mobj.group('url'), 'HuffPost')
2440
2441 # Look for embed.ly
2442 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2443 if mobj is not None:
2444 return self.url_result(mobj.group('url'))
2445 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2446 if mobj is not None:
2447 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2448
2449 # Look for funnyordie embed
2450 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2451 if matches:
2452 return self.playlist_from_matches(
2453 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2454
2455 # Look for BBC iPlayer embed
2456 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2457 if matches:
2458 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2459
2460 # Look for embedded RUTV player
2461 rutv_url = RUTVIE._extract_url(webpage)
2462 if rutv_url:
2463 return self.url_result(rutv_url, 'RUTV')
2464
2465 # Look for embedded TVC player
2466 tvc_url = TVCIE._extract_url(webpage)
2467 if tvc_url:
2468 return self.url_result(tvc_url, 'TVC')
2469
2470 # Look for embedded SportBox player
2471 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2472 if sportbox_urls:
2473 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2474
2475 # Look for embedded XHamster player
2476 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2477 if xhamster_urls:
2478 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2479
2480 # Look for embedded TNAFlixNetwork player
2481 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2482 if tnaflix_urls:
2483 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2484
2485 # Look for embedded PornHub player
2486 pornhub_urls = PornHubIE._extract_urls(webpage)
2487 if pornhub_urls:
2488 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2489
2490 # Look for embedded DrTuber player
2491 drtuber_urls = DrTuberIE._extract_urls(webpage)
2492 if drtuber_urls:
2493 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2494
2495 # Look for embedded RedTube player
2496 redtube_urls = RedTubeIE._extract_urls(webpage)
2497 if redtube_urls:
2498 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2499
2500 # Look for embedded Tvigle player
2501 mobj = re.search(
2502 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2503 if mobj is not None:
2504 return self.url_result(mobj.group('url'), 'Tvigle')
2505
2506 # Look for embedded TED player
2507 mobj = re.search(
2508 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2509 if mobj is not None:
2510 return self.url_result(mobj.group('url'), 'TED')
2511
2512 # Look for embedded Ustream videos
2513 ustream_url = UstreamIE._extract_url(webpage)
2514 if ustream_url:
2515 return self.url_result(ustream_url, UstreamIE.ie_key())
2516
2517 # Look for embedded arte.tv player
2518 mobj = re.search(
2519 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2520 webpage)
2521 if mobj is not None:
2522 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2523
2524 # Look for embedded francetv player
2525 mobj = re.search(
2526 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2527 webpage)
2528 if mobj is not None:
2529 return self.url_result(mobj.group('url'))
2530
2531 # Look for embedded smotri.com player
2532 smotri_url = SmotriIE._extract_url(webpage)
2533 if smotri_url:
2534 return self.url_result(smotri_url, 'Smotri')
2535
2536 # Look for embedded Myvi.ru player
2537 myvi_url = MyviIE._extract_url(webpage)
2538 if myvi_url:
2539 return self.url_result(myvi_url)
2540
2541 # Look for embedded soundcloud player
2542 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2543 if soundcloud_urls:
2544 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2545
2546 # Look for tunein player
2547 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2548 if tunein_urls:
2549 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2550
2551 # Look for embedded mtvservices player
2552 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2553 if mtvservices_url:
2554 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2555
2556 # Look for embedded yahoo player
2557 mobj = re.search(
2558 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2559 webpage)
2560 if mobj is not None:
2561 return self.url_result(mobj.group('url'), 'Yahoo')
2562
2563 # Look for embedded sbs.com.au player
2564 mobj = re.search(
2565 r'''(?x)
2566 (?:
2567 <meta\s+property="og:video"\s+content=|
2568 <iframe[^>]+?src=
2569 )
2570 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2571 webpage)
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'), 'SBS')
2574
2575 # Look for embedded Cinchcast player
2576 mobj = re.search(
2577 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2578 webpage)
2579 if mobj is not None:
2580 return self.url_result(mobj.group('url'), 'Cinchcast')
2581
2582 mobj = re.search(
2583 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2584 webpage)
2585 if not mobj:
2586 mobj = re.search(
2587 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2588 webpage)
2589 if mobj is not None:
2590 return self.url_result(mobj.group('url'), 'MLB')
2591
2592 mobj = re.search(
2593 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2594 webpage)
2595 if mobj is not None:
2596 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2597
2598 mobj = re.search(
2599 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2600 webpage)
2601 if mobj is not None:
2602 return self.url_result(mobj.group('url'), 'Livestream')
2603
2604 # Look for Zapiks embed
2605 mobj = re.search(
2606 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2607 if mobj is not None:
2608 return self.url_result(mobj.group('url'), 'Zapiks')
2609
2610 # Look for Kaltura embeds
2611 kaltura_url = KalturaIE._extract_url(webpage)
2612 if kaltura_url:
2613 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2614
2615 # Look for EaglePlatform embeds
2616 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2617 if eagleplatform_url:
2618 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2619
2620 # Look for ClipYou (uses EaglePlatform) embeds
2621 mobj = re.search(
2622 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2623 if mobj is not None:
2624 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2625
2626 # Look for Pladform embeds
2627 pladform_url = PladformIE._extract_url(webpage)
2628 if pladform_url:
2629 return self.url_result(pladform_url)
2630
2631 # Look for Videomore embeds
2632 videomore_url = VideomoreIE._extract_url(webpage)
2633 if videomore_url:
2634 return self.url_result(videomore_url)
2635
2636 # Look for Webcaster embeds
2637 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2638 if webcaster_url:
2639 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2640
2641 # Look for Playwire embeds
2642 mobj = re.search(
2643 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2644 if mobj is not None:
2645 return self.url_result(mobj.group('url'))
2646
2647 # Look for 5min embeds
2648 mobj = re.search(
2649 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2650 if mobj is not None:
2651 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2652
2653 # Look for Crooks and Liars embeds
2654 mobj = re.search(
2655 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2656 if mobj is not None:
2657 return self.url_result(mobj.group('url'))
2658
2659 # Look for NBC Sports VPlayer embeds
2660 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2661 if nbc_sports_url:
2662 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2663
2664 # Look for NBC News embeds
2665 nbc_news_embed_url = re.search(
2666 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2667 if nbc_news_embed_url:
2668 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2669
2670 # Look for Google Drive embeds
2671 google_drive_url = GoogleDriveIE._extract_url(webpage)
2672 if google_drive_url:
2673 return self.url_result(google_drive_url, 'GoogleDrive')
2674
2675 # Look for UDN embeds
2676 mobj = re.search(
2677 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2678 if mobj is not None:
2679 return self.url_result(
2680 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2681
2682 # Look for Senate ISVP iframe
2683 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2684 if senate_isvp_url:
2685 return self.url_result(senate_isvp_url, 'SenateISVP')
2686
2687 # Look for OnionStudios embeds
2688 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2689 if onionstudios_url:
2690 return self.url_result(onionstudios_url)
2691
2692 # Look for ViewLift embeds
2693 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2694 if viewlift_url:
2695 return self.url_result(viewlift_url)
2696
2697 # Look for JWPlatform embeds
2698 jwplatform_url = JWPlatformIE._extract_url(webpage)
2699 if jwplatform_url:
2700 return self.url_result(jwplatform_url, 'JWPlatform')
2701
2702 # Look for Digiteka embeds
2703 digiteka_url = DigitekaIE._extract_url(webpage)
2704 if digiteka_url:
2705 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2706
2707 # Look for Arkena embeds
2708 arkena_url = ArkenaIE._extract_url(webpage)
2709 if arkena_url:
2710 return self.url_result(arkena_url, ArkenaIE.ie_key())
2711
2712 # Look for Piksel embeds
2713 piksel_url = PikselIE._extract_url(webpage)
2714 if piksel_url:
2715 return self.url_result(piksel_url, PikselIE.ie_key())
2716
2717 # Look for Limelight embeds
2718 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2719 if limelight_urls:
2720 return self.playlist_result(
2721 limelight_urls, video_id, video_title, video_description)
2722
2723 # Look for Anvato embeds
2724 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2725 if anvato_urls:
2726 return self.playlist_result(
2727 anvato_urls, video_id, video_title, video_description)
2728
2729 # Look for AdobeTVVideo embeds
2730 mobj = re.search(
2731 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2732 webpage)
2733 if mobj is not None:
2734 return self.url_result(
2735 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2736 'AdobeTVVideo')
2737
2738 # Look for Vine embeds
2739 mobj = re.search(
2740 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2741 webpage)
2742 if mobj is not None:
2743 return self.url_result(
2744 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2745
2746 # Look for VODPlatform embeds
2747 mobj = re.search(
2748 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2749 webpage)
2750 if mobj is not None:
2751 return self.url_result(
2752 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2753
2754 # Look for Mangomolo embeds
2755 mobj = re.search(
2756 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2757 (?:
2758 video\?.*?\bid=(?P<video_id>\d+)|
2759 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2760 ).+?)\1''', webpage)
2761 if mobj is not None:
2762 info = {
2763 '_type': 'url_transparent',
2764 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2765 'title': video_title,
2766 'description': video_description,
2767 'thumbnail': video_thumbnail,
2768 'uploader': video_uploader,
2769 }
2770 video_id = mobj.group('video_id')
2771 if video_id:
2772 info.update({
2773 'ie_key': 'MangomoloVideo',
2774 'id': video_id,
2775 })
2776 else:
2777 info.update({
2778 'ie_key': 'MangomoloLive',
2779 'id': mobj.group('channel_id'),
2780 })
2781 return info
2782
2783 # Look for Instagram embeds
2784 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2785 if instagram_embed_url is not None:
2786 return self.url_result(
2787 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2788
2789 # Look for LiveLeak embeds
2790 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2791 if liveleak_urls:
2792 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2793
2794 # Look for 3Q SDN embeds
2795 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2796 if threeqsdn_url:
2797 return {
2798 '_type': 'url_transparent',
2799 'ie_key': ThreeQSDNIE.ie_key(),
2800 'url': self._proto_relative_url(threeqsdn_url),
2801 'title': video_title,
2802 'description': video_description,
2803 'thumbnail': video_thumbnail,
2804 'uploader': video_uploader,
2805 }
2806
2807 # Look for VBOX7 embeds
2808 vbox7_url = Vbox7IE._extract_url(webpage)
2809 if vbox7_url:
2810 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2811
2812 # Look for DBTV embeds
2813 dbtv_urls = DBTVIE._extract_urls(webpage)
2814 if dbtv_urls:
2815 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2816
2817 # Look for Videa embeds
2818 videa_urls = VideaIE._extract_urls(webpage)
2819 if videa_urls:
2820 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2821
2822 # Look for 20 minuten embeds
2823 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2824 if twentymin_urls:
2825 return self.playlist_from_matches(
2826 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2827
2828 # Look for Openload embeds
2829 openload_urls = OpenloadIE._extract_urls(webpage)
2830 if openload_urls:
2831 return self.playlist_from_matches(
2832 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2833
2834 # Look for VideoPress embeds
2835 videopress_urls = VideoPressIE._extract_urls(webpage)
2836 if videopress_urls:
2837 return self.playlist_from_matches(
2838 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2839
2840 # Look for Rutube embeds
2841 rutube_urls = RutubeIE._extract_urls(webpage)
2842 if rutube_urls:
2843 return self.playlist_from_matches(
2844 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2845
2846 # Look for WashingtonPost embeds
2847 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2848 if wapo_urls:
2849 return self.playlist_from_matches(
2850 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2851
2852 # Look for Mediaset embeds
2853 mediaset_urls = MediasetIE._extract_urls(webpage)
2854 if mediaset_urls:
2855 return self.playlist_from_matches(
2856 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2857
2858 # Look for JOJ.sk embeds
2859 joj_urls = JojIE._extract_urls(webpage)
2860 if joj_urls:
2861 return self.playlist_from_matches(
2862 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2863
2864 # Look for megaphone.fm embeds
2865 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2866 if mpfn_urls:
2867 return self.playlist_from_matches(
2868 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2869
2870 # Look for vzaar embeds
2871 vzaar_urls = VzaarIE._extract_urls(webpage)
2872 if vzaar_urls:
2873 return self.playlist_from_matches(
2874 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2875
2876 channel9_urls = Channel9IE._extract_urls(webpage)
2877 if channel9_urls:
2878 return self.playlist_from_matches(
2879 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2880
2881 vshare_urls = VShareIE._extract_urls(webpage)
2882 if vshare_urls:
2883 return self.playlist_from_matches(
2884 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2885
2886 # Look for Mediasite embeds
2887 mobj = re.search(r'''(?xi)
2888 <iframe[^>]+src="((?:https?://[a-z0-9\-\.:\[\]]+)?
2889 /Mediasite/Play/[0-9a-f]{32,34}(?:\?.*?)?)"
2890 ''', webpage)
2891 if mobj is not None:
2892 return self.url_result(smuggle_url(
2893 compat_urlparse.urljoin(url, unescapeHTML(mobj.group(1))),
2894 { 'UrlReferrer': url }), 'Livestream')
2895
2896 def merge_dicts(dict1, dict2):
2897 merged = {}
2898 for k, v in dict1.items():
2899 if v is not None:
2900 merged[k] = v
2901 for k, v in dict2.items():
2902 if v is None:
2903 continue
2904 if (k not in merged or
2905 (isinstance(v, compat_str) and v and
2906 isinstance(merged[k], compat_str) and
2907 not merged[k])):
2908 merged[k] = v
2909 return merged
2910
2911 # Look for HTML5 media
2912 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2913 if entries:
2914 if len(entries) == 1:
2915 entries[0].update({
2916 'id': video_id,
2917 'title': video_title,
2918 })
2919 else:
2920 for num, entry in enumerate(entries, start=1):
2921 entry.update({
2922 'id': '%s-%s' % (video_id, num),
2923 'title': '%s (%d)' % (video_title, num),
2924 })
2925 for entry in entries:
2926 self._sort_formats(entry['formats'])
2927 return self.playlist_result(entries, video_id, video_title)
2928
2929 jwplayer_data = self._find_jwplayer_data(
2930 webpage, video_id, transform_source=js_to_json)
2931 if jwplayer_data:
2932 info = self._parse_jwplayer_data(
2933 jwplayer_data, video_id, require_title=False, base_url=url)
2934 return merge_dicts(info, info_dict)
2935
2936 # Video.js embed
2937 mobj = re.search(
2938 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
2939 webpage)
2940 if mobj is not None:
2941 sources = self._parse_json(
2942 mobj.group(1), video_id, transform_source=js_to_json,
2943 fatal=False) or []
2944 if not isinstance(sources, list):
2945 sources = [sources]
2946 formats = []
2947 for source in sources:
2948 src = source.get('src')
2949 if not src or not isinstance(src, compat_str):
2950 continue
2951 src = compat_urlparse.urljoin(url, src)
2952 src_type = source.get('type')
2953 if isinstance(src_type, compat_str):
2954 src_type = src_type.lower()
2955 ext = determine_ext(src).lower()
2956 if src_type == 'video/youtube':
2957 return self.url_result(src, YoutubeIE.ie_key())
2958 if src_type == 'application/dash+xml' or ext == 'mpd':
2959 formats.extend(self._extract_mpd_formats(
2960 src, video_id, mpd_id='dash', fatal=False))
2961 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2962 formats.extend(self._extract_m3u8_formats(
2963 src, video_id, 'mp4', entry_protocol='m3u8_native',
2964 m3u8_id='hls', fatal=False))
2965 else:
2966 formats.append({
2967 'url': src,
2968 'ext': (mimetype2ext(src_type) or
2969 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2970 })
2971 if formats:
2972 self._sort_formats(formats)
2973 info_dict['formats'] = formats
2974 return info_dict
2975
2976 # Looking for http://schema.org/VideoObject
2977 json_ld = self._search_json_ld(
2978 webpage, video_id, default={}, expected_type='VideoObject')
2979 if json_ld.get('url'):
2980 return merge_dicts(json_ld, info_dict)
2981
2982 def check_video(vurl):
2983 if YoutubeIE.suitable(vurl):
2984 return True
2985 if RtmpIE.suitable(vurl):
2986 return True
2987 vpath = compat_urlparse.urlparse(vurl).path
2988 vext = determine_ext(vpath)
2989 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2990
2991 def filter_video(urls):
2992 return list(filter(check_video, urls))
2993
2994 # Start with something easy: JW Player in SWFObject
2995 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2996 if not found:
2997 # Look for gorilla-vid style embedding
2998 found = filter_video(re.findall(r'''(?sx)
2999 (?:
3000 jw_plugins|
3001 JWPlayerOptions|
3002 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3003 )
3004 .*?
3005 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3006 if not found:
3007 # Broaden the search a little bit
3008 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3009 if not found:
3010 # Broaden the findall a little bit: JWPlayer JS loader
3011 found = filter_video(re.findall(
3012 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3013 if not found:
3014 # Flow player
3015 found = filter_video(re.findall(r'''(?xs)
3016 flowplayer\("[^"]+",\s*
3017 \{[^}]+?\}\s*,
3018 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3019 ["']?url["']?\s*:\s*["']([^"']+)["']
3020 ''', webpage))
3021 if not found:
3022 # Cinerama player
3023 found = re.findall(
3024 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3025 if not found:
3026 # Try to find twitter cards info
3027 # twitter:player:stream should be checked before twitter:player since
3028 # it is expected to contain a raw stream (see
3029 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3030 found = filter_video(re.findall(
3031 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3032 if not found:
3033 # We look for Open Graph info:
3034 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3035 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3036 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3037 if m_video_type is not None:
3038 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3039 if not found:
3040 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3041 found = re.search(
3042 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3043 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3044 webpage)
3045 if not found:
3046 # Look also in Refresh HTTP header
3047 refresh_header = head_response.headers.get('Refresh')
3048 if refresh_header:
3049 # In python 2 response HTTP headers are bytestrings
3050 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3051 refresh_header = refresh_header.decode('iso-8859-1')
3052 found = re.search(REDIRECT_REGEX, refresh_header)
3053 if found:
3054 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3055 if new_url != url:
3056 self.report_following_redirect(new_url)
3057 return {
3058 '_type': 'url',
3059 'url': new_url,
3060 }
3061 else:
3062 found = None
3063
3064 if not found:
3065 # twitter:player is a https URL to iframe player that may or may not
3066 # be supported by youtube-dl thus this is checked the very last (see
3067 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3068 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3069 if embed_url and embed_url != url:
3070 return self.url_result(embed_url)
3071
3072 if not found:
3073 raise UnsupportedError(url)
3074
3075 entries = []
3076 for video_url in orderedSet(found):
3077 video_url = unescapeHTML(video_url)
3078 video_url = video_url.replace('\\/', '/')
3079 video_url = compat_urlparse.urljoin(url, video_url)
3080 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3081
3082 # Sometimes, jwplayer extraction will result in a YouTube URL
3083 if YoutubeIE.suitable(video_url):
3084 entries.append(self.url_result(video_url, 'Youtube'))
3085 continue
3086
3087 # here's a fun little line of code for you:
3088 video_id = os.path.splitext(video_id)[0]
3089
3090 entry_info_dict = {
3091 'id': video_id,
3092 'uploader': video_uploader,
3093 'title': video_title,
3094 'age_limit': age_limit,
3095 }
3096
3097 if RtmpIE.suitable(video_url):
3098 entry_info_dict.update({
3099 '_type': 'url_transparent',
3100 'ie_key': RtmpIE.ie_key(),
3101 'url': video_url,
3102 })
3103 entries.append(entry_info_dict)
3104 continue
3105
3106 ext = determine_ext(video_url)
3107 if ext == 'smil':
3108 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3109 elif ext == 'xspf':
3110 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3111 elif ext == 'm3u8':
3112 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3113 elif ext == 'mpd':
3114 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3115 elif ext == 'f4m':
3116 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3117 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3118 # Just matching .ism/manifest is not enough to be reliably sure
3119 # whether it's actually an ISM manifest or some other streaming
3120 # manifest since there are various streaming URL formats
3121 # possible (see [1]) as well as some other shenanigans like
3122 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3123 # so on.
3124 # Thus the most reasonable way to solve this is to delegate
3125 # to generic extractor in order to look into the contents of
3126 # the manifest itself.
3127 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3128 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3129 entry_info_dict = self.url_result(
3130 smuggle_url(video_url, {'to_generic': True}),
3131 GenericIE.ie_key())
3132 else:
3133 entry_info_dict['url'] = video_url
3134
3135 if entry_info_dict.get('formats'):
3136 self._sort_formats(entry_info_dict['formats'])
3137
3138 entries.append(entry_info_dict)
3139
3140 if len(entries) == 1:
3141 return entries[0]
3142 else:
3143 for num, e in enumerate(entries, start=1):
3144 # 'url' results don't have a title
3145 if e.get('title') is not None:
3146 e['title'] = '%s (%d)' % (e['title'], num)
3147 return {
3148 '_type': 'playlist',
3149 'entries': entries,
3150 }