]> jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/generic.py
[generic] Add support for Video.js embeds
[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 (
63 DailymotionIE,
64 DailymotionCloudIE,
65 )
66 from .dailymail import DailyMailIE
67 from .onionstudios import OnionStudiosIE
68 from .viewlift import ViewLiftEmbedIE
69 from .mtv import MTVServicesEmbeddedIE
70 from .pladform import PladformIE
71 from .videomore import VideomoreIE
72 from .webcaster import WebcasterFeedIE
73 from .googledrive import GoogleDriveIE
74 from .jwplatform import JWPlatformIE
75 from .digiteka import DigitekaIE
76 from .arkena import ArkenaIE
77 from .instagram import InstagramIE
78 from .liveleak import LiveLeakIE
79 from .threeqsdn import ThreeQSDNIE
80 from .theplatform import ThePlatformIE
81 from .vessel import VesselIE
82 from .kaltura import KalturaIE
83 from .eagleplatform import EaglePlatformIE
84 from .facebook import FacebookIE
85 from .soundcloud import SoundcloudIE
86 from .tunein import TuneInBaseIE
87 from .vbox7 import Vbox7IE
88 from .dbtv import DBTVIE
89 from .piksel import PikselIE
90 from .videa import VideaIE
91 from .twentymin import TwentyMinutenIE
92 from .ustream import UstreamIE
93 from .openload import OpenloadIE
94 from .videopress import VideoPressIE
95 from .rutube import RutubeIE
96 from .limelight import LimelightBaseIE
97 from .anvato import AnvatoIE
98 from .washingtonpost import WashingtonPostIE
99 from .wistia import WistiaIE
100 from .mediaset import MediasetIE
101 from .joj import JojIE
102 from .megaphone import MegaphoneIE
103 from .vzaar import VzaarIE
104
105
106 class GenericIE(InfoExtractor):
107 IE_DESC = 'Generic downloader that works on some sites'
108 _VALID_URL = r'.*'
109 IE_NAME = 'generic'
110 _TESTS = [
111 # Direct link to a video
112 {
113 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
114 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
115 'info_dict': {
116 'id': 'trailer',
117 'ext': 'mp4',
118 'title': 'trailer',
119 'upload_date': '20100513',
120 }
121 },
122 # Direct link to media delivered compressed (until Accept-Encoding is *)
123 {
124 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
125 'md5': '128c42e68b13950268b648275386fc74',
126 'info_dict': {
127 'id': 'FictionJunction-Parallel_Hearts',
128 'ext': 'flac',
129 'title': 'FictionJunction-Parallel_Hearts',
130 'upload_date': '20140522',
131 },
132 'expected_warnings': [
133 'URL could be a direct video link, returning it as such.'
134 ],
135 'skip': 'URL invalid',
136 },
137 # Direct download with broken HEAD
138 {
139 'url': 'http://ai-radio.org:8000/radio.opus',
140 'info_dict': {
141 'id': 'radio',
142 'ext': 'opus',
143 'title': 'radio',
144 },
145 'params': {
146 'skip_download': True, # infinite live stream
147 },
148 'expected_warnings': [
149 r'501.*Not Implemented',
150 r'400.*Bad Request',
151 ],
152 },
153 # Direct link with incorrect MIME type
154 {
155 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
156 'md5': '4ccbebe5f36706d85221f204d7eb5913',
157 'info_dict': {
158 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
159 'id': '5_Lennart_Poettering_-_Systemd',
160 'ext': 'webm',
161 'title': '5_Lennart_Poettering_-_Systemd',
162 'upload_date': '20141120',
163 },
164 'expected_warnings': [
165 'URL could be a direct video link, returning it as such.'
166 ]
167 },
168 # RSS feed
169 {
170 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
171 'info_dict': {
172 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
173 'title': 'Zero Punctuation',
174 'description': 're:.*groundbreaking video review series.*'
175 },
176 'playlist_mincount': 11,
177 },
178 # RSS feed with enclosure
179 {
180 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
181 'info_dict': {
182 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
183 'ext': 'm4v',
184 'upload_date': '20150228',
185 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
186 }
187 },
188 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
189 {
190 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
191 'info_dict': {
192 'id': 'smil',
193 'ext': 'mp4',
194 'title': 'Automatics, robotics and biocybernetics',
195 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
196 'upload_date': '20130627',
197 'formats': 'mincount:16',
198 'subtitles': 'mincount:1',
199 },
200 'params': {
201 'force_generic_extractor': True,
202 'skip_download': True,
203 },
204 },
205 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
206 {
207 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
208 'info_dict': {
209 'id': 'hds',
210 'ext': 'flv',
211 'title': 'hds',
212 'formats': 'mincount:1',
213 },
214 'params': {
215 'skip_download': True,
216 },
217 },
218 # SMIL from https://www.restudy.dk/video/play/id/1637
219 {
220 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
221 'info_dict': {
222 'id': 'video_1637',
223 'ext': 'flv',
224 'title': 'video_1637',
225 'formats': 'mincount:3',
226 },
227 'params': {
228 'skip_download': True,
229 },
230 },
231 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
232 {
233 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
234 'info_dict': {
235 'id': 'smil-service',
236 'ext': 'flv',
237 'title': 'smil-service',
238 'formats': 'mincount:1',
239 },
240 'params': {
241 'skip_download': True,
242 },
243 },
244 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
245 {
246 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
247 'info_dict': {
248 'id': '4719370',
249 'ext': 'mp4',
250 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
251 'formats': 'mincount:3',
252 },
253 'params': {
254 'skip_download': True,
255 },
256 },
257 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
258 {
259 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
260 'info_dict': {
261 'id': 'mZlp2ctYIUEB',
262 'ext': 'mp4',
263 'title': 'Tikibad ontruimd wegens brand',
264 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
265 'thumbnail': r're:^https?://.*\.jpg$',
266 'duration': 33,
267 },
268 'params': {
269 'skip_download': True,
270 },
271 },
272 # MPD from http://dash-mse-test.appspot.com/media.html
273 {
274 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
275 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
276 'info_dict': {
277 'id': 'car-20120827-manifest',
278 'ext': 'mp4',
279 'title': 'car-20120827-manifest',
280 'formats': 'mincount:9',
281 'upload_date': '20130904',
282 },
283 'params': {
284 'format': 'bestvideo',
285 },
286 },
287 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
288 {
289 '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',
290 'info_dict': {
291 'id': 'content',
292 'ext': 'mp4',
293 'title': 'content',
294 'formats': 'mincount:8',
295 },
296 'params': {
297 # m3u8 downloads
298 'skip_download': True,
299 },
300 'skip': 'video gone',
301 },
302 # m3u8 served with Content-Type: text/plain
303 {
304 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
305 'info_dict': {
306 'id': 'index',
307 'ext': 'mp4',
308 'title': 'index',
309 'upload_date': '20140720',
310 'formats': 'mincount:11',
311 },
312 'params': {
313 # m3u8 downloads
314 'skip_download': True,
315 },
316 'skip': 'video gone',
317 },
318 # google redirect
319 {
320 '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',
321 'info_dict': {
322 'id': 'cmQHVoWB5FY',
323 'ext': 'mp4',
324 'upload_date': '20130224',
325 'uploader_id': 'TheVerge',
326 'description': r're:^Chris Ziegler takes a look at the\.*',
327 'uploader': 'The Verge',
328 'title': 'First Firefox OS phones side-by-side',
329 },
330 'params': {
331 'skip_download': False,
332 }
333 },
334 {
335 # redirect in Refresh HTTP header
336 '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',
337 'info_dict': {
338 'id': 'pO8h3EaFRdo',
339 'ext': 'mp4',
340 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
341 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
342 'upload_date': '20150917',
343 'uploader_id': 'brtvofficial',
344 'uploader': 'Boiler Room',
345 },
346 'params': {
347 'skip_download': False,
348 },
349 },
350 {
351 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
352 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
353 'info_dict': {
354 'id': '13601338388002',
355 'ext': 'mp4',
356 'uploader': 'www.hodiho.fr',
357 'title': 'R\u00e9gis plante sa Jeep',
358 }
359 },
360 # bandcamp page with custom domain
361 {
362 'add_ie': ['Bandcamp'],
363 'url': 'http://bronyrock.com/track/the-pony-mash',
364 'info_dict': {
365 'id': '3235767654',
366 'ext': 'mp3',
367 'title': 'The Pony Mash',
368 'uploader': 'M_Pallante',
369 },
370 'skip': 'There is a limit of 200 free downloads / month for the test song',
371 },
372 {
373 # embedded brightcove video
374 # it also tests brightcove videos that need to set the 'Referer'
375 # in the http requests
376 'add_ie': ['BrightcoveLegacy'],
377 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
378 'info_dict': {
379 'id': '2765128793001',
380 'ext': 'mp4',
381 'title': 'Le cours de bourse : l’analyse technique',
382 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
383 'uploader': 'BFM BUSINESS',
384 },
385 'params': {
386 'skip_download': True,
387 },
388 },
389 {
390 # embedded with itemprop embedURL and video id spelled as `idVideo`
391 'add_id': ['BrightcoveLegacy'],
392 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
393 'info_dict': {
394 'id': '5255628253001',
395 'ext': 'mp4',
396 'title': 'md5:37c519b1128915607601e75a87995fc0',
397 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
398 'uploader': 'BFM BUSINESS',
399 'uploader_id': '876450612001',
400 'timestamp': 1482255315,
401 'upload_date': '20161220',
402 },
403 'params': {
404 'skip_download': True,
405 },
406 },
407 {
408 # https://github.com/rg3/youtube-dl/issues/2253
409 'url': 'http://bcove.me/i6nfkrc3',
410 'md5': '0ba9446db037002366bab3b3eb30c88c',
411 'info_dict': {
412 'id': '3101154703001',
413 'ext': 'mp4',
414 'title': 'Still no power',
415 'uploader': 'thestar.com',
416 '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.',
417 },
418 'add_ie': ['BrightcoveLegacy'],
419 'skip': 'video gone',
420 },
421 {
422 'url': 'http://www.championat.com/video/football/v/87/87499.html',
423 'md5': 'fb973ecf6e4a78a67453647444222983',
424 'info_dict': {
425 'id': '3414141473001',
426 'ext': 'mp4',
427 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
428 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
429 'uploader': 'Championat',
430 },
431 },
432 {
433 # https://github.com/rg3/youtube-dl/issues/3541
434 'add_ie': ['BrightcoveLegacy'],
435 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
436 'info_dict': {
437 'id': '3866516442001',
438 'ext': 'mp4',
439 'title': 'Leer mij vrouwen kennen: Aflevering 1',
440 'description': 'Leer mij vrouwen kennen: Aflevering 1',
441 'uploader': 'SBS Broadcasting',
442 },
443 'skip': 'Restricted to Netherlands',
444 'params': {
445 'skip_download': True, # m3u8 download
446 },
447 },
448 {
449 # Brightcove video in <iframe>
450 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
451 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
452 'info_dict': {
453 'id': '5360463607001',
454 'ext': 'mp4',
455 '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',
456 '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。',
457 'uploader': 'United Nations',
458 'uploader_id': '1362235914001',
459 'timestamp': 1489593889,
460 'upload_date': '20170315',
461 },
462 'add_ie': ['BrightcoveLegacy'],
463 },
464 {
465 # Brightcove with alternative playerID key
466 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
467 'info_dict': {
468 'id': 'nmeth.2062_SV1',
469 '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',
470 },
471 'playlist': [{
472 'info_dict': {
473 'id': '2228375078001',
474 'ext': 'mp4',
475 'title': 'nmeth.2062-sv1',
476 'description': 'nmeth.2062-sv1',
477 'timestamp': 1363357591,
478 'upload_date': '20130315',
479 'uploader': 'Nature Publishing Group',
480 'uploader_id': '1964492299001',
481 },
482 }],
483 },
484 {
485 # Brightcove with UUID in videoPlayer
486 'url': 'http://www8.hp.com/cn/zh/home.html',
487 'info_dict': {
488 'id': '5255815316001',
489 'ext': 'mp4',
490 'title': 'Sprocket Video - China',
491 'description': 'Sprocket Video - China',
492 'uploader': 'HP-Video Gallery',
493 'timestamp': 1482263210,
494 'upload_date': '20161220',
495 'uploader_id': '1107601872001',
496 },
497 'params': {
498 'skip_download': True, # m3u8 download
499 },
500 'skip': 'video rotates...weekly?',
501 },
502 {
503 # Brightcove:new type [2].
504 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
505 'md5': '2b35148fcf48da41c9fb4591650784f3',
506 'info_dict': {
507 'id': '5348741021001',
508 'ext': 'mp4',
509 'upload_date': '20170306',
510 'uploader_id': '4191638492001',
511 'timestamp': 1488769918,
512 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
513
514 },
515 },
516 {
517 # Alternative brightcove <video> attributes
518 '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/',
519 'info_dict': {
520 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
521 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
522 },
523 'playlist': [{
524 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
525 'info_dict': {
526 'id': '5311302538001',
527 'ext': 'mp4',
528 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
529 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
530 'timestamp': 1486321708,
531 'upload_date': '20170205',
532 'uploader_id': '800000640001',
533 },
534 'only_matching': True,
535 }],
536 },
537 {
538 # Brightcove with UUID in videoPlayer
539 'url': 'http://www8.hp.com/cn/zh/home.html',
540 'info_dict': {
541 'id': '5255815316001',
542 'ext': 'mp4',
543 'title': 'Sprocket Video - China',
544 'description': 'Sprocket Video - China',
545 'uploader': 'HP-Video Gallery',
546 'timestamp': 1482263210,
547 'upload_date': '20161220',
548 'uploader_id': '1107601872001',
549 },
550 'params': {
551 'skip_download': True, # m3u8 download
552 },
553 },
554 # ooyala video
555 {
556 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
557 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
558 'info_dict': {
559 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
560 'ext': 'mp4',
561 'title': '2cc213299525360.mov', # that's what we get
562 'duration': 238.231,
563 },
564 'add_ie': ['Ooyala'],
565 },
566 {
567 # ooyala video embedded with http://player.ooyala.com/iframe.js
568 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
569 'info_dict': {
570 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
571 'ext': 'mp4',
572 'title': '"Steve Jobs: Man in the Machine" trailer',
573 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
574 'duration': 135.427,
575 },
576 'params': {
577 'skip_download': True,
578 },
579 'skip': 'movie expired',
580 },
581 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
582 {
583 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
584 'info_dict': {
585 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
586 'ext': 'mp4',
587 'title': 'Steampunk Fest Comes to Honesdale',
588 'duration': 43.276,
589 },
590 'params': {
591 'skip_download': True,
592 }
593 },
594 # embed.ly video
595 {
596 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
597 'info_dict': {
598 'id': '9ODmcdjQcHQ',
599 'ext': 'mp4',
600 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
601 'upload_date': '20140225',
602 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
603 'uploader': 'Tested',
604 'uploader_id': 'testedcom',
605 },
606 # No need to test YoutubeIE here
607 'params': {
608 'skip_download': True,
609 },
610 },
611 # funnyordie embed
612 {
613 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
614 'info_dict': {
615 'id': '18e820ec3f',
616 'ext': 'mp4',
617 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
618 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
619 },
620 # HEAD requests lead to endless 301, while GET is OK
621 'expected_warnings': ['301'],
622 },
623 # RUTV embed
624 {
625 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
626 'info_dict': {
627 'id': '776940',
628 'ext': 'mp4',
629 'title': 'Охотское море стало целиком российским',
630 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
631 },
632 'params': {
633 # m3u8 download
634 'skip_download': True,
635 },
636 },
637 # TVC embed
638 {
639 '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/',
640 'info_dict': {
641 'id': '55304',
642 'ext': 'mp4',
643 'title': 'Дошкольное воспитание',
644 },
645 },
646 # SportBox embed
647 {
648 'url': 'http://www.vestifinance.ru/articles/25753',
649 'info_dict': {
650 'id': '25753',
651 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
652 },
653 'playlist': [{
654 'info_dict': {
655 'id': '370908',
656 'title': 'Госзаказ. День 3',
657 'ext': 'mp4',
658 }
659 }, {
660 'info_dict': {
661 'id': '370905',
662 'title': 'Госзаказ. День 2',
663 'ext': 'mp4',
664 }
665 }, {
666 'info_dict': {
667 'id': '370902',
668 'title': 'Госзаказ. День 1',
669 'ext': 'mp4',
670 }
671 }],
672 'params': {
673 # m3u8 download
674 'skip_download': True,
675 },
676 },
677 # Myvi.ru embed
678 {
679 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
680 'info_dict': {
681 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
682 'ext': 'mp4',
683 'title': 'Ужастики, русский трейлер (2015)',
684 'thumbnail': r're:^https?://.*\.jpg$',
685 'duration': 153,
686 }
687 },
688 # XHamster embed
689 {
690 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
691 'info_dict': {
692 'id': 'showthread',
693 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
694 },
695 'playlist_mincount': 7,
696 # This forum does not allow <iframe> syntaxes anymore
697 # Now HTML tags are displayed as-is
698 'skip': 'No videos on this page',
699 },
700 # Embedded TED video
701 {
702 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
703 'md5': '65fdff94098e4a607385a60c5177c638',
704 'info_dict': {
705 'id': '1969',
706 'ext': 'mp4',
707 'title': 'Hidden miracles of the natural world',
708 'uploader': 'Louie Schwartzberg',
709 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
710 }
711 },
712 # nowvideo embed hidden behind percent encoding
713 {
714 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
715 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
716 'info_dict': {
717 'id': '06e53103ca9aa',
718 'ext': 'flv',
719 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
720 'description': 'No description',
721 },
722 },
723 # arte embed
724 {
725 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
726 'md5': '7653032cbb25bf6c80d80f217055fa43',
727 'info_dict': {
728 'id': '048195-004_PLUS7-F',
729 'ext': 'flv',
730 'title': 'X:enius',
731 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
732 'upload_date': '20140320',
733 },
734 'params': {
735 'skip_download': 'Requires rtmpdump'
736 },
737 'skip': 'video gone',
738 },
739 # francetv embed
740 {
741 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
742 'info_dict': {
743 'id': 'EV_30231',
744 'ext': 'mp4',
745 'title': 'Alcaline, le concert avec Calogero',
746 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
747 'upload_date': '20150226',
748 'timestamp': 1424989860,
749 'duration': 5400,
750 },
751 'params': {
752 # m3u8 downloads
753 'skip_download': True,
754 },
755 'expected_warnings': [
756 'Forbidden'
757 ]
758 },
759 # Condé Nast embed
760 {
761 'url': 'http://www.wired.com/2014/04/honda-asimo/',
762 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
763 'info_dict': {
764 'id': '53501be369702d3275860000',
765 'ext': 'mp4',
766 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
767 }
768 },
769 # Dailymotion embed
770 {
771 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
772 'md5': '441aeeb82eb72c422c7f14ec533999cd',
773 'info_dict': {
774 'id': 'k2mm4bCdJ6CQ2i7c8o2',
775 'ext': 'mp4',
776 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
777 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
778 'uploader': 'Spi0n',
779 'uploader_id': 'xgditw',
780 'upload_date': '20140425',
781 'timestamp': 1398441542,
782 },
783 'add_ie': ['Dailymotion'],
784 },
785 # DailyMail embed
786 {
787 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
788 'info_dict': {
789 'id': '1495629',
790 'ext': 'mp4',
791 'title': 'Care worker punches elderly dementia patient in head 11 times',
792 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
793 },
794 'add_ie': ['DailyMail'],
795 'params': {
796 'skip_download': True,
797 },
798 },
799 # YouTube embed
800 {
801 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
802 'info_dict': {
803 'id': 'FXRb4ykk4S0',
804 'ext': 'mp4',
805 'title': 'The NBL Auction 2014',
806 'uploader': 'BADMINTON England',
807 'uploader_id': 'BADMINTONEvents',
808 'upload_date': '20140603',
809 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
810 },
811 'add_ie': ['Youtube'],
812 'params': {
813 'skip_download': True,
814 }
815 },
816 # MTVSercices embed
817 {
818 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
819 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
820 'info_dict': {
821 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
822 'ext': 'mp4',
823 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
824 'description': 'Two valets share their love for movie star Liam Neesons.',
825 'timestamp': 1349922600,
826 'upload_date': '20121011',
827 },
828 },
829 # YouTube embed via <data-embed-url="">
830 {
831 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
832 'info_dict': {
833 'id': '4vAffPZIT44',
834 'ext': 'mp4',
835 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
836 'uploader': 'Gameloft',
837 'uploader_id': 'gameloft',
838 'upload_date': '20140828',
839 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
840 },
841 'params': {
842 'skip_download': True,
843 }
844 },
845 # YouTube <object> embed
846 {
847 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
848 'md5': '516718101ec834f74318df76259fb3cc',
849 'info_dict': {
850 'id': 'msN87y-iEx0',
851 'ext': 'webm',
852 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
853 'upload_date': '20080526',
854 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
855 'uploader': 'Christopher Sykes',
856 'uploader_id': 'ChristopherJSykes',
857 },
858 'add_ie': ['Youtube'],
859 },
860 # Camtasia studio
861 {
862 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
863 'playlist': [{
864 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
865 'info_dict': {
866 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
867 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
868 'ext': 'flv',
869 'duration': 2235.90,
870 }
871 }, {
872 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
873 'info_dict': {
874 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
875 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
876 'ext': 'flv',
877 'duration': 2235.93,
878 }
879 }],
880 'info_dict': {
881 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
882 }
883 },
884 # Flowplayer
885 {
886 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
887 'md5': '9d65602bf31c6e20014319c7d07fba27',
888 'info_dict': {
889 'id': '5123ea6d5e5a7',
890 'ext': 'mp4',
891 'age_limit': 18,
892 'uploader': 'www.handjobhub.com',
893 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
894 }
895 },
896 # Multiple brightcove videos
897 # https://github.com/rg3/youtube-dl/issues/2283
898 {
899 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
900 'info_dict': {
901 'id': 'always-never',
902 'title': 'Always / Never - The New Yorker',
903 },
904 'playlist_count': 3,
905 'params': {
906 'extract_flat': False,
907 'skip_download': True,
908 }
909 },
910 # MLB embed
911 {
912 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
913 'md5': '96f09a37e44da40dd083e12d9a683327',
914 'info_dict': {
915 'id': '33322633',
916 'ext': 'mp4',
917 'title': 'Ump changes call to ball',
918 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
919 'duration': 48,
920 'timestamp': 1401537900,
921 'upload_date': '20140531',
922 'thumbnail': r're:^https?://.*\.jpg$',
923 },
924 },
925 # Wistia embed
926 {
927 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
928 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
929 'info_dict': {
930 'id': '6e2wtrbdaf',
931 'ext': 'mov',
932 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
933 'description': 'a Paywall Videos video from Remilon',
934 'duration': 644.072,
935 'uploader': 'study.com',
936 'timestamp': 1459678540,
937 'upload_date': '20160403',
938 'filesize': 24687186,
939 },
940 },
941 {
942 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
943 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
944 'info_dict': {
945 'id': 'uxjb0lwrcz',
946 'ext': 'mp4',
947 'title': 'Conversation about Hexagonal Rails Part 1',
948 'description': 'a Martin Fowler video from ThoughtWorks',
949 'duration': 1715.0,
950 'uploader': 'thoughtworks.wistia.com',
951 'timestamp': 1401832161,
952 'upload_date': '20140603',
953 },
954 },
955 # Wistia standard embed (async)
956 {
957 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
958 'info_dict': {
959 'id': '807fafadvk',
960 'ext': 'mp4',
961 'title': 'Drip Brennan Dunn Workshop',
962 'description': 'a JV Webinars video from getdrip-1',
963 'duration': 4986.95,
964 'timestamp': 1463607249,
965 'upload_date': '20160518',
966 },
967 'params': {
968 'skip_download': True,
969 }
970 },
971 # Soundcloud embed
972 {
973 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
974 'info_dict': {
975 'id': '174391317',
976 'ext': 'mp3',
977 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
978 'uploader': 'Sophos Security',
979 'title': 'Chet Chat 171 - Oct 29, 2014',
980 'upload_date': '20141029',
981 }
982 },
983 # Soundcloud multiple embeds
984 {
985 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
986 'info_dict': {
987 'id': '52809',
988 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
989 },
990 'playlist_mincount': 7,
991 },
992 # TuneIn station embed
993 {
994 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
995 'info_dict': {
996 'id': '204146',
997 'ext': 'mp3',
998 'title': 'CNRV',
999 'location': 'Paris, France',
1000 'is_live': True,
1001 },
1002 'params': {
1003 # Live stream
1004 'skip_download': True,
1005 },
1006 },
1007 # Livestream embed
1008 {
1009 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1010 'info_dict': {
1011 'id': '67864563',
1012 'ext': 'flv',
1013 'upload_date': '20141112',
1014 'title': 'Rosetta #CometLanding webcast HL 10',
1015 }
1016 },
1017 # Another Livestream embed, without 'new.' in URL
1018 {
1019 'url': 'https://www.freespeech.org/',
1020 'info_dict': {
1021 'id': '123537347',
1022 'ext': 'mp4',
1023 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1024 },
1025 'params': {
1026 # Live stream
1027 'skip_download': True,
1028 },
1029 },
1030 # LazyYT
1031 {
1032 'url': 'https://skiplagged.com/',
1033 'info_dict': {
1034 'id': 'skiplagged',
1035 'title': 'Skiplagged: The smart way to find cheap flights',
1036 },
1037 'playlist_mincount': 1,
1038 'add_ie': ['Youtube'],
1039 },
1040 # Cinchcast embed
1041 {
1042 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1043 'info_dict': {
1044 'id': '7141703',
1045 'ext': 'mp3',
1046 'upload_date': '20141126',
1047 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1048 }
1049 },
1050 # Cinerama player
1051 {
1052 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1053 'info_dict': {
1054 'id': '730m_DandD_1901_512k',
1055 'ext': 'mp4',
1056 'uploader': 'www.abc.net.au',
1057 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1058 }
1059 },
1060 # embedded viddler video
1061 {
1062 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1063 'info_dict': {
1064 'id': '4d03aad9',
1065 'ext': 'mp4',
1066 'uploader': 'deadspin',
1067 'title': 'WALL-TO-GORTAT',
1068 'timestamp': 1422285291,
1069 'upload_date': '20150126',
1070 },
1071 'add_ie': ['Viddler'],
1072 },
1073 # Libsyn embed
1074 {
1075 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1076 'info_dict': {
1077 'id': '3377616',
1078 'ext': 'mp3',
1079 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1080 'description': 'md5:601cb790edd05908957dae8aaa866465',
1081 'upload_date': '20150220',
1082 },
1083 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1084 },
1085 # jwplayer YouTube
1086 {
1087 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1088 'info_dict': {
1089 'id': 'Mrj4DVp2zeA',
1090 'ext': 'mp4',
1091 'upload_date': '20150212',
1092 'uploader': 'The National Archives UK',
1093 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1094 'uploader_id': 'NationalArchives08',
1095 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1096 },
1097 },
1098 # jwplayer rtmp
1099 {
1100 'url': 'http://www.suffolk.edu/sjc/',
1101 'info_dict': {
1102 'id': 'sjclive',
1103 'ext': 'flv',
1104 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1105 'uploader': 'www.suffolk.edu',
1106 },
1107 'params': {
1108 'skip_download': True,
1109 }
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 'thumbnail': r're:^https?://.*\.jpg$',
1119 },
1120 },
1121 {
1122 # JWPlayer config passed as variable
1123 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1124 'info_dict': {
1125 'id': '3326530_hq',
1126 'ext': 'mp4',
1127 'title': 'ARIELE | Tube Cup',
1128 'uploader': 'www.txxx.com',
1129 'age_limit': 18,
1130 },
1131 'params': {
1132 'skip_download': True,
1133 }
1134 },
1135 {
1136 # Video.js embed
1137 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1138 'info_dict': {
1139 'id': 'yygqldloqIk',
1140 'ext': 'mp4',
1141 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1142 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1143 'upload_date': '20130314',
1144 'uploader': 'PROстое3D',
1145 'uploader_id': 'PROstoe3D',
1146 },
1147 'params': {
1148 'skip_download': True,
1149 },
1150 },
1151 # rtl.nl embed
1152 {
1153 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1154 'playlist_mincount': 5,
1155 'info_dict': {
1156 'id': 'aanslagen-kopenhagen',
1157 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1158 }
1159 },
1160 # Zapiks embed
1161 {
1162 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1163 'info_dict': {
1164 'id': '118046',
1165 'ext': 'mp4',
1166 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1167 }
1168 },
1169 # Kaltura embed (different embed code)
1170 {
1171 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1172 'info_dict': {
1173 'id': '1_a52wc67y',
1174 'ext': 'flv',
1175 'upload_date': '20150127',
1176 'uploader_id': 'PremierMedia',
1177 'timestamp': int,
1178 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1179 },
1180 },
1181 # Kaltura embed with single quotes
1182 {
1183 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1184 'info_dict': {
1185 'id': '0_izeg5utt',
1186 'ext': 'mp4',
1187 'title': '35871',
1188 'timestamp': 1355743100,
1189 'upload_date': '20121217',
1190 'uploader_id': 'batchUser',
1191 },
1192 'add_ie': ['Kaltura'],
1193 },
1194 {
1195 # Kaltura embedded via quoted entry_id
1196 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1197 'info_dict': {
1198 'id': '0_utuok90b',
1199 'ext': 'mp4',
1200 'title': '06_matthew_brender_raj_dutt',
1201 'timestamp': 1466638791,
1202 'upload_date': '20160622',
1203 },
1204 'add_ie': ['Kaltura'],
1205 'expected_warnings': [
1206 'Could not send HEAD request'
1207 ],
1208 'params': {
1209 'skip_download': True,
1210 }
1211 },
1212 {
1213 # Kaltura embedded, some fileExt broken (#11480)
1214 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1215 'info_dict': {
1216 'id': '1_sgtvehim',
1217 'ext': 'mp4',
1218 'title': 'Our "Standard Models" of particle physics and cosmology',
1219 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1220 'timestamp': 1321158993,
1221 'upload_date': '20111113',
1222 'uploader_id': 'kps1',
1223 },
1224 'add_ie': ['Kaltura'],
1225 },
1226 {
1227 # Kaltura iframe embed
1228 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1229 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1230 'info_dict': {
1231 'id': '0_f2cfbpwy',
1232 'ext': 'mp4',
1233 'title': 'I. M. Pei: A Centennial Celebration',
1234 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1235 'upload_date': '20170403',
1236 'uploader_id': 'batchUser',
1237 'timestamp': 1491232186,
1238 },
1239 'add_ie': ['Kaltura'],
1240 },
1241 # EaglePlatform embed (generic URL)
1242 {
1243 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1244 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1245 'info_dict': {
1246 'id': '227304',
1247 'ext': 'mp4',
1248 'title': 'Навальный вышел на свободу',
1249 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1250 'thumbnail': r're:^https?://.*\.jpg$',
1251 'duration': 87,
1252 'view_count': int,
1253 'age_limit': 0,
1254 },
1255 'params': {
1256 'skip_download': True,
1257 },
1258 },
1259 # referrer protected EaglePlatform embed
1260 {
1261 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1262 'info_dict': {
1263 'id': '582306',
1264 'ext': 'mp4',
1265 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1266 'thumbnail': r're:^https?://.*\.jpg$',
1267 'duration': 3382,
1268 'view_count': int,
1269 },
1270 'params': {
1271 'skip_download': True,
1272 },
1273 },
1274 # ClipYou (EaglePlatform) embed (custom URL)
1275 {
1276 'url': 'http://muz-tv.ru/play/7129/',
1277 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1278 'info_dict': {
1279 'id': '12820',
1280 'ext': 'mp4',
1281 'title': "'O Sole Mio",
1282 'thumbnail': r're:^https?://.*\.jpg$',
1283 'duration': 216,
1284 'view_count': int,
1285 },
1286 'params': {
1287 'skip_download': True,
1288 },
1289 },
1290 # Pladform embed
1291 {
1292 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1293 'info_dict': {
1294 'id': '100183293',
1295 'ext': 'mp4',
1296 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
1297 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
1298 'thumbnail': r're:^https?://.*\.jpg$',
1299 'duration': 694,
1300 'age_limit': 0,
1301 },
1302 },
1303 # Playwire embed
1304 {
1305 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1306 'info_dict': {
1307 'id': '3519514',
1308 'ext': 'mp4',
1309 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1310 'thumbnail': r're:^https?://.*\.png$',
1311 'duration': 45.115,
1312 },
1313 },
1314 # 5min embed
1315 {
1316 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1317 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1318 'info_dict': {
1319 'id': '518726732',
1320 'ext': 'mp4',
1321 'title': 'Facebook Creates "On This Day" | Crunch Report',
1322 },
1323 },
1324 # SVT embed
1325 {
1326 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1327 'info_dict': {
1328 'id': '2900353',
1329 'ext': 'flv',
1330 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1331 'duration': 27,
1332 'age_limit': 0,
1333 },
1334 },
1335 # Crooks and Liars embed
1336 {
1337 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1338 'info_dict': {
1339 'id': '8RUoRhRi',
1340 'ext': 'mp4',
1341 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1342 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1343 'timestamp': 1428207000,
1344 'upload_date': '20150405',
1345 'uploader': 'Heather',
1346 },
1347 },
1348 # Crooks and Liars external embed
1349 {
1350 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1351 'info_dict': {
1352 'id': 'MTE3MjUtMzQ2MzA',
1353 'ext': 'mp4',
1354 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1355 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1356 'timestamp': 1265032391,
1357 'upload_date': '20100201',
1358 'uploader': 'Heather',
1359 },
1360 },
1361 # NBC Sports vplayer embed
1362 {
1363 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1364 'info_dict': {
1365 'id': 'ln7x1qSThw4k',
1366 'ext': 'flv',
1367 'title': "PFT Live: New leader in the 'new-look' defense",
1368 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1369 'uploader': 'NBCU-SPORTS',
1370 'upload_date': '20140107',
1371 'timestamp': 1389118457,
1372 },
1373 },
1374 # NBC News embed
1375 {
1376 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1377 'md5': '1aa589c675898ae6d37a17913cf68d66',
1378 'info_dict': {
1379 'id': '701714499682',
1380 'ext': 'mp4',
1381 'title': 'PREVIEW: On Assignment: David Letterman',
1382 '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.',
1383 },
1384 },
1385 # UDN embed
1386 {
1387 'url': 'https://video.udn.com/news/300346',
1388 'md5': 'fd2060e988c326991037b9aff9df21a6',
1389 'info_dict': {
1390 'id': '300346',
1391 'ext': 'mp4',
1392 'title': '中一中男師變性 全校師生力挺',
1393 'thumbnail': r're:^https?://.*\.jpg$',
1394 },
1395 'params': {
1396 # m3u8 download
1397 'skip_download': True,
1398 },
1399 },
1400 # Ooyala embed
1401 {
1402 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1403 'info_dict': {
1404 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1405 'ext': 'mp4',
1406 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1407 'title': 'This is what separates the Excel masters from the wannabes',
1408 'duration': 191.933,
1409 },
1410 'params': {
1411 # m3u8 downloads
1412 'skip_download': True,
1413 }
1414 },
1415 # Brightcove URL in single quotes
1416 {
1417 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1418 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1419 'info_dict': {
1420 'id': '4255764656001',
1421 'ext': 'mp4',
1422 'title': 'SN Presents: Russell Martin, World Citizen',
1423 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1424 'uploader': 'Rogers Sportsnet',
1425 'uploader_id': '1704050871',
1426 'upload_date': '20150525',
1427 'timestamp': 1432570283,
1428 },
1429 },
1430 # Dailymotion Cloud video
1431 {
1432 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1433 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1434 'info_dict': {
1435 'id': 'x2uy8t3',
1436 'ext': 'mp4',
1437 'title': 'Sauvons les abeilles ! - Le débat',
1438 'description': 'md5:d9082128b1c5277987825d684939ca26',
1439 'thumbnail': r're:^https?://.*\.jpe?g$',
1440 'timestamp': 1434970506,
1441 'upload_date': '20150622',
1442 'uploader': 'Public Sénat',
1443 'uploader_id': 'xa9gza',
1444 }
1445 },
1446 # OnionStudios embed
1447 {
1448 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1449 'info_dict': {
1450 'id': '2855',
1451 'ext': 'mp4',
1452 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1453 'thumbnail': r're:^https?://.*\.jpe?g$',
1454 'uploader': 'ClickHole',
1455 'uploader_id': 'clickhole',
1456 }
1457 },
1458 # SnagFilms embed
1459 {
1460 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1461 'info_dict': {
1462 'id': '74849a00-85a9-11e1-9660-123139220831',
1463 'ext': 'mp4',
1464 'title': '#whilewewatch',
1465 }
1466 },
1467 # AdobeTVVideo embed
1468 {
1469 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1470 'md5': '43662b577c018ad707a63766462b1e87',
1471 'info_dict': {
1472 'id': '2456',
1473 'ext': 'mp4',
1474 'title': 'New experience with Acrobat DC',
1475 'description': 'New experience with Acrobat DC',
1476 'duration': 248.667,
1477 },
1478 },
1479 # BrightcoveInPageEmbed embed
1480 {
1481 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1482 'info_dict': {
1483 'id': '4238694884001',
1484 'ext': 'flv',
1485 'title': 'Tabletop: Dread, Last Thoughts',
1486 'description': 'Tabletop: Dread, Last Thoughts',
1487 'duration': 51690,
1488 },
1489 },
1490 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1491 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1492 {
1493 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1494 'info_dict': {
1495 'id': '4785848093001',
1496 'ext': 'mp4',
1497 'title': 'The Cardinal Pell Interview',
1498 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1499 'uploader': 'GlobeCast Australia - GlobeStream',
1500 'uploader_id': '2733773828001',
1501 'upload_date': '20160304',
1502 'timestamp': 1457083087,
1503 },
1504 'params': {
1505 # m3u8 downloads
1506 'skip_download': True,
1507 },
1508 },
1509 {
1510 # Brightcove embed with whitespace around attribute names
1511 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1512 'info_dict': {
1513 'id': '3167554373001',
1514 'ext': 'mp4',
1515 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1516 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1517 'uploader_id': '1079349493',
1518 'upload_date': '20140207',
1519 'timestamp': 1391810548,
1520 },
1521 'params': {
1522 'skip_download': True,
1523 },
1524 },
1525 # Another form of arte.tv embed
1526 {
1527 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1528 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1529 'info_dict': {
1530 'id': '030273-562_PLUS7-F',
1531 'ext': 'mp4',
1532 'title': 'ARTE Reportage - Nulle part, en France',
1533 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1534 'upload_date': '20160409',
1535 },
1536 },
1537 # LiveLeak embed
1538 {
1539 'url': 'http://www.wykop.pl/link/3088787/',
1540 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1541 'info_dict': {
1542 'id': '874_1459135191',
1543 'ext': 'mp4',
1544 'title': 'Man shows poor quality of new apartment building',
1545 'description': 'The wall is like a sand pile.',
1546 'uploader': 'Lake8737',
1547 },
1548 'add_ie': [LiveLeakIE.ie_key()],
1549 },
1550 # Another LiveLeak embed pattern (#13336)
1551 {
1552 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1553 'info_dict': {
1554 'id': '2eb_1496309988',
1555 'ext': 'mp4',
1556 'title': 'Thief robs place where everyone was armed',
1557 'description': 'md5:694d73ee79e535953cf2488562288eee',
1558 'uploader': 'brazilwtf',
1559 },
1560 'add_ie': [LiveLeakIE.ie_key()],
1561 },
1562 # Duplicated embedded video URLs
1563 {
1564 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1565 'info_dict': {
1566 'id': '149298443_480_16c25b74_2',
1567 'ext': 'mp4',
1568 'title': 'vs. Blue Orange Spring Game',
1569 'uploader': 'www.hudl.com',
1570 },
1571 },
1572 # twitter:player:stream embed
1573 {
1574 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1575 'info_dict': {
1576 'id': 'master',
1577 'ext': 'mp4',
1578 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1579 'uploader': 'www.rtl.be',
1580 },
1581 'params': {
1582 # m3u8 downloads
1583 'skip_download': True,
1584 },
1585 },
1586 # twitter:player embed
1587 {
1588 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1589 'md5': 'a3e0df96369831de324f0778e126653c',
1590 'info_dict': {
1591 'id': '4909620399001',
1592 'ext': 'mp4',
1593 'title': 'What Do Black Holes Sound Like?',
1594 'description': 'what do black holes sound like',
1595 'upload_date': '20160524',
1596 'uploader_id': '29913724001',
1597 'timestamp': 1464107587,
1598 'uploader': 'TheAtlantic',
1599 },
1600 'add_ie': ['BrightcoveLegacy'],
1601 },
1602 # Nexx embed
1603 {
1604 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1605 'info_dict': {
1606 'id': '247746',
1607 'ext': 'mp4',
1608 'title': "Yesterday's Jam (OV)",
1609 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1610 'timestamp': 1492594816,
1611 'upload_date': '20170419',
1612 },
1613 'params': {
1614 'format': 'bestvideo',
1615 'skip_download': True,
1616 },
1617 },
1618 # Facebook <iframe> embed
1619 {
1620 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1621 'md5': 'fbcde74f534176ecb015849146dd3aee',
1622 'info_dict': {
1623 'id': '599637780109885',
1624 'ext': 'mp4',
1625 'title': 'Facebook video #599637780109885',
1626 },
1627 },
1628 # Facebook <iframe> embed, plugin video
1629 {
1630 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1631 'info_dict': {
1632 'id': '1754168231264132',
1633 'ext': 'mp4',
1634 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1635 'uploader': 'Tariq Ramadan (official)',
1636 'timestamp': 1496758379,
1637 'upload_date': '20170606',
1638 },
1639 'params': {
1640 'skip_download': True,
1641 },
1642 },
1643 # Facebook API embed
1644 {
1645 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1646 'md5': 'a47372ee61b39a7b90287094d447d94e',
1647 'info_dict': {
1648 'id': '10153467542406923',
1649 'ext': 'mp4',
1650 'title': 'Facebook video #10153467542406923',
1651 },
1652 },
1653 # Wordpress "YouTube Video Importer" plugin
1654 {
1655 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1656 'md5': 'd16797741b560b485194eddda8121b48',
1657 'info_dict': {
1658 'id': 'HNTXWDXV9Is',
1659 'ext': 'mp4',
1660 'title': 'Blue Devils Drumline Stanford lot 2016',
1661 'upload_date': '20160627',
1662 'uploader_id': 'GENOCIDE8GENERAL10',
1663 'uploader': 'cylus cyrus',
1664 },
1665 },
1666 {
1667 # video stored on custom kaltura server
1668 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1669 'md5': '537617d06e64dfed891fa1593c4b30cc',
1670 'info_dict': {
1671 'id': '0_1iotm5bh',
1672 'ext': 'mp4',
1673 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1674 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1675 'uploader_id': 'videos.expansion@el-mundo.net',
1676 'upload_date': '20150429',
1677 'timestamp': 1430303472,
1678 },
1679 'add_ie': ['Kaltura'],
1680 },
1681 {
1682 # Non-standard Vimeo embed
1683 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1684 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1685 'info_dict': {
1686 'id': '148867247',
1687 'ext': 'mp4',
1688 'title': 'Understanding the web - Teaser',
1689 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1690 'upload_date': '20151214',
1691 'uploader': 'OpenClassrooms',
1692 'uploader_id': 'openclassrooms',
1693 },
1694 'add_ie': ['Vimeo'],
1695 },
1696 {
1697 # generic vimeo embed that requires original URL passed as Referer
1698 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1699 'only_matching': True,
1700 },
1701 {
1702 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1703 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1704 'info_dict': {
1705 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1706 'ext': 'mp4',
1707 'title': 'Big Buck Bunny',
1708 'description': 'Royalty free test video',
1709 'timestamp': 1432816365,
1710 'upload_date': '20150528',
1711 'is_live': False,
1712 },
1713 'params': {
1714 'skip_download': True,
1715 },
1716 'add_ie': [ArkenaIE.ie_key()],
1717 },
1718 {
1719 '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/',
1720 'info_dict': {
1721 'id': '1c7141f46c',
1722 'ext': 'mp4',
1723 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1724 },
1725 'params': {
1726 'skip_download': True,
1727 },
1728 'add_ie': [Vbox7IE.ie_key()],
1729 },
1730 {
1731 # DBTV embeds
1732 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1733 'info_dict': {
1734 'id': '43254897',
1735 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1736 },
1737 'playlist_mincount': 3,
1738 },
1739 {
1740 # Videa embeds
1741 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1742 'info_dict': {
1743 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1744 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1745 },
1746 'playlist_mincount': 2,
1747 },
1748 {
1749 # 20 minuten embed
1750 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1751 'info_dict': {
1752 'id': '523629',
1753 'ext': 'mp4',
1754 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1755 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1756 },
1757 'params': {
1758 'skip_download': True,
1759 },
1760 'add_ie': [TwentyMinutenIE.ie_key()],
1761 },
1762 {
1763 # VideoPress embed
1764 'url': 'https://en.support.wordpress.com/videopress/',
1765 'info_dict': {
1766 'id': 'OcobLTqC',
1767 'ext': 'm4v',
1768 'title': 'IMG_5786',
1769 'timestamp': 1435711927,
1770 'upload_date': '20150701',
1771 },
1772 'params': {
1773 'skip_download': True,
1774 },
1775 'add_ie': [VideoPressIE.ie_key()],
1776 },
1777 {
1778 # Rutube embed
1779 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1780 'info_dict': {
1781 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1782 'ext': 'flv',
1783 'title': 'Магаззино: Казань 2',
1784 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1785 'uploader': 'Магаззино',
1786 'upload_date': '20170228',
1787 'uploader_id': '996642',
1788 },
1789 'params': {
1790 'skip_download': True,
1791 },
1792 'add_ie': [RutubeIE.ie_key()],
1793 },
1794 {
1795 # ThePlatform embedded with whitespaces in URLs
1796 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1797 'only_matching': True,
1798 },
1799 {
1800 # Senate ISVP iframe https
1801 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1802 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1803 'info_dict': {
1804 'id': 'govtaff020316',
1805 'ext': 'mp4',
1806 'title': 'Integrated Senate Video Player',
1807 },
1808 'add_ie': [SenateISVPIE.ie_key()],
1809 },
1810 {
1811 # Limelight embeds (1 channel embed + 4 media embeds)
1812 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1813 'info_dict': {
1814 'id': 'FacilitatorTraining2017',
1815 'title': 'Facilitator Training 2017',
1816 },
1817 'playlist_mincount': 5,
1818 },
1819 {
1820 # Limelight embed (LimelightPlayerUtil.embed)
1821 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1822 'info_dict': {
1823 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1824 'ext': 'mp4',
1825 'title': '07448641',
1826 'timestamp': 1499890639,
1827 'upload_date': '20170712',
1828 },
1829 'params': {
1830 'skip_download': True,
1831 },
1832 'add_ie': ['LimelightMedia'],
1833 },
1834 {
1835 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1836 'info_dict': {
1837 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1838 'title': 'Standoff with Walnut Creek murder suspect ends',
1839 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1840 },
1841 'playlist_mincount': 4,
1842 },
1843 {
1844 # WashingtonPost embed
1845 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1846 'info_dict': {
1847 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1848 'ext': 'mp4',
1849 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1850 '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.',
1851 'timestamp': 1455216756,
1852 'uploader': 'The Washington Post',
1853 'upload_date': '20160211',
1854 },
1855 'add_ie': [WashingtonPostIE.ie_key()],
1856 },
1857 {
1858 # Mediaset embed
1859 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1860 'info_dict': {
1861 'id': '720642',
1862 'ext': 'mp4',
1863 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1864 },
1865 'params': {
1866 'skip_download': True,
1867 },
1868 'add_ie': [MediasetIE.ie_key()],
1869 },
1870 {
1871 # JOJ.sk embeds
1872 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1873 'info_dict': {
1874 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1875 'title': 'Slovenskom sa prehnala vlna silných búrok',
1876 },
1877 'playlist_mincount': 5,
1878 'add_ie': [JojIE.ie_key()],
1879 },
1880 {
1881 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1882 'url': 'https://tvrain.ru/amp/418921/',
1883 'md5': 'cc00413936695987e8de148b67d14f1d',
1884 'info_dict': {
1885 'id': '418921',
1886 'ext': 'mp4',
1887 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1888 },
1889 },
1890 {
1891 # vzaar embed
1892 'url': 'http://help.vzaar.com/article/165-embedding-video',
1893 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1894 'info_dict': {
1895 'id': '8707641',
1896 'ext': 'mp4',
1897 'title': 'Building A Business Online: Principal Chairs Q & A',
1898 },
1899 },
1900 {
1901 # multiple HTML5 videos on one page
1902 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1903 'info_dict': {
1904 'id': 'keyscenarios',
1905 'title': 'Rescue Kit 14 Free Edition - Getting started',
1906 },
1907 'playlist_count': 4,
1908 }
1909 # {
1910 # # TODO: find another test
1911 # # http://schema.org/VideoObject
1912 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1913 # 'md5': '888dcf08b7ea671381f00fab74692755',
1914 # 'info_dict': {
1915 # 'id': 'nyvTSJMKId',
1916 # 'ext': 'mp4',
1917 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1918 # 'description': '#love for cats.',
1919 # 'timestamp': 1461244995,
1920 # 'upload_date': '20160421',
1921 # },
1922 # 'params': {
1923 # 'force_generic_extractor': True,
1924 # },
1925 # }
1926 ]
1927
1928 def report_following_redirect(self, new_url):
1929 """Report information extraction."""
1930 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1931
1932 def _extract_rss(self, url, video_id, doc):
1933 playlist_title = doc.find('./channel/title').text
1934 playlist_desc_el = doc.find('./channel/description')
1935 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1936
1937 entries = []
1938 for it in doc.findall('./channel/item'):
1939 next_url = xpath_text(it, 'link', fatal=False)
1940 if not next_url:
1941 enclosure_nodes = it.findall('./enclosure')
1942 for e in enclosure_nodes:
1943 next_url = e.attrib.get('url')
1944 if next_url:
1945 break
1946
1947 if not next_url:
1948 continue
1949
1950 entries.append({
1951 '_type': 'url_transparent',
1952 'url': next_url,
1953 'title': it.find('title').text,
1954 })
1955
1956 return {
1957 '_type': 'playlist',
1958 'id': url,
1959 'title': playlist_title,
1960 'description': playlist_desc,
1961 'entries': entries,
1962 }
1963
1964 def _extract_camtasia(self, url, video_id, webpage):
1965 """ Returns None if no camtasia video can be found. """
1966
1967 camtasia_cfg = self._search_regex(
1968 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1969 webpage, 'camtasia configuration file', default=None)
1970 if camtasia_cfg is None:
1971 return None
1972
1973 title = self._html_search_meta('DC.title', webpage, fatal=True)
1974
1975 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1976 camtasia_cfg = self._download_xml(
1977 camtasia_url, video_id,
1978 note='Downloading camtasia configuration',
1979 errnote='Failed to download camtasia configuration')
1980 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1981
1982 entries = []
1983 for n in fileset_node.getchildren():
1984 url_n = n.find('./uri')
1985 if url_n is None:
1986 continue
1987
1988 entries.append({
1989 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1990 'title': '%s - %s' % (title, n.tag),
1991 'url': compat_urlparse.urljoin(url, url_n.text),
1992 'duration': float_or_none(n.find('./duration').text),
1993 })
1994
1995 return {
1996 '_type': 'playlist',
1997 'entries': entries,
1998 'title': title,
1999 }
2000
2001 def _real_extract(self, url):
2002 if url.startswith('//'):
2003 return {
2004 '_type': 'url',
2005 'url': self.http_scheme() + url,
2006 }
2007
2008 parsed_url = compat_urlparse.urlparse(url)
2009 if not parsed_url.scheme:
2010 default_search = self._downloader.params.get('default_search')
2011 if default_search is None:
2012 default_search = 'fixup_error'
2013
2014 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2015 if '/' in url:
2016 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2017 return self.url_result('http://' + url)
2018 elif default_search != 'fixup_error':
2019 if default_search == 'auto_warning':
2020 if re.match(r'^(?:url|URL)$', url):
2021 raise ExtractorError(
2022 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2023 expected=True)
2024 else:
2025 self._downloader.report_warning(
2026 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2027 return self.url_result('ytsearch:' + url)
2028
2029 if default_search in ('error', 'fixup_error'):
2030 raise ExtractorError(
2031 '%r is not a valid URL. '
2032 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2033 % (url, url), expected=True)
2034 else:
2035 if ':' not in default_search:
2036 default_search += ':'
2037 return self.url_result(default_search + url)
2038
2039 url, smuggled_data = unsmuggle_url(url)
2040 force_videoid = None
2041 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2042 if smuggled_data and 'force_videoid' in smuggled_data:
2043 force_videoid = smuggled_data['force_videoid']
2044 video_id = force_videoid
2045 else:
2046 video_id = self._generic_id(url)
2047
2048 self.to_screen('%s: Requesting header' % video_id)
2049
2050 head_req = HEADRequest(url)
2051 head_response = self._request_webpage(
2052 head_req, video_id,
2053 note=False, errnote='Could not send HEAD request to %s' % url,
2054 fatal=False)
2055
2056 if head_response is not False:
2057 # Check for redirect
2058 new_url = compat_str(head_response.geturl())
2059 if url != new_url:
2060 self.report_following_redirect(new_url)
2061 if force_videoid:
2062 new_url = smuggle_url(
2063 new_url, {'force_videoid': force_videoid})
2064 return self.url_result(new_url)
2065
2066 full_response = None
2067 if head_response is False:
2068 request = sanitized_Request(url)
2069 request.add_header('Accept-Encoding', '*')
2070 full_response = self._request_webpage(request, video_id)
2071 head_response = full_response
2072
2073 info_dict = {
2074 'id': video_id,
2075 'title': self._generic_title(url),
2076 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2077 }
2078
2079 # Check for direct link to a video
2080 content_type = head_response.headers.get('Content-Type', '').lower()
2081 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2082 if m:
2083 format_id = compat_str(m.group('format_id'))
2084 if format_id.endswith('mpegurl'):
2085 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2086 elif format_id == 'f4m':
2087 formats = self._extract_f4m_formats(url, video_id)
2088 else:
2089 formats = [{
2090 'format_id': format_id,
2091 'url': url,
2092 'vcodec': 'none' if m.group('type') == 'audio' else None
2093 }]
2094 info_dict['direct'] = True
2095 self._sort_formats(formats)
2096 info_dict['formats'] = formats
2097 return info_dict
2098
2099 if not self._downloader.params.get('test', False) and not is_intentional:
2100 force = self._downloader.params.get('force_generic_extractor', False)
2101 self._downloader.report_warning(
2102 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2103
2104 if not full_response:
2105 request = sanitized_Request(url)
2106 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2107 # making it impossible to download only chunk of the file (yet we need only 512kB to
2108 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2109 # that will always result in downloading the whole file that is not desirable.
2110 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2111 # to accept raw bytes and being able to download only a chunk.
2112 # It may probably better to solve this by checking Content-Type for application/octet-stream
2113 # after HEAD request finishes, but not sure if we can rely on this.
2114 request.add_header('Accept-Encoding', '*')
2115 full_response = self._request_webpage(request, video_id)
2116
2117 first_bytes = full_response.read(512)
2118
2119 # Is it an M3U playlist?
2120 if first_bytes.startswith(b'#EXTM3U'):
2121 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2122 self._sort_formats(info_dict['formats'])
2123 return info_dict
2124
2125 # Maybe it's a direct link to a video?
2126 # Be careful not to download the whole thing!
2127 if not is_html(first_bytes):
2128 self._downloader.report_warning(
2129 'URL could be a direct video link, returning it as such.')
2130 info_dict.update({
2131 'direct': True,
2132 'url': url,
2133 })
2134 return info_dict
2135
2136 webpage = self._webpage_read_content(
2137 full_response, url, video_id, prefix=first_bytes)
2138
2139 self.report_extraction(video_id)
2140
2141 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2142 try:
2143 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2144 if doc.tag == 'rss':
2145 return self._extract_rss(url, video_id, doc)
2146 elif doc.tag == 'SmoothStreamingMedia':
2147 info_dict['formats'] = self._parse_ism_formats(doc, url)
2148 self._sort_formats(info_dict['formats'])
2149 return info_dict
2150 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2151 smil = self._parse_smil(doc, url, video_id)
2152 self._sort_formats(smil['formats'])
2153 return smil
2154 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2155 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2156 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2157 info_dict['formats'] = self._parse_mpd_formats(
2158 doc, video_id,
2159 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2160 mpd_url=url)
2161 self._sort_formats(info_dict['formats'])
2162 return info_dict
2163 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2164 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2165 self._sort_formats(info_dict['formats'])
2166 return info_dict
2167 except compat_xml_parse_error:
2168 pass
2169
2170 # Is it a Camtasia project?
2171 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2172 if camtasia_res is not None:
2173 return camtasia_res
2174
2175 # Sometimes embedded video player is hidden behind percent encoding
2176 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2177 # Unescaping the whole page allows to handle those cases in a generic way
2178 webpage = compat_urllib_parse_unquote(webpage)
2179
2180 # it's tempting to parse this further, but you would
2181 # have to take into account all the variations like
2182 # Video Title - Site Name
2183 # Site Name | Video Title
2184 # Video Title - Tagline | Site Name
2185 # and so on and so forth; it's just not practical
2186 video_title = self._og_search_title(
2187 webpage, default=None) or self._html_search_regex(
2188 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2189 default='video')
2190
2191 # Try to detect age limit automatically
2192 age_limit = self._rta_search(webpage)
2193 # And then there are the jokers who advertise that they use RTA,
2194 # but actually don't.
2195 AGE_LIMIT_MARKERS = [
2196 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2197 ]
2198 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2199 age_limit = 18
2200
2201 # video uploader is domain name
2202 video_uploader = self._search_regex(
2203 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2204
2205 video_description = self._og_search_description(webpage, default=None)
2206 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2207
2208 info_dict.update({
2209 'title': video_title,
2210 'description': video_description,
2211 'thumbnail': video_thumbnail,
2212 'age_limit': age_limit,
2213 })
2214
2215 # Look for Brightcove Legacy Studio embeds
2216 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2217 if bc_urls:
2218 entries = [{
2219 '_type': 'url',
2220 'url': smuggle_url(bc_url, {'Referer': url}),
2221 'ie_key': 'BrightcoveLegacy'
2222 } for bc_url in bc_urls]
2223
2224 return {
2225 '_type': 'playlist',
2226 'title': video_title,
2227 'id': video_id,
2228 'entries': entries,
2229 }
2230
2231 # Look for Brightcove New Studio embeds
2232 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2233 if bc_urls:
2234 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
2235
2236 # Look for Nexx embeds
2237 nexx_urls = NexxIE._extract_urls(webpage)
2238 if nexx_urls:
2239 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2240
2241 # Look for Nexx iFrame embeds
2242 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2243 if nexx_embed_urls:
2244 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2245
2246 # Look for ThePlatform embeds
2247 tp_urls = ThePlatformIE._extract_urls(webpage)
2248 if tp_urls:
2249 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2250
2251 # Look for Vessel embeds
2252 vessel_urls = VesselIE._extract_urls(webpage)
2253 if vessel_urls:
2254 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2255
2256 # Look for embedded rtl.nl player
2257 matches = re.findall(
2258 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
2259 webpage)
2260 if matches:
2261 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2262
2263 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2264 if vimeo_urls:
2265 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2266
2267 vid_me_embed_url = self._search_regex(
2268 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2269 webpage, 'vid.me embed', default=None)
2270 if vid_me_embed_url is not None:
2271 return self.url_result(vid_me_embed_url, 'Vidme')
2272
2273 # Look for YouTube embeds
2274 youtube_urls = YoutubeIE._extract_urls(webpage)
2275 if youtube_urls:
2276 return self.playlist_from_matches(
2277 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2278
2279 matches = DailymotionIE._extract_urls(webpage)
2280 if matches:
2281 return self.playlist_from_matches(matches, video_id, video_title)
2282
2283 # Look for embedded Dailymotion playlist player (#3822)
2284 m = re.search(
2285 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2286 if m:
2287 playlists = re.findall(
2288 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2289 if playlists:
2290 return self.playlist_from_matches(
2291 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2292
2293 # Look for DailyMail embeds
2294 dailymail_urls = DailyMailIE._extract_urls(webpage)
2295 if dailymail_urls:
2296 return self.playlist_from_matches(
2297 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2298
2299 # Look for embedded Wistia player
2300 wistia_url = WistiaIE._extract_url(webpage)
2301 if wistia_url:
2302 return {
2303 '_type': 'url_transparent',
2304 'url': self._proto_relative_url(wistia_url),
2305 'ie_key': WistiaIE.ie_key(),
2306 'uploader': video_uploader,
2307 }
2308
2309 # Look for SVT player
2310 svt_url = SVTIE._extract_url(webpage)
2311 if svt_url:
2312 return self.url_result(svt_url, 'SVT')
2313
2314 # Look for Bandcamp pages with custom domain
2315 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2316 if mobj is not None:
2317 burl = unescapeHTML(mobj.group(1))
2318 # Don't set the extractor because it can be a track url or an album
2319 return self.url_result(burl)
2320
2321 # Look for embedded Vevo player
2322 mobj = re.search(
2323 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2324 if mobj is not None:
2325 return self.url_result(mobj.group('url'))
2326
2327 # Look for embedded Viddler player
2328 mobj = re.search(
2329 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2330 webpage)
2331 if mobj is not None:
2332 return self.url_result(mobj.group('url'))
2333
2334 # Look for NYTimes player
2335 mobj = re.search(
2336 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2337 webpage)
2338 if mobj is not None:
2339 return self.url_result(mobj.group('url'))
2340
2341 # Look for Libsyn player
2342 mobj = re.search(
2343 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2344 if mobj is not None:
2345 return self.url_result(mobj.group('url'))
2346
2347 # Look for Ooyala videos
2348 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2349 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2350 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2351 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2352 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2353 if mobj is not None:
2354 embed_token = self._search_regex(
2355 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2356 webpage, 'ooyala embed token', default=None)
2357 return OoyalaIE._build_url_result(smuggle_url(
2358 mobj.group('ec'), {
2359 'domain': url,
2360 'embed_token': embed_token,
2361 }))
2362
2363 # Look for multiple Ooyala embeds on SBN network websites
2364 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2365 if mobj is not None:
2366 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2367 if embeds:
2368 return self.playlist_from_matches(
2369 embeds, video_id, video_title,
2370 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2371
2372 # Look for Aparat videos
2373 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2374 if mobj is not None:
2375 return self.url_result(mobj.group(1), 'Aparat')
2376
2377 # Look for MPORA videos
2378 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2379 if mobj is not None:
2380 return self.url_result(mobj.group(1), 'Mpora')
2381
2382 # Look for embedded NovaMov-based player
2383 mobj = re.search(
2384 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2385 (?P<url>http://(?:(?:embed|www)\.)?
2386 (?:novamov\.com|
2387 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2388 videoweed\.(?:es|com)|
2389 movshare\.(?:net|sx|ag)|
2390 divxstage\.(?:eu|net|ch|co|at|ag))
2391 /embed\.php.+?)\1''', webpage)
2392 if mobj is not None:
2393 return self.url_result(mobj.group('url'))
2394
2395 # Look for embedded Facebook player
2396 facebook_urls = FacebookIE._extract_urls(webpage)
2397 if facebook_urls:
2398 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2399
2400 # Look for embedded VK player
2401 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2402 if mobj is not None:
2403 return self.url_result(mobj.group('url'), 'VK')
2404
2405 # Look for embedded Odnoklassniki player
2406 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2407 if mobj is not None:
2408 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2409
2410 # Look for embedded ivi player
2411 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2412 if mobj is not None:
2413 return self.url_result(mobj.group('url'), 'Ivi')
2414
2415 # Look for embedded Huffington Post player
2416 mobj = re.search(
2417 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2418 if mobj is not None:
2419 return self.url_result(mobj.group('url'), 'HuffPost')
2420
2421 # Look for embed.ly
2422 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2423 if mobj is not None:
2424 return self.url_result(mobj.group('url'))
2425 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2426 if mobj is not None:
2427 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2428
2429 # Look for funnyordie embed
2430 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2431 if matches:
2432 return self.playlist_from_matches(
2433 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2434
2435 # Look for BBC iPlayer embed
2436 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2437 if matches:
2438 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2439
2440 # Look for embedded RUTV player
2441 rutv_url = RUTVIE._extract_url(webpage)
2442 if rutv_url:
2443 return self.url_result(rutv_url, 'RUTV')
2444
2445 # Look for embedded TVC player
2446 tvc_url = TVCIE._extract_url(webpage)
2447 if tvc_url:
2448 return self.url_result(tvc_url, 'TVC')
2449
2450 # Look for embedded SportBox player
2451 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2452 if sportbox_urls:
2453 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2454
2455 # Look for embedded XHamster player
2456 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2457 if xhamster_urls:
2458 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2459
2460 # Look for embedded TNAFlixNetwork player
2461 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2462 if tnaflix_urls:
2463 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2464
2465 # Look for embedded PornHub player
2466 pornhub_urls = PornHubIE._extract_urls(webpage)
2467 if pornhub_urls:
2468 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2469
2470 # Look for embedded DrTuber player
2471 drtuber_urls = DrTuberIE._extract_urls(webpage)
2472 if drtuber_urls:
2473 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2474
2475 # Look for embedded RedTube player
2476 redtube_urls = RedTubeIE._extract_urls(webpage)
2477 if redtube_urls:
2478 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2479
2480 # Look for embedded Tvigle player
2481 mobj = re.search(
2482 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2483 if mobj is not None:
2484 return self.url_result(mobj.group('url'), 'Tvigle')
2485
2486 # Look for embedded TED player
2487 mobj = re.search(
2488 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2489 if mobj is not None:
2490 return self.url_result(mobj.group('url'), 'TED')
2491
2492 # Look for embedded Ustream videos
2493 ustream_url = UstreamIE._extract_url(webpage)
2494 if ustream_url:
2495 return self.url_result(ustream_url, UstreamIE.ie_key())
2496
2497 # Look for embedded arte.tv player
2498 mobj = re.search(
2499 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2500 webpage)
2501 if mobj is not None:
2502 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2503
2504 # Look for embedded francetv player
2505 mobj = re.search(
2506 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2507 webpage)
2508 if mobj is not None:
2509 return self.url_result(mobj.group('url'))
2510
2511 # Look for embedded smotri.com player
2512 smotri_url = SmotriIE._extract_url(webpage)
2513 if smotri_url:
2514 return self.url_result(smotri_url, 'Smotri')
2515
2516 # Look for embedded Myvi.ru player
2517 myvi_url = MyviIE._extract_url(webpage)
2518 if myvi_url:
2519 return self.url_result(myvi_url)
2520
2521 # Look for embedded soundcloud player
2522 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2523 if soundcloud_urls:
2524 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2525
2526 # Look for tunein player
2527 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2528 if tunein_urls:
2529 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2530
2531 # Look for embedded mtvservices player
2532 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2533 if mtvservices_url:
2534 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2535
2536 # Look for embedded yahoo player
2537 mobj = re.search(
2538 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2539 webpage)
2540 if mobj is not None:
2541 return self.url_result(mobj.group('url'), 'Yahoo')
2542
2543 # Look for embedded sbs.com.au player
2544 mobj = re.search(
2545 r'''(?x)
2546 (?:
2547 <meta\s+property="og:video"\s+content=|
2548 <iframe[^>]+?src=
2549 )
2550 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2551 webpage)
2552 if mobj is not None:
2553 return self.url_result(mobj.group('url'), 'SBS')
2554
2555 # Look for embedded Cinchcast player
2556 mobj = re.search(
2557 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2558 webpage)
2559 if mobj is not None:
2560 return self.url_result(mobj.group('url'), 'Cinchcast')
2561
2562 mobj = re.search(
2563 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2564 webpage)
2565 if not mobj:
2566 mobj = re.search(
2567 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2568 webpage)
2569 if mobj is not None:
2570 return self.url_result(mobj.group('url'), 'MLB')
2571
2572 mobj = re.search(
2573 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2574 webpage)
2575 if mobj is not None:
2576 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2577
2578 mobj = re.search(
2579 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2580 webpage)
2581 if mobj is not None:
2582 return self.url_result(mobj.group('url'), 'Livestream')
2583
2584 # Look for Zapiks embed
2585 mobj = re.search(
2586 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2587 if mobj is not None:
2588 return self.url_result(mobj.group('url'), 'Zapiks')
2589
2590 # Look for Kaltura embeds
2591 kaltura_url = KalturaIE._extract_url(webpage)
2592 if kaltura_url:
2593 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2594
2595 # Look for EaglePlatform embeds
2596 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2597 if eagleplatform_url:
2598 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2599
2600 # Look for ClipYou (uses EaglePlatform) embeds
2601 mobj = re.search(
2602 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2603 if mobj is not None:
2604 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2605
2606 # Look for Pladform embeds
2607 pladform_url = PladformIE._extract_url(webpage)
2608 if pladform_url:
2609 return self.url_result(pladform_url)
2610
2611 # Look for Videomore embeds
2612 videomore_url = VideomoreIE._extract_url(webpage)
2613 if videomore_url:
2614 return self.url_result(videomore_url)
2615
2616 # Look for Webcaster embeds
2617 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2618 if webcaster_url:
2619 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2620
2621 # Look for Playwire embeds
2622 mobj = re.search(
2623 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2624 if mobj is not None:
2625 return self.url_result(mobj.group('url'))
2626
2627 # Look for 5min embeds
2628 mobj = re.search(
2629 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2630 if mobj is not None:
2631 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2632
2633 # Look for Crooks and Liars embeds
2634 mobj = re.search(
2635 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2636 if mobj is not None:
2637 return self.url_result(mobj.group('url'))
2638
2639 # Look for NBC Sports VPlayer embeds
2640 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2641 if nbc_sports_url:
2642 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2643
2644 # Look for NBC News embeds
2645 nbc_news_embed_url = re.search(
2646 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2647 if nbc_news_embed_url:
2648 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2649
2650 # Look for Google Drive embeds
2651 google_drive_url = GoogleDriveIE._extract_url(webpage)
2652 if google_drive_url:
2653 return self.url_result(google_drive_url, 'GoogleDrive')
2654
2655 # Look for UDN embeds
2656 mobj = re.search(
2657 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2658 if mobj is not None:
2659 return self.url_result(
2660 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2661
2662 # Look for Senate ISVP iframe
2663 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2664 if senate_isvp_url:
2665 return self.url_result(senate_isvp_url, 'SenateISVP')
2666
2667 # Look for Dailymotion Cloud videos
2668 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2669 if dmcloud_url:
2670 return self.url_result(dmcloud_url, 'DailymotionCloud')
2671
2672 # Look for OnionStudios embeds
2673 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2674 if onionstudios_url:
2675 return self.url_result(onionstudios_url)
2676
2677 # Look for ViewLift embeds
2678 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2679 if viewlift_url:
2680 return self.url_result(viewlift_url)
2681
2682 # Look for JWPlatform embeds
2683 jwplatform_url = JWPlatformIE._extract_url(webpage)
2684 if jwplatform_url:
2685 return self.url_result(jwplatform_url, 'JWPlatform')
2686
2687 # Look for Digiteka embeds
2688 digiteka_url = DigitekaIE._extract_url(webpage)
2689 if digiteka_url:
2690 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2691
2692 # Look for Arkena embeds
2693 arkena_url = ArkenaIE._extract_url(webpage)
2694 if arkena_url:
2695 return self.url_result(arkena_url, ArkenaIE.ie_key())
2696
2697 # Look for Piksel embeds
2698 piksel_url = PikselIE._extract_url(webpage)
2699 if piksel_url:
2700 return self.url_result(piksel_url, PikselIE.ie_key())
2701
2702 # Look for Limelight embeds
2703 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2704 if limelight_urls:
2705 return self.playlist_result(
2706 limelight_urls, video_id, video_title, video_description)
2707
2708 # Look for Anvato embeds
2709 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2710 if anvato_urls:
2711 return self.playlist_result(
2712 anvato_urls, video_id, video_title, video_description)
2713
2714 # Look for AdobeTVVideo embeds
2715 mobj = re.search(
2716 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2717 webpage)
2718 if mobj is not None:
2719 return self.url_result(
2720 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2721 'AdobeTVVideo')
2722
2723 # Look for Vine embeds
2724 mobj = re.search(
2725 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2726 webpage)
2727 if mobj is not None:
2728 return self.url_result(
2729 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2730
2731 # Look for VODPlatform embeds
2732 mobj = re.search(
2733 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2734 webpage)
2735 if mobj is not None:
2736 return self.url_result(
2737 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2738
2739 # Look for Mangomolo embeds
2740 mobj = re.search(
2741 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2742 (?:
2743 video\?.*?\bid=(?P<video_id>\d+)|
2744 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2745 ).+?)\1''', webpage)
2746 if mobj is not None:
2747 info = {
2748 '_type': 'url_transparent',
2749 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2750 'title': video_title,
2751 'description': video_description,
2752 'thumbnail': video_thumbnail,
2753 'uploader': video_uploader,
2754 }
2755 video_id = mobj.group('video_id')
2756 if video_id:
2757 info.update({
2758 'ie_key': 'MangomoloVideo',
2759 'id': video_id,
2760 })
2761 else:
2762 info.update({
2763 'ie_key': 'MangomoloLive',
2764 'id': mobj.group('channel_id'),
2765 })
2766 return info
2767
2768 # Look for Instagram embeds
2769 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2770 if instagram_embed_url is not None:
2771 return self.url_result(
2772 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2773
2774 # Look for LiveLeak embeds
2775 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2776 if liveleak_urls:
2777 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2778
2779 # Look for 3Q SDN embeds
2780 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2781 if threeqsdn_url:
2782 return {
2783 '_type': 'url_transparent',
2784 'ie_key': ThreeQSDNIE.ie_key(),
2785 'url': self._proto_relative_url(threeqsdn_url),
2786 'title': video_title,
2787 'description': video_description,
2788 'thumbnail': video_thumbnail,
2789 'uploader': video_uploader,
2790 }
2791
2792 # Look for VBOX7 embeds
2793 vbox7_url = Vbox7IE._extract_url(webpage)
2794 if vbox7_url:
2795 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2796
2797 # Look for DBTV embeds
2798 dbtv_urls = DBTVIE._extract_urls(webpage)
2799 if dbtv_urls:
2800 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2801
2802 # Look for Videa embeds
2803 videa_urls = VideaIE._extract_urls(webpage)
2804 if videa_urls:
2805 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2806
2807 # Look for 20 minuten embeds
2808 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2809 if twentymin_urls:
2810 return self.playlist_from_matches(
2811 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2812
2813 # Look for Openload embeds
2814 openload_urls = OpenloadIE._extract_urls(webpage)
2815 if openload_urls:
2816 return self.playlist_from_matches(
2817 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2818
2819 # Look for VideoPress embeds
2820 videopress_urls = VideoPressIE._extract_urls(webpage)
2821 if videopress_urls:
2822 return self.playlist_from_matches(
2823 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2824
2825 # Look for Rutube embeds
2826 rutube_urls = RutubeIE._extract_urls(webpage)
2827 if rutube_urls:
2828 return self.playlist_from_matches(
2829 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2830
2831 # Look for WashingtonPost embeds
2832 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2833 if wapo_urls:
2834 return self.playlist_from_matches(
2835 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2836
2837 # Look for Mediaset embeds
2838 mediaset_urls = MediasetIE._extract_urls(webpage)
2839 if mediaset_urls:
2840 return self.playlist_from_matches(
2841 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2842
2843 # Look for JOJ.sk embeds
2844 joj_urls = JojIE._extract_urls(webpage)
2845 if joj_urls:
2846 return self.playlist_from_matches(
2847 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2848
2849 # Look for megaphone.fm embeds
2850 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2851 if mpfn_urls:
2852 return self.playlist_from_matches(
2853 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2854
2855 # Look for vzaar embeds
2856 vzaar_urls = VzaarIE._extract_urls(webpage)
2857 if vzaar_urls:
2858 return self.playlist_from_matches(
2859 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2860
2861 def merge_dicts(dict1, dict2):
2862 merged = {}
2863 for k, v in dict1.items():
2864 if v is not None:
2865 merged[k] = v
2866 for k, v in dict2.items():
2867 if v is None:
2868 continue
2869 if (k not in merged or
2870 (isinstance(v, compat_str) and v and
2871 isinstance(merged[k], compat_str) and
2872 not merged[k])):
2873 merged[k] = v
2874 return merged
2875
2876 # Look for HTML5 media
2877 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2878 if entries:
2879 if len(entries) == 1:
2880 entries[0].update({
2881 'id': video_id,
2882 'title': video_title,
2883 })
2884 else:
2885 for num, entry in enumerate(entries, start=1):
2886 entry.update({
2887 'id': '%s-%s' % (video_id, num),
2888 'title': '%s (%d)' % (video_title, num),
2889 })
2890 for entry in entries:
2891 self._sort_formats(entry['formats'])
2892 return self.playlist_result(entries, video_id, video_title)
2893
2894 jwplayer_data = self._find_jwplayer_data(
2895 webpage, video_id, transform_source=js_to_json)
2896 if jwplayer_data:
2897 info = self._parse_jwplayer_data(
2898 jwplayer_data, video_id, require_title=False, base_url=url)
2899 return merge_dicts(info, info_dict)
2900
2901 # Video.js embed
2902 mobj = re.search(
2903 r'(?s)\bvideojs\s*\(.+?\bplayer\.src\s*\(\s*(\[.+?\])\s*\)\s*;',
2904 webpage)
2905 if mobj is not None:
2906 sources = self._parse_json(
2907 mobj.group(1), video_id, transform_source=js_to_json,
2908 fatal=False) or []
2909 formats = []
2910 for source in sources:
2911 src = source.get('src')
2912 if not src or not isinstance(src, compat_str):
2913 continue
2914 src = compat_urlparse.urljoin(url, src)
2915 src_type = source.get('type')
2916 if isinstance(src_type, compat_str):
2917 src_type = src_type.lower()
2918 ext = determine_ext(src).lower()
2919 if src_type == 'video/youtube':
2920 return self.url_result(src, YoutubeIE.ie_key())
2921 if src_type == 'application/dash+xml' or ext == 'mpd':
2922 formats.extend(self._extract_mpd_formats(
2923 src, video_id, mpd_id='dash', fatal=False))
2924 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2925 formats.extend(self._extract_m3u8_formats(
2926 src, video_id, 'mp4', entry_protocol='m3u8_native',
2927 m3u8_id='hls', fatal=False))
2928 else:
2929 formats.append({
2930 'url': src,
2931 'ext': (mimetype2ext(src_type) or
2932 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2933 })
2934 if formats:
2935 self._sort_formats(formats)
2936 info_dict['formats'] = formats
2937 return info_dict
2938
2939 # Looking for http://schema.org/VideoObject
2940 json_ld = self._search_json_ld(
2941 webpage, video_id, default={}, expected_type='VideoObject')
2942 if json_ld.get('url'):
2943 return merge_dicts(json_ld, info_dict)
2944
2945 def check_video(vurl):
2946 if YoutubeIE.suitable(vurl):
2947 return True
2948 if RtmpIE.suitable(vurl):
2949 return True
2950 vpath = compat_urlparse.urlparse(vurl).path
2951 vext = determine_ext(vpath)
2952 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
2953
2954 def filter_video(urls):
2955 return list(filter(check_video, urls))
2956
2957 # Start with something easy: JW Player in SWFObject
2958 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2959 if not found:
2960 # Look for gorilla-vid style embedding
2961 found = filter_video(re.findall(r'''(?sx)
2962 (?:
2963 jw_plugins|
2964 JWPlayerOptions|
2965 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2966 )
2967 .*?
2968 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2969 if not found:
2970 # Broaden the search a little bit
2971 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2972 if not found:
2973 # Broaden the findall a little bit: JWPlayer JS loader
2974 found = filter_video(re.findall(
2975 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2976 if not found:
2977 # Flow player
2978 found = filter_video(re.findall(r'''(?xs)
2979 flowplayer\("[^"]+",\s*
2980 \{[^}]+?\}\s*,
2981 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2982 ["']?url["']?\s*:\s*["']([^"']+)["']
2983 ''', webpage))
2984 if not found:
2985 # Cinerama player
2986 found = re.findall(
2987 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2988 if not found:
2989 # Try to find twitter cards info
2990 # twitter:player:stream should be checked before twitter:player since
2991 # it is expected to contain a raw stream (see
2992 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2993 found = filter_video(re.findall(
2994 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2995 if not found:
2996 # We look for Open Graph info:
2997 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2998 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2999 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3000 if m_video_type is not None:
3001 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3002 if not found:
3003 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3004 found = re.search(
3005 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3006 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3007 webpage)
3008 if not found:
3009 # Look also in Refresh HTTP header
3010 refresh_header = head_response.headers.get('Refresh')
3011 if refresh_header:
3012 # In python 2 response HTTP headers are bytestrings
3013 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3014 refresh_header = refresh_header.decode('iso-8859-1')
3015 found = re.search(REDIRECT_REGEX, refresh_header)
3016 if found:
3017 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3018 if new_url != url:
3019 self.report_following_redirect(new_url)
3020 return {
3021 '_type': 'url',
3022 'url': new_url,
3023 }
3024 else:
3025 found = None
3026
3027 if not found:
3028 # twitter:player is a https URL to iframe player that may or may not
3029 # be supported by youtube-dl thus this is checked the very last (see
3030 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3031 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3032 if embed_url and embed_url != url:
3033 return self.url_result(embed_url)
3034
3035 if not found:
3036 raise UnsupportedError(url)
3037
3038 entries = []
3039 for video_url in orderedSet(found):
3040 video_url = unescapeHTML(video_url)
3041 video_url = video_url.replace('\\/', '/')
3042 video_url = compat_urlparse.urljoin(url, video_url)
3043 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3044
3045 # Sometimes, jwplayer extraction will result in a YouTube URL
3046 if YoutubeIE.suitable(video_url):
3047 entries.append(self.url_result(video_url, 'Youtube'))
3048 continue
3049
3050 # here's a fun little line of code for you:
3051 video_id = os.path.splitext(video_id)[0]
3052
3053 entry_info_dict = {
3054 'id': video_id,
3055 'uploader': video_uploader,
3056 'title': video_title,
3057 'age_limit': age_limit,
3058 }
3059
3060 if RtmpIE.suitable(video_url):
3061 entry_info_dict.update({
3062 '_type': 'url_transparent',
3063 'ie_key': RtmpIE.ie_key(),
3064 'url': video_url,
3065 })
3066 entries.append(entry_info_dict)
3067 continue
3068
3069 ext = determine_ext(video_url)
3070 if ext == 'smil':
3071 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3072 elif ext == 'xspf':
3073 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3074 elif ext == 'm3u8':
3075 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3076 elif ext == 'mpd':
3077 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3078 elif ext == 'f4m':
3079 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3080 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3081 # Just matching .ism/manifest is not enough to be reliably sure
3082 # whether it's actually an ISM manifest or some other streaming
3083 # manifest since there are various streaming URL formats
3084 # possible (see [1]) as well as some other shenanigans like
3085 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3086 # so on.
3087 # Thus the most reasonable way to solve this is to delegate
3088 # to generic extractor in order to look into the contents of
3089 # the manifest itself.
3090 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3091 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3092 entry_info_dict = self.url_result(
3093 smuggle_url(video_url, {'to_generic': True}),
3094 GenericIE.ie_key())
3095 else:
3096 entry_info_dict['url'] = video_url
3097
3098 if entry_info_dict.get('formats'):
3099 self._sort_formats(entry_info_dict['formats'])
3100
3101 entries.append(entry_info_dict)
3102
3103 if len(entries) == 1:
3104 return entries[0]
3105 else:
3106 for num, e in enumerate(entries, start=1):
3107 # 'url' results don't have a title
3108 if e.get('title') is not None:
3109 e['title'] = '%s (%d)' % (e['title'], num)
3110 return {
3111 '_type': 'playlist',
3112 'entries': entries,
3113 }