]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
Update changelog
[youtubedl] / youtube_dl / extractor / generic.py
1 # coding: utf-8
2
3 from __future__ import unicode_literals
4
5 import os
6 import re
7 import sys
8
9 from .common import InfoExtractor
10 from .youtube import YoutubeIE
11 from ..compat import (
12 compat_etree_fromstring,
13 compat_str,
14 compat_urllib_parse_unquote,
15 compat_urlparse,
16 compat_xml_parse_error,
17 )
18 from ..utils import (
19 determine_ext,
20 ExtractorError,
21 float_or_none,
22 HEADRequest,
23 is_html,
24 js_to_json,
25 KNOWN_EXTENSIONS,
26 mimetype2ext,
27 orderedSet,
28 sanitized_Request,
29 smuggle_url,
30 unescapeHTML,
31 unified_strdate,
32 unsmuggle_url,
33 UnsupportedError,
34 xpath_text,
35 )
36 from .commonprotocols import RtmpIE
37 from .brightcove import (
38 BrightcoveLegacyIE,
39 BrightcoveNewIE,
40 )
41 from .nexx import (
42 NexxIE,
43 NexxEmbedIE,
44 )
45 from .nbc import NBCSportsVPlayerIE
46 from .ooyala import OoyalaIE
47 from .rutv import RUTVIE
48 from .tvc import TVCIE
49 from .sportbox import SportBoxEmbedIE
50 from .smotri import SmotriIE
51 from .myvi import MyviIE
52 from .condenast import CondeNastIE
53 from .udn import UDNEmbedIE
54 from .senateisvp import SenateISVPIE
55 from .svt import SVTIE
56 from .pornhub import PornHubIE
57 from .xhamster import XHamsterEmbedIE
58 from .tnaflix import TNAFlixNetworkEmbedIE
59 from .drtuber import DrTuberIE
60 from .redtube import RedTubeIE
61 from .vimeo import VimeoIE
62 from .dailymotion import DailymotionIE
63 from .dailymail import DailyMailIE
64 from .onionstudios import OnionStudiosIE
65 from .viewlift import ViewLiftEmbedIE
66 from .mtv import MTVServicesEmbeddedIE
67 from .pladform import PladformIE
68 from .videomore import VideomoreIE
69 from .webcaster import WebcasterFeedIE
70 from .googledrive import GoogleDriveIE
71 from .jwplatform import JWPlatformIE
72 from .digiteka import DigitekaIE
73 from .arkena import ArkenaIE
74 from .instagram import InstagramIE
75 from .liveleak import LiveLeakIE
76 from .threeqsdn import ThreeQSDNIE
77 from .theplatform import ThePlatformIE
78 from .vessel import VesselIE
79 from .kaltura import KalturaIE
80 from .eagleplatform import EaglePlatformIE
81 from .facebook import FacebookIE
82 from .soundcloud import SoundcloudIE
83 from .tunein import TuneInBaseIE
84 from .vbox7 import Vbox7IE
85 from .dbtv import DBTVIE
86 from .piksel import PikselIE
87 from .videa import VideaIE
88 from .twentymin import TwentyMinutenIE
89 from .ustream import UstreamIE
90 from .openload import OpenloadIE
91 from .videopress import VideoPressIE
92 from .rutube import RutubeIE
93 from .limelight import LimelightBaseIE
94 from .anvato import AnvatoIE
95 from .washingtonpost import WashingtonPostIE
96 from .wistia import WistiaIE
97 from .mediaset import MediasetIE
98 from .joj import JojIE
99 from .megaphone import MegaphoneIE
100 from .vzaar import VzaarIE
101 from .channel9 import Channel9IE
102 from .vshare import VShareIE
103 from .mediasite import MediasiteIE
104 from .springboardplatform import SpringboardPlatformIE
105 from .yapfiles import YapFilesIE
106 from .vice import ViceIE
107
108
109 class GenericIE(InfoExtractor):
110 IE_DESC = 'Generic downloader that works on some sites'
111 _VALID_URL = r'.*'
112 IE_NAME = 'generic'
113 _TESTS = [
114 # Direct link to a video
115 {
116 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
117 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
118 'info_dict': {
119 'id': 'trailer',
120 'ext': 'mp4',
121 'title': 'trailer',
122 'upload_date': '20100513',
123 }
124 },
125 # Direct link to media delivered compressed (until Accept-Encoding is *)
126 {
127 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
128 'md5': '128c42e68b13950268b648275386fc74',
129 'info_dict': {
130 'id': 'FictionJunction-Parallel_Hearts',
131 'ext': 'flac',
132 'title': 'FictionJunction-Parallel_Hearts',
133 'upload_date': '20140522',
134 },
135 'expected_warnings': [
136 'URL could be a direct video link, returning it as such.'
137 ],
138 'skip': 'URL invalid',
139 },
140 # Direct download with broken HEAD
141 {
142 'url': 'http://ai-radio.org:8000/radio.opus',
143 'info_dict': {
144 'id': 'radio',
145 'ext': 'opus',
146 'title': 'radio',
147 },
148 'params': {
149 'skip_download': True, # infinite live stream
150 },
151 'expected_warnings': [
152 r'501.*Not Implemented',
153 r'400.*Bad Request',
154 ],
155 },
156 # Direct link with incorrect MIME type
157 {
158 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
159 'md5': '4ccbebe5f36706d85221f204d7eb5913',
160 'info_dict': {
161 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
162 'id': '5_Lennart_Poettering_-_Systemd',
163 'ext': 'webm',
164 'title': '5_Lennart_Poettering_-_Systemd',
165 'upload_date': '20141120',
166 },
167 'expected_warnings': [
168 'URL could be a direct video link, returning it as such.'
169 ]
170 },
171 # RSS feed
172 {
173 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
174 'info_dict': {
175 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
176 'title': 'Zero Punctuation',
177 'description': 're:.*groundbreaking video review series.*'
178 },
179 'playlist_mincount': 11,
180 },
181 # RSS feed with enclosure
182 {
183 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
184 'info_dict': {
185 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
186 'ext': 'm4v',
187 'upload_date': '20150228',
188 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
189 }
190 },
191 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
192 {
193 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
194 'info_dict': {
195 'id': 'smil',
196 'ext': 'mp4',
197 'title': 'Automatics, robotics and biocybernetics',
198 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
199 'upload_date': '20130627',
200 'formats': 'mincount:16',
201 'subtitles': 'mincount:1',
202 },
203 'params': {
204 'force_generic_extractor': True,
205 'skip_download': True,
206 },
207 },
208 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
209 {
210 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
211 'info_dict': {
212 'id': 'hds',
213 'ext': 'flv',
214 'title': 'hds',
215 'formats': 'mincount:1',
216 },
217 'params': {
218 'skip_download': True,
219 },
220 },
221 # SMIL from https://www.restudy.dk/video/play/id/1637
222 {
223 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
224 'info_dict': {
225 'id': 'video_1637',
226 'ext': 'flv',
227 'title': 'video_1637',
228 'formats': 'mincount:3',
229 },
230 'params': {
231 'skip_download': True,
232 },
233 },
234 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
235 {
236 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
237 'info_dict': {
238 'id': 'smil-service',
239 'ext': 'flv',
240 'title': 'smil-service',
241 'formats': 'mincount:1',
242 },
243 'params': {
244 'skip_download': True,
245 },
246 },
247 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
248 {
249 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
250 'info_dict': {
251 'id': '4719370',
252 'ext': 'mp4',
253 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
254 'formats': 'mincount:3',
255 },
256 'params': {
257 'skip_download': True,
258 },
259 },
260 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
261 {
262 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
263 'info_dict': {
264 'id': 'mZlp2ctYIUEB',
265 'ext': 'mp4',
266 'title': 'Tikibad ontruimd wegens brand',
267 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
268 'thumbnail': r're:^https?://.*\.jpg$',
269 'duration': 33,
270 },
271 'params': {
272 'skip_download': True,
273 },
274 },
275 # MPD from http://dash-mse-test.appspot.com/media.html
276 {
277 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
278 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
279 'info_dict': {
280 'id': 'car-20120827-manifest',
281 'ext': 'mp4',
282 'title': 'car-20120827-manifest',
283 'formats': 'mincount:9',
284 'upload_date': '20130904',
285 },
286 'params': {
287 'format': 'bestvideo',
288 },
289 },
290 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
291 {
292 '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',
293 'info_dict': {
294 'id': 'content',
295 'ext': 'mp4',
296 'title': 'content',
297 'formats': 'mincount:8',
298 },
299 'params': {
300 # m3u8 downloads
301 'skip_download': True,
302 },
303 'skip': 'video gone',
304 },
305 # m3u8 served with Content-Type: text/plain
306 {
307 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
308 'info_dict': {
309 'id': 'index',
310 'ext': 'mp4',
311 'title': 'index',
312 'upload_date': '20140720',
313 'formats': 'mincount:11',
314 },
315 'params': {
316 # m3u8 downloads
317 'skip_download': True,
318 },
319 'skip': 'video gone',
320 },
321 # google redirect
322 {
323 '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',
324 'info_dict': {
325 'id': 'cmQHVoWB5FY',
326 'ext': 'mp4',
327 'upload_date': '20130224',
328 'uploader_id': 'TheVerge',
329 'description': r're:^Chris Ziegler takes a look at the\.*',
330 'uploader': 'The Verge',
331 'title': 'First Firefox OS phones side-by-side',
332 },
333 'params': {
334 'skip_download': False,
335 }
336 },
337 {
338 # redirect in Refresh HTTP header
339 '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',
340 'info_dict': {
341 'id': 'pO8h3EaFRdo',
342 'ext': 'mp4',
343 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
344 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
345 'upload_date': '20150917',
346 'uploader_id': 'brtvofficial',
347 'uploader': 'Boiler Room',
348 },
349 'params': {
350 'skip_download': False,
351 },
352 },
353 {
354 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
355 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
356 'info_dict': {
357 'id': '13601338388002',
358 'ext': 'mp4',
359 'uploader': 'www.hodiho.fr',
360 'title': 'R\u00e9gis plante sa Jeep',
361 }
362 },
363 # bandcamp page with custom domain
364 {
365 'add_ie': ['Bandcamp'],
366 'url': 'http://bronyrock.com/track/the-pony-mash',
367 'info_dict': {
368 'id': '3235767654',
369 'ext': 'mp3',
370 'title': 'The Pony Mash',
371 'uploader': 'M_Pallante',
372 },
373 'skip': 'There is a limit of 200 free downloads / month for the test song',
374 },
375 {
376 # embedded brightcove video
377 # it also tests brightcove videos that need to set the 'Referer'
378 # in the http requests
379 'add_ie': ['BrightcoveLegacy'],
380 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
381 'info_dict': {
382 'id': '2765128793001',
383 'ext': 'mp4',
384 'title': 'Le cours de bourse : lā€™analyse technique',
385 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
386 'uploader': 'BFM BUSINESS',
387 },
388 'params': {
389 'skip_download': True,
390 },
391 },
392 {
393 # embedded with itemprop embedURL and video id spelled as `idVideo`
394 'add_id': ['BrightcoveLegacy'],
395 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
396 'info_dict': {
397 'id': '5255628253001',
398 'ext': 'mp4',
399 'title': 'md5:37c519b1128915607601e75a87995fc0',
400 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
401 'uploader': 'BFM BUSINESS',
402 'uploader_id': '876450612001',
403 'timestamp': 1482255315,
404 'upload_date': '20161220',
405 },
406 'params': {
407 'skip_download': True,
408 },
409 },
410 {
411 # https://github.com/rg3/youtube-dl/issues/2253
412 'url': 'http://bcove.me/i6nfkrc3',
413 'md5': '0ba9446db037002366bab3b3eb30c88c',
414 'info_dict': {
415 'id': '3101154703001',
416 'ext': 'mp4',
417 'title': 'Still no power',
418 'uploader': 'thestar.com',
419 '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.',
420 },
421 'add_ie': ['BrightcoveLegacy'],
422 'skip': 'video gone',
423 },
424 {
425 'url': 'http://www.championat.com/video/football/v/87/87499.html',
426 'md5': 'fb973ecf6e4a78a67453647444222983',
427 'info_dict': {
428 'id': '3414141473001',
429 'ext': 'mp4',
430 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
431 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
432 'uploader': 'Championat',
433 },
434 },
435 {
436 # https://github.com/rg3/youtube-dl/issues/3541
437 'add_ie': ['BrightcoveLegacy'],
438 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
439 'info_dict': {
440 'id': '3866516442001',
441 'ext': 'mp4',
442 'title': 'Leer mij vrouwen kennen: Aflevering 1',
443 'description': 'Leer mij vrouwen kennen: Aflevering 1',
444 'uploader': 'SBS Broadcasting',
445 },
446 'skip': 'Restricted to Netherlands',
447 'params': {
448 'skip_download': True, # m3u8 download
449 },
450 },
451 {
452 # Brightcove video in <iframe>
453 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
454 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
455 'info_dict': {
456 'id': '5360463607001',
457 'ext': 'mp4',
458 'title': '叙利äŗšå¤±ę˜Žå„æē«„åœØåŗŸå¢ŸäøŠę¼”å”±ć€Šåæƒč·³ć€‹ å‘¼åčŽ·å¾—ę­£åøøē«„幓ē”Ÿę“»',
459 'description': 'č”åˆå›½å„æē«„åŸŗ金会äø­äøœå’ŒåŒ—非åŒŗ域大ä½æć€ä½œę›²å®¶ę‰Žå¾·Ā·čæŖę‹‰å°¼ļ¼ˆZade Diraniļ¼‰åœØ3꜈15ę—„å™åˆ©äŗšå†²ēŖēˆ†å‘7å‘Ø幓ēŗŖåæµę—„之际发åøƒäŗ†äøŗ叙利äŗšč°±å†™ēš„ę­Œę›²ć€Šåæƒč·³ć€‹ļ¼ˆHEARTBEATļ¼‰ļ¼Œäøŗ受到六幓冲ēŖå½±å“ēš„叙利äŗšå„æē«„发å‡ŗå¼ŗēƒˆå‘å–Šļ¼Œå‘¼åäø–ē•Œåšå‡ŗ共同åŠŖ力ļ¼Œä½æ叙利äŗšå„æē«„é‡ę–°čŽ·å¾—äŗ«ęœ‰ę­£åøøē«„幓ē”Ÿę“»ēš„ęƒåˆ©ć€‚',
460 'uploader': 'United Nations',
461 'uploader_id': '1362235914001',
462 'timestamp': 1489593889,
463 'upload_date': '20170315',
464 },
465 'add_ie': ['BrightcoveLegacy'],
466 },
467 {
468 # Brightcove with alternative playerID key
469 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
470 'info_dict': {
471 'id': 'nmeth.2062_SV1',
472 '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',
473 },
474 'playlist': [{
475 'info_dict': {
476 'id': '2228375078001',
477 'ext': 'mp4',
478 'title': 'nmeth.2062-sv1',
479 'description': 'nmeth.2062-sv1',
480 'timestamp': 1363357591,
481 'upload_date': '20130315',
482 'uploader': 'Nature Publishing Group',
483 'uploader_id': '1964492299001',
484 },
485 }],
486 },
487 {
488 # Brightcove with UUID in videoPlayer
489 'url': 'http://www8.hp.com/cn/zh/home.html',
490 'info_dict': {
491 'id': '5255815316001',
492 'ext': 'mp4',
493 'title': 'Sprocket Video - China',
494 'description': 'Sprocket Video - China',
495 'uploader': 'HP-Video Gallery',
496 'timestamp': 1482263210,
497 'upload_date': '20161220',
498 'uploader_id': '1107601872001',
499 },
500 'params': {
501 'skip_download': True, # m3u8 download
502 },
503 'skip': 'video rotates...weekly?',
504 },
505 {
506 # Brightcove:new type [2].
507 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
508 'md5': '2b35148fcf48da41c9fb4591650784f3',
509 'info_dict': {
510 'id': '5348741021001',
511 'ext': 'mp4',
512 'upload_date': '20170306',
513 'uploader_id': '4191638492001',
514 'timestamp': 1488769918,
515 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
516
517 },
518 },
519 {
520 # Alternative brightcove <video> attributes
521 '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/',
522 'info_dict': {
523 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
524 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidĆ©os avec TĆ©lĆ©-Loisirs",
525 },
526 'playlist': [{
527 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
528 'info_dict': {
529 'id': '5311302538001',
530 'ext': 'mp4',
531 'title': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
532 'description': "Guillaume Canet eĢvoque les rumeurs d'infideĢliteĢ de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 fĆ©vrier 2017)",
533 'timestamp': 1486321708,
534 'upload_date': '20170205',
535 'uploader_id': '800000640001',
536 },
537 'only_matching': True,
538 }],
539 },
540 {
541 # Brightcove with UUID in videoPlayer
542 'url': 'http://www8.hp.com/cn/zh/home.html',
543 'info_dict': {
544 'id': '5255815316001',
545 'ext': 'mp4',
546 'title': 'Sprocket Video - China',
547 'description': 'Sprocket Video - China',
548 'uploader': 'HP-Video Gallery',
549 'timestamp': 1482263210,
550 'upload_date': '20161220',
551 'uploader_id': '1107601872001',
552 },
553 'params': {
554 'skip_download': True, # m3u8 download
555 },
556 },
557 # ooyala video
558 {
559 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
560 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
561 'info_dict': {
562 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
563 'ext': 'mp4',
564 'title': '2cc213299525360.mov', # that's what we get
565 'duration': 238.231,
566 },
567 'add_ie': ['Ooyala'],
568 },
569 {
570 # ooyala video embedded with http://player.ooyala.com/iframe.js
571 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
572 'info_dict': {
573 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
574 'ext': 'mp4',
575 'title': '"Steve Jobs: Man in the Machine" trailer',
576 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
577 'duration': 135.427,
578 },
579 'params': {
580 'skip_download': True,
581 },
582 'skip': 'movie expired',
583 },
584 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
585 {
586 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
587 'info_dict': {
588 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
589 'ext': 'mp4',
590 'title': 'Steampunk Fest Comes to Honesdale',
591 'duration': 43.276,
592 },
593 'params': {
594 'skip_download': True,
595 }
596 },
597 # embed.ly video
598 {
599 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
600 'info_dict': {
601 'id': '9ODmcdjQcHQ',
602 'ext': 'mp4',
603 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
604 'upload_date': '20140225',
605 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
606 'uploader': 'Tested',
607 'uploader_id': 'testedcom',
608 },
609 # No need to test YoutubeIE here
610 'params': {
611 'skip_download': True,
612 },
613 },
614 # funnyordie embed
615 {
616 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
617 'info_dict': {
618 'id': '18e820ec3f',
619 'ext': 'mp4',
620 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
621 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
622 },
623 # HEAD requests lead to endless 301, while GET is OK
624 'expected_warnings': ['301'],
625 },
626 # RUTV embed
627 {
628 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
629 'info_dict': {
630 'id': '776940',
631 'ext': 'mp4',
632 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
633 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
634 },
635 'params': {
636 # m3u8 download
637 'skip_download': True,
638 },
639 },
640 # TVC embed
641 {
642 '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/',
643 'info_dict': {
644 'id': '55304',
645 'ext': 'mp4',
646 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
647 },
648 },
649 # SportBox embed
650 {
651 'url': 'http://www.vestifinance.ru/articles/25753',
652 'info_dict': {
653 'id': '25753',
654 'title': 'ŠŸŃ€ŃŠ¼Ń‹Šµ трŠ°Š½ŃŠ»ŃŃ†ŠøŠø с Š¤Š¾Ń€ŃƒŠ¼Š°-Š²Ń‹ŃŃ‚Š°Š²ŠŗŠø "Š“Š¾ŃŠ·Š°ŠŗŠ°Š·-2013"',
655 },
656 'playlist': [{
657 'info_dict': {
658 'id': '370908',
659 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
660 'ext': 'mp4',
661 }
662 }, {
663 'info_dict': {
664 'id': '370905',
665 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
666 'ext': 'mp4',
667 }
668 }, {
669 'info_dict': {
670 'id': '370902',
671 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
672 'ext': 'mp4',
673 }
674 }],
675 'params': {
676 # m3u8 download
677 'skip_download': True,
678 },
679 },
680 # Myvi.ru embed
681 {
682 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
683 'info_dict': {
684 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
685 'ext': 'mp4',
686 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
687 'thumbnail': r're:^https?://.*\.jpg$',
688 'duration': 153,
689 }
690 },
691 # XHamster embed
692 {
693 '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',
694 'info_dict': {
695 'id': 'showthread',
696 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
697 },
698 'playlist_mincount': 7,
699 # This forum does not allow <iframe> syntaxes anymore
700 # Now HTML tags are displayed as-is
701 'skip': 'No videos on this page',
702 },
703 # Embedded TED video
704 {
705 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
706 'md5': '65fdff94098e4a607385a60c5177c638',
707 'info_dict': {
708 'id': '1969',
709 'ext': 'mp4',
710 'title': 'Hidden miracles of the natural world',
711 'uploader': 'Louie Schwartzberg',
712 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
713 }
714 },
715 # nowvideo embed hidden behind percent encoding
716 {
717 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
718 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
719 'info_dict': {
720 'id': '06e53103ca9aa',
721 'ext': 'flv',
722 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
723 'description': 'No description',
724 },
725 },
726 # arte embed
727 {
728 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
729 'md5': '7653032cbb25bf6c80d80f217055fa43',
730 'info_dict': {
731 'id': '048195-004_PLUS7-F',
732 'ext': 'flv',
733 'title': 'X:enius',
734 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
735 'upload_date': '20140320',
736 },
737 'params': {
738 'skip_download': 'Requires rtmpdump'
739 },
740 'skip': 'video gone',
741 },
742 # francetv embed
743 {
744 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
745 'info_dict': {
746 'id': 'EV_30231',
747 'ext': 'mp4',
748 'title': 'Alcaline, le concert avec Calogero',
749 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
750 'upload_date': '20150226',
751 'timestamp': 1424989860,
752 'duration': 5400,
753 },
754 'params': {
755 # m3u8 downloads
756 'skip_download': True,
757 },
758 'expected_warnings': [
759 'Forbidden'
760 ]
761 },
762 # CondƩ Nast embed
763 {
764 'url': 'http://www.wired.com/2014/04/honda-asimo/',
765 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
766 'info_dict': {
767 'id': '53501be369702d3275860000',
768 'ext': 'mp4',
769 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
770 }
771 },
772 # Dailymotion embed
773 {
774 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
775 'md5': '441aeeb82eb72c422c7f14ec533999cd',
776 'info_dict': {
777 'id': 'k2mm4bCdJ6CQ2i7c8o2',
778 'ext': 'mp4',
779 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
780 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
781 'uploader': 'Spi0n',
782 'uploader_id': 'xgditw',
783 'upload_date': '20140425',
784 'timestamp': 1398441542,
785 },
786 'add_ie': ['Dailymotion'],
787 },
788 # DailyMail embed
789 {
790 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
791 'info_dict': {
792 'id': '1495629',
793 'ext': 'mp4',
794 'title': 'Care worker punches elderly dementia patient in head 11 times',
795 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
796 },
797 'add_ie': ['DailyMail'],
798 'params': {
799 'skip_download': True,
800 },
801 },
802 # YouTube embed
803 {
804 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
805 'info_dict': {
806 'id': 'FXRb4ykk4S0',
807 'ext': 'mp4',
808 'title': 'The NBL Auction 2014',
809 'uploader': 'BADMINTON England',
810 'uploader_id': 'BADMINTONEvents',
811 'upload_date': '20140603',
812 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
813 },
814 'add_ie': ['Youtube'],
815 'params': {
816 'skip_download': True,
817 }
818 },
819 # MTVSercices embed
820 {
821 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
822 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
823 'info_dict': {
824 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
825 'ext': 'mp4',
826 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
827 'description': 'Two valets share their love for movie star Liam Neesons.',
828 'timestamp': 1349922600,
829 'upload_date': '20121011',
830 },
831 },
832 # YouTube embed via <data-embed-url="">
833 {
834 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
835 'info_dict': {
836 'id': '4vAffPZIT44',
837 'ext': 'mp4',
838 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
839 'uploader': 'Gameloft',
840 'uploader_id': 'gameloft',
841 'upload_date': '20140828',
842 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
843 },
844 'params': {
845 'skip_download': True,
846 }
847 },
848 # YouTube <object> embed
849 {
850 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
851 'md5': '516718101ec834f74318df76259fb3cc',
852 'info_dict': {
853 'id': 'msN87y-iEx0',
854 'ext': 'webm',
855 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
856 'upload_date': '20080526',
857 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
858 'uploader': 'Christopher Sykes',
859 'uploader_id': 'ChristopherJSykes',
860 },
861 'add_ie': ['Youtube'],
862 },
863 # Camtasia studio
864 {
865 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
866 'playlist': [{
867 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
868 'info_dict': {
869 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
870 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
871 'ext': 'flv',
872 'duration': 2235.90,
873 }
874 }, {
875 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
876 'info_dict': {
877 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
878 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
879 'ext': 'flv',
880 'duration': 2235.93,
881 }
882 }],
883 'info_dict': {
884 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
885 }
886 },
887 # Flowplayer
888 {
889 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
890 'md5': '9d65602bf31c6e20014319c7d07fba27',
891 'info_dict': {
892 'id': '5123ea6d5e5a7',
893 'ext': 'mp4',
894 'age_limit': 18,
895 'uploader': 'www.handjobhub.com',
896 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
897 }
898 },
899 # Multiple brightcove videos
900 # https://github.com/rg3/youtube-dl/issues/2283
901 {
902 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
903 'info_dict': {
904 'id': 'always-never',
905 'title': 'Always / Never - The New Yorker',
906 },
907 'playlist_count': 3,
908 'params': {
909 'extract_flat': False,
910 'skip_download': True,
911 }
912 },
913 # MLB embed
914 {
915 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
916 'md5': '96f09a37e44da40dd083e12d9a683327',
917 'info_dict': {
918 'id': '33322633',
919 'ext': 'mp4',
920 'title': 'Ump changes call to ball',
921 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
922 'duration': 48,
923 'timestamp': 1401537900,
924 'upload_date': '20140531',
925 'thumbnail': r're:^https?://.*\.jpg$',
926 },
927 },
928 # Wistia embed
929 {
930 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
931 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
932 'info_dict': {
933 'id': '6e2wtrbdaf',
934 'ext': 'mov',
935 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
936 'description': 'a Paywall Videos video from Remilon',
937 'duration': 644.072,
938 'uploader': 'study.com',
939 'timestamp': 1459678540,
940 'upload_date': '20160403',
941 'filesize': 24687186,
942 },
943 },
944 {
945 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
946 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
947 'info_dict': {
948 'id': 'uxjb0lwrcz',
949 'ext': 'mp4',
950 'title': 'Conversation about Hexagonal Rails Part 1',
951 'description': 'a Martin Fowler video from ThoughtWorks',
952 'duration': 1715.0,
953 'uploader': 'thoughtworks.wistia.com',
954 'timestamp': 1401832161,
955 'upload_date': '20140603',
956 },
957 },
958 # Wistia standard embed (async)
959 {
960 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
961 'info_dict': {
962 'id': '807fafadvk',
963 'ext': 'mp4',
964 'title': 'Drip Brennan Dunn Workshop',
965 'description': 'a JV Webinars video from getdrip-1',
966 'duration': 4986.95,
967 'timestamp': 1463607249,
968 'upload_date': '20160518',
969 },
970 'params': {
971 'skip_download': True,
972 }
973 },
974 # Soundcloud embed
975 {
976 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
977 'info_dict': {
978 'id': '174391317',
979 'ext': 'mp3',
980 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
981 'uploader': 'Sophos Security',
982 'title': 'Chet Chat 171 - Oct 29, 2014',
983 'upload_date': '20141029',
984 }
985 },
986 # Soundcloud multiple embeds
987 {
988 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
989 'info_dict': {
990 'id': '52809',
991 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
992 },
993 'playlist_mincount': 7,
994 },
995 # TuneIn station embed
996 {
997 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
998 'info_dict': {
999 'id': '204146',
1000 'ext': 'mp3',
1001 'title': 'CNRV',
1002 'location': 'Paris, France',
1003 'is_live': True,
1004 },
1005 'params': {
1006 # Live stream
1007 'skip_download': True,
1008 },
1009 },
1010 # Livestream embed
1011 {
1012 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1013 'info_dict': {
1014 'id': '67864563',
1015 'ext': 'flv',
1016 'upload_date': '20141112',
1017 'title': 'Rosetta #CometLanding webcast HL 10',
1018 }
1019 },
1020 # Another Livestream embed, without 'new.' in URL
1021 {
1022 'url': 'https://www.freespeech.org/',
1023 'info_dict': {
1024 'id': '123537347',
1025 'ext': 'mp4',
1026 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1027 },
1028 'params': {
1029 # Live stream
1030 'skip_download': True,
1031 },
1032 },
1033 # LazyYT
1034 {
1035 'url': 'https://skiplagged.com/',
1036 'info_dict': {
1037 'id': 'skiplagged',
1038 'title': 'Skiplagged: The smart way to find cheap flights',
1039 },
1040 'playlist_mincount': 1,
1041 'add_ie': ['Youtube'],
1042 },
1043 # Cinchcast embed
1044 {
1045 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1046 'info_dict': {
1047 'id': '7141703',
1048 'ext': 'mp3',
1049 'upload_date': '20141126',
1050 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1051 }
1052 },
1053 # Cinerama player
1054 {
1055 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1056 'info_dict': {
1057 'id': '730m_DandD_1901_512k',
1058 'ext': 'mp4',
1059 'uploader': 'www.abc.net.au',
1060 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1061 }
1062 },
1063 # embedded viddler video
1064 {
1065 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1066 'info_dict': {
1067 'id': '4d03aad9',
1068 'ext': 'mp4',
1069 'uploader': 'deadspin',
1070 'title': 'WALL-TO-GORTAT',
1071 'timestamp': 1422285291,
1072 'upload_date': '20150126',
1073 },
1074 'add_ie': ['Viddler'],
1075 },
1076 # Libsyn embed
1077 {
1078 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1079 'info_dict': {
1080 'id': '3377616',
1081 'ext': 'mp3',
1082 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1083 'description': 'md5:601cb790edd05908957dae8aaa866465',
1084 'upload_date': '20150220',
1085 },
1086 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
1087 },
1088 # jwplayer YouTube
1089 {
1090 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1091 'info_dict': {
1092 'id': 'Mrj4DVp2zeA',
1093 'ext': 'mp4',
1094 'upload_date': '20150212',
1095 'uploader': 'The National Archives UK',
1096 'description': 'md5:8078af856dca76edc42910b61273dbbf',
1097 'uploader_id': 'NationalArchives08',
1098 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
1099 },
1100 },
1101 # jwplayer rtmp
1102 {
1103 'url': 'http://www.suffolk.edu/sjc/live.php',
1104 'info_dict': {
1105 'id': 'live',
1106 'ext': 'flv',
1107 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1108 'uploader': 'www.suffolk.edu',
1109 },
1110 'params': {
1111 'skip_download': True,
1112 },
1113 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
1114 },
1115 # Complex jwplayer
1116 {
1117 'url': 'http://www.indiedb.com/games/king-machine/videos',
1118 'info_dict': {
1119 'id': 'videos',
1120 'ext': 'mp4',
1121 'title': 'king machine trailer 1',
1122 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
1123 'thumbnail': r're:^https?://.*\.jpg$',
1124 },
1125 },
1126 {
1127 # JWPlayer config passed as variable
1128 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1129 'info_dict': {
1130 'id': '3326530_hq',
1131 'ext': 'mp4',
1132 'title': 'ARIELE | Tube Cup',
1133 'uploader': 'www.txxx.com',
1134 'age_limit': 18,
1135 },
1136 'params': {
1137 'skip_download': True,
1138 }
1139 },
1140 {
1141 # JWPlatform iframe
1142 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1143 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1144 'info_dict': {
1145 'id': 'O0c5JcKT',
1146 'ext': 'mp4',
1147 'upload_date': '20171122',
1148 'timestamp': 1511366290,
1149 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1150 },
1151 'add_ie': [JWPlatformIE.ie_key()],
1152 },
1153 {
1154 # Video.js embed, multiple formats
1155 'url': 'http://ortcam.com/solidworks-урŠ¾Šŗ-6-Š½Š°ŃŃ‚Ń€Š¾Š¹ŠŗŠ°-чŠµŃ€Ń‚ŠµŠ¶Š°_33f9b7351.html',
1156 'info_dict': {
1157 'id': 'yygqldloqIk',
1158 'ext': 'mp4',
1159 'title': 'SolidWorks. Š£Ń€Š¾Šŗ 6 ŠŠ°ŃŃ‚Ń€Š¾Š¹ŠŗŠ° чŠµŃ€Ń‚ŠµŠ¶Š°',
1160 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1161 'upload_date': '20130314',
1162 'uploader': 'PROстŠ¾Šµ3D',
1163 'uploader_id': 'PROstoe3D',
1164 },
1165 'params': {
1166 'skip_download': True,
1167 },
1168 },
1169 {
1170 # Video.js embed, single format
1171 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1172 'info_dict': {
1173 'id': 'watch',
1174 'ext': 'mp4',
1175 'title': 'Step 1 - Good Foundation',
1176 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1177 },
1178 'params': {
1179 'skip_download': True,
1180 },
1181 },
1182 # rtl.nl embed
1183 {
1184 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1185 'playlist_mincount': 5,
1186 'info_dict': {
1187 'id': 'aanslagen-kopenhagen',
1188 'title': 'Aanslagen Kopenhagen',
1189 }
1190 },
1191 # Zapiks embed
1192 {
1193 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1194 'info_dict': {
1195 'id': '118046',
1196 'ext': 'mp4',
1197 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
1198 }
1199 },
1200 # Kaltura embed (different embed code)
1201 {
1202 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1203 'info_dict': {
1204 'id': '1_a52wc67y',
1205 'ext': 'flv',
1206 'upload_date': '20150127',
1207 'uploader_id': 'PremierMedia',
1208 'timestamp': int,
1209 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1210 },
1211 },
1212 # Kaltura embed with single quotes
1213 {
1214 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1215 'info_dict': {
1216 'id': '0_izeg5utt',
1217 'ext': 'mp4',
1218 'title': '35871',
1219 'timestamp': 1355743100,
1220 'upload_date': '20121217',
1221 'uploader_id': 'batchUser',
1222 },
1223 'add_ie': ['Kaltura'],
1224 },
1225 {
1226 # Kaltura embedded via quoted entry_id
1227 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1228 'info_dict': {
1229 'id': '0_utuok90b',
1230 'ext': 'mp4',
1231 'title': '06_matthew_brender_raj_dutt',
1232 'timestamp': 1466638791,
1233 'upload_date': '20160622',
1234 },
1235 'add_ie': ['Kaltura'],
1236 'expected_warnings': [
1237 'Could not send HEAD request'
1238 ],
1239 'params': {
1240 'skip_download': True,
1241 }
1242 },
1243 {
1244 # Kaltura embedded, some fileExt broken (#11480)
1245 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1246 'info_dict': {
1247 'id': '1_sgtvehim',
1248 'ext': 'mp4',
1249 'title': 'Our "Standard Models" of particle physics and cosmology',
1250 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1251 'timestamp': 1321158993,
1252 'upload_date': '20111113',
1253 'uploader_id': 'kps1',
1254 },
1255 'add_ie': ['Kaltura'],
1256 },
1257 {
1258 # Kaltura iframe embed
1259 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1260 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1261 'info_dict': {
1262 'id': '0_f2cfbpwy',
1263 'ext': 'mp4',
1264 'title': 'I. M. Pei: A Centennial Celebration',
1265 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1266 'upload_date': '20170403',
1267 'uploader_id': 'batchUser',
1268 'timestamp': 1491232186,
1269 },
1270 'add_ie': ['Kaltura'],
1271 },
1272 # EaglePlatform embed (generic URL)
1273 {
1274 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
1275 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1276 'info_dict': {
1277 'id': '227304',
1278 'ext': 'mp4',
1279 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
1280 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
1281 'thumbnail': r're:^https?://.*\.jpg$',
1282 'duration': 87,
1283 'view_count': int,
1284 'age_limit': 0,
1285 },
1286 'params': {
1287 'skip_download': True,
1288 },
1289 },
1290 # referrer protected EaglePlatform embed
1291 {
1292 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1293 'info_dict': {
1294 'id': '582306',
1295 'ext': 'mp4',
1296 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1297 'thumbnail': r're:^https?://.*\.jpg$',
1298 'duration': 3382,
1299 'view_count': int,
1300 },
1301 'params': {
1302 'skip_download': True,
1303 },
1304 },
1305 # ClipYou (EaglePlatform) embed (custom URL)
1306 {
1307 'url': 'http://muz-tv.ru/play/7129/',
1308 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
1309 'info_dict': {
1310 'id': '12820',
1311 'ext': 'mp4',
1312 'title': "'O Sole Mio",
1313 'thumbnail': r're:^https?://.*\.jpg$',
1314 'duration': 216,
1315 'view_count': int,
1316 },
1317 'params': {
1318 'skip_download': True,
1319 },
1320 'skip': 'This video is unavailable.',
1321 },
1322 # Pladform embed
1323 {
1324 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1325 'info_dict': {
1326 'id': '100183293',
1327 'ext': 'mp4',
1328 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
1329 'description': 'Š”Š¾ŠŗуŠ¼ŠµŠ½Ń‚Š°Š»ŃŒŠ½Ń‹Š¹ сŠµŃ€ŠøŠ°Š»-рŠ°ŃŃŠ»ŠµŠ“Š¾Š²Š°Š½ŠøŠµ Š¾Š“Š½Š¾Š¹ ŠøŠ· сŠ°Š¼Ń‹Ń… Š¶ŃƒŃ‚ŠŗŠøх тŠ°Š¹Š½ Š„Š„ Š²ŠµŠŗŠ°',
1330 'thumbnail': r're:^https?://.*\.jpg$',
1331 'duration': 694,
1332 'age_limit': 0,
1333 },
1334 'skip': 'HTTP Error 404: Not Found',
1335 },
1336 # Playwire embed
1337 {
1338 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1339 'info_dict': {
1340 'id': '3519514',
1341 'ext': 'mp4',
1342 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1343 'thumbnail': r're:^https?://.*\.png$',
1344 'duration': 45.115,
1345 },
1346 },
1347 # 5min embed
1348 {
1349 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1350 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1351 'info_dict': {
1352 'id': '518726732',
1353 'ext': 'mp4',
1354 'title': 'Facebook Creates "On This Day" | Crunch Report',
1355 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1356 'timestamp': 1427237531,
1357 'uploader': 'Crunch Report',
1358 'upload_date': '20150324',
1359 },
1360 'params': {
1361 # m3u8 download
1362 'skip_download': True,
1363 },
1364 },
1365 # SVT embed
1366 {
1367 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1368 'info_dict': {
1369 'id': '2900353',
1370 'ext': 'flv',
1371 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1372 'duration': 27,
1373 'age_limit': 0,
1374 },
1375 },
1376 # Crooks and Liars embed
1377 {
1378 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1379 'info_dict': {
1380 'id': '8RUoRhRi',
1381 'ext': 'mp4',
1382 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1383 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1384 'timestamp': 1428207000,
1385 'upload_date': '20150405',
1386 'uploader': 'Heather',
1387 },
1388 },
1389 # Crooks and Liars external embed
1390 {
1391 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1392 'info_dict': {
1393 'id': 'MTE3MjUtMzQ2MzA',
1394 'ext': 'mp4',
1395 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1396 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1397 'timestamp': 1265032391,
1398 'upload_date': '20100201',
1399 'uploader': 'Heather',
1400 },
1401 },
1402 # NBC Sports vplayer embed
1403 {
1404 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1405 'info_dict': {
1406 'id': 'ln7x1qSThw4k',
1407 'ext': 'flv',
1408 'title': "PFT Live: New leader in the 'new-look' defense",
1409 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1410 'uploader': 'NBCU-SPORTS',
1411 'upload_date': '20140107',
1412 'timestamp': 1389118457,
1413 },
1414 'skip': 'Invalid Page URL',
1415 },
1416 # NBC News embed
1417 {
1418 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1419 'md5': '1aa589c675898ae6d37a17913cf68d66',
1420 'info_dict': {
1421 'id': 'x_dtl_oa_LettermanliftPR_160608',
1422 'ext': 'mp4',
1423 'title': 'David Letterman: A Preview',
1424 '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.',
1425 'upload_date': '20160609',
1426 'timestamp': 1465431544,
1427 'uploader': 'NBCU-NEWS',
1428 },
1429 },
1430 # UDN embed
1431 {
1432 'url': 'https://video.udn.com/news/300346',
1433 'md5': 'fd2060e988c326991037b9aff9df21a6',
1434 'info_dict': {
1435 'id': '300346',
1436 'ext': 'mp4',
1437 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1438 'thumbnail': r're:^https?://.*\.jpg$',
1439 },
1440 'params': {
1441 # m3u8 download
1442 'skip_download': True,
1443 },
1444 'expected_warnings': ['Failed to parse JSON Expecting value'],
1445 },
1446 # Ooyala embed
1447 {
1448 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1449 'info_dict': {
1450 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1451 'ext': 'mp4',
1452 'description': 'Index/Match versus VLOOKUP.',
1453 'title': 'This is what separates the Excel masters from the wannabes',
1454 'duration': 191.933,
1455 },
1456 'params': {
1457 # m3u8 downloads
1458 'skip_download': True,
1459 }
1460 },
1461 # Brightcove URL in single quotes
1462 {
1463 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1464 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1465 'info_dict': {
1466 'id': '4255764656001',
1467 'ext': 'mp4',
1468 'title': 'SN Presents: Russell Martin, World Citizen',
1469 'description': 'To understand why he was the Toronto Blue Jaysā€™ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1470 'uploader': 'Rogers Sportsnet',
1471 'uploader_id': '1704050871',
1472 'upload_date': '20150525',
1473 'timestamp': 1432570283,
1474 },
1475 },
1476 # OnionStudios embed
1477 {
1478 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1479 'info_dict': {
1480 'id': '2855',
1481 'ext': 'mp4',
1482 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1483 'thumbnail': r're:^https?://.*\.jpe?g$',
1484 'uploader': 'ClickHole',
1485 'uploader_id': 'clickhole',
1486 }
1487 },
1488 # SnagFilms embed
1489 {
1490 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1491 'info_dict': {
1492 'id': '74849a00-85a9-11e1-9660-123139220831',
1493 'ext': 'mp4',
1494 'title': '#whilewewatch',
1495 }
1496 },
1497 # AdobeTVVideo embed
1498 {
1499 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1500 'md5': '43662b577c018ad707a63766462b1e87',
1501 'info_dict': {
1502 'id': '2456',
1503 'ext': 'mp4',
1504 'title': 'New experience with Acrobat DC',
1505 'description': 'New experience with Acrobat DC',
1506 'duration': 248.667,
1507 },
1508 },
1509 # BrightcoveInPageEmbed embed
1510 {
1511 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1512 'info_dict': {
1513 'id': '4238694884001',
1514 'ext': 'flv',
1515 'title': 'Tabletop: Dread, Last Thoughts',
1516 'description': 'Tabletop: Dread, Last Thoughts',
1517 'duration': 51690,
1518 },
1519 },
1520 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1521 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1522 {
1523 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1524 'info_dict': {
1525 'id': '4785848093001',
1526 'ext': 'mp4',
1527 'title': 'The Cardinal Pell Interview',
1528 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1529 'uploader': 'GlobeCast Australia - GlobeStream',
1530 'uploader_id': '2733773828001',
1531 'upload_date': '20160304',
1532 'timestamp': 1457083087,
1533 },
1534 'params': {
1535 # m3u8 downloads
1536 'skip_download': True,
1537 },
1538 },
1539 {
1540 # Brightcove embed with whitespace around attribute names
1541 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1542 'info_dict': {
1543 'id': '3167554373001',
1544 'ext': 'mp4',
1545 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1546 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1547 'uploader_id': '1079349493',
1548 'upload_date': '20140207',
1549 'timestamp': 1391810548,
1550 },
1551 'params': {
1552 'skip_download': True,
1553 },
1554 },
1555 # Another form of arte.tv embed
1556 {
1557 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1558 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1559 'info_dict': {
1560 'id': '030273-562_PLUS7-F',
1561 'ext': 'mp4',
1562 'title': 'ARTE Reportage - Nulle part, en France',
1563 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1564 'upload_date': '20160409',
1565 },
1566 },
1567 # LiveLeak embed
1568 {
1569 'url': 'http://www.wykop.pl/link/3088787/',
1570 'md5': '7619da8c820e835bef21a1efa2a0fc71',
1571 'info_dict': {
1572 'id': '874_1459135191',
1573 'ext': 'mp4',
1574 'title': 'Man shows poor quality of new apartment building',
1575 'description': 'The wall is like a sand pile.',
1576 'uploader': 'Lake8737',
1577 },
1578 'add_ie': [LiveLeakIE.ie_key()],
1579 },
1580 # Another LiveLeak embed pattern (#13336)
1581 {
1582 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1583 'info_dict': {
1584 'id': '2eb_1496309988',
1585 'ext': 'mp4',
1586 'title': 'Thief robs place where everyone was armed',
1587 'description': 'md5:694d73ee79e535953cf2488562288eee',
1588 'uploader': 'brazilwtf',
1589 },
1590 'add_ie': [LiveLeakIE.ie_key()],
1591 },
1592 # Duplicated embedded video URLs
1593 {
1594 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1595 'info_dict': {
1596 'id': '149298443_480_16c25b74_2',
1597 'ext': 'mp4',
1598 'title': 'vs. Blue Orange Spring Game',
1599 'uploader': 'www.hudl.com',
1600 },
1601 },
1602 # twitter:player:stream embed
1603 {
1604 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1605 'info_dict': {
1606 'id': 'master',
1607 'ext': 'mp4',
1608 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1609 'uploader': 'www.rtl.be',
1610 },
1611 'params': {
1612 # m3u8 downloads
1613 'skip_download': True,
1614 },
1615 },
1616 # twitter:player embed
1617 {
1618 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1619 'md5': 'a3e0df96369831de324f0778e126653c',
1620 'info_dict': {
1621 'id': '4909620399001',
1622 'ext': 'mp4',
1623 'title': 'What Do Black Holes Sound Like?',
1624 'description': 'what do black holes sound like',
1625 'upload_date': '20160524',
1626 'uploader_id': '29913724001',
1627 'timestamp': 1464107587,
1628 'uploader': 'TheAtlantic',
1629 },
1630 'add_ie': ['BrightcoveLegacy'],
1631 },
1632 # Facebook <iframe> embed
1633 {
1634 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1635 'md5': 'fbcde74f534176ecb015849146dd3aee',
1636 'info_dict': {
1637 'id': '599637780109885',
1638 'ext': 'mp4',
1639 'title': 'Facebook video #599637780109885',
1640 },
1641 },
1642 # Facebook <iframe> embed, plugin video
1643 {
1644 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1645 'info_dict': {
1646 'id': '1754168231264132',
1647 'ext': 'mp4',
1648 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1649 'uploader': 'Tariq Ramadan (official)',
1650 'timestamp': 1496758379,
1651 'upload_date': '20170606',
1652 },
1653 'params': {
1654 'skip_download': True,
1655 },
1656 },
1657 # Facebook API embed
1658 {
1659 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1660 'md5': 'a47372ee61b39a7b90287094d447d94e',
1661 'info_dict': {
1662 'id': '10153467542406923',
1663 'ext': 'mp4',
1664 'title': 'Facebook video #10153467542406923',
1665 },
1666 },
1667 # Wordpress "YouTube Video Importer" plugin
1668 {
1669 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1670 'md5': 'd16797741b560b485194eddda8121b48',
1671 'info_dict': {
1672 'id': 'HNTXWDXV9Is',
1673 'ext': 'mp4',
1674 'title': 'Blue Devils Drumline Stanford lot 2016',
1675 'upload_date': '20160627',
1676 'uploader_id': 'GENOCIDE8GENERAL10',
1677 'uploader': 'cylus cyrus',
1678 },
1679 },
1680 {
1681 # video stored on custom kaltura server
1682 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1683 'md5': '537617d06e64dfed891fa1593c4b30cc',
1684 'info_dict': {
1685 'id': '0_1iotm5bh',
1686 'ext': 'mp4',
1687 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1688 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1689 'uploader_id': 'videos.expansion@el-mundo.net',
1690 'upload_date': '20150429',
1691 'timestamp': 1430303472,
1692 },
1693 'add_ie': ['Kaltura'],
1694 },
1695 {
1696 # Non-standard Vimeo embed
1697 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1698 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1699 'info_dict': {
1700 'id': '148867247',
1701 'ext': 'mp4',
1702 'title': 'Understanding the web - Teaser',
1703 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1704 'upload_date': '20151214',
1705 'uploader': 'OpenClassrooms',
1706 'uploader_id': 'openclassrooms',
1707 },
1708 'add_ie': ['Vimeo'],
1709 },
1710 {
1711 # generic vimeo embed that requires original URL passed as Referer
1712 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1713 'only_matching': True,
1714 },
1715 {
1716 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1717 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1718 'info_dict': {
1719 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1720 'ext': 'mp4',
1721 'title': 'Big Buck Bunny',
1722 'description': 'Royalty free test video',
1723 'timestamp': 1432816365,
1724 'upload_date': '20150528',
1725 'is_live': False,
1726 },
1727 'params': {
1728 'skip_download': True,
1729 },
1730 'add_ie': [ArkenaIE.ie_key()],
1731 },
1732 {
1733 '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/',
1734 'info_dict': {
1735 'id': '1c7141f46c',
1736 'ext': 'mp4',
1737 'title': 'ŠŠ ŠšŠžŠ”ŠŖŠœ ŠžŠ¢ Š’Š—Š Š˜Š’: Š˜Š·Ń‚ŠøчŠ°Š½Šµ Š½Š° Š³Š°Š· Š½Š° Š±ŠµŠ½Š·ŠøŠ½Š¾ŃŃ‚Š°Š½Ń†Šøя Š² ŠŸŠ»Š¾Š²Š“ŠøŠ²',
1738 },
1739 'params': {
1740 'skip_download': True,
1741 },
1742 'add_ie': [Vbox7IE.ie_key()],
1743 },
1744 {
1745 # DBTV embeds
1746 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
1747 'info_dict': {
1748 'id': '43254897',
1749 'title': 'Etter ett Ƅrs planlegging, klaffet endelig alt: - Jeg mƄtte ta en liten dans',
1750 },
1751 'playlist_mincount': 3,
1752 },
1753 {
1754 # Videa embeds
1755 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1756 'info_dict': {
1757 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1758 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1759 },
1760 'playlist_mincount': 2,
1761 },
1762 {
1763 # 20 minuten embed
1764 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1765 'info_dict': {
1766 'id': '523629',
1767 'ext': 'mp4',
1768 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1769 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1770 },
1771 'params': {
1772 'skip_download': True,
1773 },
1774 'add_ie': [TwentyMinutenIE.ie_key()],
1775 },
1776 {
1777 # VideoPress embed
1778 'url': 'https://en.support.wordpress.com/videopress/',
1779 'info_dict': {
1780 'id': 'OcobLTqC',
1781 'ext': 'm4v',
1782 'title': 'IMG_5786',
1783 'timestamp': 1435711927,
1784 'upload_date': '20150701',
1785 },
1786 'params': {
1787 'skip_download': True,
1788 },
1789 'add_ie': [VideoPressIE.ie_key()],
1790 },
1791 {
1792 # Rutube embed
1793 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1794 'info_dict': {
1795 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1796 'ext': 'flv',
1797 'title': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾: ŠšŠ°Š·Š°Š½ŃŒ 2',
1798 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1799 'uploader': 'ŠœŠ°Š³Š°Š·Š·ŠøŠ½Š¾',
1800 'upload_date': '20170228',
1801 'uploader_id': '996642',
1802 },
1803 'params': {
1804 'skip_download': True,
1805 },
1806 'add_ie': [RutubeIE.ie_key()],
1807 },
1808 {
1809 # ThePlatform embedded with whitespaces in URLs
1810 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1811 'only_matching': True,
1812 },
1813 {
1814 # Senate ISVP iframe https
1815 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1816 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1817 'info_dict': {
1818 'id': 'govtaff020316',
1819 'ext': 'mp4',
1820 'title': 'Integrated Senate Video Player',
1821 },
1822 'add_ie': [SenateISVPIE.ie_key()],
1823 },
1824 {
1825 # Limelight embeds (1 channel embed + 4 media embeds)
1826 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1827 'info_dict': {
1828 'id': 'FacilitatorTraining2017',
1829 'title': 'Facilitator Training 2017',
1830 },
1831 'playlist_mincount': 5,
1832 },
1833 {
1834 # Limelight embed (LimelightPlayerUtil.embed)
1835 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1836 'info_dict': {
1837 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1838 'ext': 'mp4',
1839 'title': '07448641',
1840 'timestamp': 1499890639,
1841 'upload_date': '20170712',
1842 },
1843 'params': {
1844 'skip_download': True,
1845 },
1846 'add_ie': ['LimelightMedia'],
1847 },
1848 {
1849 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1850 'info_dict': {
1851 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1852 'title': 'Standoff with Walnut Creek murder suspect ends',
1853 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1854 },
1855 'playlist_mincount': 4,
1856 },
1857 {
1858 # WashingtonPost embed
1859 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1860 'info_dict': {
1861 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1862 'ext': 'mp4',
1863 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1864 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script ā€” and enlisted actors.',
1865 'timestamp': 1455216756,
1866 'uploader': 'The Washington Post',
1867 'upload_date': '20160211',
1868 },
1869 'add_ie': [WashingtonPostIE.ie_key()],
1870 },
1871 {
1872 # Mediaset embed
1873 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1874 'info_dict': {
1875 'id': '720642',
1876 'ext': 'mp4',
1877 'title': 'Serracchiani: "Voglio vivere in una societĆ  aperta, con tutela del patto di fiducia"',
1878 },
1879 'params': {
1880 'skip_download': True,
1881 },
1882 'add_ie': [MediasetIE.ie_key()],
1883 },
1884 {
1885 # JOJ.sk embeds
1886 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1887 'info_dict': {
1888 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1889 'title': 'Slovenskom sa prehnala vlna silnĆ½ch bĆŗrok',
1890 },
1891 'playlist_mincount': 5,
1892 'add_ie': [JojIE.ie_key()],
1893 },
1894 {
1895 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1896 'url': 'https://tvrain.ru/amp/418921/',
1897 'md5': 'cc00413936695987e8de148b67d14f1d',
1898 'info_dict': {
1899 'id': '418921',
1900 'ext': 'mp4',
1901 'title': 'Š”тŠ°Ń ŠŠ°Š¼ŠøŠ½: Ā«ŠœŃ‹ Š½Š°Ń€ŃƒŃˆŠøŠ»Šø Š“ŠµŠ²ŃŃ‚Š²ŠµŠ½Š½Š¾ŃŃ‚ŃŒ ŠšŃ€ŠµŠ¼Š»ŃĀ»',
1902 },
1903 },
1904 {
1905 # vzaar embed
1906 'url': 'http://help.vzaar.com/article/165-embedding-video',
1907 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
1908 'info_dict': {
1909 'id': '8707641',
1910 'ext': 'mp4',
1911 'title': 'Building A Business Online: Principal Chairs Q & A',
1912 },
1913 },
1914 {
1915 # multiple HTML5 videos on one page
1916 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1917 'info_dict': {
1918 'id': 'keyscenarios',
1919 'title': 'Rescue Kit 14 Free Edition - Getting started',
1920 },
1921 'playlist_count': 4,
1922 },
1923 {
1924 # vshare embed
1925 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1926 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1927 'info_dict': {
1928 'id': '0f64ce6',
1929 'title': 'vl14062007715967',
1930 'ext': 'mp4',
1931 }
1932 },
1933 {
1934 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1935 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1936 'info_dict': {
1937 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1938 'ext': 'mp4',
1939 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1940 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1941 'timestamp': 1474354800,
1942 'upload_date': '20160920',
1943 }
1944 },
1945 {
1946 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1947 'info_dict': {
1948 'id': '1731611',
1949 'ext': 'mp4',
1950 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1951 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1952 'timestamp': 1516100691,
1953 'upload_date': '20180116',
1954 },
1955 'params': {
1956 'skip_download': True,
1957 },
1958 'add_ie': [SpringboardPlatformIE.ie_key()],
1959 },
1960 {
1961 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1962 'info_dict': {
1963 'id': 'uPDB5I9wfp8',
1964 'ext': 'webm',
1965 'title': 'Pocoyo: 90 minutos de episĆ³dios completos PortuguĆŖs para crianƧas - PARTE 3',
1966 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1967 'upload_date': '20160219',
1968 'uploader': 'Pocoyo - PortuguĆŖs (BR)',
1969 'uploader_id': 'PocoyoBrazil',
1970 },
1971 'add_ie': [YoutubeIE.ie_key()],
1972 'params': {
1973 'skip_download': True,
1974 },
1975 },
1976 {
1977 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1978 'info_dict': {
1979 'id': 'vMDE4NzI1Mjgt690b',
1980 'ext': 'mp4',
1981 'title': 'ŠšŠ¾Ń‚ŃŃ‚Š°',
1982 },
1983 'add_ie': [YapFilesIE.ie_key()],
1984 'params': {
1985 'skip_download': True,
1986 },
1987 }
1988 # {
1989 # # TODO: find another test
1990 # # http://schema.org/VideoObject
1991 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1992 # 'md5': '888dcf08b7ea671381f00fab74692755',
1993 # 'info_dict': {
1994 # 'id': 'nyvTSJMKId',
1995 # 'ext': 'mp4',
1996 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1997 # 'description': '#love for cats.',
1998 # 'timestamp': 1461244995,
1999 # 'upload_date': '20160421',
2000 # },
2001 # 'params': {
2002 # 'force_generic_extractor': True,
2003 # },
2004 # }
2005 ]
2006
2007 def report_following_redirect(self, new_url):
2008 """Report information extraction."""
2009 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
2010
2011 def _extract_rss(self, url, video_id, doc):
2012 playlist_title = doc.find('./channel/title').text
2013 playlist_desc_el = doc.find('./channel/description')
2014 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2015
2016 entries = []
2017 for it in doc.findall('./channel/item'):
2018 next_url = xpath_text(it, 'link', fatal=False)
2019 if not next_url:
2020 enclosure_nodes = it.findall('./enclosure')
2021 for e in enclosure_nodes:
2022 next_url = e.attrib.get('url')
2023 if next_url:
2024 break
2025
2026 if not next_url:
2027 continue
2028
2029 entries.append({
2030 '_type': 'url_transparent',
2031 'url': next_url,
2032 'title': it.find('title').text,
2033 })
2034
2035 return {
2036 '_type': 'playlist',
2037 'id': url,
2038 'title': playlist_title,
2039 'description': playlist_desc,
2040 'entries': entries,
2041 }
2042
2043 def _extract_camtasia(self, url, video_id, webpage):
2044 """ Returns None if no camtasia video can be found. """
2045
2046 camtasia_cfg = self._search_regex(
2047 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2048 webpage, 'camtasia configuration file', default=None)
2049 if camtasia_cfg is None:
2050 return None
2051
2052 title = self._html_search_meta('DC.title', webpage, fatal=True)
2053
2054 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2055 camtasia_cfg = self._download_xml(
2056 camtasia_url, video_id,
2057 note='Downloading camtasia configuration',
2058 errnote='Failed to download camtasia configuration')
2059 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2060
2061 entries = []
2062 for n in fileset_node.getchildren():
2063 url_n = n.find('./uri')
2064 if url_n is None:
2065 continue
2066
2067 entries.append({
2068 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2069 'title': '%s - %s' % (title, n.tag),
2070 'url': compat_urlparse.urljoin(url, url_n.text),
2071 'duration': float_or_none(n.find('./duration').text),
2072 })
2073
2074 return {
2075 '_type': 'playlist',
2076 'entries': entries,
2077 'title': title,
2078 }
2079
2080 def _real_extract(self, url):
2081 if url.startswith('//'):
2082 return {
2083 '_type': 'url',
2084 'url': self.http_scheme() + url,
2085 }
2086
2087 parsed_url = compat_urlparse.urlparse(url)
2088 if not parsed_url.scheme:
2089 default_search = self._downloader.params.get('default_search')
2090 if default_search is None:
2091 default_search = 'fixup_error'
2092
2093 if default_search in ('auto', 'auto_warning', 'fixup_error'):
2094 if '/' in url:
2095 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2096 return self.url_result('http://' + url)
2097 elif default_search != 'fixup_error':
2098 if default_search == 'auto_warning':
2099 if re.match(r'^(?:url|URL)$', url):
2100 raise ExtractorError(
2101 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2102 expected=True)
2103 else:
2104 self._downloader.report_warning(
2105 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
2106 return self.url_result('ytsearch:' + url)
2107
2108 if default_search in ('error', 'fixup_error'):
2109 raise ExtractorError(
2110 '%r is not a valid URL. '
2111 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2112 % (url, url), expected=True)
2113 else:
2114 if ':' not in default_search:
2115 default_search += ':'
2116 return self.url_result(default_search + url)
2117
2118 url, smuggled_data = unsmuggle_url(url)
2119 force_videoid = None
2120 is_intentional = smuggled_data and smuggled_data.get('to_generic')
2121 if smuggled_data and 'force_videoid' in smuggled_data:
2122 force_videoid = smuggled_data['force_videoid']
2123 video_id = force_videoid
2124 else:
2125 video_id = self._generic_id(url)
2126
2127 self.to_screen('%s: Requesting header' % video_id)
2128
2129 head_req = HEADRequest(url)
2130 head_response = self._request_webpage(
2131 head_req, video_id,
2132 note=False, errnote='Could not send HEAD request to %s' % url,
2133 fatal=False)
2134
2135 if head_response is not False:
2136 # Check for redirect
2137 new_url = compat_str(head_response.geturl())
2138 if url != new_url:
2139 self.report_following_redirect(new_url)
2140 if force_videoid:
2141 new_url = smuggle_url(
2142 new_url, {'force_videoid': force_videoid})
2143 return self.url_result(new_url)
2144
2145 full_response = None
2146 if head_response is False:
2147 request = sanitized_Request(url)
2148 request.add_header('Accept-Encoding', '*')
2149 full_response = self._request_webpage(request, video_id)
2150 head_response = full_response
2151
2152 info_dict = {
2153 'id': video_id,
2154 'title': self._generic_title(url),
2155 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
2156 }
2157
2158 # Check for direct link to a video
2159 content_type = head_response.headers.get('Content-Type', '').lower()
2160 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
2161 if m:
2162 format_id = compat_str(m.group('format_id'))
2163 if format_id.endswith('mpegurl'):
2164 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
2165 elif format_id == 'f4m':
2166 formats = self._extract_f4m_formats(url, video_id)
2167 else:
2168 formats = [{
2169 'format_id': format_id,
2170 'url': url,
2171 'vcodec': 'none' if m.group('type') == 'audio' else None
2172 }]
2173 info_dict['direct'] = True
2174 self._sort_formats(formats)
2175 info_dict['formats'] = formats
2176 return info_dict
2177
2178 if not self._downloader.params.get('test', False) and not is_intentional:
2179 force = self._downloader.params.get('force_generic_extractor', False)
2180 self._downloader.report_warning(
2181 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
2182
2183 if not full_response:
2184 request = sanitized_Request(url)
2185 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2186 # making it impossible to download only chunk of the file (yet we need only 512kB to
2187 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2188 # that will always result in downloading the whole file that is not desirable.
2189 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2190 # to accept raw bytes and being able to download only a chunk.
2191 # It may probably better to solve this by checking Content-Type for application/octet-stream
2192 # after HEAD request finishes, but not sure if we can rely on this.
2193 request.add_header('Accept-Encoding', '*')
2194 full_response = self._request_webpage(request, video_id)
2195
2196 first_bytes = full_response.read(512)
2197
2198 # Is it an M3U playlist?
2199 if first_bytes.startswith(b'#EXTM3U'):
2200 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
2201 self._sort_formats(info_dict['formats'])
2202 return info_dict
2203
2204 # Maybe it's a direct link to a video?
2205 # Be careful not to download the whole thing!
2206 if not is_html(first_bytes):
2207 self._downloader.report_warning(
2208 'URL could be a direct video link, returning it as such.')
2209 info_dict.update({
2210 'direct': True,
2211 'url': url,
2212 })
2213 return info_dict
2214
2215 webpage = self._webpage_read_content(
2216 full_response, url, video_id, prefix=first_bytes)
2217
2218 self.report_extraction(video_id)
2219
2220 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
2221 try:
2222 doc = compat_etree_fromstring(webpage.encode('utf-8'))
2223 if doc.tag == 'rss':
2224 return self._extract_rss(url, video_id, doc)
2225 elif doc.tag == 'SmoothStreamingMedia':
2226 info_dict['formats'] = self._parse_ism_formats(doc, url)
2227 self._sort_formats(info_dict['formats'])
2228 return info_dict
2229 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
2230 smil = self._parse_smil(doc, url, video_id)
2231 self._sort_formats(smil['formats'])
2232 return smil
2233 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2234 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
2235 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
2236 info_dict['formats'] = self._parse_mpd_formats(
2237 doc,
2238 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
2239 mpd_url=url)
2240 self._sort_formats(info_dict['formats'])
2241 return info_dict
2242 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2243 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
2244 self._sort_formats(info_dict['formats'])
2245 return info_dict
2246 except compat_xml_parse_error:
2247 pass
2248
2249 # Is it a Camtasia project?
2250 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2251 if camtasia_res is not None:
2252 return camtasia_res
2253
2254 # Sometimes embedded video player is hidden behind percent encoding
2255 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2256 # Unescaping the whole page allows to handle those cases in a generic way
2257 webpage = compat_urllib_parse_unquote(webpage)
2258
2259 # it's tempting to parse this further, but you would
2260 # have to take into account all the variations like
2261 # Video Title - Site Name
2262 # Site Name | Video Title
2263 # Video Title - Tagline | Site Name
2264 # and so on and so forth; it's just not practical
2265 video_title = self._og_search_title(
2266 webpage, default=None) or self._html_search_regex(
2267 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2268 default='video')
2269
2270 # Try to detect age limit automatically
2271 age_limit = self._rta_search(webpage)
2272 # And then there are the jokers who advertise that they use RTA,
2273 # but actually don't.
2274 AGE_LIMIT_MARKERS = [
2275 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
2276 ]
2277 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2278 age_limit = 18
2279
2280 # video uploader is domain name
2281 video_uploader = self._search_regex(
2282 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
2283
2284 video_description = self._og_search_description(webpage, default=None)
2285 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2286
2287 info_dict.update({
2288 'title': video_title,
2289 'description': video_description,
2290 'thumbnail': video_thumbnail,
2291 'age_limit': age_limit,
2292 })
2293
2294 # Look for Brightcove Legacy Studio embeds
2295 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
2296 if bc_urls:
2297 entries = [{
2298 '_type': 'url',
2299 'url': smuggle_url(bc_url, {'Referer': url}),
2300 'ie_key': 'BrightcoveLegacy'
2301 } for bc_url in bc_urls]
2302
2303 return {
2304 '_type': 'playlist',
2305 'title': video_title,
2306 'id': video_id,
2307 'entries': entries,
2308 }
2309
2310 # Look for Brightcove New Studio embeds
2311 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
2312 if bc_urls:
2313 return self.playlist_from_matches(
2314 bc_urls, video_id, video_title,
2315 getter=lambda x: smuggle_url(x, {'referrer': url}),
2316 ie='BrightcoveNew')
2317
2318 # Look for Nexx embeds
2319 nexx_urls = NexxIE._extract_urls(webpage)
2320 if nexx_urls:
2321 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2322
2323 # Look for Nexx iFrame embeds
2324 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2325 if nexx_embed_urls:
2326 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2327
2328 # Look for ThePlatform embeds
2329 tp_urls = ThePlatformIE._extract_urls(webpage)
2330 if tp_urls:
2331 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
2332
2333 # Look for Vessel embeds
2334 vessel_urls = VesselIE._extract_urls(webpage)
2335 if vessel_urls:
2336 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
2337
2338 # Look for embedded rtl.nl player
2339 matches = re.findall(
2340 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
2341 webpage)
2342 if matches:
2343 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
2344
2345 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2346 if vimeo_urls:
2347 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
2348
2349 vid_me_embed_url = self._search_regex(
2350 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2351 webpage, 'vid.me embed', default=None)
2352 if vid_me_embed_url is not None:
2353 return self.url_result(vid_me_embed_url, 'Vidme')
2354
2355 # Look for YouTube embeds
2356 youtube_urls = YoutubeIE._extract_urls(webpage)
2357 if youtube_urls:
2358 return self.playlist_from_matches(
2359 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
2360
2361 matches = DailymotionIE._extract_urls(webpage)
2362 if matches:
2363 return self.playlist_from_matches(matches, video_id, video_title)
2364
2365 # Look for embedded Dailymotion playlist player (#3822)
2366 m = re.search(
2367 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2368 if m:
2369 playlists = re.findall(
2370 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2371 if playlists:
2372 return self.playlist_from_matches(
2373 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
2374
2375 # Look for DailyMail embeds
2376 dailymail_urls = DailyMailIE._extract_urls(webpage)
2377 if dailymail_urls:
2378 return self.playlist_from_matches(
2379 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2380
2381 # Look for embedded Wistia player
2382 wistia_url = WistiaIE._extract_url(webpage)
2383 if wistia_url:
2384 return {
2385 '_type': 'url_transparent',
2386 'url': self._proto_relative_url(wistia_url),
2387 'ie_key': WistiaIE.ie_key(),
2388 'uploader': video_uploader,
2389 }
2390
2391 # Look for SVT player
2392 svt_url = SVTIE._extract_url(webpage)
2393 if svt_url:
2394 return self.url_result(svt_url, 'SVT')
2395
2396 # Look for Bandcamp pages with custom domain
2397 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2398 if mobj is not None:
2399 burl = unescapeHTML(mobj.group(1))
2400 # Don't set the extractor because it can be a track url or an album
2401 return self.url_result(burl)
2402
2403 # Look for embedded Vevo player
2404 mobj = re.search(
2405 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2406 if mobj is not None:
2407 return self.url_result(mobj.group('url'))
2408
2409 # Look for embedded Viddler player
2410 mobj = re.search(
2411 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2412 webpage)
2413 if mobj is not None:
2414 return self.url_result(mobj.group('url'))
2415
2416 # Look for NYTimes player
2417 mobj = re.search(
2418 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2419 webpage)
2420 if mobj is not None:
2421 return self.url_result(mobj.group('url'))
2422
2423 # Look for Libsyn player
2424 mobj = re.search(
2425 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2426 if mobj is not None:
2427 return self.url_result(mobj.group('url'))
2428
2429 # Look for Ooyala videos
2430 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
2431 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2432 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
2433 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2434 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
2435 if mobj is not None:
2436 embed_token = self._search_regex(
2437 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2438 webpage, 'ooyala embed token', default=None)
2439 return OoyalaIE._build_url_result(smuggle_url(
2440 mobj.group('ec'), {
2441 'domain': url,
2442 'embed_token': embed_token,
2443 }))
2444
2445 # Look for multiple Ooyala embeds on SBN network websites
2446 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2447 if mobj is not None:
2448 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2449 if embeds:
2450 return self.playlist_from_matches(
2451 embeds, video_id, video_title,
2452 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
2453
2454 # Look for Aparat videos
2455 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
2456 if mobj is not None:
2457 return self.url_result(mobj.group(1), 'Aparat')
2458
2459 # Look for MPORA videos
2460 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
2461 if mobj is not None:
2462 return self.url_result(mobj.group(1), 'Mpora')
2463
2464 # Look for embedded NovaMov-based player
2465 mobj = re.search(
2466 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
2467 (?P<url>http://(?:(?:embed|www)\.)?
2468 (?:novamov\.com|
2469 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2470 videoweed\.(?:es|com)|
2471 movshare\.(?:net|sx|ag)|
2472 divxstage\.(?:eu|net|ch|co|at|ag))
2473 /embed\.php.+?)\1''', webpage)
2474 if mobj is not None:
2475 return self.url_result(mobj.group('url'))
2476
2477 # Look for embedded Facebook player
2478 facebook_urls = FacebookIE._extract_urls(webpage)
2479 if facebook_urls:
2480 return self.playlist_from_matches(facebook_urls, video_id, video_title)
2481
2482 # Look for embedded VK player
2483 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2484 if mobj is not None:
2485 return self.url_result(mobj.group('url'), 'VK')
2486
2487 # Look for embedded Odnoklassniki player
2488 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2489 if mobj is not None:
2490 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2491
2492 # Look for embedded ivi player
2493 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2494 if mobj is not None:
2495 return self.url_result(mobj.group('url'), 'Ivi')
2496
2497 # Look for embedded Huffington Post player
2498 mobj = re.search(
2499 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
2500 if mobj is not None:
2501 return self.url_result(mobj.group('url'), 'HuffPost')
2502
2503 # Look for embed.ly
2504 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2505 if mobj is not None:
2506 return self.url_result(mobj.group('url'))
2507 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2508 if mobj is not None:
2509 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
2510
2511 # Look for funnyordie embed
2512 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2513 if matches:
2514 return self.playlist_from_matches(
2515 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
2516
2517 # Look for BBC iPlayer embed
2518 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2519 if matches:
2520 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
2521
2522 # Look for embedded RUTV player
2523 rutv_url = RUTVIE._extract_url(webpage)
2524 if rutv_url:
2525 return self.url_result(rutv_url, 'RUTV')
2526
2527 # Look for embedded TVC player
2528 tvc_url = TVCIE._extract_url(webpage)
2529 if tvc_url:
2530 return self.url_result(tvc_url, 'TVC')
2531
2532 # Look for embedded SportBox player
2533 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2534 if sportbox_urls:
2535 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
2536
2537 # Look for embedded XHamster player
2538 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2539 if xhamster_urls:
2540 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2541
2542 # Look for embedded TNAFlixNetwork player
2543 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2544 if tnaflix_urls:
2545 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2546
2547 # Look for embedded PornHub player
2548 pornhub_urls = PornHubIE._extract_urls(webpage)
2549 if pornhub_urls:
2550 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
2551
2552 # Look for embedded DrTuber player
2553 drtuber_urls = DrTuberIE._extract_urls(webpage)
2554 if drtuber_urls:
2555 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
2556
2557 # Look for embedded RedTube player
2558 redtube_urls = RedTubeIE._extract_urls(webpage)
2559 if redtube_urls:
2560 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
2561
2562 # Look for embedded Tvigle player
2563 mobj = re.search(
2564 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2565 if mobj is not None:
2566 return self.url_result(mobj.group('url'), 'Tvigle')
2567
2568 # Look for embedded TED player
2569 mobj = re.search(
2570 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
2571 if mobj is not None:
2572 return self.url_result(mobj.group('url'), 'TED')
2573
2574 # Look for embedded Ustream videos
2575 ustream_url = UstreamIE._extract_url(webpage)
2576 if ustream_url:
2577 return self.url_result(ustream_url, UstreamIE.ie_key())
2578
2579 # Look for embedded arte.tv player
2580 mobj = re.search(
2581 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2582 webpage)
2583 if mobj is not None:
2584 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2585
2586 # Look for embedded francetv player
2587 mobj = re.search(
2588 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2589 webpage)
2590 if mobj is not None:
2591 return self.url_result(mobj.group('url'))
2592
2593 # Look for embedded smotri.com player
2594 smotri_url = SmotriIE._extract_url(webpage)
2595 if smotri_url:
2596 return self.url_result(smotri_url, 'Smotri')
2597
2598 # Look for embedded Myvi.ru player
2599 myvi_url = MyviIE._extract_url(webpage)
2600 if myvi_url:
2601 return self.url_result(myvi_url)
2602
2603 # Look for embedded soundcloud player
2604 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2605 if soundcloud_urls:
2606 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2607
2608 # Look for tunein player
2609 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2610 if tunein_urls:
2611 return self.playlist_from_matches(tunein_urls, video_id, video_title)
2612
2613 # Look for embedded mtvservices player
2614 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2615 if mtvservices_url:
2616 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2617
2618 # Look for embedded yahoo player
2619 mobj = re.search(
2620 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2621 webpage)
2622 if mobj is not None:
2623 return self.url_result(mobj.group('url'), 'Yahoo')
2624
2625 # Look for embedded sbs.com.au player
2626 mobj = re.search(
2627 r'''(?x)
2628 (?:
2629 <meta\s+property="og:video"\s+content=|
2630 <iframe[^>]+?src=
2631 )
2632 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2633 webpage)
2634 if mobj is not None:
2635 return self.url_result(mobj.group('url'), 'SBS')
2636
2637 # Look for embedded Cinchcast player
2638 mobj = re.search(
2639 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2640 webpage)
2641 if mobj is not None:
2642 return self.url_result(mobj.group('url'), 'Cinchcast')
2643
2644 mobj = re.search(
2645 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2646 webpage)
2647 if not mobj:
2648 mobj = re.search(
2649 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2650 webpage)
2651 if mobj is not None:
2652 return self.url_result(mobj.group('url'), 'MLB')
2653
2654 mobj = re.search(
2655 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2656 webpage)
2657 if mobj is not None:
2658 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2659
2660 mobj = re.search(
2661 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2662 webpage)
2663 if mobj is not None:
2664 return self.url_result(mobj.group('url'), 'Livestream')
2665
2666 # Look for Zapiks embed
2667 mobj = re.search(
2668 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2669 if mobj is not None:
2670 return self.url_result(mobj.group('url'), 'Zapiks')
2671
2672 # Look for Kaltura embeds
2673 kaltura_url = KalturaIE._extract_url(webpage)
2674 if kaltura_url:
2675 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2676
2677 # Look for EaglePlatform embeds
2678 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2679 if eagleplatform_url:
2680 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
2681
2682 # Look for ClipYou (uses EaglePlatform) embeds
2683 mobj = re.search(
2684 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2685 if mobj is not None:
2686 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2687
2688 # Look for Pladform embeds
2689 pladform_url = PladformIE._extract_url(webpage)
2690 if pladform_url:
2691 return self.url_result(pladform_url)
2692
2693 # Look for Videomore embeds
2694 videomore_url = VideomoreIE._extract_url(webpage)
2695 if videomore_url:
2696 return self.url_result(videomore_url)
2697
2698 # Look for Webcaster embeds
2699 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2700 if webcaster_url:
2701 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2702
2703 # Look for Playwire embeds
2704 mobj = re.search(
2705 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2706 if mobj is not None:
2707 return self.url_result(mobj.group('url'))
2708
2709 # Look for 5min embeds
2710 mobj = re.search(
2711 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2712 if mobj is not None:
2713 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2714
2715 # Look for Crooks and Liars embeds
2716 mobj = re.search(
2717 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2718 if mobj is not None:
2719 return self.url_result(mobj.group('url'))
2720
2721 # Look for NBC Sports VPlayer embeds
2722 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2723 if nbc_sports_url:
2724 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2725
2726 # Look for NBC News embeds
2727 nbc_news_embed_url = re.search(
2728 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2729 if nbc_news_embed_url:
2730 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2731
2732 # Look for Google Drive embeds
2733 google_drive_url = GoogleDriveIE._extract_url(webpage)
2734 if google_drive_url:
2735 return self.url_result(google_drive_url, 'GoogleDrive')
2736
2737 # Look for UDN embeds
2738 mobj = re.search(
2739 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2740 if mobj is not None:
2741 return self.url_result(
2742 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2743
2744 # Look for Senate ISVP iframe
2745 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2746 if senate_isvp_url:
2747 return self.url_result(senate_isvp_url, 'SenateISVP')
2748
2749 # Look for OnionStudios embeds
2750 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2751 if onionstudios_url:
2752 return self.url_result(onionstudios_url)
2753
2754 # Look for ViewLift embeds
2755 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2756 if viewlift_url:
2757 return self.url_result(viewlift_url)
2758
2759 # Look for JWPlatform embeds
2760 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2761 if jwplatform_urls:
2762 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
2763
2764 # Look for Digiteka embeds
2765 digiteka_url = DigitekaIE._extract_url(webpage)
2766 if digiteka_url:
2767 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2768
2769 # Look for Arkena embeds
2770 arkena_url = ArkenaIE._extract_url(webpage)
2771 if arkena_url:
2772 return self.url_result(arkena_url, ArkenaIE.ie_key())
2773
2774 # Look for Piksel embeds
2775 piksel_url = PikselIE._extract_url(webpage)
2776 if piksel_url:
2777 return self.url_result(piksel_url, PikselIE.ie_key())
2778
2779 # Look for Limelight embeds
2780 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2781 if limelight_urls:
2782 return self.playlist_result(
2783 limelight_urls, video_id, video_title, video_description)
2784
2785 # Look for Anvato embeds
2786 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2787 if anvato_urls:
2788 return self.playlist_result(
2789 anvato_urls, video_id, video_title, video_description)
2790
2791 # Look for AdobeTVVideo embeds
2792 mobj = re.search(
2793 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2794 webpage)
2795 if mobj is not None:
2796 return self.url_result(
2797 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2798 'AdobeTVVideo')
2799
2800 # Look for Vine embeds
2801 mobj = re.search(
2802 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2803 webpage)
2804 if mobj is not None:
2805 return self.url_result(
2806 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2807
2808 # Look for VODPlatform embeds
2809 mobj = re.search(
2810 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
2811 webpage)
2812 if mobj is not None:
2813 return self.url_result(
2814 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
2815
2816 # Look for Mangomolo embeds
2817 mobj = re.search(
2818 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
2819 (?:
2820 video\?.*?\bid=(?P<video_id>\d+)|
2821 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2822 ).+?)\1''', webpage)
2823 if mobj is not None:
2824 info = {
2825 '_type': 'url_transparent',
2826 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2827 'title': video_title,
2828 'description': video_description,
2829 'thumbnail': video_thumbnail,
2830 'uploader': video_uploader,
2831 }
2832 video_id = mobj.group('video_id')
2833 if video_id:
2834 info.update({
2835 'ie_key': 'MangomoloVideo',
2836 'id': video_id,
2837 })
2838 else:
2839 info.update({
2840 'ie_key': 'MangomoloLive',
2841 'id': mobj.group('channel_id'),
2842 })
2843 return info
2844
2845 # Look for Instagram embeds
2846 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2847 if instagram_embed_url is not None:
2848 return self.url_result(
2849 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2850
2851 # Look for LiveLeak embeds
2852 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2853 if liveleak_urls:
2854 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
2855
2856 # Look for 3Q SDN embeds
2857 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2858 if threeqsdn_url:
2859 return {
2860 '_type': 'url_transparent',
2861 'ie_key': ThreeQSDNIE.ie_key(),
2862 'url': self._proto_relative_url(threeqsdn_url),
2863 'title': video_title,
2864 'description': video_description,
2865 'thumbnail': video_thumbnail,
2866 'uploader': video_uploader,
2867 }
2868
2869 # Look for VBOX7 embeds
2870 vbox7_url = Vbox7IE._extract_url(webpage)
2871 if vbox7_url:
2872 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2873
2874 # Look for DBTV embeds
2875 dbtv_urls = DBTVIE._extract_urls(webpage)
2876 if dbtv_urls:
2877 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
2878
2879 # Look for Videa embeds
2880 videa_urls = VideaIE._extract_urls(webpage)
2881 if videa_urls:
2882 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
2883
2884 # Look for 20 minuten embeds
2885 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2886 if twentymin_urls:
2887 return self.playlist_from_matches(
2888 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
2889
2890 # Look for Openload embeds
2891 openload_urls = OpenloadIE._extract_urls(webpage)
2892 if openload_urls:
2893 return self.playlist_from_matches(
2894 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
2895
2896 # Look for VideoPress embeds
2897 videopress_urls = VideoPressIE._extract_urls(webpage)
2898 if videopress_urls:
2899 return self.playlist_from_matches(
2900 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
2901
2902 # Look for Rutube embeds
2903 rutube_urls = RutubeIE._extract_urls(webpage)
2904 if rutube_urls:
2905 return self.playlist_from_matches(
2906 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
2907
2908 # Look for WashingtonPost embeds
2909 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2910 if wapo_urls:
2911 return self.playlist_from_matches(
2912 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2913
2914 # Look for Mediaset embeds
2915 mediaset_urls = MediasetIE._extract_urls(webpage)
2916 if mediaset_urls:
2917 return self.playlist_from_matches(
2918 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2919
2920 # Look for JOJ.sk embeds
2921 joj_urls = JojIE._extract_urls(webpage)
2922 if joj_urls:
2923 return self.playlist_from_matches(
2924 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2925
2926 # Look for megaphone.fm embeds
2927 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2928 if mpfn_urls:
2929 return self.playlist_from_matches(
2930 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2931
2932 # Look for vzaar embeds
2933 vzaar_urls = VzaarIE._extract_urls(webpage)
2934 if vzaar_urls:
2935 return self.playlist_from_matches(
2936 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2937
2938 channel9_urls = Channel9IE._extract_urls(webpage)
2939 if channel9_urls:
2940 return self.playlist_from_matches(
2941 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
2942
2943 vshare_urls = VShareIE._extract_urls(webpage)
2944 if vshare_urls:
2945 return self.playlist_from_matches(
2946 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
2947
2948 # Look for Mediasite embeds
2949 mediasite_urls = MediasiteIE._extract_urls(webpage)
2950 if mediasite_urls:
2951 entries = [
2952 self.url_result(smuggle_url(
2953 compat_urlparse.urljoin(url, mediasite_url),
2954 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
2955 for mediasite_url in mediasite_urls]
2956 return self.playlist_result(entries, video_id, video_title)
2957
2958 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
2959 if springboardplatform_urls:
2960 return self.playlist_from_matches(
2961 springboardplatform_urls, video_id, video_title,
2962 ie=SpringboardPlatformIE.ie_key())
2963
2964 yapfiles_urls = YapFilesIE._extract_urls(webpage)
2965 if yapfiles_urls:
2966 return self.playlist_from_matches(
2967 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
2968
2969 vice_urls = ViceIE._extract_urls(webpage)
2970 if vice_urls:
2971 return self.playlist_from_matches(
2972 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
2973
2974 def merge_dicts(dict1, dict2):
2975 merged = {}
2976 for k, v in dict1.items():
2977 if v is not None:
2978 merged[k] = v
2979 for k, v in dict2.items():
2980 if v is None:
2981 continue
2982 if (k not in merged or
2983 (isinstance(v, compat_str) and v and
2984 isinstance(merged[k], compat_str) and
2985 not merged[k])):
2986 merged[k] = v
2987 return merged
2988
2989 # Look for HTML5 media
2990 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2991 if entries:
2992 if len(entries) == 1:
2993 entries[0].update({
2994 'id': video_id,
2995 'title': video_title,
2996 })
2997 else:
2998 for num, entry in enumerate(entries, start=1):
2999 entry.update({
3000 'id': '%s-%s' % (video_id, num),
3001 'title': '%s (%d)' % (video_title, num),
3002 })
3003 for entry in entries:
3004 self._sort_formats(entry['formats'])
3005 return self.playlist_result(entries, video_id, video_title)
3006
3007 jwplayer_data = self._find_jwplayer_data(
3008 webpage, video_id, transform_source=js_to_json)
3009 if jwplayer_data:
3010 info = self._parse_jwplayer_data(
3011 jwplayer_data, video_id, require_title=False, base_url=url)
3012 return merge_dicts(info, info_dict)
3013
3014 # Video.js embed
3015 mobj = re.search(
3016 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
3017 webpage)
3018 if mobj is not None:
3019 sources = self._parse_json(
3020 mobj.group(1), video_id, transform_source=js_to_json,
3021 fatal=False) or []
3022 if not isinstance(sources, list):
3023 sources = [sources]
3024 formats = []
3025 for source in sources:
3026 src = source.get('src')
3027 if not src or not isinstance(src, compat_str):
3028 continue
3029 src = compat_urlparse.urljoin(url, src)
3030 src_type = source.get('type')
3031 if isinstance(src_type, compat_str):
3032 src_type = src_type.lower()
3033 ext = determine_ext(src).lower()
3034 if src_type == 'video/youtube':
3035 return self.url_result(src, YoutubeIE.ie_key())
3036 if src_type == 'application/dash+xml' or ext == 'mpd':
3037 formats.extend(self._extract_mpd_formats(
3038 src, video_id, mpd_id='dash', fatal=False))
3039 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3040 formats.extend(self._extract_m3u8_formats(
3041 src, video_id, 'mp4', entry_protocol='m3u8_native',
3042 m3u8_id='hls', fatal=False))
3043 else:
3044 formats.append({
3045 'url': src,
3046 'ext': (mimetype2ext(src_type) or
3047 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3048 })
3049 if formats:
3050 self._sort_formats(formats)
3051 info_dict['formats'] = formats
3052 return info_dict
3053
3054 # Looking for http://schema.org/VideoObject
3055 json_ld = self._search_json_ld(
3056 webpage, video_id, default={}, expected_type='VideoObject')
3057 if json_ld.get('url'):
3058 return merge_dicts(json_ld, info_dict)
3059
3060 def check_video(vurl):
3061 if YoutubeIE.suitable(vurl):
3062 return True
3063 if RtmpIE.suitable(vurl):
3064 return True
3065 vpath = compat_urlparse.urlparse(vurl).path
3066 vext = determine_ext(vpath)
3067 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
3068
3069 def filter_video(urls):
3070 return list(filter(check_video, urls))
3071
3072 # Start with something easy: JW Player in SWFObject
3073 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
3074 if not found:
3075 # Look for gorilla-vid style embedding
3076 found = filter_video(re.findall(r'''(?sx)
3077 (?:
3078 jw_plugins|
3079 JWPlayerOptions|
3080 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3081 )
3082 .*?
3083 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
3084 if not found:
3085 # Broaden the search a little bit
3086 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
3087 if not found:
3088 # Broaden the findall a little bit: JWPlayer JS loader
3089 found = filter_video(re.findall(
3090 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
3091 if not found:
3092 # Flow player
3093 found = filter_video(re.findall(r'''(?xs)
3094 flowplayer\("[^"]+",\s*
3095 \{[^}]+?\}\s*,
3096 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
3097 ["']?url["']?\s*:\s*["']([^"']+)["']
3098 ''', webpage))
3099 if not found:
3100 # Cinerama player
3101 found = re.findall(
3102 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
3103 if not found:
3104 # Try to find twitter cards info
3105 # twitter:player:stream should be checked before twitter:player since
3106 # it is expected to contain a raw stream (see
3107 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3108 found = filter_video(re.findall(
3109 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
3110 if not found:
3111 # We look for Open Graph info:
3112 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
3113 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
3114 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3115 if m_video_type is not None:
3116 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
3117 if not found:
3118 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
3119 found = re.search(
3120 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
3121 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
3122 webpage)
3123 if not found:
3124 # Look also in Refresh HTTP header
3125 refresh_header = head_response.headers.get('Refresh')
3126 if refresh_header:
3127 # In python 2 response HTTP headers are bytestrings
3128 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3129 refresh_header = refresh_header.decode('iso-8859-1')
3130 found = re.search(REDIRECT_REGEX, refresh_header)
3131 if found:
3132 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
3133 if new_url != url:
3134 self.report_following_redirect(new_url)
3135 return {
3136 '_type': 'url',
3137 'url': new_url,
3138 }
3139 else:
3140 found = None
3141
3142 if not found:
3143 # twitter:player is a https URL to iframe player that may or may not
3144 # be supported by youtube-dl thus this is checked the very last (see
3145 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3146 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
3147 if embed_url and embed_url != url:
3148 return self.url_result(embed_url)
3149
3150 if not found:
3151 raise UnsupportedError(url)
3152
3153 entries = []
3154 for video_url in orderedSet(found):
3155 video_url = unescapeHTML(video_url)
3156 video_url = video_url.replace('\\/', '/')
3157 video_url = compat_urlparse.urljoin(url, video_url)
3158 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
3159
3160 # Sometimes, jwplayer extraction will result in a YouTube URL
3161 if YoutubeIE.suitable(video_url):
3162 entries.append(self.url_result(video_url, 'Youtube'))
3163 continue
3164
3165 # here's a fun little line of code for you:
3166 video_id = os.path.splitext(video_id)[0]
3167
3168 entry_info_dict = {
3169 'id': video_id,
3170 'uploader': video_uploader,
3171 'title': video_title,
3172 'age_limit': age_limit,
3173 }
3174
3175 if RtmpIE.suitable(video_url):
3176 entry_info_dict.update({
3177 '_type': 'url_transparent',
3178 'ie_key': RtmpIE.ie_key(),
3179 'url': video_url,
3180 })
3181 entries.append(entry_info_dict)
3182 continue
3183
3184 ext = determine_ext(video_url)
3185 if ext == 'smil':
3186 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
3187 elif ext == 'xspf':
3188 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
3189 elif ext == 'm3u8':
3190 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
3191 elif ext == 'mpd':
3192 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3193 elif ext == 'f4m':
3194 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
3195 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
3196 # Just matching .ism/manifest is not enough to be reliably sure
3197 # whether it's actually an ISM manifest or some other streaming
3198 # manifest since there are various streaming URL formats
3199 # possible (see [1]) as well as some other shenanigans like
3200 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3201 # so on.
3202 # Thus the most reasonable way to solve this is to delegate
3203 # to generic extractor in order to look into the contents of
3204 # the manifest itself.
3205 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3206 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3207 entry_info_dict = self.url_result(
3208 smuggle_url(video_url, {'to_generic': True}),
3209 GenericIE.ie_key())
3210 else:
3211 entry_info_dict['url'] = video_url
3212
3213 if entry_info_dict.get('formats'):
3214 self._sort_formats(entry_info_dict['formats'])
3215
3216 entries.append(entry_info_dict)
3217
3218 if len(entries) == 1:
3219 return entries[0]
3220 else:
3221 for num, e in enumerate(entries, start=1):
3222 # 'url' results don't have a title
3223 if e.get('title') is not None:
3224 e['title'] = '%s (%d)' % (e['title'], num)
3225 return {
3226 '_type': 'playlist',
3227 'entries': entries,
3228 }