]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/generic.py
Rapsys Git / youtubedl / blob
? search:
summary | shortlog | log | commit | commitdiff | tree
history | raw | HEAD
Update changelog.
[youtubedl] / youtube_dl / extractor / generic.py
1 # encoding: 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_urllib_parse_unquote,
14 compat_urlparse,
15 compat_xml_parse_error,
16 )
17 from ..utils import (
18 determine_ext,
19 ExtractorError,
20 float_or_none,
21 HEADRequest,
22 is_html,
23 orderedSet,
24 sanitized_Request,
25 smuggle_url,
26 unescapeHTML,
27 unified_strdate,
28 unsmuggle_url,
29 UnsupportedError,
30 url_basename,
31 xpath_text,
32 )
33 from .brightcove import (
34 BrightcoveLegacyIE,
35 BrightcoveNewIE,
36 )
37 from .nbc import NBCSportsVPlayerIE
38 from .ooyala import OoyalaIE
39 from .rutv import RUTVIE
40 from .tvc import TVCIE
41 from .sportbox import SportBoxEmbedIE
42 from .smotri import SmotriIE
43 from .myvi import MyviIE
44 from .condenast import CondeNastIE
45 from .udn import UDNEmbedIE
46 from .senateisvp import SenateISVPIE
47 from .svt import SVTIE
48 from .pornhub import PornHubIE
49 from .xhamster import XHamsterEmbedIE
50 from .tnaflix import TNAFlixNetworkEmbedIE
51 from .vimeo import VimeoIE
52 from .dailymotion import (
53 DailymotionIE,
54 DailymotionCloudIE,
55 )
56 from .onionstudios import OnionStudiosIE
57 from .viewlift import ViewLiftEmbedIE
58 from .screenwavemedia import ScreenwaveMediaIE
59 from .mtv import MTVServicesEmbeddedIE
60 from .pladform import PladformIE
61 from .videomore import VideomoreIE
62 from .googledrive import GoogleDriveIE
63 from .jwplatform import JWPlatformIE
64 from .digiteka import DigitekaIE
65 from .arkena import ArkenaIE
66 from .instagram import InstagramIE
67 from .liveleak import LiveLeakIE
68 from .threeqsdn import ThreeQSDNIE
69 from .theplatform import ThePlatformIE
70 from .vessel import VesselIE
71 from .kaltura import KalturaIE
72 from .eagleplatform import EaglePlatformIE
73 from .facebook import FacebookIE
74 from .soundcloud import SoundcloudIE
75 from .vbox7 import Vbox7IE
76
77
78 class GenericIE(InfoExtractor):
79 IE_DESC = 'Generic downloader that works on some sites'
80 _VALID_URL = r'.*'
81 IE_NAME = 'generic'
82 _TESTS = [
83 # Direct link to a video
84 {
85 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
86 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
87 'info_dict': {
88 'id': 'trailer',
89 'ext': 'mp4',
90 'title': 'trailer',
91 'upload_date': '20100513',
92 }
93 },
94 # Direct link to media delivered compressed (until Accept-Encoding is *)
95 {
96 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
97 'md5': '128c42e68b13950268b648275386fc74',
98 'info_dict': {
99 'id': 'FictionJunction-Parallel_Hearts',
100 'ext': 'flac',
101 'title': 'FictionJunction-Parallel_Hearts',
102 'upload_date': '20140522',
103 },
104 'expected_warnings': [
105 'URL could be a direct video link, returning it as such.'
106 ]
107 },
108 # Direct download with broken HEAD
109 {
110 'url': 'http://ai-radio.org:8000/radio.opus',
111 'info_dict': {
112 'id': 'radio',
113 'ext': 'opus',
114 'title': 'radio',
115 },
116 'params': {
117 'skip_download': True, # infinite live stream
118 },
119 'expected_warnings': [
120 r'501.*Not Implemented',
121 r'400.*Bad Request',
122 ],
123 },
124 # Direct link with incorrect MIME type
125 {
126 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
127 'md5': '4ccbebe5f36706d85221f204d7eb5913',
128 'info_dict': {
129 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
130 'id': '5_Lennart_Poettering_-_Systemd',
131 'ext': 'webm',
132 'title': '5_Lennart_Poettering_-_Systemd',
133 'upload_date': '20141120',
134 },
135 'expected_warnings': [
136 'URL could be a direct video link, returning it as such.'
137 ]
138 },
139 # RSS feed
140 {
141 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
142 'info_dict': {
143 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
144 'title': 'Zero Punctuation',
145 'description': 're:.*groundbreaking video review series.*'
146 },
147 'playlist_mincount': 11,
148 },
149 # RSS feed with enclosure
150 {
151 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
152 'info_dict': {
153 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
154 'ext': 'm4v',
155 'upload_date': '20150228',
156 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
157 }
158 },
159 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
160 {
161 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
162 'info_dict': {
163 'id': 'smil',
164 'ext': 'mp4',
165 'title': 'Automatics, robotics and biocybernetics',
166 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
167 'upload_date': '20130627',
168 'formats': 'mincount:16',
169 'subtitles': 'mincount:1',
170 },
171 'params': {
172 'force_generic_extractor': True,
173 'skip_download': True,
174 },
175 },
176 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
177 {
178 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
179 'info_dict': {
180 'id': 'hds',
181 'ext': 'flv',
182 'title': 'hds',
183 'formats': 'mincount:1',
184 },
185 'params': {
186 'skip_download': True,
187 },
188 },
189 # SMIL from https://www.restudy.dk/video/play/id/1637
190 {
191 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
192 'info_dict': {
193 'id': 'video_1637',
194 'ext': 'flv',
195 'title': 'video_1637',
196 'formats': 'mincount:3',
197 },
198 'params': {
199 'skip_download': True,
200 },
201 },
202 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
203 {
204 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
205 'info_dict': {
206 'id': 'smil-service',
207 'ext': 'flv',
208 'title': 'smil-service',
209 'formats': 'mincount:1',
210 },
211 'params': {
212 'skip_download': True,
213 },
214 },
215 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
216 {
217 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
218 'info_dict': {
219 'id': '4719370',
220 'ext': 'mp4',
221 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
222 'formats': 'mincount:3',
223 },
224 'params': {
225 'skip_download': True,
226 },
227 },
228 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
229 {
230 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
231 'info_dict': {
232 'id': 'mZlp2ctYIUEB',
233 'ext': 'mp4',
234 'title': 'Tikibad ontruimd wegens brand',
235 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
236 'thumbnail': 're:^https?://.*\.jpg$',
237 'duration': 33,
238 },
239 'params': {
240 'skip_download': True,
241 },
242 },
243 # MPD from http://dash-mse-test.appspot.com/media.html
244 {
245 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
246 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
247 'info_dict': {
248 'id': 'car-20120827-manifest',
249 'ext': 'mp4',
250 'title': 'car-20120827-manifest',
251 'formats': 'mincount:9',
252 'upload_date': '20130904',
253 },
254 'params': {
255 'format': 'bestvideo',
256 },
257 },
258 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
259 {
260 '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',
261 'info_dict': {
262 'id': 'content',
263 'ext': 'mp4',
264 'title': 'content',
265 'formats': 'mincount:8',
266 },
267 'params': {
268 # m3u8 downloads
269 'skip_download': True,
270 }
271 },
272 # m3u8 served with Content-Type: text/plain
273 {
274 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
275 'info_dict': {
276 'id': 'index',
277 'ext': 'mp4',
278 'title': 'index',
279 'upload_date': '20140720',
280 'formats': 'mincount:11',
281 },
282 'params': {
283 # m3u8 downloads
284 'skip_download': True,
285 }
286 },
287 # google redirect
288 {
289 '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',
290 'info_dict': {
291 'id': 'cmQHVoWB5FY',
292 'ext': 'mp4',
293 'upload_date': '20130224',
294 'uploader_id': 'TheVerge',
295 'description': 're:^Chris Ziegler takes a look at the\.*',
296 'uploader': 'The Verge',
297 'title': 'First Firefox OS phones side-by-side',
298 },
299 'params': {
300 'skip_download': False,
301 }
302 },
303 {
304 # redirect in Refresh HTTP header
305 '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',
306 'info_dict': {
307 'id': 'pO8h3EaFRdo',
308 'ext': 'mp4',
309 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
310 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
311 'upload_date': '20150917',
312 'uploader_id': 'brtvofficial',
313 'uploader': 'Boiler Room',
314 },
315 'params': {
316 'skip_download': False,
317 },
318 },
319 {
320 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
321 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
322 'info_dict': {
323 'id': '13601338388002',
324 'ext': 'mp4',
325 'uploader': 'www.hodiho.fr',
326 'title': 'R\u00e9gis plante sa Jeep',
327 }
328 },
329 # bandcamp page with custom domain
330 {
331 'add_ie': ['Bandcamp'],
332 'url': 'http://bronyrock.com/track/the-pony-mash',
333 'info_dict': {
334 'id': '3235767654',
335 'ext': 'mp3',
336 'title': 'The Pony Mash',
337 'uploader': 'M_Pallante',
338 },
339 'skip': 'There is a limit of 200 free downloads / month for the test song',
340 },
341 # embedded brightcove video
342 # it also tests brightcove videos that need to set the 'Referer' in the
343 # http requests
344 {
345 'add_ie': ['BrightcoveLegacy'],
346 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
347 'info_dict': {
348 'id': '2765128793001',
349 'ext': 'mp4',
350 'title': 'Le cours de bourse : lā€™analyse technique',
351 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
352 'uploader': 'BFM BUSINESS',
353 },
354 'params': {
355 'skip_download': True,
356 },
357 },
358 {
359 # https://github.com/rg3/youtube-dl/issues/2253
360 'url': 'http://bcove.me/i6nfkrc3',
361 'md5': '0ba9446db037002366bab3b3eb30c88c',
362 'info_dict': {
363 'id': '3101154703001',
364 'ext': 'mp4',
365 'title': 'Still no power',
366 'uploader': 'thestar.com',
367 '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.',
368 },
369 'add_ie': ['BrightcoveLegacy'],
370 },
371 {
372 'url': 'http://www.championat.com/video/football/v/87/87499.html',
373 'md5': 'fb973ecf6e4a78a67453647444222983',
374 'info_dict': {
375 'id': '3414141473001',
376 'ext': 'mp4',
377 'title': 'Š’ŠøŠ“ŠµŠ¾. Š£Š“Š°Š»ŠµŠ½ŠøŠµ Š”Š·Š°Š³Š¾ŠµŠ²Š° (Š¦Š”ŠšŠ)',
378 'description': 'ŠžŠ½Š»Š°Š¹Š½-трŠ°Š½ŃŠ»ŃŃ†Šøя Š¼Š°Ń‚чŠ° Š¦Š”ŠšŠ - "Š’Š¾Š»Š³Š°"',
379 'uploader': 'Championat',
380 },
381 },
382 {
383 # https://github.com/rg3/youtube-dl/issues/3541
384 'add_ie': ['BrightcoveLegacy'],
385 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
386 'info_dict': {
387 'id': '3866516442001',
388 'ext': 'mp4',
389 'title': 'Leer mij vrouwen kennen: Aflevering 1',
390 'description': 'Leer mij vrouwen kennen: Aflevering 1',
391 'uploader': 'SBS Broadcasting',
392 },
393 'skip': 'Restricted to Netherlands',
394 'params': {
395 'skip_download': True, # m3u8 download
396 },
397 },
398 # ooyala video
399 {
400 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
401 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
402 'info_dict': {
403 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
404 'ext': 'mp4',
405 'title': '2cc213299525360.mov', # that's what we get
406 'duration': 238.231,
407 },
408 'add_ie': ['Ooyala'],
409 },
410 {
411 # ooyala video embedded with http://player.ooyala.com/iframe.js
412 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
413 'info_dict': {
414 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
415 'ext': 'mp4',
416 'title': '"Steve Jobs: Man in the Machine" trailer',
417 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
418 'duration': 135.427,
419 },
420 'params': {
421 'skip_download': True,
422 },
423 },
424 # embed.ly video
425 {
426 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
427 'info_dict': {
428 'id': '9ODmcdjQcHQ',
429 'ext': 'mp4',
430 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
431 'upload_date': '20140225',
432 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
433 'uploader': 'Tested',
434 'uploader_id': 'testedcom',
435 },
436 # No need to test YoutubeIE here
437 'params': {
438 'skip_download': True,
439 },
440 },
441 # funnyordie embed
442 {
443 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
444 'info_dict': {
445 'id': '18e820ec3f',
446 'ext': 'mp4',
447 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
448 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
449 },
450 },
451 # RUTV embed
452 {
453 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
454 'info_dict': {
455 'id': '776940',
456 'ext': 'mp4',
457 'title': 'ŠžŃ…Š¾Ń‚сŠŗŠ¾Šµ Š¼Š¾Ń€Šµ стŠ°Š»Š¾ цŠµŠ»ŠøŠŗŠ¾Š¼ рŠ¾ŃŃŠøŠ¹ŃŠŗŠøŠ¼',
458 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
459 },
460 'params': {
461 # m3u8 download
462 'skip_download': True,
463 },
464 },
465 # TVC embed
466 {
467 '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/',
468 'info_dict': {
469 'id': '55304',
470 'ext': 'mp4',
471 'title': 'Š”Š¾ŃˆŠŗŠ¾Š»ŃŒŠ½Š¾Šµ Š²Š¾ŃŠæŠøтŠ°Š½ŠøŠµ',
472 },
473 },
474 # SportBox embed
475 {
476 'url': 'http://www.vestifinance.ru/articles/25753',
477 'info_dict': {
478 'id': '25753',
479 '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"',
480 },
481 'playlist': [{
482 'info_dict': {
483 'id': '370908',
484 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 3',
485 'ext': 'mp4',
486 }
487 }, {
488 'info_dict': {
489 'id': '370905',
490 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 2',
491 'ext': 'mp4',
492 }
493 }, {
494 'info_dict': {
495 'id': '370902',
496 'title': 'Š“Š¾ŃŠ·Š°ŠŗŠ°Š·. Š”ŠµŠ½ŃŒ 1',
497 'ext': 'mp4',
498 }
499 }],
500 'params': {
501 # m3u8 download
502 'skip_download': True,
503 },
504 },
505 # Myvi.ru embed
506 {
507 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
508 'info_dict': {
509 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
510 'ext': 'mp4',
511 'title': 'Š£Š¶Š°ŃŃ‚ŠøŠŗŠø, руссŠŗŠøŠ¹ трŠµŠ¹Š»ŠµŃ€ (2015)',
512 'thumbnail': 're:^https?://.*\.jpg$',
513 'duration': 153,
514 }
515 },
516 # XHamster embed
517 {
518 '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',
519 'info_dict': {
520 'id': 'showthread',
521 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
522 },
523 'playlist_mincount': 7,
524 },
525 # Embedded TED video
526 {
527 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
528 'md5': '65fdff94098e4a607385a60c5177c638',
529 'info_dict': {
530 'id': '1969',
531 'ext': 'mp4',
532 'title': 'Hidden miracles of the natural world',
533 'uploader': 'Louie Schwartzberg',
534 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
535 }
536 },
537 # Embedded Ustream video
538 {
539 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
540 'md5': '27b99cdb639c9b12a79bca876a073417',
541 'info_dict': {
542 'id': '45734260',
543 'ext': 'flv',
544 'uploader': 'AU SPA: The NSA and Privacy',
545 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
546 }
547 },
548 # nowvideo embed hidden behind percent encoding
549 {
550 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
551 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
552 'info_dict': {
553 'id': '06e53103ca9aa',
554 'ext': 'flv',
555 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
556 'description': 'No description',
557 },
558 },
559 # arte embed
560 {
561 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
562 'md5': '7653032cbb25bf6c80d80f217055fa43',
563 'info_dict': {
564 'id': '048195-004_PLUS7-F',
565 'ext': 'flv',
566 'title': 'X:enius',
567 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
568 'upload_date': '20140320',
569 },
570 'params': {
571 'skip_download': 'Requires rtmpdump'
572 }
573 },
574 # francetv embed
575 {
576 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
577 'info_dict': {
578 'id': 'EV_30231',
579 'ext': 'mp4',
580 'title': 'Alcaline, le concert avec Calogero',
581 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
582 'upload_date': '20150226',
583 'timestamp': 1424989860,
584 'duration': 5400,
585 },
586 'params': {
587 # m3u8 downloads
588 'skip_download': True,
589 },
590 'expected_warnings': [
591 'Forbidden'
592 ]
593 },
594 # CondƩ Nast embed
595 {
596 'url': 'http://www.wired.com/2014/04/honda-asimo/',
597 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
598 'info_dict': {
599 'id': '53501be369702d3275860000',
600 'ext': 'mp4',
601 'title': 'Hondaā€™s New Asimo Robot Is More Human Than Ever',
602 }
603 },
604 # Dailymotion embed
605 {
606 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
607 'md5': '441aeeb82eb72c422c7f14ec533999cd',
608 'info_dict': {
609 'id': 'k2mm4bCdJ6CQ2i7c8o2',
610 'ext': 'mp4',
611 'title': 'Le Zap de Spi0n nĀ°216 - Zapping du Web',
612 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
613 'uploader': 'Spi0n',
614 'uploader_id': 'xgditw',
615 'upload_date': '20140425',
616 'timestamp': 1398441542,
617 },
618 'add_ie': ['Dailymotion'],
619 },
620 # YouTube embed
621 {
622 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
623 'info_dict': {
624 'id': 'FXRb4ykk4S0',
625 'ext': 'mp4',
626 'title': 'The NBL Auction 2014',
627 'uploader': 'BADMINTON England',
628 'uploader_id': 'BADMINTONEvents',
629 'upload_date': '20140603',
630 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
631 },
632 'add_ie': ['Youtube'],
633 'params': {
634 'skip_download': True,
635 }
636 },
637 # MTVSercices embed
638 {
639 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
640 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
641 'info_dict': {
642 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
643 'ext': 'mp4',
644 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
645 'description': 'Two valets share their love for movie star Liam Neesons.',
646 'timestamp': 1349922600,
647 'upload_date': '20121011',
648 },
649 },
650 # YouTube embed via <data-embed-url="">
651 {
652 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
653 'info_dict': {
654 'id': '4vAffPZIT44',
655 'ext': 'mp4',
656 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
657 'uploader': 'Gameloft',
658 'uploader_id': 'gameloft',
659 'upload_date': '20140828',
660 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
661 },
662 'params': {
663 'skip_download': True,
664 }
665 },
666 # Camtasia studio
667 {
668 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
669 'playlist': [{
670 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
671 'info_dict': {
672 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
673 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
674 'ext': 'flv',
675 'duration': 2235.90,
676 }
677 }, {
678 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
679 'info_dict': {
680 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
681 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
682 'ext': 'flv',
683 'duration': 2235.93,
684 }
685 }],
686 'info_dict': {
687 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
688 }
689 },
690 # Flowplayer
691 {
692 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
693 'md5': '9d65602bf31c6e20014319c7d07fba27',
694 'info_dict': {
695 'id': '5123ea6d5e5a7',
696 'ext': 'mp4',
697 'age_limit': 18,
698 'uploader': 'www.handjobhub.com',
699 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
700 }
701 },
702 # Multiple brightcove videos
703 # https://github.com/rg3/youtube-dl/issues/2283
704 {
705 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
706 'info_dict': {
707 'id': 'always-never',
708 'title': 'Always / Never - The New Yorker',
709 },
710 'playlist_count': 3,
711 'params': {
712 'extract_flat': False,
713 'skip_download': True,
714 }
715 },
716 # MLB embed
717 {
718 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
719 'md5': '96f09a37e44da40dd083e12d9a683327',
720 'info_dict': {
721 'id': '33322633',
722 'ext': 'mp4',
723 'title': 'Ump changes call to ball',
724 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
725 'duration': 48,
726 'timestamp': 1401537900,
727 'upload_date': '20140531',
728 'thumbnail': 're:^https?://.*\.jpg$',
729 },
730 },
731 # Wistia embed
732 {
733 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
734 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
735 'info_dict': {
736 'id': '6e2wtrbdaf',
737 'ext': 'mov',
738 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
739 'description': 'a Paywall Videos video from Remilon',
740 'duration': 644.072,
741 'uploader': 'study.com',
742 'timestamp': 1459678540,
743 'upload_date': '20160403',
744 'filesize': 24687186,
745 },
746 },
747 {
748 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
749 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
750 'info_dict': {
751 'id': 'uxjb0lwrcz',
752 'ext': 'mp4',
753 'title': 'Conversation about Hexagonal Rails Part 1',
754 'description': 'a Martin Fowler video from ThoughtWorks',
755 'duration': 1715.0,
756 'uploader': 'thoughtworks.wistia.com',
757 'timestamp': 1401832161,
758 'upload_date': '20140603',
759 },
760 },
761 # Wistia standard embed (async)
762 {
763 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
764 'info_dict': {
765 'id': '807fafadvk',
766 'ext': 'mp4',
767 'title': 'Drip Brennan Dunn Workshop',
768 'description': 'a JV Webinars video from getdrip-1',
769 'duration': 4986.95,
770 'timestamp': 1463607249,
771 'upload_date': '20160518',
772 },
773 'params': {
774 'skip_download': True,
775 }
776 },
777 # Soundcloud embed
778 {
779 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
780 'info_dict': {
781 'id': '174391317',
782 'ext': 'mp3',
783 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
784 'uploader': 'Sophos Security',
785 'title': 'Chet Chat 171 - Oct 29, 2014',
786 'upload_date': '20141029',
787 }
788 },
789 # Soundcloud multiple embeds
790 {
791 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
792 'info_dict': {
793 'id': '52809',
794 'title': 'Guitar Essentials: Legato Workoutā€”One-Hour to Fluid Performance | TAB + AUDIO',
795 },
796 'playlist_mincount': 7,
797 },
798 # Livestream embed
799 {
800 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
801 'info_dict': {
802 'id': '67864563',
803 'ext': 'flv',
804 'upload_date': '20141112',
805 'title': 'Rosetta #CometLanding webcast HL 10',
806 }
807 },
808 # Another Livestream embed, without 'new.' in URL
809 {
810 'url': 'https://www.freespeech.org/',
811 'info_dict': {
812 'id': '123537347',
813 'ext': 'mp4',
814 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
815 },
816 'params': {
817 # Live stream
818 'skip_download': True,
819 },
820 },
821 # LazyYT
822 {
823 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
824 'info_dict': {
825 'id': '1986',
826 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
827 },
828 'playlist_mincount': 2,
829 },
830 # Cinchcast embed
831 {
832 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
833 'info_dict': {
834 'id': '7141703',
835 'ext': 'mp3',
836 'upload_date': '20141126',
837 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
838 }
839 },
840 # Cinerama player
841 {
842 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
843 'info_dict': {
844 'id': '730m_DandD_1901_512k',
845 'ext': 'mp4',
846 'uploader': 'www.abc.net.au',
847 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
848 }
849 },
850 # embedded viddler video
851 {
852 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
853 'info_dict': {
854 'id': '4d03aad9',
855 'ext': 'mp4',
856 'uploader': 'deadspin',
857 'title': 'WALL-TO-GORTAT',
858 'timestamp': 1422285291,
859 'upload_date': '20150126',
860 },
861 'add_ie': ['Viddler'],
862 },
863 # Libsyn embed
864 {
865 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
866 'info_dict': {
867 'id': '3377616',
868 'ext': 'mp3',
869 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
870 'description': 'md5:601cb790edd05908957dae8aaa866465',
871 'upload_date': '20150220',
872 },
873 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
874 },
875 # jwplayer YouTube
876 {
877 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
878 'info_dict': {
879 'id': 'Mrj4DVp2zeA',
880 'ext': 'mp4',
881 'upload_date': '20150212',
882 'uploader': 'The National Archives UK',
883 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
884 'uploader_id': 'NationalArchives08',
885 'title': 'Webinar: Using Discovery, The National Archivesā€™ online catalogue',
886 },
887 },
888 # rtl.nl embed
889 {
890 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
891 'playlist_mincount': 5,
892 'info_dict': {
893 'id': 'aanslagen-kopenhagen',
894 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
895 }
896 },
897 # Zapiks embed
898 {
899 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
900 'info_dict': {
901 'id': '118046',
902 'ext': 'mp4',
903 'title': 'EP3S5 - Bon AppƩtit - Baqueira Mi Corazon !',
904 }
905 },
906 # Kaltura embed (different embed code)
907 {
908 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
909 'info_dict': {
910 'id': '1_a52wc67y',
911 'ext': 'flv',
912 'upload_date': '20150127',
913 'uploader_id': 'PremierMedia',
914 'timestamp': int,
915 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
916 },
917 },
918 # Kaltura embed protected with referrer
919 {
920 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
921 'info_dict': {
922 'id': '1_g4fbemnq',
923 'ext': 'mp4',
924 'title': 'Violetta - Achter De Schermen - Ruggero',
925 'description': 'Achter de schermen met Ruggero',
926 'timestamp': 1435133761,
927 'upload_date': '20150624',
928 'uploader_id': 'echojecka',
929 },
930 },
931 # Kaltura embed with single quotes
932 {
933 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
934 'info_dict': {
935 'id': '0_izeg5utt',
936 'ext': 'mp4',
937 'title': '35871',
938 'timestamp': 1355743100,
939 'upload_date': '20121217',
940 'uploader_id': 'batchUser',
941 },
942 'add_ie': ['Kaltura'],
943 },
944 {
945 # Kaltura embedded via quoted entry_id
946 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
947 'info_dict': {
948 'id': '0_utuok90b',
949 'ext': 'mp4',
950 'title': '06_matthew_brender_raj_dutt',
951 'timestamp': 1466638791,
952 'upload_date': '20160622',
953 },
954 'add_ie': ['Kaltura'],
955 'expected_warnings': [
956 'Could not send HEAD request'
957 ],
958 'params': {
959 'skip_download': True,
960 }
961 },
962 # Eagle.Platform embed (generic URL)
963 {
964 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
965 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
966 'info_dict': {
967 'id': '227304',
968 'ext': 'mp4',
969 'title': 'ŠŠ°Š²Š°Š»ŃŒŠ½Ń‹Š¹ Š²Ń‹ŃˆŠµŠ» Š½Š° сŠ²Š¾Š±Š¾Š“у',
970 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
971 'thumbnail': 're:^https?://.*\.jpg$',
972 'duration': 87,
973 'view_count': int,
974 'age_limit': 0,
975 },
976 },
977 # ClipYou (Eagle.Platform) embed (custom URL)
978 {
979 'url': 'http://muz-tv.ru/play/7129/',
980 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
981 'info_dict': {
982 'id': '12820',
983 'ext': 'mp4',
984 'title': "'O Sole Mio",
985 'thumbnail': 're:^https?://.*\.jpg$',
986 'duration': 216,
987 'view_count': int,
988 },
989 },
990 # Pladform embed
991 {
992 'url': 'http://muz-tv.ru/kinozal/view/7400/',
993 'info_dict': {
994 'id': '100183293',
995 'ext': 'mp4',
996 'title': 'Š¢Š°Š¹Š½Ń‹ ŠæŠµŃ€ŠµŠ²Š°Š»Š° Š”ŃŃ‚Š»Š¾Š²Š° ā€¢ 1 сŠµŃ€Šøя 2 чŠ°ŃŃ‚ŃŒ',
997 '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°',
998 'thumbnail': 're:^https?://.*\.jpg$',
999 'duration': 694,
1000 'age_limit': 0,
1001 },
1002 },
1003 # Playwire embed
1004 {
1005 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1006 'info_dict': {
1007 'id': '3519514',
1008 'ext': 'mp4',
1009 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
1010 'thumbnail': 're:^https?://.*\.png$',
1011 'duration': 45.115,
1012 },
1013 },
1014 # 5min embed
1015 {
1016 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1017 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1018 'info_dict': {
1019 'id': '518726732',
1020 'ext': 'mp4',
1021 'title': 'Facebook Creates "On This Day" | Crunch Report',
1022 },
1023 },
1024 # SVT embed
1025 {
1026 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1027 'info_dict': {
1028 'id': '2900353',
1029 'ext': 'flv',
1030 'title': 'HƤr trycker Jagr till Giroux (under SVT-intervjun)',
1031 'duration': 27,
1032 'age_limit': 0,
1033 },
1034 },
1035 # Crooks and Liars embed
1036 {
1037 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1038 'info_dict': {
1039 'id': '8RUoRhRi',
1040 'ext': 'mp4',
1041 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1042 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1043 'timestamp': 1428207000,
1044 'upload_date': '20150405',
1045 'uploader': 'Heather',
1046 },
1047 },
1048 # Crooks and Liars external embed
1049 {
1050 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1051 'info_dict': {
1052 'id': 'MTE3MjUtMzQ2MzA',
1053 'ext': 'mp4',
1054 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1055 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1056 'timestamp': 1265032391,
1057 'upload_date': '20100201',
1058 'uploader': 'Heather',
1059 },
1060 },
1061 # NBC Sports vplayer embed
1062 {
1063 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
1064 'info_dict': {
1065 'id': 'ln7x1qSThw4k',
1066 'ext': 'flv',
1067 'title': "PFT Live: New leader in the 'new-look' defense",
1068 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
1069 'uploader': 'NBCU-SPORTS',
1070 'upload_date': '20140107',
1071 'timestamp': 1389118457,
1072 },
1073 },
1074 # NBC News embed
1075 {
1076 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1077 'md5': '1aa589c675898ae6d37a17913cf68d66',
1078 'info_dict': {
1079 'id': '701714499682',
1080 'ext': 'mp4',
1081 'title': 'PREVIEW: On Assignment: David Letterman',
1082 '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.',
1083 },
1084 },
1085 # UDN embed
1086 {
1087 'url': 'https://video.udn.com/news/300346',
1088 'md5': 'fd2060e988c326991037b9aff9df21a6',
1089 'info_dict': {
1090 'id': '300346',
1091 'ext': 'mp4',
1092 'title': 'äø­äø€äø­ē”·åø«č®Šę€§ å…Øę ”åø«ē”ŸåŠ›ęŒŗ',
1093 'thumbnail': 're:^https?://.*\.jpg$',
1094 },
1095 'params': {
1096 # m3u8 download
1097 'skip_download': True,
1098 },
1099 },
1100 # Ooyala embed
1101 {
1102 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1103 'info_dict': {
1104 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1105 'ext': 'mp4',
1106 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
1107 'title': 'This is what separates the Excel masters from the wannabes',
1108 'duration': 191.933,
1109 },
1110 'params': {
1111 # m3u8 downloads
1112 'skip_download': True,
1113 }
1114 },
1115 # Brightcove URL in single quotes
1116 {
1117 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1118 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1119 'info_dict': {
1120 'id': '4255764656001',
1121 'ext': 'mp4',
1122 'title': 'SN Presents: Russell Martin, World Citizen',
1123 'description': 'To understand why he was the Toronto Blue Jaysā€™ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1124 'uploader': 'Rogers Sportsnet',
1125 'uploader_id': '1704050871',
1126 'upload_date': '20150525',
1127 'timestamp': 1432570283,
1128 },
1129 },
1130 # Dailymotion Cloud video
1131 {
1132 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
1133 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
1134 'info_dict': {
1135 'id': 'x2uy8t3',
1136 'ext': 'mp4',
1137 'title': 'Sauvons les abeilles ! - Le dƩbat',
1138 'description': 'md5:d9082128b1c5277987825d684939ca26',
1139 'thumbnail': 're:^https?://.*\.jpe?g$',
1140 'timestamp': 1434970506,
1141 'upload_date': '20150622',
1142 'uploader': 'Public SĆ©nat',
1143 'uploader_id': 'xa9gza',
1144 }
1145 },
1146 # OnionStudios embed
1147 {
1148 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1149 'info_dict': {
1150 'id': '2855',
1151 'ext': 'mp4',
1152 'title': 'Donā€™t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1153 'thumbnail': 're:^https?://.*\.jpe?g$',
1154 'uploader': 'ClickHole',
1155 'uploader_id': 'clickhole',
1156 }
1157 },
1158 # SnagFilms embed
1159 {
1160 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1161 'info_dict': {
1162 'id': '74849a00-85a9-11e1-9660-123139220831',
1163 'ext': 'mp4',
1164 'title': '#whilewewatch',
1165 }
1166 },
1167 # AdobeTVVideo embed
1168 {
1169 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1170 'md5': '43662b577c018ad707a63766462b1e87',
1171 'info_dict': {
1172 'id': '2456',
1173 'ext': 'mp4',
1174 'title': 'New experience with Acrobat DC',
1175 'description': 'New experience with Acrobat DC',
1176 'duration': 248.667,
1177 },
1178 },
1179 # ScreenwaveMedia embed
1180 {
1181 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1182 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1183 'info_dict': {
1184 'id': 'cinemasnob-55d26273809dd',
1185 'ext': 'mp4',
1186 'title': 'cinemasnob',
1187 },
1188 },
1189 # BrightcoveInPageEmbed embed
1190 {
1191 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1192 'info_dict': {
1193 'id': '4238694884001',
1194 'ext': 'flv',
1195 'title': 'Tabletop: Dread, Last Thoughts',
1196 'description': 'Tabletop: Dread, Last Thoughts',
1197 'duration': 51690,
1198 },
1199 },
1200 # JWPlayer with M3U8
1201 {
1202 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1203 'info_dict': {
1204 'id': 'playlist',
1205 'ext': 'mp4',
1206 'title': 'Š”Š»ŃƒŃ‡Š°Š¹Š½Ń‹Š¹ ŠæрŠ¾Ń…Š¾Š¶ŠøŠ¹ ŠæŠ¾Š¹Š¼Š°Š» Š°Š²Ń‚Š¾ŃƒŠ³Š¾Š½Ń‰ŠøŠŗŠ° Š² ŠœŃƒŃ€Š¼Š°Š½ŃŠŗŠµ. Š’Š˜Š”Š•Šž | Š Š•Š Š¢Š’',
1207 'uploader': 'ren.tv',
1208 },
1209 'params': {
1210 # m3u8 downloads
1211 'skip_download': True,
1212 }
1213 },
1214 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1215 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1216 {
1217 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1218 'info_dict': {
1219 'id': '4785848093001',
1220 'ext': 'mp4',
1221 'title': 'The Cardinal Pell Interview',
1222 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1223 'uploader': 'GlobeCast Australia - GlobeStream',
1224 'uploader_id': '2733773828001',
1225 'upload_date': '20160304',
1226 'timestamp': 1457083087,
1227 },
1228 'params': {
1229 # m3u8 downloads
1230 'skip_download': True,
1231 },
1232 },
1233 # Another form of arte.tv embed
1234 {
1235 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1236 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1237 'info_dict': {
1238 'id': '030273-562_PLUS7-F',
1239 'ext': 'mp4',
1240 'title': 'ARTE Reportage - Nulle part, en France',
1241 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1242 'upload_date': '20160409',
1243 },
1244 },
1245 # LiveLeak embed
1246 {
1247 'url': 'http://www.wykop.pl/link/3088787/',
1248 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1249 'info_dict': {
1250 'id': '874_1459135191',
1251 'ext': 'mp4',
1252 'title': 'Man shows poor quality of new apartment building',
1253 'description': 'The wall is like a sand pile.',
1254 'uploader': 'Lake8737',
1255 }
1256 },
1257 # Duplicated embedded video URLs
1258 {
1259 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1260 'info_dict': {
1261 'id': '149298443_480_16c25b74_2',
1262 'ext': 'mp4',
1263 'title': 'vs. Blue Orange Spring Game',
1264 'uploader': 'www.hudl.com',
1265 },
1266 },
1267 # twitter:player:stream embed
1268 {
1269 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1270 'info_dict': {
1271 'id': 'master',
1272 'ext': 'mp4',
1273 'title': 'Une nouvelle espĆØce de dinosaure dĆ©couverte en Argentine',
1274 'uploader': 'www.rtl.be',
1275 },
1276 'params': {
1277 # m3u8 downloads
1278 'skip_download': True,
1279 },
1280 },
1281 # twitter:player embed
1282 {
1283 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1284 'md5': 'a3e0df96369831de324f0778e126653c',
1285 'info_dict': {
1286 'id': '4909620399001',
1287 'ext': 'mp4',
1288 'title': 'What Do Black Holes Sound Like?',
1289 'description': 'what do black holes sound like',
1290 'upload_date': '20160524',
1291 'uploader_id': '29913724001',
1292 'timestamp': 1464107587,
1293 'uploader': 'TheAtlantic',
1294 },
1295 'add_ie': ['BrightcoveLegacy'],
1296 },
1297 # Facebook <iframe> embed
1298 {
1299 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
1300 'md5': 'fbcde74f534176ecb015849146dd3aee',
1301 'info_dict': {
1302 'id': '599637780109885',
1303 'ext': 'mp4',
1304 'title': 'Facebook video #599637780109885',
1305 },
1306 },
1307 # Facebook API embed
1308 {
1309 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
1310 'md5': 'a47372ee61b39a7b90287094d447d94e',
1311 'info_dict': {
1312 'id': '10153467542406923',
1313 'ext': 'mp4',
1314 'title': 'Facebook video #10153467542406923',
1315 },
1316 },
1317 # Wordpress "YouTube Video Importer" plugin
1318 {
1319 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
1320 'md5': 'd16797741b560b485194eddda8121b48',
1321 'info_dict': {
1322 'id': 'HNTXWDXV9Is',
1323 'ext': 'mp4',
1324 'title': 'Blue Devils Drumline Stanford lot 2016',
1325 'upload_date': '20160627',
1326 'uploader_id': 'GENOCIDE8GENERAL10',
1327 'uploader': 'cylus cyrus',
1328 },
1329 },
1330 {
1331 # video stored on custom kaltura server
1332 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1333 'md5': '537617d06e64dfed891fa1593c4b30cc',
1334 'info_dict': {
1335 'id': '0_1iotm5bh',
1336 'ext': 'mp4',
1337 'title': 'Elecciones britƔnicas: 5 lecciones para Rajoy',
1338 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1339 'uploader_id': 'videos.expansion@el-mundo.net',
1340 'upload_date': '20150429',
1341 'timestamp': 1430303472,
1342 },
1343 'add_ie': ['Kaltura'],
1344 },
1345 {
1346 # Non-standard Vimeo embed
1347 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1348 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1349 'info_dict': {
1350 'id': '148867247',
1351 'ext': 'mp4',
1352 'title': 'Understanding the web - Teaser',
1353 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1354 'upload_date': '20151214',
1355 'uploader': 'OpenClassrooms',
1356 'uploader_id': 'openclassrooms',
1357 },
1358 'add_ie': ['Vimeo'],
1359 },
1360 {
1361 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1362 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1363 'info_dict': {
1364 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1365 'ext': 'mp4',
1366 'title': 'Big Buck Bunny',
1367 'description': 'Royalty free test video',
1368 'timestamp': 1432816365,
1369 'upload_date': '20150528',
1370 'is_live': False,
1371 },
1372 'params': {
1373 'skip_download': True,
1374 },
1375 'add_ie': [ArkenaIE.ie_key()],
1376 },
1377 {
1378 '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/',
1379 'info_dict': {
1380 'id': '1c7141f46c',
1381 'ext': 'mp4',
1382 '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',
1383 },
1384 'params': {
1385 'skip_download': True,
1386 },
1387 'add_ie': [Vbox7IE.ie_key()],
1388 },
1389 # {
1390 # # TODO: find another test
1391 # # http://schema.org/VideoObject
1392 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1393 # 'md5': '888dcf08b7ea671381f00fab74692755',
1394 # 'info_dict': {
1395 # 'id': 'nyvTSJMKId',
1396 # 'ext': 'mp4',
1397 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1398 # 'description': '#love for cats.',
1399 # 'timestamp': 1461244995,
1400 # 'upload_date': '20160421',
1401 # },
1402 # 'params': {
1403 # 'force_generic_extractor': True,
1404 # },
1405 # }
1406 ]
1407
1408 def report_following_redirect(self, new_url):
1409 """Report information extraction."""
1410 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
1411
1412 def _extract_rss(self, url, video_id, doc):
1413 playlist_title = doc.find('./channel/title').text
1414 playlist_desc_el = doc.find('./channel/description')
1415 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1416
1417 entries = []
1418 for it in doc.findall('./channel/item'):
1419 next_url = xpath_text(it, 'link', fatal=False)
1420 if not next_url:
1421 enclosure_nodes = it.findall('./enclosure')
1422 for e in enclosure_nodes:
1423 next_url = e.attrib.get('url')
1424 if next_url:
1425 break
1426
1427 if not next_url:
1428 continue
1429
1430 entries.append({
1431 '_type': 'url',
1432 'url': next_url,
1433 'title': it.find('title').text,
1434 })
1435
1436 return {
1437 '_type': 'playlist',
1438 'id': url,
1439 'title': playlist_title,
1440 'description': playlist_desc,
1441 'entries': entries,
1442 }
1443
1444 def _extract_camtasia(self, url, video_id, webpage):
1445 """ Returns None if no camtasia video can be found. """
1446
1447 camtasia_cfg = self._search_regex(
1448 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1449 webpage, 'camtasia configuration file', default=None)
1450 if camtasia_cfg is None:
1451 return None
1452
1453 title = self._html_search_meta('DC.title', webpage, fatal=True)
1454
1455 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1456 camtasia_cfg = self._download_xml(
1457 camtasia_url, video_id,
1458 note='Downloading camtasia configuration',
1459 errnote='Failed to download camtasia configuration')
1460 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1461
1462 entries = []
1463 for n in fileset_node.getchildren():
1464 url_n = n.find('./uri')
1465 if url_n is None:
1466 continue
1467
1468 entries.append({
1469 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1470 'title': '%s - %s' % (title, n.tag),
1471 'url': compat_urlparse.urljoin(url, url_n.text),
1472 'duration': float_or_none(n.find('./duration').text),
1473 })
1474
1475 return {
1476 '_type': 'playlist',
1477 'entries': entries,
1478 'title': title,
1479 }
1480
1481 def _real_extract(self, url):
1482 if url.startswith('//'):
1483 return {
1484 '_type': 'url',
1485 'url': self.http_scheme() + url,
1486 }
1487
1488 parsed_url = compat_urlparse.urlparse(url)
1489 if not parsed_url.scheme:
1490 default_search = self._downloader.params.get('default_search')
1491 if default_search is None:
1492 default_search = 'fixup_error'
1493
1494 if default_search in ('auto', 'auto_warning', 'fixup_error'):
1495 if '/' in url:
1496 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1497 return self.url_result('http://' + url)
1498 elif default_search != 'fixup_error':
1499 if default_search == 'auto_warning':
1500 if re.match(r'^(?:url|URL)$', url):
1501 raise ExtractorError(
1502 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1503 expected=True)
1504 else:
1505 self._downloader.report_warning(
1506 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
1507 return self.url_result('ytsearch:' + url)
1508
1509 if default_search in ('error', 'fixup_error'):
1510 raise ExtractorError(
1511 '%r is not a valid URL. '
1512 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1513 % (url, url), expected=True)
1514 else:
1515 if ':' not in default_search:
1516 default_search += ':'
1517 return self.url_result(default_search + url)
1518
1519 url, smuggled_data = unsmuggle_url(url)
1520 force_videoid = None
1521 is_intentional = smuggled_data and smuggled_data.get('to_generic')
1522 if smuggled_data and 'force_videoid' in smuggled_data:
1523 force_videoid = smuggled_data['force_videoid']
1524 video_id = force_videoid
1525 else:
1526 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
1527
1528 self.to_screen('%s: Requesting header' % video_id)
1529
1530 head_req = HEADRequest(url)
1531 head_response = self._request_webpage(
1532 head_req, video_id,
1533 note=False, errnote='Could not send HEAD request to %s' % url,
1534 fatal=False)
1535
1536 if head_response is not False:
1537 # Check for redirect
1538 new_url = head_response.geturl()
1539 if url != new_url:
1540 self.report_following_redirect(new_url)
1541 if force_videoid:
1542 new_url = smuggle_url(
1543 new_url, {'force_videoid': force_videoid})
1544 return self.url_result(new_url)
1545
1546 full_response = None
1547 if head_response is False:
1548 request = sanitized_Request(url)
1549 request.add_header('Accept-Encoding', '*')
1550 full_response = self._request_webpage(request, video_id)
1551 head_response = full_response
1552
1553 info_dict = {
1554 'id': video_id,
1555 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
1556 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
1557 }
1558
1559 # Check for direct link to a video
1560 content_type = head_response.headers.get('Content-Type', '').lower()
1561 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
1562 if m:
1563 format_id = m.group('format_id')
1564 if format_id.endswith('mpegurl'):
1565 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
1566 elif format_id == 'f4m':
1567 formats = self._extract_f4m_formats(url, video_id)
1568 else:
1569 formats = [{
1570 'format_id': m.group('format_id'),
1571 'url': url,
1572 'vcodec': 'none' if m.group('type') == 'audio' else None
1573 }]
1574 info_dict['direct'] = True
1575 self._sort_formats(formats)
1576 info_dict['formats'] = formats
1577 return info_dict
1578
1579 if not self._downloader.params.get('test', False) and not is_intentional:
1580 force = self._downloader.params.get('force_generic_extractor', False)
1581 self._downloader.report_warning(
1582 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
1583
1584 if not full_response:
1585 request = sanitized_Request(url)
1586 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1587 # making it impossible to download only chunk of the file (yet we need only 512kB to
1588 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1589 # that will always result in downloading the whole file that is not desirable.
1590 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1591 # to accept raw bytes and being able to download only a chunk.
1592 # It may probably better to solve this by checking Content-Type for application/octet-stream
1593 # after HEAD request finishes, but not sure if we can rely on this.
1594 request.add_header('Accept-Encoding', '*')
1595 full_response = self._request_webpage(request, video_id)
1596
1597 first_bytes = full_response.read(512)
1598
1599 # Is it an M3U playlist?
1600 if first_bytes.startswith(b'#EXTM3U'):
1601 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
1602 self._sort_formats(info_dict['formats'])
1603 return info_dict
1604
1605 # Maybe it's a direct link to a video?
1606 # Be careful not to download the whole thing!
1607 if not is_html(first_bytes):
1608 self._downloader.report_warning(
1609 'URL could be a direct video link, returning it as such.')
1610 info_dict.update({
1611 'direct': True,
1612 'url': url,
1613 })
1614 return info_dict
1615
1616 webpage = self._webpage_read_content(
1617 full_response, url, video_id, prefix=first_bytes)
1618
1619 self.report_extraction(video_id)
1620
1621 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
1622 try:
1623 doc = compat_etree_fromstring(webpage.encode('utf-8'))
1624 if doc.tag == 'rss':
1625 return self._extract_rss(url, video_id, doc)
1626 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
1627 smil = self._parse_smil(doc, url, video_id)
1628 self._sort_formats(smil['formats'])
1629 return smil
1630 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1631 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1632 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
1633 info_dict['formats'] = self._parse_mpd_formats(
1634 doc, video_id, mpd_base_url=url.rpartition('/')[0])
1635 self._sort_formats(info_dict['formats'])
1636 return info_dict
1637 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1638 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
1639 self._sort_formats(info_dict['formats'])
1640 return info_dict
1641 except compat_xml_parse_error:
1642 pass
1643
1644 # Is it a Camtasia project?
1645 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1646 if camtasia_res is not None:
1647 return camtasia_res
1648
1649 # Sometimes embedded video player is hidden behind percent encoding
1650 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1651 # Unescaping the whole page allows to handle those cases in a generic way
1652 webpage = compat_urllib_parse_unquote(webpage)
1653
1654 # it's tempting to parse this further, but you would
1655 # have to take into account all the variations like
1656 # Video Title - Site Name
1657 # Site Name | Video Title
1658 # Video Title - Tagline | Site Name
1659 # and so on and so forth; it's just not practical
1660 video_title = self._og_search_title(
1661 webpage, default=None) or self._html_search_regex(
1662 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1663 default='video')
1664
1665 # Try to detect age limit automatically
1666 age_limit = self._rta_search(webpage)
1667 # And then there are the jokers who advertise that they use RTA,
1668 # but actually don't.
1669 AGE_LIMIT_MARKERS = [
1670 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1671 ]
1672 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1673 age_limit = 18
1674
1675 # video uploader is domain name
1676 video_uploader = self._search_regex(
1677 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
1678
1679 video_description = self._og_search_description(webpage, default=None)
1680 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1681
1682 # Helper method
1683 def _playlist_from_matches(matches, getter=None, ie=None):
1684 urlrs = orderedSet(
1685 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
1686 for m in matches)
1687 return self.playlist_result(
1688 urlrs, playlist_id=video_id, playlist_title=video_title)
1689
1690 # Look for Brightcove Legacy Studio embeds
1691 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
1692 if bc_urls:
1693 self.to_screen('Brightcove video detected.')
1694 entries = [{
1695 '_type': 'url',
1696 'url': smuggle_url(bc_url, {'Referer': url}),
1697 'ie_key': 'BrightcoveLegacy'
1698 } for bc_url in bc_urls]
1699
1700 return {
1701 '_type': 'playlist',
1702 'title': video_title,
1703 'id': video_id,
1704 'entries': entries,
1705 }
1706
1707 # Look for Brightcove New Studio embeds
1708 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1709 if bc_urls:
1710 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
1711
1712 # Look for ThePlatform embeds
1713 tp_urls = ThePlatformIE._extract_urls(webpage)
1714 if tp_urls:
1715 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1716
1717 # Look for Vessel embeds
1718 vessel_urls = VesselIE._extract_urls(webpage)
1719 if vessel_urls:
1720 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1721
1722 # Look for embedded rtl.nl player
1723 matches = re.findall(
1724 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
1725 webpage)
1726 if matches:
1727 return _playlist_from_matches(matches, ie='RtlNl')
1728
1729 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1730 if vimeo_url is not None:
1731 return self.url_result(vimeo_url)
1732
1733 vid_me_embed_url = self._search_regex(
1734 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1735 webpage, 'vid.me embed', default=None)
1736 if vid_me_embed_url is not None:
1737 return self.url_result(vid_me_embed_url, 'Vidme')
1738
1739 # Look for embedded YouTube player
1740 matches = re.findall(r'''(?x)
1741 (?:
1742 <iframe[^>]+?src=|
1743 data-video-url=|
1744 <embed[^>]+?src=|
1745 embedSWF\(?:\s*|
1746 new\s+SWFObject\(
1747 )
1748 (["\'])
1749 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1750 (?:embed|v|p)/.+?)
1751 \1''', webpage)
1752 if matches:
1753 return _playlist_from_matches(
1754 matches, lambda m: unescapeHTML(m[1]))
1755
1756 # Look for lazyYT YouTube embed
1757 matches = re.findall(
1758 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1759 if matches:
1760 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1761
1762 # Look for Wordpress "YouTube Video Importer" plugin
1763 matches = re.findall(r'''(?x)<div[^>]+
1764 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1765 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1766 if matches:
1767 return _playlist_from_matches(matches, lambda m: m[-1])
1768
1769 matches = DailymotionIE._extract_urls(webpage)
1770 if matches:
1771 return _playlist_from_matches(matches)
1772
1773 # Look for embedded Dailymotion playlist player (#3822)
1774 m = re.search(
1775 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1776 if m:
1777 playlists = re.findall(
1778 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1779 if playlists:
1780 return _playlist_from_matches(
1781 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1782
1783 # Look for embedded Wistia player
1784 match = re.search(
1785 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
1786 if match:
1787 embed_url = self._proto_relative_url(
1788 unescapeHTML(match.group('url')))
1789 return {
1790 '_type': 'url_transparent',
1791 'url': embed_url,
1792 'ie_key': 'Wistia',
1793 'uploader': video_uploader,
1794 }
1795
1796 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
1797 if match:
1798 return {
1799 '_type': 'url_transparent',
1800 'url': 'wistia:%s' % match.group('id'),
1801 'ie_key': 'Wistia',
1802 'uploader': video_uploader,
1803 }
1804
1805 match = re.search(
1806 r'''(?sx)
1807 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1808 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1809 ''', webpage)
1810 if match:
1811 return self.url_result(self._proto_relative_url(
1812 'wistia:%s' % match.group('id')), 'Wistia')
1813
1814 # Look for SVT player
1815 svt_url = SVTIE._extract_url(webpage)
1816 if svt_url:
1817 return self.url_result(svt_url, 'SVT')
1818
1819 # Look for embedded condenast player
1820 matches = re.findall(
1821 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1822 webpage)
1823 if matches:
1824 return {
1825 '_type': 'playlist',
1826 'entries': [{
1827 '_type': 'url',
1828 'ie_key': 'CondeNast',
1829 'url': ma,
1830 } for ma in matches],
1831 'title': video_title,
1832 'id': video_id,
1833 }
1834
1835 # Look for Bandcamp pages with custom domain
1836 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1837 if mobj is not None:
1838 burl = unescapeHTML(mobj.group(1))
1839 # Don't set the extractor because it can be a track url or an album
1840 return self.url_result(burl)
1841
1842 # Look for embedded Vevo player
1843 mobj = re.search(
1844 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1845 if mobj is not None:
1846 return self.url_result(mobj.group('url'))
1847
1848 # Look for embedded Viddler player
1849 mobj = re.search(
1850 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1851 webpage)
1852 if mobj is not None:
1853 return self.url_result(mobj.group('url'))
1854
1855 # Look for NYTimes player
1856 mobj = re.search(
1857 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1858 webpage)
1859 if mobj is not None:
1860 return self.url_result(mobj.group('url'))
1861
1862 # Look for Libsyn player
1863 mobj = re.search(
1864 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1865 if mobj is not None:
1866 return self.url_result(mobj.group('url'))
1867
1868 # Look for Ooyala videos
1869 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
1870 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
1871 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1872 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
1873 if mobj is not None:
1874 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
1875
1876 # Look for multiple Ooyala embeds on SBN network websites
1877 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1878 if mobj is not None:
1879 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1880 if embeds:
1881 return _playlist_from_matches(
1882 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
1883
1884 # Look for Aparat videos
1885 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
1886 if mobj is not None:
1887 return self.url_result(mobj.group(1), 'Aparat')
1888
1889 # Look for MPORA videos
1890 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
1891 if mobj is not None:
1892 return self.url_result(mobj.group(1), 'Mpora')
1893
1894 # Look for embedded NovaMov-based player
1895 mobj = re.search(
1896 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
1897 (?P<url>http://(?:(?:embed|www)\.)?
1898 (?:novamov\.com|
1899 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1900 videoweed\.(?:es|com)|
1901 movshare\.(?:net|sx|ag)|
1902 divxstage\.(?:eu|net|ch|co|at|ag))
1903 /embed\.php.+?)\1''', webpage)
1904 if mobj is not None:
1905 return self.url_result(mobj.group('url'))
1906
1907 # Look for embedded Facebook player
1908 facebook_url = FacebookIE._extract_url(webpage)
1909 if facebook_url is not None:
1910 return self.url_result(facebook_url, 'Facebook')
1911
1912 # Look for embedded VK player
1913 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1914 if mobj is not None:
1915 return self.url_result(mobj.group('url'), 'VK')
1916
1917 # Look for embedded Odnoklassniki player
1918 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1919 if mobj is not None:
1920 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1921
1922 # Look for embedded ivi player
1923 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1924 if mobj is not None:
1925 return self.url_result(mobj.group('url'), 'Ivi')
1926
1927 # Look for embedded Huffington Post player
1928 mobj = re.search(
1929 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
1930 if mobj is not None:
1931 return self.url_result(mobj.group('url'), 'HuffPost')
1932
1933 # Look for embed.ly
1934 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1935 if mobj is not None:
1936 return self.url_result(mobj.group('url'))
1937 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1938 if mobj is not None:
1939 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1940
1941 # Look for funnyordie embed
1942 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1943 if matches:
1944 return _playlist_from_matches(
1945 matches, getter=unescapeHTML, ie='FunnyOrDie')
1946
1947 # Look for BBC iPlayer embed
1948 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1949 if matches:
1950 return _playlist_from_matches(matches, ie='BBCCoUk')
1951
1952 # Look for embedded RUTV player
1953 rutv_url = RUTVIE._extract_url(webpage)
1954 if rutv_url:
1955 return self.url_result(rutv_url, 'RUTV')
1956
1957 # Look for embedded TVC player
1958 tvc_url = TVCIE._extract_url(webpage)
1959 if tvc_url:
1960 return self.url_result(tvc_url, 'TVC')
1961
1962 # Look for embedded SportBox player
1963 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1964 if sportbox_urls:
1965 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1966
1967 # Look for embedded PornHub player
1968 pornhub_url = PornHubIE._extract_url(webpage)
1969 if pornhub_url:
1970 return self.url_result(pornhub_url, 'PornHub')
1971
1972 # Look for embedded XHamster player
1973 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1974 if xhamster_urls:
1975 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1976
1977 # Look for embedded TNAFlixNetwork player
1978 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1979 if tnaflix_urls:
1980 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1981
1982 # Look for embedded Tvigle player
1983 mobj = re.search(
1984 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1985 if mobj is not None:
1986 return self.url_result(mobj.group('url'), 'Tvigle')
1987
1988 # Look for embedded TED player
1989 mobj = re.search(
1990 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
1991 if mobj is not None:
1992 return self.url_result(mobj.group('url'), 'TED')
1993
1994 # Look for embedded Ustream videos
1995 mobj = re.search(
1996 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1997 if mobj is not None:
1998 return self.url_result(mobj.group('url'), 'Ustream')
1999
2000 # Look for embedded arte.tv player
2001 mobj = re.search(
2002 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
2003 webpage)
2004 if mobj is not None:
2005 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2006
2007 # Look for embedded francetv player
2008 mobj = re.search(
2009 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2010 webpage)
2011 if mobj is not None:
2012 return self.url_result(mobj.group('url'))
2013
2014 # Look for embedded smotri.com player
2015 smotri_url = SmotriIE._extract_url(webpage)
2016 if smotri_url:
2017 return self.url_result(smotri_url, 'Smotri')
2018
2019 # Look for embedded Myvi.ru player
2020 myvi_url = MyviIE._extract_url(webpage)
2021 if myvi_url:
2022 return self.url_result(myvi_url)
2023
2024 # Look for embedded soundcloud player
2025 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2026 if soundcloud_urls:
2027 return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
2028
2029 # Look for embedded mtvservices player
2030 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2031 if mtvservices_url:
2032 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
2033
2034 # Look for embedded yahoo player
2035 mobj = re.search(
2036 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2037 webpage)
2038 if mobj is not None:
2039 return self.url_result(mobj.group('url'), 'Yahoo')
2040
2041 # Look for embedded sbs.com.au player
2042 mobj = re.search(
2043 r'''(?x)
2044 (?:
2045 <meta\s+property="og:video"\s+content=|
2046 <iframe[^>]+?src=
2047 )
2048 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2049 webpage)
2050 if mobj is not None:
2051 return self.url_result(mobj.group('url'), 'SBS')
2052
2053 # Look for embedded Cinchcast player
2054 mobj = re.search(
2055 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2056 webpage)
2057 if mobj is not None:
2058 return self.url_result(mobj.group('url'), 'Cinchcast')
2059
2060 mobj = re.search(
2061 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
2062 webpage)
2063 if not mobj:
2064 mobj = re.search(
2065 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2066 webpage)
2067 if mobj is not None:
2068 return self.url_result(mobj.group('url'), 'MLB')
2069
2070 mobj = re.search(
2071 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
2072 webpage)
2073 if mobj is not None:
2074 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2075
2076 mobj = re.search(
2077 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
2078 webpage)
2079 if mobj is not None:
2080 return self.url_result(mobj.group('url'), 'Livestream')
2081
2082 # Look for Zapiks embed
2083 mobj = re.search(
2084 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2085 if mobj is not None:
2086 return self.url_result(mobj.group('url'), 'Zapiks')
2087
2088 # Look for Kaltura embeds
2089 kaltura_url = KalturaIE._extract_url(webpage)
2090 if kaltura_url:
2091 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
2092
2093 # Look for Eagle.Platform embeds
2094 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2095 if eagleplatform_url:
2096 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
2097
2098 # Look for ClipYou (uses Eagle.Platform) embeds
2099 mobj = re.search(
2100 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2101 if mobj is not None:
2102 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2103
2104 # Look for Pladform embeds
2105 pladform_url = PladformIE._extract_url(webpage)
2106 if pladform_url:
2107 return self.url_result(pladform_url)
2108
2109 # Look for Videomore embeds
2110 videomore_url = VideomoreIE._extract_url(webpage)
2111 if videomore_url:
2112 return self.url_result(videomore_url)
2113
2114 # Look for Playwire embeds
2115 mobj = re.search(
2116 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2117 if mobj is not None:
2118 return self.url_result(mobj.group('url'))
2119
2120 # Look for 5min embeds
2121 mobj = re.search(
2122 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2123 if mobj is not None:
2124 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2125
2126 # Look for Crooks and Liars embeds
2127 mobj = re.search(
2128 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2129 if mobj is not None:
2130 return self.url_result(mobj.group('url'))
2131
2132 # Look for NBC Sports VPlayer embeds
2133 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2134 if nbc_sports_url:
2135 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2136
2137 # Look for NBC News embeds
2138 nbc_news_embed_url = re.search(
2139 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2140 if nbc_news_embed_url:
2141 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2142
2143 # Look for Google Drive embeds
2144 google_drive_url = GoogleDriveIE._extract_url(webpage)
2145 if google_drive_url:
2146 return self.url_result(google_drive_url, 'GoogleDrive')
2147
2148 # Look for UDN embeds
2149 mobj = re.search(
2150 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
2151 if mobj is not None:
2152 return self.url_result(
2153 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
2154
2155 # Look for Senate ISVP iframe
2156 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2157 if senate_isvp_url:
2158 return self.url_result(senate_isvp_url, 'SenateISVP')
2159
2160 # Look for Dailymotion Cloud videos
2161 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2162 if dmcloud_url:
2163 return self.url_result(dmcloud_url, 'DailymotionCloud')
2164
2165 # Look for OnionStudios embeds
2166 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2167 if onionstudios_url:
2168 return self.url_result(onionstudios_url)
2169
2170 # Look for ViewLift embeds
2171 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2172 if viewlift_url:
2173 return self.url_result(viewlift_url)
2174
2175 # Look for JWPlatform embeds
2176 jwplatform_url = JWPlatformIE._extract_url(webpage)
2177 if jwplatform_url:
2178 return self.url_result(jwplatform_url, 'JWPlatform')
2179
2180 # Look for ScreenwaveMedia embeds
2181 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
2182 if mobj is not None:
2183 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
2184
2185 # Look for Digiteka embeds
2186 digiteka_url = DigitekaIE._extract_url(webpage)
2187 if digiteka_url:
2188 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
2189
2190 # Look for Arkena embeds
2191 arkena_url = ArkenaIE._extract_url(webpage)
2192 if arkena_url:
2193 return self.url_result(arkena_url, ArkenaIE.ie_key())
2194
2195 # Look for Limelight embeds
2196 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2197 if mobj:
2198 lm = {
2199 'Media': 'media',
2200 'Channel': 'channel',
2201 'ChannelList': 'channel_list',
2202 }
2203 return self.url_result('limelight:%s:%s' % (
2204 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2205
2206 # Look for AdobeTVVideo embeds
2207 mobj = re.search(
2208 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2209 webpage)
2210 if mobj is not None:
2211 return self.url_result(
2212 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2213 'AdobeTVVideo')
2214
2215 # Look for Vine embeds
2216 mobj = re.search(
2217 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2218 webpage)
2219 if mobj is not None:
2220 return self.url_result(
2221 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2222
2223 # Look for VODPlatform embeds
2224 mobj = re.search(
2225 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)',
2226 webpage)
2227 if mobj is not None:
2228 return self.url_result(
2229 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform')
2230
2231 # Look for Instagram embeds
2232 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2233 if instagram_embed_url is not None:
2234 return self.url_result(
2235 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
2236
2237 # Look for LiveLeak embeds
2238 liveleak_url = LiveLeakIE._extract_url(webpage)
2239 if liveleak_url:
2240 return self.url_result(liveleak_url, 'LiveLeak')
2241
2242 # Look for 3Q SDN embeds
2243 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2244 if threeqsdn_url:
2245 return {
2246 '_type': 'url_transparent',
2247 'ie_key': ThreeQSDNIE.ie_key(),
2248 'url': self._proto_relative_url(threeqsdn_url),
2249 'title': video_title,
2250 'description': video_description,
2251 'thumbnail': video_thumbnail,
2252 'uploader': video_uploader,
2253 }
2254
2255 # Look for VBOX7 embeds
2256 vbox7_url = Vbox7IE._extract_url(webpage)
2257 if vbox7_url:
2258 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2259
2260 # Looking for http://schema.org/VideoObject
2261 json_ld = self._search_json_ld(
2262 webpage, video_id, default={}, expected_type='VideoObject')
2263 if json_ld.get('url'):
2264 info_dict.update({
2265 'title': video_title or info_dict['title'],
2266 'description': video_description,
2267 'thumbnail': video_thumbnail,
2268 'age_limit': age_limit
2269 })
2270 info_dict.update(json_ld)
2271 return info_dict
2272
2273 def check_video(vurl):
2274 if YoutubeIE.suitable(vurl):
2275 return True
2276 vpath = compat_urlparse.urlparse(vurl).path
2277 vext = determine_ext(vpath)
2278 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2279
2280 def filter_video(urls):
2281 return list(filter(check_video, urls))
2282
2283 # Start with something easy: JW Player in SWFObject
2284 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
2285 if not found:
2286 # Look for gorilla-vid style embedding
2287 found = filter_video(re.findall(r'''(?sx)
2288 (?:
2289 jw_plugins|
2290 JWPlayerOptions|
2291 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2292 )
2293 .*?
2294 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
2295 if not found:
2296 # Broaden the search a little bit
2297 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
2298 if not found:
2299 # Broaden the findall a little bit: JWPlayer JS loader
2300 found = filter_video(re.findall(
2301 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
2302 if not found:
2303 # Flow player
2304 found = filter_video(re.findall(r'''(?xs)
2305 flowplayer\("[^"]+",\s*
2306 \{[^}]+?\}\s*,
2307 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
2308 ["']?url["']?\s*:\s*["']([^"']+)["']
2309 ''', webpage))
2310 if not found:
2311 # Cinerama player
2312 found = re.findall(
2313 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
2314 if not found:
2315 # Try to find twitter cards info
2316 # twitter:player:stream should be checked before twitter:player since
2317 # it is expected to contain a raw stream (see
2318 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2319 found = filter_video(re.findall(
2320 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
2321 if not found:
2322 # We look for Open Graph info:
2323 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
2324 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
2325 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2326 if m_video_type is not None:
2327 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
2328 if not found:
2329 # HTML5 video
2330 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
2331 if not found:
2332 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
2333 found = re.search(
2334 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
2335 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
2336 webpage)
2337 if not found:
2338 # Look also in Refresh HTTP header
2339 refresh_header = head_response.headers.get('Refresh')
2340 if refresh_header:
2341 # In python 2 response HTTP headers are bytestrings
2342 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2343 refresh_header = refresh_header.decode('iso-8859-1')
2344 found = re.search(REDIRECT_REGEX, refresh_header)
2345 if found:
2346 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
2347 self.report_following_redirect(new_url)
2348 return {
2349 '_type': 'url',
2350 'url': new_url,
2351 }
2352
2353 if not found:
2354 # twitter:player is a https URL to iframe player that may or may not
2355 # be supported by youtube-dl thus this is checked the very last (see
2356 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
2357 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
2358 if embed_url:
2359 return self.url_result(embed_url)
2360
2361 if not found:
2362 raise UnsupportedError(url)
2363
2364 entries = []
2365 for video_url in orderedSet(found):
2366 video_url = unescapeHTML(video_url)
2367 video_url = video_url.replace('\\/', '/')
2368 video_url = compat_urlparse.urljoin(url, video_url)
2369 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
2370
2371 # Sometimes, jwplayer extraction will result in a YouTube URL
2372 if YoutubeIE.suitable(video_url):
2373 entries.append(self.url_result(video_url, 'Youtube'))
2374 continue
2375
2376 # here's a fun little line of code for you:
2377 video_id = os.path.splitext(video_id)[0]
2378
2379 entry_info_dict = {
2380 'id': video_id,
2381 'uploader': video_uploader,
2382 'title': video_title,
2383 'age_limit': age_limit,
2384 }
2385
2386 ext = determine_ext(video_url)
2387 if ext == 'smil':
2388 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
2389 elif ext == 'xspf':
2390 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
2391 elif ext == 'm3u8':
2392 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
2393 elif ext == 'mpd':
2394 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
2395 elif ext == 'f4m':
2396 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
2397 else:
2398 entry_info_dict['url'] = video_url
2399
2400 if entry_info_dict.get('formats'):
2401 self._sort_formats(entry_info_dict['formats'])
2402
2403 entries.append(entry_info_dict)
2404
2405 if len(entries) == 1:
2406 return entries[0]
2407 else:
2408 for num, e in enumerate(entries, start=1):
2409 # 'url' results don't have a title
2410 if e.get('title') is not None:
2411 e['title'] = '%s (%d)' % (e['title'], num)
2412 return {
2413 '_type': 'playlist',
2414 'entries': entries,
2415 }
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...