]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[urplay] fix typo and check with flake8
[yt-dlp.git] / youtube_dl / extractor / generic.py
CommitLineData
cfe50f04
JMF
1# encoding: utf-8
2
79649588
PH
3from __future__ import unicode_literals
4
9b122384
PH
5import os
6import re
6c91a5a7 7import sys
9b122384
PH
8
9from .common import InfoExtractor
fc9713a1 10from .youtube import YoutubeIE
8c25f81b 11from ..compat import (
f7854627 12 compat_etree_fromstring,
1ddb9456 13 compat_urllib_parse_unquote,
a5caba1e 14 compat_urlparse,
f7300c5c 15 compat_xml_parse_error,
8c25f81b
PH
16)
17from ..utils import (
b759a0d4 18 determine_ext,
9b122384 19 ExtractorError,
c8e9a235 20 float_or_none,
aa94a6d3 21 HEADRequest,
61ca9a80 22 is_html,
ed2d6a19 23 orderedSet,
5c2266df 24 sanitized_Request,
9d4660ca
PH
25 smuggle_url,
26 unescapeHTML,
42393ce2 27 unified_strdate,
4d54ef20 28 unsmuggle_url,
416c7fcb 29 UnsupportedError,
42393ce2 30 url_basename,
76c73715 31 xpath_text,
9b122384 32)
ed126900 33from .brightcove import (
4fcaa4f4 34 BrightcoveLegacyIE,
5c17f0a6 35 BrightcoveNewIE,
ed126900 36)
a2edf2e7 37from .nbc import NBCSportsVPlayerIE
c0d0b01f 38from .ooyala import OoyalaIE
93d020dd 39from .rutv import RUTVIE
954c1d05 40from .tvc import TVCIE
d40a3b5b 41from .sportbox import SportBoxEmbedIE
cb3ac1c6 42from .smotri import SmotriIE
6dd94d3a 43from .myvi import MyviIE
1419fafd 44from .condenast import CondeNastIE
418c5cc3 45from .udn import UDNEmbedIE
2fe1b5bd 46from .senateisvp import SenateISVPIE
bab19a8e 47from .svt import SVTIE
65d161c4 48from .pornhub import PornHubIE
2bb5b6d0 49from .xhamster import XHamsterEmbedIE
2c9ca782 50from .tnaflix import TNAFlixNetworkEmbedIE
b407e173 51from .vimeo import VimeoIE
756f574e 52from .dailymotion import DailymotionCloudIE
1ac1c4c2 53from .onionstudios import OnionStudiosIE
67167920 54from .viewlift import ViewLiftEmbedIE
efd712c6 55from .screenwavemedia import ScreenwaveMediaIE
46fde8a1 56from .mtv import MTVServicesEmbeddedIE
45dad7ba 57from .pladform import PladformIE
ff18735c 58from .videomore import VideomoreIE
5b251628 59from .googledrive import GoogleDriveIE
7cb09524 60from .jwplatform import JWPlatformIE
aecfcd4e 61from .digiteka import DigitekaIE
5a51775a 62from .instagram import InstagramIE
b8f67449 63from .liveleak import LiveLeakIE
5d39176f 64from .threeqsdn import ThreeQSDNIE
4d8819d2 65from .theplatform import ThePlatformIE
48a5eabc 66from .vessel import VesselIE
c287f2bc 67from .kaltura import KalturaIE
06a96da1 68from .eagleplatform import EaglePlatformIE
9b122384 69
0838239e 70
9b122384 71class GenericIE(InfoExtractor):
79649588 72 IE_DESC = 'Generic downloader that works on some sites'
9b122384 73 _VALID_URL = r'.*'
79649588 74 IE_NAME = 'generic'
cfe50f04 75 _TESTS = [
c5fa81fe
S
76 # Direct link to a video
77 {
78 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
79 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
80 'info_dict': {
81 'id': 'trailer',
82 'ext': 'mp4',
83 'title': 'trailer',
84 'upload_date': '20100513',
85 }
86 },
c5138a7c 87 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
88 {
89 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
90 'md5': '128c42e68b13950268b648275386fc74',
91 'info_dict': {
92 'id': 'FictionJunction-Parallel_Hearts',
93 'ext': 'flac',
94 'title': 'FictionJunction-Parallel_Hearts',
95 'upload_date': '20140522',
96 },
97 'expected_warnings': [
98 'URL could be a direct video link, returning it as such.'
99 ]
100 },
101 # Direct download with broken HEAD
102 {
103 'url': 'http://ai-radio.org:8000/radio.opus',
104 'info_dict': {
105 'id': 'radio',
106 'ext': 'opus',
107 'title': 'radio',
108 },
109 'params': {
110 'skip_download': True, # infinite live stream
111 },
112 'expected_warnings': [
ef0e4e7b
YCH
113 r'501.*Not Implemented',
114 r'400.*Bad Request',
c5fa81fe
S
115 ],
116 },
117 # Direct link with incorrect MIME type
118 {
119 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
120 'md5': '4ccbebe5f36706d85221f204d7eb5913',
121 'info_dict': {
122 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
123 'id': '5_Lennart_Poettering_-_Systemd',
124 'ext': 'webm',
125 'title': '5_Lennart_Poettering_-_Systemd',
126 'upload_date': '20141120',
127 },
128 'expected_warnings': [
129 'URL could be a direct video link, returning it as such.'
130 ]
131 },
132 # RSS feed
133 {
134 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
135 'info_dict': {
136 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
137 'title': 'Zero Punctuation',
138 'description': 're:.*groundbreaking video review series.*'
139 },
140 'playlist_mincount': 11,
141 },
142 # RSS feed with enclosure
143 {
144 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
145 'info_dict': {
146 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
147 'ext': 'm4v',
148 'upload_date': '20150228',
149 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
150 }
151 },
8765222d
S
152 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
153 {
154 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
155 'info_dict': {
156 'id': 'smil',
157 'ext': 'mp4',
158 'title': 'Automatics, robotics and biocybernetics',
159 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 160 'upload_date': '20130627',
8765222d
S
161 'formats': 'mincount:16',
162 'subtitles': 'mincount:1',
163 },
164 'params': {
165 'force_generic_extractor': True,
166 'skip_download': True,
167 },
168 },
169 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
170 {
171 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
172 'info_dict': {
173 'id': 'hds',
174 'ext': 'flv',
175 'title': 'hds',
176 'formats': 'mincount:1',
177 },
178 'params': {
179 'skip_download': True,
180 },
181 },
182 # SMIL from https://www.restudy.dk/video/play/id/1637
183 {
184 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
185 'info_dict': {
186 'id': 'video_1637',
187 'ext': 'flv',
188 'title': 'video_1637',
189 'formats': 'mincount:3',
190 },
191 'params': {
192 'skip_download': True,
193 },
194 },
195 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
196 {
197 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
198 'info_dict': {
199 'id': 'smil-service',
200 'ext': 'flv',
201 'title': 'smil-service',
202 'formats': 'mincount:1',
203 },
204 'params': {
205 'skip_download': True,
206 },
207 },
208 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
209 {
210 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
211 'info_dict': {
212 'id': '4719370',
213 'ext': 'mp4',
214 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
215 'formats': 'mincount:3',
216 },
217 'params': {
218 'skip_download': True,
219 },
220 },
1de5cd3b
S
221 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
222 {
223 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
224 'info_dict': {
225 'id': 'mZlp2ctYIUEB',
226 'ext': 'mp4',
227 'title': 'Tikibad ontruimd wegens brand',
228 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
229 'thumbnail': 're:^https?://.*\.jpg$',
230 'duration': 33,
231 },
232 'params': {
233 'skip_download': True,
234 },
235 },
9d939cec
S
236 # MPD from http://dash-mse-test.appspot.com/media.html
237 {
238 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
239 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
240 'info_dict': {
241 'id': 'car-20120827-manifest',
242 'ext': 'mp4',
243 'title': 'car-20120827-manifest',
244 'formats': 'mincount:9',
0738187f 245 'upload_date': '20130904',
9d939cec
S
246 },
247 'params': {
248 'format': 'bestvideo',
249 },
250 },
20938f76
S
251 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
252 {
253 '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',
254 'info_dict': {
255 'id': 'content',
256 'ext': 'mp4',
257 'title': 'content',
258 'formats': 'mincount:8',
259 },
260 'params': {
261 # m3u8 downloads
262 'skip_download': True,
263 }
264 },
edd9b71c
S
265 # m3u8 served with Content-Type: text/plain
266 {
267 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
268 'info_dict': {
269 'id': 'index',
270 'ext': 'mp4',
271 'title': 'index',
272 'upload_date': '20140720',
273 'formats': 'mincount:11',
274 },
275 'params': {
276 # m3u8 downloads
277 'skip_download': True,
278 }
279 },
c5fa81fe
S
280 # google redirect
281 {
282 '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',
283 'info_dict': {
284 'id': 'cmQHVoWB5FY',
285 'ext': 'mp4',
286 'upload_date': '20130224',
287 'uploader_id': 'TheVerge',
288 'description': 're:^Chris Ziegler takes a look at the\.*',
289 'uploader': 'The Verge',
290 'title': 'First Firefox OS phones side-by-side',
291 },
292 'params': {
293 'skip_download': False,
294 }
295 },
6c91a5a7
S
296 {
297 # redirect in Refresh HTTP header
298 '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',
299 'info_dict': {
300 'id': 'pO8h3EaFRdo',
301 'ext': 'mp4',
302 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
303 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
304 'upload_date': '20150917',
305 'uploader_id': 'brtvofficial',
306 'uploader': 'Boiler Room',
307 },
308 'params': {
309 'skip_download': False,
310 },
311 },
cfe50f04 312 {
79649588 313 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 314 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 315 'info_dict': {
d360a146
S
316 'id': '13601338388002',
317 'ext': 'mp4',
79649588
PH
318 'uploader': 'www.hodiho.fr',
319 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
320 }
321 },
c19f7764
JMF
322 # bandcamp page with custom domain
323 {
79649588
PH
324 'add_ie': ['Bandcamp'],
325 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 326 'info_dict': {
fd50bf62
S
327 'id': '3235767654',
328 'ext': 'mp3',
79649588
PH
329 'title': 'The Pony Mash',
330 'uploader': 'M_Pallante',
c19f7764 331 },
79649588 332 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 333 },
eeb165e6 334 # embedded brightcove video
dd5bcdc4
JMF
335 # it also tests brightcove videos that need to set the 'Referer' in the
336 # http requests
eeb165e6 337 {
3b7d9aa4 338 'add_ie': ['BrightcoveLegacy'],
79649588
PH
339 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
340 'info_dict': {
341 'id': '2765128793001',
342 'ext': 'mp4',
343 'title': 'Le cours de bourse : l’analyse technique',
344 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
345 'uploader': 'BFM BUSINESS',
eeb165e6 346 },
79649588
PH
347 'params': {
348 'skip_download': True,
eeb165e6
JMF
349 },
350 },
17ab4d3b
PH
351 {
352 # https://github.com/rg3/youtube-dl/issues/2253
353 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
354 'md5': '0ba9446db037002366bab3b3eb30c88c',
355 'info_dict': {
fd50bf62
S
356 'id': '3101154703001',
357 'ext': 'mp4',
17ab4d3b
PH
358 'title': 'Still no power',
359 'uploader': 'thestar.com',
360 '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.',
361 },
3b7d9aa4 362 'add_ie': ['BrightcoveLegacy'],
17ab4d3b 363 },
0479c625
S
364 {
365 'url': 'http://www.championat.com/video/football/v/87/87499.html',
366 'md5': 'fb973ecf6e4a78a67453647444222983',
367 'info_dict': {
368 'id': '3414141473001',
369 'ext': 'mp4',
370 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
371 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
372 'uploader': 'Championat',
373 },
374 },
bdf97017 375 {
37aab278 376 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 377 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
378 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
379 'info_dict': {
380 'id': '3866516442001',
37aab278 381 'ext': 'mp4',
bdf97017
NJ
382 'title': 'Leer mij vrouwen kennen: Aflevering 1',
383 'description': 'Leer mij vrouwen kennen: Aflevering 1',
384 'uploader': 'SBS Broadcasting',
385 },
37aab278 386 'skip': 'Restricted to Netherlands',
bdf97017 387 'params': {
37aab278 388 'skip_download': True, # m3u8 download
bdf97017
NJ
389 },
390 },
c0d0b01f
JMF
391 # ooyala video
392 {
79649588 393 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 394 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
395 'info_dict': {
396 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
397 'ext': 'mp4',
3486df38 398 'title': '2cc213299525360.mov', # that's what we get
53e06b25 399 'duration': 238.231,
c0d0b01f 400 },
87830900 401 'add_ie': ['Ooyala'],
c0d0b01f 402 },
bf94d763
S
403 {
404 # ooyala video embedded with http://player.ooyala.com/iframe.js
405 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
406 'info_dict': {
407 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
408 'ext': 'mp4',
409 'title': '"Steve Jobs: Man in the Machine" trailer',
410 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 411 'duration': 135.427,
bf94d763
S
412 },
413 'params': {
414 'skip_download': True,
415 },
416 },
1b86cc41 417 # embed.ly video
418 {
419 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
420 'info_dict': {
421 'id': '9ODmcdjQcHQ',
422 'ext': 'mp4',
0a5bce56
PH
423 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
424 'upload_date': '20140225',
425 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
426 'uploader': 'Tested',
427 'uploader_id': 'testedcom',
1b86cc41 428 },
429 # No need to test YoutubeIE here
430 'params': {
431 'skip_download': True,
432 },
433 },
60cc4dc4
PH
434 # funnyordie embed
435 {
436 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
437 'info_dict': {
438 'id': '18e820ec3f',
439 'ext': 'mp4',
440 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
441 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 442 },
60cc4dc4 443 },
93d020dd
S
444 # RUTV embed
445 {
446 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
447 'info_dict': {
448 'id': '776940',
449 'ext': 'mp4',
450 'title': 'Охотское море стало целиком российским',
451 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
452 },
453 'params': {
454 # m3u8 download
455 'skip_download': True,
456 },
aab74fa1 457 },
f37bdbe5
S
458 # TVC embed
459 {
460 '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/',
461 'info_dict': {
462 'id': '55304',
463 'ext': 'mp4',
464 'title': 'Дошкольное воспитание',
465 },
466 },
b827a601
S
467 # SportBox embed
468 {
469 'url': 'http://www.vestifinance.ru/articles/25753',
470 'info_dict': {
471 'id': '25753',
472 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
473 },
474 'playlist': [{
475 'info_dict': {
476 'id': '370908',
477 'title': 'Госзаказ. День 3',
478 'ext': 'mp4',
479 }
480 }, {
481 'info_dict': {
482 'id': '370905',
483 'title': 'Госзаказ. День 2',
484 'ext': 'mp4',
485 }
486 }, {
487 'info_dict': {
488 'id': '370902',
489 'title': 'Госзаказ. День 1',
490 'ext': 'mp4',
491 }
492 }],
493 'params': {
494 # m3u8 download
495 'skip_download': True,
496 },
497 },
bf20b9c5
S
498 # Myvi.ru embed
499 {
500 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
501 'info_dict': {
502 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
503 'ext': 'mp4',
504 'title': 'Ужастики, русский трейлер (2015)',
505 'thumbnail': 're:^https?://.*\.jpg$',
506 'duration': 153,
507 }
508 },
c76799c5
S
509 # XHamster embed
510 {
511 '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',
512 'info_dict': {
513 'id': 'showthread',
514 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
515 },
516 'playlist_mincount': 7,
517 },
aab74fa1
PH
518 # Embedded TED video
519 {
520 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 521 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 522 'info_dict': {
a8eb5a8e 523 'id': '1969',
aab74fa1 524 'ext': 'mp4',
a8eb5a8e
PH
525 'title': 'Hidden miracles of the natural world',
526 'uploader': 'Louie Schwartzberg',
527 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 528 }
60cc4dc4 529 },
dfb1b146 530 # Embedded Ustream video
5c386252 531 {
532 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
533 'md5': '27b99cdb639c9b12a79bca876a073417',
534 'info_dict': {
ca6aada4 535 'id': '45734260',
536 'ext': 'flv',
537 'uploader': 'AU SPA: The NSA and Privacy',
5c386252 538 'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
539 }
540 },
d95e35d6
S
541 # nowvideo embed hidden behind percent encoding
542 {
543 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
544 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
545 'info_dict': {
546 'id': '06e53103ca9aa',
547 'ext': 'flv',
548 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
549 'description': 'No description',
550 },
0f2a2ba1 551 },
893f8832
PH
552 # arte embed
553 {
554 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
555 'md5': '7653032cbb25bf6c80d80f217055fa43',
556 'info_dict': {
557 'id': '048195-004_PLUS7-F',
558 'ext': 'flv',
559 'title': 'X:enius',
560 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
561 'upload_date': '20140320',
562 },
563 'params': {
564 'skip_download': 'Requires rtmpdump'
565 }
566 },
cbd55ade
S
567 # francetv embed
568 {
569 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
570 'info_dict': {
571 'id': 'EV_30231',
572 'ext': 'mp4',
573 'title': 'Alcaline, le concert avec Calogero',
574 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
575 'upload_date': '20150226',
576 'timestamp': 1424989860,
577 'duration': 5400,
578 },
579 'params': {
580 # m3u8 downloads
581 'skip_download': True,
582 },
583 'expected_warnings': [
584 'Forbidden'
585 ]
586 },
fa35cdad
PH
587 # Condé Nast embed
588 {
589 'url': 'http://www.wired.com/2014/04/honda-asimo/',
590 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
591 'info_dict': {
592 'id': '53501be369702d3275860000',
593 'ext': 'mp4',
594 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
595 }
ebd3c7b3
PH
596 },
597 # Dailymotion embed
598 {
599 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
600 'md5': '441aeeb82eb72c422c7f14ec533999cd',
601 'info_dict': {
602 'id': 'k2mm4bCdJ6CQ2i7c8o2',
603 'ext': 'mp4',
604 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 605 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 606 'uploader': 'Spi0n',
0738187f
YCH
607 'uploader_id': 'xgditw',
608 'upload_date': '20140425',
609 'timestamp': 1398441542,
ebd3c7b3
PH
610 },
611 'add_ie': ['Dailymotion'],
2b88feed
PH
612 },
613 # YouTube embed
614 {
615 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
616 'info_dict': {
617 'id': 'FXRb4ykk4S0',
618 'ext': 'mp4',
619 'title': 'The NBL Auction 2014',
620 'uploader': 'BADMINTON England',
621 'uploader_id': 'BADMINTONEvents',
622 'upload_date': '20140603',
623 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
624 },
625 'add_ie': ['Youtube'],
626 'params': {
627 'skip_download': True,
628 }
629 },
c5cd249e
JMF
630 # MTVSercices embed
631 {
1fa309da
YCH
632 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
633 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 634 'info_dict': {
1fa309da 635 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 636 'ext': 'mp4',
1fa309da
YCH
637 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
638 'description': 'Two valets share their love for movie star Liam Neesons.',
c5cd249e
JMF
639 },
640 },
61013473 641 # YouTube embed via <data-embed-url="">
642 {
643 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 644 'info_dict': {
a8eb5a8e 645 'id': '4vAffPZIT44',
61013473 646 'ext': 'mp4',
a8eb5a8e 647 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
648 'uploader': 'Gameloft',
649 'uploader_id': 'gameloft',
a8eb5a8e
PH
650 'upload_date': '20140828',
651 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
652 },
653 'params': {
654 'skip_download': True,
61013473 655 }
c8e9a235
PH
656 },
657 # Camtasia studio
658 {
659 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
660 'playlist': [{
661 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
662 'info_dict': {
663 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
664 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
665 'ext': 'flv',
666 'duration': 2235.90,
667 }
668 }, {
669 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
670 'info_dict': {
671 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
672 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
673 'ext': 'flv',
674 'duration': 2235.93,
675 }
676 }],
677 'info_dict': {
678 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
679 }
4d805e06
PH
680 },
681 # Flowplayer
682 {
683 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
684 'md5': '9d65602bf31c6e20014319c7d07fba27',
685 'info_dict': {
686 'id': '5123ea6d5e5a7',
687 'ext': 'mp4',
688 'age_limit': 18,
689 'uploader': 'www.handjobhub.com',
d6d9186f 690 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 691 }
0990305d 692 },
22a6f150
PH
693 # Multiple brightcove videos
694 # https://github.com/rg3/youtube-dl/issues/2283
695 {
696 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
697 'info_dict': {
698 'id': 'always-never',
699 'title': 'Always / Never - The New Yorker',
700 },
701 'playlist_count': 3,
702 'params': {
703 'extract_flat': False,
704 'skip_download': True,
705 }
1a94ff68
S
706 },
707 # MLB embed
708 {
709 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
710 'md5': '96f09a37e44da40dd083e12d9a683327',
711 'info_dict': {
712 'id': '33322633',
713 'ext': 'mp4',
714 'title': 'Ump changes call to ball',
715 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
716 'duration': 48,
717 'timestamp': 1401537900,
718 'upload_date': '20140531',
719 'thumbnail': 're:^https?://.*\.jpg$',
720 },
721 },
746c67d7
NJ
722 # Wistia embed
723 {
6c114b12
S
724 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
725 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 726 'info_dict': {
6c114b12 727 'id': '6e2wtrbdaf',
746c67d7 728 'ext': 'mov',
6c114b12
S
729 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
730 'description': 'a Paywall Videos video from Remilon',
731 'duration': 644.072,
732 'uploader': 'study.com',
733 'timestamp': 1459678540,
734 'upload_date': '20160403',
735 'filesize': 24687186,
746c67d7
NJ
736 },
737 },
52cffcb1 738 {
739 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
740 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
741 'info_dict': {
742 'id': 'uxjb0lwrcz',
743 'ext': 'mp4',
6c114b12 744 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 745 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 746 'duration': 1715.0,
85d7b765 747 'uploader': 'thoughtworks.wistia.com',
0738187f 748 'timestamp': 1401832161,
6c114b12 749 'upload_date': '20140603',
70b7e3fb 750 },
52cffcb1 751 },
7ded6545
S
752 # Wistia standard embed (async)
753 {
754 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
755 'info_dict': {
756 'id': '807fafadvk',
757 'ext': 'mp4',
758 'title': 'Drip Brennan Dunn Workshop',
759 'description': 'a JV Webinars video from getdrip-1',
760 'duration': 4986.95,
7ded6545 761 'timestamp': 1463607249,
6c114b12 762 'upload_date': '20160518',
7ded6545
S
763 },
764 'params': {
765 'skip_download': True,
766 }
767 },
ac645ac7
PH
768 # Soundcloud embed
769 {
770 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
771 'info_dict': {
772 'id': '174391317',
773 'ext': 'mp3',
774 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
775 'uploader': 'Sophos Security',
776 'title': 'Chet Chat 171 - Oct 29, 2014',
777 'upload_date': '20141029',
778 }
af63fed7
PH
779 },
780 # Livestream embed
781 {
782 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
783 'info_dict': {
784 'id': '67864563',
785 'ext': 'flv',
786 'upload_date': '20141112',
787 'title': 'Rosetta #CometLanding webcast HL 10',
788 }
789 },
78d3b3e2
YCH
790 # Another Livestream embed, without 'new.' in URL
791 {
792 'url': 'https://www.freespeech.org/',
793 'info_dict': {
794 'id': '123537347',
795 'ext': 'mp4',
796 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
797 },
798 'params': {
799 # Live stream
800 'skip_download': True,
801 },
802 },
65f3a228
PH
803 # LazyYT
804 {
805 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
806 'info_dict': {
11e611a7 807 'id': '1986',
65f3a228
PH
808 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
809 },
810 'playlist_mincount': 2,
4e262a88 811 },
42bdd9d0
PH
812 # Cinchcast embed
813 {
814 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
815 'info_dict': {
816 'id': '7141703',
817 'ext': 'mp3',
818 'upload_date': '20141126',
819 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
820 }
821 },
501f13fb
PH
822 # Cinerama player
823 {
824 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
825 'info_dict': {
826 'id': '730m_DandD_1901_512k',
827 'ext': 'mp4',
828 'uploader': 'www.abc.net.au',
829 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
830 }
796df3c6
S
831 },
832 # embedded viddler video
833 {
834 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
835 'info_dict': {
836 'id': '4d03aad9',
837 'ext': 'mp4',
838 'uploader': 'deadspin',
839 'title': 'WALL-TO-GORTAT',
840 'timestamp': 1422285291,
841 'upload_date': '20150126',
842 },
843 'add_ie': ['Viddler'],
a0f71985 844 },
2051acde
S
845 # Libsyn embed
846 {
847 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
848 'info_dict': {
849 'id': '3377616',
850 'ext': 'mp3',
851 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
852 'description': 'md5:601cb790edd05908957dae8aaa866465',
853 'upload_date': '20150220',
854 },
855 },
a0f71985
PH
856 # jwplayer YouTube
857 {
858 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
859 'info_dict': {
860 'id': 'Mrj4DVp2zeA',
861 'ext': 'mp4',
f37e3f99 862 'upload_date': '20150212',
a0f71985
PH
863 'uploader': 'The National Archives UK',
864 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
865 'uploader_id': 'NationalArchives08',
866 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
867 },
59b8ab58
PH
868 },
869 # rtl.nl embed
870 {
871 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
872 'playlist_mincount': 5,
873 'info_dict': {
874 'id': 'aanslagen-kopenhagen',
875 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
876 }
255fca5e
S
877 },
878 # Zapiks embed
879 {
880 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
881 'info_dict': {
882 'id': '118046',
883 'ext': 'mp4',
884 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
885 }
886 },
66e568de
S
887 # Kaltura embed (different embed code)
888 {
889 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
890 'info_dict': {
891 'id': '1_a52wc67y',
892 'ext': 'flv',
893 'upload_date': '20150127',
894 'uploader_id': 'PremierMedia',
895 'timestamp': int,
896 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
897 },
898 },
6da620de
S
899 # Kaltura embed protected with referrer
900 {
901 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero',
902 'info_dict': {
903 'id': '1_g4fbemnq',
904 'ext': 'mp4',
905 'title': 'Violetta - Achter De Schermen - Ruggero',
906 'description': 'Achter de schermen met Ruggero',
907 'timestamp': 1435133761,
908 'upload_date': '20150624',
909 'uploader_id': 'echojecka',
910 },
911 },
87703231
YCH
912 # Kaltura embed with single quotes
913 {
914 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
915 'info_dict': {
916 'id': '0_izeg5utt',
917 'ext': 'mp4',
918 'title': '35871',
919 'timestamp': 1355743100,
920 'upload_date': '20121217',
921 'uploader_id': 'batchUser',
922 },
923 'add_ie': ['Kaltura'],
924 },
427cd050
S
925 {
926 # Kaltura embedded via quoted entry_id
927 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
928 'info_dict': {
929 'id': '0_utuok90b',
930 'ext': 'mp4',
931 'title': '06_matthew_brender_raj_dutt',
932 'timestamp': 1466638791,
933 'upload_date': '20160622',
934 },
935 'add_ie': ['Kaltura'],
936 'expected_warnings': [
937 'Could not send HEAD request'
938 ],
939 'params': {
940 'skip_download': True,
941 }
942 },
135c9c42
S
943 # Eagle.Platform embed (generic URL)
944 {
945 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
4645432d 946 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
135c9c42
S
947 'info_dict': {
948 'id': '227304',
949 'ext': 'mp4',
950 'title': 'Навальный вышел на свободу',
951 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
952 'thumbnail': 're:^https?://.*\.jpg$',
953 'duration': 87,
954 'view_count': int,
955 'age_limit': 0,
956 },
957 },
d47ae7f6
S
958 # ClipYou (Eagle.Platform) embed (custom URL)
959 {
960 'url': 'http://muz-tv.ru/play/7129/',
4645432d 961 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
962 'info_dict': {
963 'id': '12820',
964 'ext': 'mp4',
965 'title': "'O Sole Mio",
966 'thumbnail': 're:^https?://.*\.jpg$',
967 'duration': 216,
968 'view_count': int,
969 },
970 },
f8388757
S
971 # Pladform embed
972 {
973 'url': 'http://muz-tv.ru/kinozal/view/7400/',
974 'info_dict': {
975 'id': '100183293',
976 'ext': 'mp4',
62259846 977 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757
S
978 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
979 'thumbnail': 're:^https?://.*\.jpg$',
980 'duration': 694,
981 'age_limit': 0,
982 },
983 },
c798f15b
S
984 # Playwire embed
985 {
986 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
987 'info_dict': {
988 'id': '3519514',
989 'ext': 'mp4',
990 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
991 'thumbnail': 're:^https?://.*\.png$',
992 'duration': 45.115,
993 },
994 },
ad320e9b
NJ
995 # 5min embed
996 {
997 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
998 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
999 'info_dict': {
1000 'id': '518726732',
1001 'ext': 'mp4',
1002 'title': 'Facebook Creates "On This Day" | Crunch Report',
1003 },
1004 },
dc455a5f
S
1005 # SVT embed
1006 {
1007 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1008 'info_dict': {
1009 'id': '2900353',
1010 'ext': 'flv',
1011 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1012 'duration': 27,
1013 'age_limit': 0,
1014 },
1015 },
a4257017
S
1016 # Crooks and Liars embed
1017 {
1018 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1019 'info_dict': {
1020 'id': '8RUoRhRi',
1021 'ext': 'mp4',
1022 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1023 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1024 'timestamp': 1428207000,
1025 'upload_date': '20150405',
1026 'uploader': 'Heather',
1027 },
1028 },
1029 # Crooks and Liars external embed
1030 {
1031 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1032 'info_dict': {
1033 'id': 'MTE3MjUtMzQ2MzA',
1034 'ext': 'mp4',
1035 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1036 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1037 'timestamp': 1265032391,
1038 'upload_date': '20100201',
1039 'uploader': 'Heather',
1040 },
1041 },
facecb84 1042 # NBC Sports vplayer embed
a2edf2e7 1043 {
facecb84 1044 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1045 'info_dict': {
facecb84
S
1046 'id': 'ln7x1qSThw4k',
1047 'ext': 'flv',
1048 'title': "PFT Live: New leader in the 'new-look' defense",
1049 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1050 'uploader': 'NBCU-SPORTS',
1051 'upload_date': '20140107',
1052 'timestamp': 1389118457,
a2edf2e7 1053 },
418c5cc3 1054 },
de3eb07e
YCH
1055 # NBC News embed
1056 {
1057 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1058 'md5': '1aa589c675898ae6d37a17913cf68d66',
1059 'info_dict': {
1060 'id': '701714499682',
1061 'ext': 'mp4',
1062 'title': 'PREVIEW: On Assignment: David Letterman',
1063 '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.',
1064 },
1065 },
418c5cc3
YCH
1066 # UDN embed
1067 {
811586eb 1068 'url': 'https://video.udn.com/news/300346',
01c58f84 1069 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1070 'info_dict': {
01c58f84 1071 'id': '300346',
418c5cc3 1072 'ext': 'mp4',
01c58f84 1073 'title': '中一中男師變性 全校師生力挺',
418c5cc3 1074 'thumbnail': 're:^https?://.*\.jpg$',
811586eb
YCH
1075 },
1076 'params': {
1077 # m3u8 download
1078 'skip_download': True,
1079 },
edfcf7ab
YCH
1080 },
1081 # Ooyala embed
1082 {
1083 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1084 'info_dict': {
1085 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1086 'ext': 'mp4',
cce9d15d 1087 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
edfcf7ab 1088 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 1089 'duration': 191.933,
edfcf7ab
YCH
1090 },
1091 'params': {
1092 # m3u8 downloads
1093 'skip_download': True,
1094 }
d6fd958c 1095 },
b26733ba
YCH
1096 # Brightcove URL in single quotes
1097 {
1098 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1099 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1100 'info_dict': {
1101 'id': '4255764656001',
1102 'ext': 'mp4',
1103 'title': 'SN Presents: Russell Martin, World Citizen',
1104 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1105 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1106 'uploader_id': '1704050871',
1107 'upload_date': '20150525',
1108 'timestamp': 1432570283,
b26733ba 1109 },
756f574e
YCH
1110 },
1111 # Dailymotion Cloud video
1112 {
1113 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
7d52c052 1114 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
756f574e 1115 'info_dict': {
7d52c052 1116 'id': 'x2uy8t3',
756f574e 1117 'ext': 'mp4',
7d52c052
YCH
1118 'title': 'Sauvons les abeilles ! - Le débat',
1119 'description': 'md5:d9082128b1c5277987825d684939ca26',
756f574e 1120 'thumbnail': 're:^https?://.*\.jpe?g$',
7d52c052
YCH
1121 'timestamp': 1434970506,
1122 'upload_date': '20150622',
1123 'uploader': 'Public Sénat',
1124 'uploader_id': 'xa9gza',
756f574e 1125 }
a5158f38 1126 },
8084be78
S
1127 # OnionStudios embed
1128 {
1129 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1130 'info_dict': {
1131 'id': '2855',
1132 'ext': 'mp4',
1133 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
1134 'thumbnail': 're:^https?://.*\.jpe?g$',
1135 'uploader': 'ClickHole',
1136 'uploader_id': 'clickhole',
1137 }
1138 },
b8c1cc1a
S
1139 # SnagFilms embed
1140 {
1141 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1142 'info_dict': {
1143 'id': '74849a00-85a9-11e1-9660-123139220831',
1144 'ext': 'mp4',
1145 'title': '#whilewewatch',
1146 }
1147 },
a5158f38
YCH
1148 # AdobeTVVideo embed
1149 {
1150 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1151 'md5': '43662b577c018ad707a63766462b1e87',
1152 'info_dict': {
1153 'id': '2456',
1154 'ext': 'mp4',
1155 'title': 'New experience with Acrobat DC',
1156 'description': 'New experience with Acrobat DC',
1157 'duration': 248.667,
1158 },
1f812580
S
1159 },
1160 # ScreenwaveMedia embed
1161 {
1162 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1',
1163 'md5': '24ace5baba0d35d55c6810b51f34e9e0',
1164 'info_dict': {
1165 'id': 'cinemasnob-55d26273809dd',
1166 'ext': 'mp4',
1167 'title': 'cinemasnob',
1168 },
ed126900 1169 },
1170 # BrightcoveInPageEmbed embed
1171 {
1172 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1173 'info_dict': {
1174 'id': '4238694884001',
1175 'ext': 'flv',
1176 'title': 'Tabletop: Dread, Last Thoughts',
1177 'description': 'Tabletop: Dread, Last Thoughts',
1178 'duration': 51690,
1179 },
750b9ff0
YCH
1180 },
1181 # JWPlayer with M3U8
1182 {
1183 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video',
1184 'info_dict': {
1185 'id': 'playlist',
1186 'ext': 'mp4',
1187 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ',
1188 'uploader': 'ren.tv',
1189 },
1190 'params': {
1191 # m3u8 downloads
1192 'skip_download': True,
1193 }
d10fe835
YCH
1194 },
1195 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1196 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1197 {
1198 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1199 'info_dict': {
1200 'id': '4785848093001',
1201 'ext': 'mp4',
1202 'title': 'The Cardinal Pell Interview',
1203 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1204 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1205 'uploader_id': '2733773828001',
1206 'upload_date': '20160304',
1207 'timestamp': 1457083087,
d10fe835
YCH
1208 },
1209 'params': {
1210 # m3u8 downloads
1211 'skip_download': True,
1212 },
1213 },
134c207e
YCH
1214 # Another form of arte.tv embed
1215 {
1216 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1217 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1218 'info_dict': {
1219 'id': '030273-562_PLUS7-F',
1220 'ext': 'mp4',
1221 'title': 'ARTE Reportage - Nulle part, en France',
1222 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1223 'upload_date': '20160409',
1224 },
1225 },
b8f67449
KM
1226 # LiveLeak embed
1227 {
1228 'url': 'http://www.wykop.pl/link/3088787/',
1229 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
1230 'info_dict': {
1231 'id': '874_1459135191',
1232 'ext': 'mp4',
1233 'title': 'Man shows poor quality of new apartment building',
1234 'description': 'The wall is like a sand pile.',
1235 'uploader': 'Lake8737',
1236 }
1237 },
4a120778
YCH
1238 # Duplicated embedded video URLs
1239 {
1240 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1241 'info_dict': {
1242 'id': '149298443_480_16c25b74_2',
1243 'ext': 'mp4',
1244 'title': 'vs. Blue Orange Spring Game',
1245 'uploader': 'www.hudl.com',
1246 },
1247 },
cfe50f04 1248 ]
9b122384 1249
9b122384
PH
1250 def report_following_redirect(self, new_url):
1251 """Report information extraction."""
79649588 1252 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 1253
4fc946b5
PH
1254 def _extract_rss(self, url, video_id, doc):
1255 playlist_title = doc.find('./channel/title').text
1256 playlist_desc_el = doc.find('./channel/description')
1257 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1258
76c73715
PH
1259 entries = []
1260 for it in doc.findall('./channel/item'):
1261 next_url = xpath_text(it, 'link', fatal=False)
1262 if not next_url:
1263 enclosure_nodes = it.findall('./enclosure')
1264 for e in enclosure_nodes:
1265 next_url = e.attrib.get('url')
1266 if next_url:
1267 break
1268
1269 if not next_url:
1270 continue
1271
1272 entries.append({
1273 '_type': 'url',
1274 'url': next_url,
1275 'title': it.find('title').text,
1276 })
4fc946b5
PH
1277
1278 return {
1279 '_type': 'playlist',
1280 'id': url,
1281 'title': playlist_title,
1282 'description': playlist_desc,
1283 'entries': entries,
1284 }
1285
c8e9a235
PH
1286 def _extract_camtasia(self, url, video_id, webpage):
1287 """ Returns None if no camtasia video can be found. """
1288
1289 camtasia_cfg = self._search_regex(
1290 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1291 webpage, 'camtasia configuration file', default=None)
1292 if camtasia_cfg is None:
1293 return None
1294
1295 title = self._html_search_meta('DC.title', webpage, fatal=True)
1296
1297 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1298 camtasia_cfg = self._download_xml(
1299 camtasia_url, video_id,
1300 note='Downloading camtasia configuration',
1301 errnote='Failed to download camtasia configuration')
1302 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1303
1304 entries = []
1305 for n in fileset_node.getchildren():
1306 url_n = n.find('./uri')
1307 if url_n is None:
1308 continue
1309
1310 entries.append({
1311 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
1312 'title': '%s - %s' % (title, n.tag),
1313 'url': compat_urlparse.urljoin(url, url_n.text),
1314 'duration': float_or_none(n.find('./duration').text),
1315 })
1316
1317 return {
1318 '_type': 'playlist',
1319 'entries': entries,
1320 'title': title,
1321 }
1322
9b122384 1323 def _real_extract(self, url):
ebd3c7b3
PH
1324 if url.startswith('//'):
1325 return {
1326 '_type': 'url',
20991253 1327 'url': self.http_scheme() + url,
ebd3c7b3
PH
1328 }
1329
a7130543
JMF
1330 parsed_url = compat_urlparse.urlparse(url)
1331 if not parsed_url.scheme:
04b4d394
PH
1332 default_search = self._downloader.params.get('default_search')
1333 if default_search is None:
1f7ccb90 1334 default_search = 'fixup_error'
04b4d394 1335
1f7ccb90 1336 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
1337 if '/' in url:
1338 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
1339 return self.url_result('http://' + url)
1f7ccb90 1340 elif default_search != 'fixup_error':
9c1fc022 1341 if default_search == 'auto_warning':
0e67ab0d
PH
1342 if re.match(r'^(?:url|URL)$', url):
1343 raise ExtractorError(
1344 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
1345 expected=True)
1346 else:
1347 self._downloader.report_warning(
7571c02c 1348 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 1349 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
1350
1351 if default_search in ('error', 'fixup_error'):
7571c02c 1352 raise ExtractorError(
b74e86f4
PH
1353 '%r is not a valid URL. '
1354 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
1355 % (url, url), expected=True)
04b4d394 1356 else:
f2f2c0c2
PH
1357 if ':' not in default_search:
1358 default_search += ':'
04b4d394 1359 return self.url_result(default_search + url)
4d54ef20
PH
1360
1361 url, smuggled_data = unsmuggle_url(url)
1362 force_videoid = None
d6e6a422 1363 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
1364 if smuggled_data and 'force_videoid' in smuggled_data:
1365 force_videoid = smuggled_data['force_videoid']
1366 video_id = force_videoid
1367 else:
1ddb9456 1368 video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
a7130543 1369
79649588 1370 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 1371
ebab4520 1372 head_req = HEADRequest(url)
23be51d8 1373 head_response = self._request_webpage(
ebab4520
PH
1374 head_req, video_id,
1375 note=False, errnote='Could not send HEAD request to %s' % url,
1376 fatal=False)
42393ce2 1377
23be51d8 1378 if head_response is not False:
42393ce2 1379 # Check for redirect
23be51d8 1380 new_url = head_response.geturl()
42393ce2
PH
1381 if url != new_url:
1382 self.report_following_redirect(new_url)
4d54ef20
PH
1383 if force_videoid:
1384 new_url = smuggle_url(
1385 new_url, {'force_videoid': force_videoid})
cecaaf3f 1386 return self.url_result(new_url)
42393ce2 1387
23be51d8
PH
1388 full_response = None
1389 if head_response is False:
5c2266df 1390 request = sanitized_Request(url)
58bde34a
S
1391 request.add_header('Accept-Encoding', '*')
1392 full_response = self._request_webpage(request, video_id)
23be51d8
PH
1393 head_response = full_response
1394
f930e0c7
S
1395 info_dict = {
1396 'id': video_id,
1397 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
303dcdb9 1398 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
1399 }
1400
23be51d8 1401 # Check for direct link to a video
955737b2 1402 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 1403 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 1404 if m:
f930e0c7
S
1405 format_id = m.group('format_id')
1406 if format_id.endswith('mpegurl'):
eadc3ccd 1407 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
1408 elif format_id == 'f4m':
1409 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 1410 else:
1411 formats = [{
1412 'format_id': m.group('format_id'),
1413 'url': url,
1414 'vcodec': 'none' if m.group('type') == 'audio' else None
1415 }]
de6c51e8 1416 info_dict['direct'] = True
19dbaeec 1417 self._sort_formats(formats)
de6c51e8 1418 info_dict['formats'] = formats
f930e0c7 1419 return info_dict
42393ce2 1420
d6e6a422 1421 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
1422 force = self._downloader.params.get('force_generic_extractor', False)
1423 self._downloader.report_warning(
1424 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 1425
4e262a88 1426 if not full_response:
5c2266df 1427 request = sanitized_Request(url)
58bde34a
S
1428 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
1429 # making it impossible to download only chunk of the file (yet we need only 512kB to
1430 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
1431 # that will always result in downloading the whole file that is not desirable.
1432 # Therefore for extraction pass we have to override Accept-Encoding to any in order
1433 # to accept raw bytes and being able to download only a chunk.
1434 # It may probably better to solve this by checking Content-Type for application/octet-stream
1435 # after HEAD request finishes, but not sure if we can rely on this.
1436 request.add_header('Accept-Encoding', '*')
1437 full_response = self._request_webpage(request, video_id)
4e262a88 1438
5940862d
S
1439 first_bytes = full_response.read(512)
1440
1441 # Is it an M3U playlist?
0d769bcb 1442 if first_bytes.startswith(b'#EXTM3U'):
5940862d 1443 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 1444 self._sort_formats(info_dict['formats'])
5940862d
S
1445 return info_dict
1446
4e262a88
PH
1447 # Maybe it's a direct link to a video?
1448 # Be careful not to download the whole thing!
61ca9a80 1449 if not is_html(first_bytes):
4e262a88
PH
1450 self._downloader.report_warning(
1451 'URL could be a direct video link, returning it as such.')
f930e0c7 1452 info_dict.update({
4e262a88
PH
1453 'direct': True,
1454 'url': url,
f930e0c7
S
1455 })
1456 return info_dict
4e262a88
PH
1457
1458 webpage = self._webpage_read_content(
1459 full_response, url, video_id, prefix=first_bytes)
1460
9b122384 1461 self.report_extraction(video_id)
887c6acd 1462
1b840245 1463 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 1464 try:
f7854627 1465 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
1466 if doc.tag == 'rss':
1467 return self._extract_rss(url, video_id, doc)
e5e8d20a 1468 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
1469 smil = self._parse_smil(doc, url, video_id)
1470 self._sort_formats(smil['formats'])
1471 return smil
729accb4
S
1472 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
1473 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1b840245 1474 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7
S
1475 info_dict['formats'] = self._parse_mpd_formats(
1476 doc, video_id, mpd_base_url=url.rpartition('/')[0])
19dbaeec 1477 self._sort_formats(info_dict['formats'])
f930e0c7
S
1478 return info_dict
1479 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
1480 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 1481 self._sort_formats(info_dict['formats'])
f930e0c7 1482 return info_dict
f7300c5c 1483 except compat_xml_parse_error:
4fc946b5
PH
1484 pass
1485
c8e9a235
PH
1486 # Is it a Camtasia project?
1487 camtasia_res = self._extract_camtasia(url, video_id, webpage)
1488 if camtasia_res is not None:
1489 return camtasia_res
1490
14390730
S
1491 # Sometimes embedded video player is hidden behind percent encoding
1492 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
1493 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 1494 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 1495
887c6acd
PH
1496 # it's tempting to parse this further, but you would
1497 # have to take into account all the variations like
1498 # Video Title - Site Name
1499 # Site Name | Video Title
1500 # Video Title - Tagline | Site Name
1501 # and so on and so forth; it's just not practical
6f41b2bc
S
1502 video_title = self._og_search_title(
1503 webpage, default=None) or self._html_search_regex(
79649588
PH
1504 r'(?s)<title>(.*?)</title>', webpage, 'video title',
1505 default='video')
ef4fd848 1506
4d805e06
PH
1507 # Try to detect age limit automatically
1508 age_limit = self._rta_search(webpage)
1509 # And then there are the jokers who advertise that they use RTA,
1510 # but actually don't.
1511 AGE_LIMIT_MARKERS = [
1512 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
1513 ]
1514 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
1515 age_limit = 18
1516
ef4fd848
PH
1517 # video uploader is domain name
1518 video_uploader = self._search_regex(
79649588 1519 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 1520
6f41b2bc
S
1521 video_description = self._og_search_description(webpage, default=None)
1522 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
1523
ed2d6a19 1524 # Helper method
83992676 1525 def _playlist_from_matches(matches, getter=None, ie=None):
3b2f933b 1526 urlrs = orderedSet(
83992676 1527 self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
3b2f933b 1528 for m in matches)
ed2d6a19
PH
1529 return self.playlist_result(
1530 urlrs, playlist_id=video_id, playlist_title=video_title)
1531
1f4b722b 1532 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 1533 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 1534 if bc_urls:
79649588 1535 self.to_screen('Brightcove video detected.')
99877772
PH
1536 entries = [{
1537 '_type': 'url',
1538 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 1539 'ie_key': 'BrightcoveLegacy'
99877772
PH
1540 } for bc_url in bc_urls]
1541
1542 return {
1543 '_type': 'playlist',
1544 'title': video_title,
1545 'id': video_id,
1546 'entries': entries,
1547 }
cfe50f04 1548
f6519f89
S
1549 # Look for Brightcove New Studio embeds
1550 bc_urls = BrightcoveNewIE._extract_urls(webpage)
1551 if bc_urls:
1552 return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
ed126900 1553
4d8819d2
S
1554 # Look for ThePlatform embeds
1555 tp_urls = ThePlatformIE._extract_urls(webpage)
1556 if tp_urls:
1557 return _playlist_from_matches(tp_urls, ie='ThePlatform')
1558
48a5eabc
S
1559 # Look for Vessel embeds
1560 vessel_urls = VesselIE._extract_urls(webpage)
1561 if vessel_urls:
1562 return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
1563
59b8ab58
PH
1564 # Look for embedded rtl.nl player
1565 matches = re.findall(
97b570a9 1566 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
59b8ab58
PH
1567 webpage)
1568 if matches:
1569 return _playlist_from_matches(matches, ie='RtlNl')
1570
b407e173
YCH
1571 vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
1572 if vimeo_url is not None:
1573 return self.url_result(vimeo_url)
7115ca84 1574
a1b85269
YCH
1575 vid_me_embed_url = self._search_regex(
1576 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
1577 webpage, 'vid.me embed', default=None)
1578 if vid_me_embed_url is not None:
1579 return self.url_result(vid_me_embed_url, 'Vidme')
1580
53c1d3ef 1581 # Look for embedded YouTube player
1f9da904 1582 matches = re.findall(r'''(?x)
2b88feed
PH
1583 (?:
1584 <iframe[^>]+?src=|
c71dfccc 1585 data-video-url=|
2b88feed 1586 <embed[^>]+?src=|
a7e97f6d
PH
1587 embedSWF\(?:\s*|
1588 new\s+SWFObject\(
2b88feed
PH
1589 )
1590 (["\'])
1bf5423e 1591 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
6b08cdf6 1592 (?:embed|v|p)/.+?)
1f9da904 1593 \1''', webpage)
887c6acd 1594 if matches:
ed2d6a19 1595 return _playlist_from_matches(
3b2f933b 1596 matches, lambda m: unescapeHTML(m[1]))
53c1d3ef 1597
65f3a228
PH
1598 # Look for lazyYT YouTube embed
1599 matches = re.findall(
1600 r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
1601 if matches:
1602 return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
1603
355e4fd0
PH
1604 # Look for embedded Dailymotion player
1605 matches = re.findall(
5a490592 1606 r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
355e4fd0 1607 if matches:
ed2d6a19
PH
1608 return _playlist_from_matches(
1609 matches, lambda m: unescapeHTML(m[1]))
355e4fd0 1610
8489578d
NJ
1611 # Look for embedded Dailymotion playlist player (#3822)
1612 m = re.search(
1613 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
1614 if m:
1615 playlists = re.findall(
1616 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
1617 if playlists:
1618 return _playlist_from_matches(
1619 playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
1620
ef4fd848
PH
1621 # Look for embedded Wistia player
1622 match = re.search(
281d3f1d 1623 r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
ef4fd848 1624 if match:
9471c444
NJ
1625 embed_url = self._proto_relative_url(
1626 unescapeHTML(match.group('url')))
ef4fd848
PH
1627 return {
1628 '_type': 'url_transparent',
9471c444 1629 'url': embed_url,
ef4fd848
PH
1630 'ie_key': 'Wistia',
1631 'uploader': video_uploader,
ef4fd848 1632 }
5f6a1245 1633
9471c444 1634 match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
746c67d7
NJ
1635 if match:
1636 return {
1637 '_type': 'url_transparent',
6c114b12 1638 'url': 'wistia:%s' % match.group('id'),
746c67d7
NJ
1639 'ie_key': 'Wistia',
1640 'uploader': video_uploader,
746c67d7 1641 }
ef4fd848 1642
aa5957ac
S
1643 match = re.search(
1644 r'''(?sx)
1645 <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
1646 <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
1647 ''', webpage)
1648 if match:
1649 return self.url_result(self._proto_relative_url(
1650 'wistia:%s' % match.group('id')), 'Wistia')
1651
bab19a8e
S
1652 # Look for SVT player
1653 svt_url = SVTIE._extract_url(webpage)
1654 if svt_url:
1655 return self.url_result(svt_url, 'SVT')
1656
fa35cdad
PH
1657 # Look for embedded condenast player
1658 matches = re.findall(
1659 r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
1660 webpage)
1661 if matches:
1662 return {
1663 '_type': 'playlist',
1664 'entries': [{
1665 '_type': 'url',
1666 'ie_key': 'CondeNast',
1667 'url': ma,
1668 } for ma in matches],
1669 'title': video_title,
1670 'id': video_id,
1671 }
1672
c19f7764
JMF
1673 # Look for Bandcamp pages with custom domain
1674 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
1675 if mobj is not None:
1676 burl = unescapeHTML(mobj.group(1))
09804265
JMF
1677 # Don't set the extractor because it can be a track url or an album
1678 return self.url_result(burl)
c19f7764 1679
f25571ff
PH
1680 # Look for embedded Vevo player
1681 mobj = re.search(
1682 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
1683 if mobj is not None:
1684 return self.url_result(mobj.group('url'))
796df3c6
S
1685
1686 # Look for embedded Viddler player
cb454b33
S
1687 mobj = re.search(
1688 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
1689 webpage)
796df3c6
S
1690 if mobj is not None:
1691 return self.url_result(mobj.group('url'))
f25571ff 1692
3378d67a
S
1693 # Look for NYTimes player
1694 mobj = re.search(
1695 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
1696 webpage)
1697 if mobj is not None:
1698 return self.url_result(mobj.group('url'))
1699
cefdf970
S
1700 # Look for Libsyn player
1701 mobj = re.search(
1702 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
1703 if mobj is not None:
1704 return self.url_result(mobj.group('url'))
1705
c0d0b01f 1706 # Look for Ooyala videos
8a37aa15 1707 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 1708 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
1709 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
1710 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 1711 if mobj is not None:
cce9d15d 1712 return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url}))
c0d0b01f 1713
f076b638 1714 # Look for multiple Ooyala embeds on SBN network websites
1715 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
1716 if mobj is not None:
1717 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
1718 if embeds:
1719 return _playlist_from_matches(
cce9d15d 1720 embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 1721
aa94a6d3 1722 # Look for Aparat videos
48099643 1723 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
1724 if mobj is not None:
1725 return self.url_result(mobj.group(1), 'Aparat')
1726
c93c2ab1 1727 # Look for MPORA videos
c3f51436 1728 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
1729 if mobj is not None:
1730 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 1731
15c0e8e7 1732 # Look for embedded NovaMov-based player
8f89e687 1733 mobj = re.search(
8dfa187b 1734 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
1735 (?P<url>http://(?:(?:embed|www)\.)?
1736 (?:novamov\.com|
1737 nowvideo\.(?:ch|sx|eu|at|ag|co)|
1738 videoweed\.(?:es|com)|
1739 movshare\.(?:net|sx|ag)|
1740 divxstage\.(?:eu|net|ch|co|at|ag))
1741 /embed\.php.+?)\1''', webpage)
8f89e687 1742 if mobj is not None:
15c0e8e7 1743 return self.url_result(mobj.group('url'))
50f56607 1744
9834872b
PH
1745 # Look for embedded Facebook player
1746 mobj = re.search(
db1f3888 1747 r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
9834872b
PH
1748 if mobj is not None:
1749 return self.url_result(mobj.group('url'), 'Facebook')
1750
ca97a56e
S
1751 # Look for embedded VK player
1752 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
1753 if mobj is not None:
1754 return self.url_result(mobj.group('url'), 'VK')
1755
33d4fdab
S
1756 # Look for embedded Odnoklassniki player
1757 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
1758 if mobj is not None:
1759 return self.url_result(mobj.group('url'), 'Odnoklassniki')
1760
0364fa8b
S
1761 # Look for embedded ivi player
1762 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
1763 if mobj is not None:
1764 return self.url_result(mobj.group('url'), 'Ivi')
1765
db1f3888
PH
1766 # Look for embedded Huffington Post player
1767 mobj = re.search(
c3f51436 1768 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
1769 if mobj is not None:
1770 return self.url_result(mobj.group('url'), 'HuffPost')
1771
1b86cc41 1772 # Look for embed.ly
1773 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
1774 if mobj is not None:
1775 return self.url_result(mobj.group('url'))
1776 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
1777 if mobj is not None:
f7e6f7fa 1778 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 1779
60cc4dc4
PH
1780 # Look for funnyordie embed
1781 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
1782 if matches:
ed2d6a19
PH
1783 return _playlist_from_matches(
1784 matches, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 1785
db546cf8
S
1786 # Look for BBC iPlayer embed
1787 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
1788 if matches:
476eae0c 1789 return _playlist_from_matches(matches, ie='BBCCoUk')
db546cf8 1790
93d020dd
S
1791 # Look for embedded RUTV player
1792 rutv_url = RUTVIE._extract_url(webpage)
1793 if rutv_url:
1794 return self.url_result(rutv_url, 'RUTV')
1795
494f20cb 1796 # Look for embedded TVC player
b8599718
S
1797 tvc_url = TVCIE._extract_url(webpage)
1798 if tvc_url:
1799 return self.url_result(tvc_url, 'TVC')
494f20cb 1800
d40a3b5b
S
1801 # Look for embedded SportBox player
1802 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
1803 if sportbox_urls:
1804 return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
1805
78e2b74b 1806 # Look for embedded PornHub player
65d161c4
S
1807 pornhub_url = PornHubIE._extract_url(webpage)
1808 if pornhub_url:
1809 return self.url_result(pornhub_url, 'PornHub')
1810
2bb5b6d0
S
1811 # Look for embedded XHamster player
1812 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
1813 if xhamster_urls:
1814 return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
1815
2c9ca782
S
1816 # Look for embedded TNAFlixNetwork player
1817 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
1818 if tnaflix_urls:
1819 return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
1820
9872d311
S
1821 # Look for embedded Tvigle player
1822 mobj = re.search(
1823 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
1824 if mobj is not None:
1825 return self.url_result(mobj.group('url'), 'Tvigle')
1826
7e2ede98
JMF
1827 # Look for embedded TED player
1828 mobj = re.search(
d7cc31b6 1829 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
1830 if mobj is not None:
1831 return self.url_result(mobj.group('url'), 'TED')
1832
5c386252 1833 # Look for embedded Ustream videos
1834 mobj = re.search(
1835 r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
1836 if mobj is not None:
1837 return self.url_result(mobj.group('url'), 'Ustream')
1838
893f8832
PH
1839 # Look for embedded arte.tv player
1840 mobj = re.search(
134c207e 1841 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
1842 webpage)
1843 if mobj is not None:
1844 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
1845
cbd55ade
S
1846 # Look for embedded francetv player
1847 mobj = re.search(
1848 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
1849 webpage)
1850 if mobj is not None:
1851 return self.url_result(mobj.group('url'))
1852
cb3ac1c6
S
1853 # Look for embedded smotri.com player
1854 smotri_url = SmotriIE._extract_url(webpage)
1855 if smotri_url:
1856 return self.url_result(smotri_url, 'Smotri')
1857
e6c2d9ad 1858 # Look for embedded Myvi.ru player
6dd94d3a 1859 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
1860 if myvi_url:
1861 return self.url_result(myvi_url)
1862
dfb1b146 1863 # Look for embedded soundcloud player
20991253 1864 mobj = re.search(
ac645ac7 1865 r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
20991253
PH
1866 webpage)
1867 if mobj is not None:
1868 url = unescapeHTML(mobj.group('url'))
1869 return self.url_result(url)
1870
c5cd249e 1871 # Look for embedded mtvservices player
46fde8a1
S
1872 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
1873 if mtvservices_url:
1874 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 1875
49807b4a
S
1876 # Look for embedded yahoo player
1877 mobj = re.search(
1878 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
1879 webpage)
1880 if mobj is not None:
1881 return self.url_result(mobj.group('url'), 'Yahoo')
1882
2ef6fcb5
PH
1883 # Look for embedded sbs.com.au player
1884 mobj = re.search(
e98b8e79
PH
1885 r'''(?x)
1886 (?:
1887 <meta\s+property="og:video"\s+content=|
1888 <iframe[^>]+?src=
1889 )
1890 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
1891 webpage)
1892 if mobj is not None:
1893 return self.url_result(mobj.group('url'), 'SBS')
1894
42bdd9d0
PH
1895 # Look for embedded Cinchcast player
1896 mobj = re.search(
1897 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
1898 webpage)
1899 if mobj is not None:
1900 return self.url_result(mobj.group('url'), 'Cinchcast')
1901
1a94ff68 1902 mobj = re.search(
5263cdfc 1903 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 1904 webpage)
8001607e
YCH
1905 if not mobj:
1906 mobj = re.search(
1907 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
1908 webpage)
1a94ff68
S
1909 if mobj is not None:
1910 return self.url_result(mobj.group('url'), 'MLB')
1911
1419fafd 1912 mobj = re.search(
dd467d33 1913 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
1914 webpage)
1915 if mobj is not None:
1916 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
1917
af63fed7 1918 mobj = re.search(
78d3b3e2 1919 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
1920 webpage)
1921 if mobj is not None:
1922 return self.url_result(mobj.group('url'), 'Livestream')
1923
255fca5e
S
1924 # Look for Zapiks embed
1925 mobj = re.search(
1926 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
1927 if mobj is not None:
1928 return self.url_result(mobj.group('url'), 'Zapiks')
1929
e3216b82 1930 # Look for Kaltura embeds
c287f2bc
S
1931 kaltura_url = KalturaIE._extract_url(webpage)
1932 if kaltura_url:
1933 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 1934
135c9c42 1935 # Look for Eagle.Platform embeds
06a96da1
S
1936 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
1937 if eagleplatform_url:
1938 return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
135c9c42 1939
d47ae7f6
S
1940 # Look for ClipYou (uses Eagle.Platform) embeds
1941 mobj = re.search(
1942 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
1943 if mobj is not None:
1944 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
1945
f8388757 1946 # Look for Pladform embeds
45dad7ba
S
1947 pladform_url = PladformIE._extract_url(webpage)
1948 if pladform_url:
1949 return self.url_result(pladform_url)
f8388757 1950
ff18735c
S
1951 # Look for Videomore embeds
1952 videomore_url = VideomoreIE._extract_url(webpage)
1953 if videomore_url:
1954 return self.url_result(videomore_url)
1955
2dcc114f
S
1956 # Look for Playwire embeds
1957 mobj = re.search(
1958 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
1959 if mobj is not None:
1960 return self.url_result(mobj.group('url'))
1961
ad320e9b
NJ
1962 # Look for 5min embeds
1963 mobj = re.search(
1964 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
1965 if mobj is not None:
1966 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
1967
18153f1b
S
1968 # Look for Crooks and Liars embeds
1969 mobj = re.search(
1970 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
1971 if mobj is not None:
1972 return self.url_result(mobj.group('url'))
1973
a2edf2e7
YCH
1974 # Look for NBC Sports VPlayer embeds
1975 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
1976 if nbc_sports_url:
1977 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
1978
de3eb07e
YCH
1979 # Look for NBC News embeds
1980 nbc_news_embed_url = re.search(
1981 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
1982 if nbc_news_embed_url:
1983 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
1984
653789af 1985 # Look for Google Drive embeds
5b251628 1986 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 1987 if google_drive_url:
1988 return self.url_result(google_drive_url, 'GoogleDrive')
1989
418c5cc3
YCH
1990 # Look for UDN embeds
1991 mobj = re.search(
c39fd7b1 1992 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
1993 if mobj is not None:
1994 return self.url_result(
0a160363 1995 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 1996
2fe1b5bd
YCH
1997 # Look for Senate ISVP iframe
1998 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
1999 if senate_isvp_url:
25c3a734 2000 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2001
756f574e
YCH
2002 # Look for Dailymotion Cloud videos
2003 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2004 if dmcloud_url:
2005 return self.url_result(dmcloud_url, 'DailymotionCloud')
2006
1ac1c4c2
S
2007 # Look for OnionStudios embeds
2008 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2009 if onionstudios_url:
2010 return self.url_result(onionstudios_url)
2011
67167920 2012 # Look for ViewLift embeds
2013 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2014 if viewlift_url:
2015 return self.url_result(viewlift_url)
eedd20ef 2016
7cb09524 2017 # Look for JWPlatform embeds
2018 jwplatform_url = JWPlatformIE._extract_url(webpage)
2019 if jwplatform_url:
2020 return self.url_result(jwplatform_url, 'JWPlatform')
2021
8ca31a0e 2022 # Look for ScreenwaveMedia embeds
efd712c6 2023 mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage)
8ca31a0e 2024 if mobj is not None:
efd712c6 2025 return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia')
8ca31a0e 2026
aecfcd4e
S
2027 # Look for Digiteka embeds
2028 digiteka_url = DigitekaIE._extract_url(webpage)
2029 if digiteka_url:
2030 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2031
1bf996fa 2032 # Look for Limelight embeds
2033 mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
2034 if mobj:
2035 lm = {
2036 'Media': 'media',
2037 'Channel': 'channel',
2038 'ChannelList': 'channel_list',
2039 }
2040 return self.url_result('limelight:%s:%s' % (
2041 lm[mobj.group(1)], mobj.group(2)), 'Limelight%s' % mobj.group(1), mobj.group(2))
2042
a5158f38
YCH
2043 # Look for AdobeTVVideo embeds
2044 mobj = re.search(
2045 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2046 webpage)
2047 if mobj is not None:
2048 return self.url_result(
2049 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2050 'AdobeTVVideo')
2051
088e1aac
YCH
2052 # Look for Vine embeds
2053 mobj = re.search(
2054 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2055 webpage)
2056 if mobj is not None:
2057 return self.url_result(
2058 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2059
5a51775a
YCH
2060 # Look for Instagram embeds
2061 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2062 if instagram_embed_url is not None:
11e60fca
S
2063 return self.url_result(
2064 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2065
b8f67449
KM
2066 # Look for LiveLeak embeds
2067 liveleak_url = LiveLeakIE._extract_url(webpage)
2068 if liveleak_url:
2069 return self.url_result(liveleak_url, 'LiveLeak')
2070
5d39176f
S
2071 # Look for 3Q SDN embeds
2072 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2073 if threeqsdn_url:
6f41b2bc
S
2074 return {
2075 '_type': 'url_transparent',
2076 'ie_key': ThreeQSDNIE.ie_key(),
2077 'url': self._proto_relative_url(threeqsdn_url),
2078 'title': video_title,
2079 'description': video_description,
2080 'thumbnail': video_thumbnail,
2081 'uploader': video_uploader,
2082 }
5d39176f 2083
ced659bb 2084 def check_video(vurl):
a0f71985
PH
2085 if YoutubeIE.suitable(vurl):
2086 return True
ced659bb
S
2087 vpath = compat_urlparse.urlparse(vurl).path
2088 vext = determine_ext(vpath)
2089 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
2090
2091 def filter_video(urls):
2092 return list(filter(check_video, urls))
2093
9b122384 2094 # Start with something easy: JW Player in SWFObject
ced659bb 2095 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 2096 if not found:
d981cef6 2097 # Look for gorilla-vid style embedding
ced659bb 2098 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
2099 (?:
2100 jw_plugins|
2101 JWPlayerOptions|
2102 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2103 )
a0f71985
PH
2104 .*?
2105 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 2106 if not found:
9b122384 2107 # Broaden the search a little bit
ced659bb 2108 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
2109 if not found:
2110 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 2111 found = filter_video(re.findall(
54a9328b 2112 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
2113 if not found:
2114 # Flow player
ced659bb 2115 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
2116 flowplayer\("[^"]+",\s*
2117 \{[^}]+?\}\s*,
52585fd6 2118 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 2119 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 2120 ''', webpage))
501f13fb
PH
2121 if not found:
2122 # Cinerama player
2123 found = re.findall(
2124 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 2125 if not found:
9b122384 2126 # Try to find twitter cards info
ced659bb
S
2127 found = filter_video(re.findall(
2128 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 2129 if not found:
9b122384
PH
2130 # We look for Open Graph info:
2131 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 2132 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
2133 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
2134 if m_video_type is not None:
ced659bb 2135 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 2136 if not found:
7fea7156 2137 # HTML5 video
12439dd5 2138 found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
b30b8698 2139 if not found:
ed9a25dd 2140 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 2141 found = re.search(
89ef304b 2142 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 2143 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 2144 webpage)
84f81016
S
2145 if not found:
2146 # Look also in Refresh HTTP header
2147 refresh_header = head_response.headers.get('Refresh')
2148 if refresh_header:
6c91a5a7
S
2149 # In python 2 response HTTP headers are bytestrings
2150 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
2151 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 2152 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 2153 if found:
b37317d8 2154 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
89ef304b
PH
2155 self.report_following_redirect(new_url)
2156 return {
2157 '_type': 'url',
2158 'url': new_url,
2159 }
b30b8698 2160 if not found:
416c7fcb 2161 raise UnsupportedError(url)
9b122384 2162
b30b8698 2163 entries = []
4a120778 2164 for video_url in orderedSet(found):
949b6497 2165 video_url = unescapeHTML(video_url)
6cc37c69 2166 video_url = video_url.replace('\\/', '/')
b30b8698 2167 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 2168 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 2169
b30b8698
PH
2170 # Sometimes, jwplayer extraction will result in a YouTube URL
2171 if YoutubeIE.suitable(video_url):
2172 entries.append(self.url_result(video_url, 'Youtube'))
2173 continue
9b122384 2174
b30b8698
PH
2175 # here's a fun little line of code for you:
2176 video_id = os.path.splitext(video_id)[0]
fc9713a1 2177
28602e74
YCH
2178 entry_info_dict = {
2179 'id': video_id,
2180 'uploader': video_uploader,
2181 'title': video_title,
2182 'age_limit': age_limit,
2183 }
2184
729accb4
S
2185 ext = determine_ext(video_url)
2186 if ext == 'smil':
28602e74 2187 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
2188 elif ext == 'xspf':
2189 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
2190 elif ext == 'm3u8':
2191 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
2192 elif ext == 'mpd':
2193 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
2194 elif ext == 'f4m':
2195 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
d6fd958c 2196 else:
28602e74
YCH
2197 entry_info_dict['url'] = video_url
2198
19dbaeec
S
2199 if entry_info_dict.get('formats'):
2200 self._sort_formats(entry_info_dict['formats'])
2201
28602e74 2202 entries.append(entry_info_dict)
b30b8698
PH
2203
2204 if len(entries) == 1:
669f0e7c 2205 return entries[0]
b30b8698
PH
2206 else:
2207 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
2208 # 'url' results don't have a title
2209 if e.get('title') is not None:
2210 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
2211 return {
2212 '_type': 'playlist',
2213 'entries': entries,
2214 }