]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
release 2017.10.01
[yt-dlp.git] / youtube_dl / extractor / generic.py
CommitLineData
dcdb292f 1# coding: utf-8
cfe50f04 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,
4e363703 13 compat_str,
1ddb9456 14 compat_urllib_parse_unquote,
a5caba1e 15 compat_urlparse,
f7300c5c 16 compat_xml_parse_error,
8c25f81b
PH
17)
18from ..utils import (
b759a0d4 19 determine_ext,
9b122384 20 ExtractorError,
c8e9a235 21 float_or_none,
aa94a6d3 22 HEADRequest,
61ca9a80 23 is_html,
a4a554a7 24 js_to_json,
63d990d2
S
25 KNOWN_EXTENSIONS,
26 mimetype2ext,
ed2d6a19 27 orderedSet,
5c2266df 28 sanitized_Request,
9d4660ca
PH
29 smuggle_url,
30 unescapeHTML,
42393ce2 31 unified_strdate,
4d54ef20 32 unsmuggle_url,
416c7fcb 33 UnsupportedError,
76c73715 34 xpath_text,
9b122384 35)
b7a8c1bc 36from .commonprotocols import RtmpIE
ed126900 37from .brightcove import (
4fcaa4f4 38 BrightcoveLegacyIE,
5c17f0a6 39 BrightcoveNewIE,
ed126900 40)
3f59b015
S
41from .nexx import (
42 NexxIE,
43 NexxEmbedIE,
44)
a2edf2e7 45from .nbc import NBCSportsVPlayerIE
c0d0b01f 46from .ooyala import OoyalaIE
93d020dd 47from .rutv import RUTVIE
954c1d05 48from .tvc import TVCIE
d40a3b5b 49from .sportbox import SportBoxEmbedIE
cb3ac1c6 50from .smotri import SmotriIE
6dd94d3a 51from .myvi import MyviIE
1419fafd 52from .condenast import CondeNastIE
418c5cc3 53from .udn import UDNEmbedIE
2fe1b5bd 54from .senateisvp import SenateISVPIE
bab19a8e 55from .svt import SVTIE
65d161c4 56from .pornhub import PornHubIE
2bb5b6d0 57from .xhamster import XHamsterEmbedIE
2c9ca782 58from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 59from .drtuber import DrTuberIE
e28ed498 60from .redtube import RedTubeIE
b407e173 61from .vimeo import VimeoIE
ad213a1d
YCH
62from .dailymotion import (
63 DailymotionIE,
64 DailymotionCloudIE,
65)
71a1db89 66from .dailymail import DailyMailIE
1ac1c4c2 67from .onionstudios import OnionStudiosIE
67167920 68from .viewlift import ViewLiftEmbedIE
46fde8a1 69from .mtv import MTVServicesEmbeddedIE
45dad7ba 70from .pladform import PladformIE
ff18735c 71from .videomore import VideomoreIE
83f1481b 72from .webcaster import WebcasterFeedIE
5b251628 73from .googledrive import GoogleDriveIE
7cb09524 74from .jwplatform import JWPlatformIE
aecfcd4e 75from .digiteka import DigitekaIE
1979969f 76from .arkena import ArkenaIE
5a51775a 77from .instagram import InstagramIE
b8f67449 78from .liveleak import LiveLeakIE
5d39176f 79from .threeqsdn import ThreeQSDNIE
4d8819d2 80from .theplatform import ThePlatformIE
48a5eabc 81from .vessel import VesselIE
c287f2bc 82from .kaltura import KalturaIE
06a96da1 83from .eagleplatform import EaglePlatformIE
fd6ca382 84from .facebook import FacebookIE
94aae015 85from .soundcloud import SoundcloudIE
027e2312 86from .tunein import TuneInBaseIE
2a1321a2 87from .vbox7 import Vbox7IE
b0c8f2e9 88from .dbtv import DBTVIE
b1c35797 89from .piksel import PikselIE
e186a9ec 90from .videa import VideaIE
b687c85e 91from .twentymin import TwentyMinutenIE
d77ac737 92from .ustream import UstreamIE
17f8deeb 93from .openload import OpenloadIE
6ef3e65a 94from .videopress import VideoPressIE
eb3079b6 95from .rutube import RutubeIE
e5d39886 96from .limelight import LimelightBaseIE
7986c3ab 97from .anvato import AnvatoIE
55719459 98from .washingtonpost import WashingtonPostIE
58bb4402 99from .wistia import WistiaIE
5d29af3d 100from .mediaset import MediasetIE
73cf76a9 101from .joj import JojIE
24e966e8 102from .megaphone import MegaphoneIE
41918eaa 103from .vzaar import VzaarIE
9b122384 104
0838239e 105
9b122384 106class GenericIE(InfoExtractor):
79649588 107 IE_DESC = 'Generic downloader that works on some sites'
9b122384 108 _VALID_URL = r'.*'
79649588 109 IE_NAME = 'generic'
cfe50f04 110 _TESTS = [
c5fa81fe
S
111 # Direct link to a video
112 {
113 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
114 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
115 'info_dict': {
116 'id': 'trailer',
117 'ext': 'mp4',
118 'title': 'trailer',
119 'upload_date': '20100513',
120 }
121 },
c5138a7c 122 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
123 {
124 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
125 'md5': '128c42e68b13950268b648275386fc74',
126 'info_dict': {
127 'id': 'FictionJunction-Parallel_Hearts',
128 'ext': 'flac',
129 'title': 'FictionJunction-Parallel_Hearts',
130 'upload_date': '20140522',
131 },
132 'expected_warnings': [
133 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
134 ],
135 'skip': 'URL invalid',
c5fa81fe
S
136 },
137 # Direct download with broken HEAD
138 {
139 'url': 'http://ai-radio.org:8000/radio.opus',
140 'info_dict': {
141 'id': 'radio',
142 'ext': 'opus',
143 'title': 'radio',
144 },
145 'params': {
146 'skip_download': True, # infinite live stream
147 },
148 'expected_warnings': [
ef0e4e7b
YCH
149 r'501.*Not Implemented',
150 r'400.*Bad Request',
c5fa81fe
S
151 ],
152 },
153 # Direct link with incorrect MIME type
154 {
155 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
156 'md5': '4ccbebe5f36706d85221f204d7eb5913',
157 'info_dict': {
158 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
159 'id': '5_Lennart_Poettering_-_Systemd',
160 'ext': 'webm',
161 'title': '5_Lennart_Poettering_-_Systemd',
162 'upload_date': '20141120',
163 },
164 'expected_warnings': [
165 'URL could be a direct video link, returning it as such.'
166 ]
167 },
168 # RSS feed
169 {
170 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
171 'info_dict': {
172 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
173 'title': 'Zero Punctuation',
174 'description': 're:.*groundbreaking video review series.*'
175 },
176 'playlist_mincount': 11,
177 },
178 # RSS feed with enclosure
179 {
180 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
181 'info_dict': {
182 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
183 'ext': 'm4v',
184 'upload_date': '20150228',
185 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
186 }
187 },
8765222d
S
188 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
189 {
190 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
191 'info_dict': {
192 'id': 'smil',
193 'ext': 'mp4',
194 'title': 'Automatics, robotics and biocybernetics',
195 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 196 'upload_date': '20130627',
8765222d
S
197 'formats': 'mincount:16',
198 'subtitles': 'mincount:1',
199 },
200 'params': {
201 'force_generic_extractor': True,
202 'skip_download': True,
203 },
204 },
205 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
206 {
207 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
208 'info_dict': {
209 'id': 'hds',
210 'ext': 'flv',
211 'title': 'hds',
212 'formats': 'mincount:1',
213 },
214 'params': {
215 'skip_download': True,
216 },
217 },
218 # SMIL from https://www.restudy.dk/video/play/id/1637
219 {
220 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
221 'info_dict': {
222 'id': 'video_1637',
223 'ext': 'flv',
224 'title': 'video_1637',
225 'formats': 'mincount:3',
226 },
227 'params': {
228 'skip_download': True,
229 },
230 },
231 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
232 {
233 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
234 'info_dict': {
235 'id': 'smil-service',
236 'ext': 'flv',
237 'title': 'smil-service',
238 'formats': 'mincount:1',
239 },
240 'params': {
241 'skip_download': True,
242 },
243 },
244 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
245 {
246 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
247 'info_dict': {
248 'id': '4719370',
249 'ext': 'mp4',
250 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
251 'formats': 'mincount:3',
252 },
253 'params': {
254 'skip_download': True,
255 },
256 },
1de5cd3b
S
257 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
258 {
259 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
260 'info_dict': {
261 'id': 'mZlp2ctYIUEB',
262 'ext': 'mp4',
263 'title': 'Tikibad ontruimd wegens brand',
264 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 265 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
266 'duration': 33,
267 },
268 'params': {
269 'skip_download': True,
270 },
271 },
9d939cec
S
272 # MPD from http://dash-mse-test.appspot.com/media.html
273 {
274 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
275 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
276 'info_dict': {
277 'id': 'car-20120827-manifest',
278 'ext': 'mp4',
279 'title': 'car-20120827-manifest',
280 'formats': 'mincount:9',
0738187f 281 'upload_date': '20130904',
9d939cec
S
282 },
283 'params': {
284 'format': 'bestvideo',
285 },
286 },
20938f76
S
287 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
288 {
289 'url': 'http://once.unicornmedia.com/now/master/playlist/bb0b18ba-64f5-4b1b-a29f-0ac252f06b68/77a785f3-5188-4806-b788-0893a61634ed/93677179-2d99-4ef4-9e17-fe70d49abfbf/content.m3u8',
290 'info_dict': {
291 'id': 'content',
292 'ext': 'mp4',
293 'title': 'content',
294 'formats': 'mincount:8',
295 },
296 'params': {
297 # m3u8 downloads
298 'skip_download': True,
39efc6e3
YCH
299 },
300 'skip': 'video gone',
20938f76 301 },
edd9b71c
S
302 # m3u8 served with Content-Type: text/plain
303 {
304 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
305 'info_dict': {
306 'id': 'index',
307 'ext': 'mp4',
308 'title': 'index',
309 'upload_date': '20140720',
310 'formats': 'mincount:11',
311 },
312 'params': {
313 # m3u8 downloads
314 'skip_download': True,
39efc6e3
YCH
315 },
316 'skip': 'video gone',
edd9b71c 317 },
c5fa81fe
S
318 # google redirect
319 {
320 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE',
321 'info_dict': {
322 'id': 'cmQHVoWB5FY',
323 'ext': 'mp4',
324 'upload_date': '20130224',
325 'uploader_id': 'TheVerge',
ec85ded8 326 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
327 'uploader': 'The Verge',
328 'title': 'First Firefox OS phones side-by-side',
329 },
330 'params': {
331 'skip_download': False,
332 }
333 },
6c91a5a7
S
334 {
335 # redirect in Refresh HTTP header
336 'url': 'https://www.facebook.com/l.php?u=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DpO8h3EaFRdo&h=TAQHsoToz&enc=AZN16h-b6o4Zq9pZkCCdOLNKMN96BbGMNtcFwHSaazus4JHT_MFYkAA-WARTX2kvsCIdlAIyHZjl6d33ILIJU7Jzwk_K3mcenAXoAzBNoZDI_Q7EXGDJnIhrGkLXo_LJ_pAa2Jzbx17UHMd3jAs--6j2zaeto5w9RTn8T_1kKg3fdC5WPX9Dbb18vzH7YFX0eSJmoa6SP114rvlkw6pkS1-T&s=1',
337 'info_dict': {
338 'id': 'pO8h3EaFRdo',
339 'ext': 'mp4',
340 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
341 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
342 'upload_date': '20150917',
343 'uploader_id': 'brtvofficial',
344 'uploader': 'Boiler Room',
345 },
346 'params': {
347 'skip_download': False,
348 },
349 },
cfe50f04 350 {
79649588 351 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 352 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 353 'info_dict': {
d360a146
S
354 'id': '13601338388002',
355 'ext': 'mp4',
79649588
PH
356 'uploader': 'www.hodiho.fr',
357 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
358 }
359 },
c19f7764
JMF
360 # bandcamp page with custom domain
361 {
79649588
PH
362 'add_ie': ['Bandcamp'],
363 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 364 'info_dict': {
fd50bf62
S
365 'id': '3235767654',
366 'ext': 'mp3',
79649588
PH
367 'title': 'The Pony Mash',
368 'uploader': 'M_Pallante',
c19f7764 369 },
79649588 370 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 371 },
eeb165e6 372 {
53a664ed
S
373 # embedded brightcove video
374 # it also tests brightcove videos that need to set the 'Referer'
375 # in the http requests
3b7d9aa4 376 'add_ie': ['BrightcoveLegacy'],
79649588
PH
377 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
378 'info_dict': {
379 'id': '2765128793001',
380 'ext': 'mp4',
381 'title': 'Le cours de bourse : l’analyse technique',
382 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
383 'uploader': 'BFM BUSINESS',
eeb165e6 384 },
79649588
PH
385 'params': {
386 'skip_download': True,
eeb165e6
JMF
387 },
388 },
53a664ed
S
389 {
390 # embedded with itemprop embedURL and video id spelled as `idVideo`
391 'add_id': ['BrightcoveLegacy'],
392 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
393 'info_dict': {
394 'id': '5255628253001',
395 'ext': 'mp4',
396 'title': 'md5:37c519b1128915607601e75a87995fc0',
397 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
398 'uploader': 'BFM BUSINESS',
399 'uploader_id': '876450612001',
400 'timestamp': 1482255315,
401 'upload_date': '20161220',
402 },
403 'params': {
404 'skip_download': True,
405 },
406 },
17ab4d3b
PH
407 {
408 # https://github.com/rg3/youtube-dl/issues/2253
409 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
410 'md5': '0ba9446db037002366bab3b3eb30c88c',
411 'info_dict': {
fd50bf62
S
412 'id': '3101154703001',
413 'ext': 'mp4',
17ab4d3b
PH
414 'title': 'Still no power',
415 'uploader': 'thestar.com',
416 'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
417 },
3b7d9aa4 418 'add_ie': ['BrightcoveLegacy'],
39efc6e3 419 'skip': 'video gone',
17ab4d3b 420 },
0479c625
S
421 {
422 'url': 'http://www.championat.com/video/football/v/87/87499.html',
423 'md5': 'fb973ecf6e4a78a67453647444222983',
424 'info_dict': {
425 'id': '3414141473001',
426 'ext': 'mp4',
427 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
428 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
429 'uploader': 'Championat',
430 },
431 },
bdf97017 432 {
37aab278 433 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 434 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
435 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
436 'info_dict': {
437 'id': '3866516442001',
37aab278 438 'ext': 'mp4',
bdf97017
NJ
439 'title': 'Leer mij vrouwen kennen: Aflevering 1',
440 'description': 'Leer mij vrouwen kennen: Aflevering 1',
441 'uploader': 'SBS Broadcasting',
442 },
37aab278 443 'skip': 'Restricted to Netherlands',
bdf97017 444 'params': {
37aab278 445 'skip_download': True, # m3u8 download
bdf97017
NJ
446 },
447 },
06d0ad9a
YCH
448 {
449 # Brightcove video in <iframe>
450 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
451 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
452 'info_dict': {
453 'id': '5360463607001',
454 'ext': 'mp4',
455 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
456 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
457 'uploader': 'United Nations',
458 'uploader_id': '1362235914001',
459 'timestamp': 1489593889,
460 'upload_date': '20170315',
461 },
462 'add_ie': ['BrightcoveLegacy'],
463 },
16e2c8f7
YCH
464 {
465 # Brightcove with alternative playerID key
466 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
467 'info_dict': {
468 'id': 'nmeth.2062_SV1',
469 'title': 'Simultaneous multiview imaging of the Drosophila syncytial blastoderm : Quantitative high-speed imaging of entire developing embryos with simultaneous multiview light-sheet microscopy : Nature Methods : Nature Research',
470 },
471 'playlist': [{
472 'info_dict': {
473 'id': '2228375078001',
474 'ext': 'mp4',
475 'title': 'nmeth.2062-sv1',
476 'description': 'nmeth.2062-sv1',
477 'timestamp': 1363357591,
478 'upload_date': '20130315',
479 'uploader': 'Nature Publishing Group',
480 'uploader_id': '1964492299001',
481 },
482 }],
483 },
40158f55
JH
484 {
485 # Brightcove with UUID in videoPlayer
486 'url': 'http://www8.hp.com/cn/zh/home.html',
487 'info_dict': {
488 'id': '5255815316001',
489 'ext': 'mp4',
490 'title': 'Sprocket Video - China',
491 'description': 'Sprocket Video - China',
492 'uploader': 'HP-Video Gallery',
493 'timestamp': 1482263210,
494 'upload_date': '20161220',
495 'uploader_id': '1107601872001',
496 },
497 'params': {
498 'skip_download': True, # m3u8 download
499 },
500 'skip': 'video rotates...weekly?',
501 },
502 {
503 # Brightcove:new type [2].
504 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
505 'md5': '2b35148fcf48da41c9fb4591650784f3',
506 'info_dict': {
507 'id': '5348741021001',
508 'ext': 'mp4',
509 'upload_date': '20170306',
510 'uploader_id': '4191638492001',
511 'timestamp': 1488769918,
512 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
513
514 },
515 },
516 {
517 # Alternative brightcove <video> attributes
518 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
519 'info_dict': {
520 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
521 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
522 },
523 'playlist': [{
524 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
525 'info_dict': {
526 'id': '5311302538001',
527 'ext': 'mp4',
528 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
529 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
530 'timestamp': 1486321708,
531 'upload_date': '20170205',
532 'uploader_id': '800000640001',
533 },
534 'only_matching': True,
535 }],
536 },
b68a812e
S
537 {
538 # Brightcove with UUID in videoPlayer
539 'url': 'http://www8.hp.com/cn/zh/home.html',
540 'info_dict': {
541 'id': '5255815316001',
542 'ext': 'mp4',
543 'title': 'Sprocket Video - China',
544 'description': 'Sprocket Video - China',
545 'uploader': 'HP-Video Gallery',
546 'timestamp': 1482263210,
547 'upload_date': '20161220',
548 'uploader_id': '1107601872001',
549 },
550 'params': {
551 'skip_download': True, # m3u8 download
552 },
553 },
c0d0b01f
JMF
554 # ooyala video
555 {
79649588 556 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 557 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
558 'info_dict': {
559 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
560 'ext': 'mp4',
3486df38 561 'title': '2cc213299525360.mov', # that's what we get
53e06b25 562 'duration': 238.231,
c0d0b01f 563 },
87830900 564 'add_ie': ['Ooyala'],
c0d0b01f 565 },
bf94d763
S
566 {
567 # ooyala video embedded with http://player.ooyala.com/iframe.js
568 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
569 'info_dict': {
570 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
571 'ext': 'mp4',
572 'title': '"Steve Jobs: Man in the Machine" trailer',
573 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 574 'duration': 135.427,
bf94d763
S
575 },
576 'params': {
577 'skip_download': True,
578 },
39efc6e3 579 'skip': 'movie expired',
bf94d763 580 },
198d4cb4
GR
581 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
582 {
583 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
584 'info_dict': {
585 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
586 'ext': 'mp4',
587 'title': 'Steampunk Fest Comes to Honesdale',
588 'duration': 43.276,
589 },
590 'params': {
591 'skip_download': True,
592 }
593 },
1b86cc41 594 # embed.ly video
595 {
596 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
597 'info_dict': {
598 'id': '9ODmcdjQcHQ',
599 'ext': 'mp4',
0a5bce56
PH
600 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
601 'upload_date': '20140225',
602 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
603 'uploader': 'Tested',
604 'uploader_id': 'testedcom',
1b86cc41 605 },
606 # No need to test YoutubeIE here
607 'params': {
608 'skip_download': True,
609 },
610 },
60cc4dc4
PH
611 # funnyordie embed
612 {
613 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
614 'info_dict': {
615 'id': '18e820ec3f',
616 'ext': 'mp4',
617 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
618 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 619 },
39efc6e3
YCH
620 # HEAD requests lead to endless 301, while GET is OK
621 'expected_warnings': ['301'],
60cc4dc4 622 },
93d020dd
S
623 # RUTV embed
624 {
625 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
626 'info_dict': {
627 'id': '776940',
628 'ext': 'mp4',
629 'title': 'Охотское море стало целиком российским',
630 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
631 },
632 'params': {
633 # m3u8 download
634 'skip_download': True,
635 },
aab74fa1 636 },
f37bdbe5
S
637 # TVC embed
638 {
639 'url': 'http://sch1298sz.mskobr.ru/dou_edu/karamel_ki/filial_galleries/video/iframe_src_http_tvc_ru_video_iframe_id_55304_isplay_false_acc_video_id_channel_brand_id_11_show_episodes_episode_id_32307_frameb/',
640 'info_dict': {
641 'id': '55304',
642 'ext': 'mp4',
643 'title': 'Дошкольное воспитание',
644 },
645 },
b827a601
S
646 # SportBox embed
647 {
648 'url': 'http://www.vestifinance.ru/articles/25753',
649 'info_dict': {
650 'id': '25753',
05d1e7aa 651 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
652 },
653 'playlist': [{
654 'info_dict': {
655 'id': '370908',
656 'title': 'Госзаказ. День 3',
657 'ext': 'mp4',
658 }
659 }, {
660 'info_dict': {
661 'id': '370905',
662 'title': 'Госзаказ. День 2',
663 'ext': 'mp4',
664 }
665 }, {
666 'info_dict': {
667 'id': '370902',
668 'title': 'Госзаказ. День 1',
669 'ext': 'mp4',
670 }
671 }],
672 'params': {
673 # m3u8 download
674 'skip_download': True,
675 },
676 },
bf20b9c5
S
677 # Myvi.ru embed
678 {
679 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
680 'info_dict': {
681 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
682 'ext': 'mp4',
683 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 684 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
685 'duration': 153,
686 }
687 },
c76799c5
S
688 # XHamster embed
689 {
690 'url': 'http://www.numisc.com/forum/showthread.php?11696-FM15-which-pumiscer-was-this-%28-vid-%29-%28-alfa-as-fuck-srx-%29&s=711f5db534502e22260dec8c5e2d66d8',
691 'info_dict': {
692 'id': 'showthread',
693 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
694 },
695 'playlist_mincount': 7,
39efc6e3
YCH
696 # This forum does not allow <iframe> syntaxes anymore
697 # Now HTML tags are displayed as-is
698 'skip': 'No videos on this page',
c76799c5 699 },
aab74fa1
PH
700 # Embedded TED video
701 {
702 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 703 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 704 'info_dict': {
a8eb5a8e 705 'id': '1969',
aab74fa1 706 'ext': 'mp4',
a8eb5a8e
PH
707 'title': 'Hidden miracles of the natural world',
708 'uploader': 'Louie Schwartzberg',
709 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 710 }
60cc4dc4 711 },
d95e35d6
S
712 # nowvideo embed hidden behind percent encoding
713 {
714 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
715 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
716 'info_dict': {
717 'id': '06e53103ca9aa',
718 'ext': 'flv',
719 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
720 'description': 'No description',
721 },
0f2a2ba1 722 },
893f8832
PH
723 # arte embed
724 {
725 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
726 'md5': '7653032cbb25bf6c80d80f217055fa43',
727 'info_dict': {
728 'id': '048195-004_PLUS7-F',
729 'ext': 'flv',
730 'title': 'X:enius',
731 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
732 'upload_date': '20140320',
733 },
734 'params': {
735 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
736 },
737 'skip': 'video gone',
893f8832 738 },
cbd55ade
S
739 # francetv embed
740 {
741 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
742 'info_dict': {
743 'id': 'EV_30231',
744 'ext': 'mp4',
745 'title': 'Alcaline, le concert avec Calogero',
746 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
747 'upload_date': '20150226',
748 'timestamp': 1424989860,
749 'duration': 5400,
750 },
751 'params': {
752 # m3u8 downloads
753 'skip_download': True,
754 },
755 'expected_warnings': [
756 'Forbidden'
757 ]
758 },
fa35cdad
PH
759 # Condé Nast embed
760 {
761 'url': 'http://www.wired.com/2014/04/honda-asimo/',
762 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
763 'info_dict': {
764 'id': '53501be369702d3275860000',
765 'ext': 'mp4',
766 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
767 }
ebd3c7b3
PH
768 },
769 # Dailymotion embed
770 {
771 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
772 'md5': '441aeeb82eb72c422c7f14ec533999cd',
773 'info_dict': {
774 'id': 'k2mm4bCdJ6CQ2i7c8o2',
775 'ext': 'mp4',
776 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 777 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 778 'uploader': 'Spi0n',
0738187f
YCH
779 'uploader_id': 'xgditw',
780 'upload_date': '20140425',
781 'timestamp': 1398441542,
ebd3c7b3
PH
782 },
783 'add_ie': ['Dailymotion'],
2b88feed 784 },
71a1db89
S
785 # DailyMail embed
786 {
787 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
788 'info_dict': {
789 'id': '1495629',
790 'ext': 'mp4',
791 'title': 'Care worker punches elderly dementia patient in head 11 times',
792 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
793 },
794 'add_ie': ['DailyMail'],
795 'params': {
796 'skip_download': True,
797 },
798 },
2b88feed
PH
799 # YouTube embed
800 {
801 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
802 'info_dict': {
803 'id': 'FXRb4ykk4S0',
804 'ext': 'mp4',
805 'title': 'The NBL Auction 2014',
806 'uploader': 'BADMINTON England',
807 'uploader_id': 'BADMINTONEvents',
808 'upload_date': '20140603',
809 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
810 },
811 'add_ie': ['Youtube'],
812 'params': {
813 'skip_download': True,
814 }
815 },
c5cd249e
JMF
816 # MTVSercices embed
817 {
1fa309da
YCH
818 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
819 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 820 'info_dict': {
1fa309da 821 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 822 'ext': 'mp4',
1fa309da
YCH
823 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
824 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
825 'timestamp': 1349922600,
826 'upload_date': '20121011',
c5cd249e
JMF
827 },
828 },
61013473 829 # YouTube embed via <data-embed-url="">
830 {
831 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 832 'info_dict': {
a8eb5a8e 833 'id': '4vAffPZIT44',
61013473 834 'ext': 'mp4',
a8eb5a8e 835 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
836 'uploader': 'Gameloft',
837 'uploader_id': 'gameloft',
a8eb5a8e
PH
838 'upload_date': '20140828',
839 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
840 },
841 'params': {
842 'skip_download': True,
61013473 843 }
c8e9a235 844 },
61568e50
JH
845 # YouTube <object> embed
846 {
847 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
848 'md5': '516718101ec834f74318df76259fb3cc',
849 'info_dict': {
850 'id': 'msN87y-iEx0',
851 'ext': 'webm',
852 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
853 'upload_date': '20080526',
854 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
855 'uploader': 'Christopher Sykes',
856 'uploader_id': 'ChristopherJSykes',
857 },
858 'add_ie': ['Youtube'],
859 },
c8e9a235
PH
860 # Camtasia studio
861 {
862 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
863 'playlist': [{
864 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
865 'info_dict': {
866 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
867 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
868 'ext': 'flv',
869 'duration': 2235.90,
870 }
871 }, {
872 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
873 'info_dict': {
874 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
875 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
876 'ext': 'flv',
877 'duration': 2235.93,
878 }
879 }],
880 'info_dict': {
881 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
882 }
4d805e06
PH
883 },
884 # Flowplayer
885 {
886 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
887 'md5': '9d65602bf31c6e20014319c7d07fba27',
888 'info_dict': {
889 'id': '5123ea6d5e5a7',
890 'ext': 'mp4',
891 'age_limit': 18,
892 'uploader': 'www.handjobhub.com',
d6d9186f 893 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 894 }
0990305d 895 },
22a6f150
PH
896 # Multiple brightcove videos
897 # https://github.com/rg3/youtube-dl/issues/2283
898 {
899 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
900 'info_dict': {
901 'id': 'always-never',
902 'title': 'Always / Never - The New Yorker',
903 },
904 'playlist_count': 3,
905 'params': {
906 'extract_flat': False,
907 'skip_download': True,
908 }
1a94ff68
S
909 },
910 # MLB embed
911 {
912 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
913 'md5': '96f09a37e44da40dd083e12d9a683327',
914 'info_dict': {
915 'id': '33322633',
916 'ext': 'mp4',
917 'title': 'Ump changes call to ball',
918 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
919 'duration': 48,
920 'timestamp': 1401537900,
921 'upload_date': '20140531',
ec85ded8 922 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
923 },
924 },
746c67d7
NJ
925 # Wistia embed
926 {
6c114b12
S
927 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
928 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 929 'info_dict': {
6c114b12 930 'id': '6e2wtrbdaf',
746c67d7 931 'ext': 'mov',
6c114b12
S
932 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
933 'description': 'a Paywall Videos video from Remilon',
934 'duration': 644.072,
935 'uploader': 'study.com',
936 'timestamp': 1459678540,
937 'upload_date': '20160403',
938 'filesize': 24687186,
746c67d7
NJ
939 },
940 },
52cffcb1 941 {
942 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
943 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
944 'info_dict': {
945 'id': 'uxjb0lwrcz',
946 'ext': 'mp4',
6c114b12 947 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 948 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 949 'duration': 1715.0,
85d7b765 950 'uploader': 'thoughtworks.wistia.com',
0738187f 951 'timestamp': 1401832161,
6c114b12 952 'upload_date': '20140603',
70b7e3fb 953 },
52cffcb1 954 },
7ded6545
S
955 # Wistia standard embed (async)
956 {
957 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
958 'info_dict': {
959 'id': '807fafadvk',
960 'ext': 'mp4',
961 'title': 'Drip Brennan Dunn Workshop',
962 'description': 'a JV Webinars video from getdrip-1',
963 'duration': 4986.95,
7ded6545 964 'timestamp': 1463607249,
6c114b12 965 'upload_date': '20160518',
7ded6545
S
966 },
967 'params': {
968 'skip_download': True,
969 }
970 },
ac645ac7
PH
971 # Soundcloud embed
972 {
973 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
974 'info_dict': {
975 'id': '174391317',
976 'ext': 'mp3',
977 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
978 'uploader': 'Sophos Security',
979 'title': 'Chet Chat 171 - Oct 29, 2014',
980 'upload_date': '20141029',
981 }
af63fed7 982 },
db19df6c
S
983 # Soundcloud multiple embeds
984 {
985 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
986 'info_dict': {
987 'id': '52809',
988 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
989 },
990 'playlist_mincount': 7,
991 },
027e2312
S
992 # TuneIn station embed
993 {
994 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
995 'info_dict': {
996 'id': '204146',
997 'ext': 'mp3',
998 'title': 'CNRV',
999 'location': 'Paris, France',
1000 'is_live': True,
1001 },
1002 'params': {
1003 # Live stream
1004 'skip_download': True,
1005 },
1006 },
af63fed7
PH
1007 # Livestream embed
1008 {
1009 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1010 'info_dict': {
1011 'id': '67864563',
1012 'ext': 'flv',
1013 'upload_date': '20141112',
1014 'title': 'Rosetta #CometLanding webcast HL 10',
1015 }
1016 },
78d3b3e2
YCH
1017 # Another Livestream embed, without 'new.' in URL
1018 {
1019 'url': 'https://www.freespeech.org/',
1020 'info_dict': {
1021 'id': '123537347',
1022 'ext': 'mp4',
1023 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1024 },
1025 'params': {
1026 # Live stream
1027 'skip_download': True,
1028 },
1029 },
65f3a228
PH
1030 # LazyYT
1031 {
e8e4cc5a 1032 'url': 'https://skiplagged.com/',
65f3a228 1033 'info_dict': {
e8e4cc5a
JH
1034 'id': 'skiplagged',
1035 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1036 },
e8e4cc5a
JH
1037 'playlist_mincount': 1,
1038 'add_ie': ['Youtube'],
4e262a88 1039 },
42bdd9d0
PH
1040 # Cinchcast embed
1041 {
1042 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1043 'info_dict': {
1044 'id': '7141703',
1045 'ext': 'mp3',
1046 'upload_date': '20141126',
1047 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1048 }
1049 },
501f13fb
PH
1050 # Cinerama player
1051 {
1052 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1053 'info_dict': {
1054 'id': '730m_DandD_1901_512k',
1055 'ext': 'mp4',
1056 'uploader': 'www.abc.net.au',
1057 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1058 }
796df3c6
S
1059 },
1060 # embedded viddler video
1061 {
1062 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1063 'info_dict': {
1064 'id': '4d03aad9',
1065 'ext': 'mp4',
1066 'uploader': 'deadspin',
1067 'title': 'WALL-TO-GORTAT',
1068 'timestamp': 1422285291,
1069 'upload_date': '20150126',
1070 },
1071 'add_ie': ['Viddler'],
a0f71985 1072 },
2051acde
S
1073 # Libsyn embed
1074 {
1075 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1076 'info_dict': {
1077 'id': '3377616',
1078 'ext': 'mp3',
1079 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1080 'description': 'md5:601cb790edd05908957dae8aaa866465',
1081 'upload_date': '20150220',
1082 },
326fa4e6 1083 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1084 },
a0f71985
PH
1085 # jwplayer YouTube
1086 {
1087 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1088 'info_dict': {
1089 'id': 'Mrj4DVp2zeA',
1090 'ext': 'mp4',
f37e3f99 1091 'upload_date': '20150212',
a0f71985
PH
1092 'uploader': 'The National Archives UK',
1093 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
1094 'uploader_id': 'NationalArchives08',
1095 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1096 },
59b8ab58 1097 },
5620f840
S
1098 # jwplayer rtmp
1099 {
1100 'url': 'http://www.suffolk.edu/sjc/',
1101 'info_dict': {
1102 'id': 'sjclive',
1103 'ext': 'flv',
1104 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1105 'uploader': 'www.suffolk.edu',
1106 },
1107 'params': {
1108 'skip_download': True,
1109 }
1110 },
a4a554a7
YCH
1111 # Complex jwplayer
1112 {
1113 'url': 'http://www.indiedb.com/games/king-machine/videos',
1114 'info_dict': {
1115 'id': 'videos',
1116 'ext': 'mp4',
1117 'title': 'king machine trailer 1',
1118 'thumbnail': r're:^https?://.*\.jpg$',
1119 },
1120 },
03486dbb
RU
1121 {
1122 # JWPlayer config passed as variable
1123 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1124 'info_dict': {
1125 'id': '3326530_hq',
1126 'ext': 'mp4',
1127 'title': 'ARIELE | Tube Cup',
1128 'uploader': 'www.txxx.com',
1129 'age_limit': 18,
1130 },
1131 'params': {
1132 'skip_download': True,
1133 }
1134 },
63d990d2 1135 {
c5b7014a 1136 # Video.js embed, multiple formats
63d990d2
S
1137 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1138 'info_dict': {
1139 'id': 'yygqldloqIk',
1140 'ext': 'mp4',
1141 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1142 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1143 'upload_date': '20130314',
1144 'uploader': 'PROстое3D',
1145 'uploader_id': 'PROstoe3D',
1146 },
1147 'params': {
1148 'skip_download': True,
1149 },
1150 },
c5b7014a
S
1151 {
1152 # Video.js embed, single format
1153 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1154 'info_dict': {
1155 'id': 'watch',
1156 'ext': 'mp4',
1157 'title': 'Step 1 - Good Foundation',
1158 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1159 },
1160 'params': {
1161 'skip_download': True,
1162 },
1163 },
59b8ab58
PH
1164 # rtl.nl embed
1165 {
1166 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1167 'playlist_mincount': 5,
1168 'info_dict': {
1169 'id': 'aanslagen-kopenhagen',
1170 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
1171 }
255fca5e
S
1172 },
1173 # Zapiks embed
1174 {
1175 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1176 'info_dict': {
1177 'id': '118046',
1178 'ext': 'mp4',
1179 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1180 }
1181 },
66e568de
S
1182 # Kaltura embed (different embed code)
1183 {
1184 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1185 'info_dict': {
1186 'id': '1_a52wc67y',
1187 'ext': 'flv',
1188 'upload_date': '20150127',
1189 'uploader_id': 'PremierMedia',
1190 'timestamp': int,
1191 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1192 },
1193 },
87703231
YCH
1194 # Kaltura embed with single quotes
1195 {
1196 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1197 'info_dict': {
1198 'id': '0_izeg5utt',
1199 'ext': 'mp4',
1200 'title': '35871',
1201 'timestamp': 1355743100,
1202 'upload_date': '20121217',
1203 'uploader_id': 'batchUser',
1204 },
1205 'add_ie': ['Kaltura'],
1206 },
427cd050
S
1207 {
1208 # Kaltura embedded via quoted entry_id
1209 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1210 'info_dict': {
1211 'id': '0_utuok90b',
1212 'ext': 'mp4',
1213 'title': '06_matthew_brender_raj_dutt',
1214 'timestamp': 1466638791,
1215 'upload_date': '20160622',
1216 },
1217 'add_ie': ['Kaltura'],
1218 'expected_warnings': [
1219 'Could not send HEAD request'
1220 ],
1221 'params': {
1222 'skip_download': True,
1223 }
1224 },
8ab7e6c4
YCH
1225 {
1226 # Kaltura embedded, some fileExt broken (#11480)
1227 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1228 'info_dict': {
1229 'id': '1_sgtvehim',
1230 'ext': 'mp4',
1231 'title': 'Our "Standard Models" of particle physics and cosmology',
1232 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1233 'timestamp': 1321158993,
1234 'upload_date': '20111113',
1235 'uploader_id': 'kps1',
1236 },
1237 'add_ie': ['Kaltura'],
1238 },
a01825a5
JH
1239 {
1240 # Kaltura iframe embed
1241 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1242 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1243 'info_dict': {
1244 'id': '0_f2cfbpwy',
1245 'ext': 'mp4',
1246 'title': 'I. M. Pei: A Centennial Celebration',
1247 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1248 'upload_date': '20170403',
1249 'uploader_id': 'batchUser',
1250 'timestamp': 1491232186,
1251 },
1252 'add_ie': ['Kaltura'],
1253 },
665e9452 1254 # EaglePlatform embed (generic URL)
135c9c42
S
1255 {
1256 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
4645432d 1257 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
135c9c42
S
1258 'info_dict': {
1259 'id': '227304',
1260 'ext': 'mp4',
1261 'title': 'Навальный вышел на свободу',
1262 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
ec85ded8 1263 'thumbnail': r're:^https?://.*\.jpg$',
135c9c42
S
1264 'duration': 87,
1265 'view_count': int,
1266 'age_limit': 0,
1267 },
250b042c
S
1268 'params': {
1269 'skip_download': True,
1270 },
1271 },
1272 # referrer protected EaglePlatform embed
1273 {
1274 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1275 'info_dict': {
1276 'id': '582306',
1277 'ext': 'mp4',
1278 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1279 'thumbnail': r're:^https?://.*\.jpg$',
1280 'duration': 3382,
1281 'view_count': int,
1282 },
1283 'params': {
1284 'skip_download': True,
1285 },
135c9c42 1286 },
665e9452 1287 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1288 {
1289 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1290 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1291 'info_dict': {
1292 'id': '12820',
1293 'ext': 'mp4',
1294 'title': "'O Sole Mio",
ec85ded8 1295 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1296 'duration': 216,
1297 'view_count': int,
1298 },
250b042c
S
1299 'params': {
1300 'skip_download': True,
1301 },
d47ae7f6 1302 },
f8388757
S
1303 # Pladform embed
1304 {
1305 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1306 'info_dict': {
1307 'id': '100183293',
1308 'ext': 'mp4',
62259846 1309 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1310 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1311 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1312 'duration': 694,
1313 'age_limit': 0,
1314 },
1315 },
c798f15b
S
1316 # Playwire embed
1317 {
1318 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1319 'info_dict': {
1320 'id': '3519514',
1321 'ext': 'mp4',
1322 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1323 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1324 'duration': 45.115,
1325 },
1326 },
ad320e9b
NJ
1327 # 5min embed
1328 {
1329 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1330 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1331 'info_dict': {
1332 'id': '518726732',
1333 'ext': 'mp4',
1334 'title': 'Facebook Creates "On This Day" | Crunch Report',
1335 },
1336 },
dc455a5f
S
1337 # SVT embed
1338 {
1339 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
1340 'info_dict': {
1341 'id': '2900353',
1342 'ext': 'flv',
1343 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
1344 'duration': 27,
1345 'age_limit': 0,
1346 },
1347 },
a4257017
S
1348 # Crooks and Liars embed
1349 {
1350 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1351 'info_dict': {
1352 'id': '8RUoRhRi',
1353 'ext': 'mp4',
1354 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1355 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1356 'timestamp': 1428207000,
1357 'upload_date': '20150405',
1358 'uploader': 'Heather',
1359 },
1360 },
1361 # Crooks and Liars external embed
1362 {
1363 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1364 'info_dict': {
1365 'id': 'MTE3MjUtMzQ2MzA',
1366 'ext': 'mp4',
1367 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1368 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1369 'timestamp': 1265032391,
1370 'upload_date': '20100201',
1371 'uploader': 'Heather',
1372 },
1373 },
facecb84 1374 # NBC Sports vplayer embed
a2edf2e7 1375 {
facecb84 1376 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1377 'info_dict': {
facecb84
S
1378 'id': 'ln7x1qSThw4k',
1379 'ext': 'flv',
1380 'title': "PFT Live: New leader in the 'new-look' defense",
1381 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1382 'uploader': 'NBCU-SPORTS',
1383 'upload_date': '20140107',
1384 'timestamp': 1389118457,
a2edf2e7 1385 },
418c5cc3 1386 },
de3eb07e
YCH
1387 # NBC News embed
1388 {
1389 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1390 'md5': '1aa589c675898ae6d37a17913cf68d66',
1391 'info_dict': {
1392 'id': '701714499682',
1393 'ext': 'mp4',
1394 'title': 'PREVIEW: On Assignment: David Letterman',
1395 '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.',
1396 },
1397 },
418c5cc3
YCH
1398 # UDN embed
1399 {
811586eb 1400 'url': 'https://video.udn.com/news/300346',
01c58f84 1401 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1402 'info_dict': {
01c58f84 1403 'id': '300346',
418c5cc3 1404 'ext': 'mp4',
01c58f84 1405 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1406 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1407 },
1408 'params': {
1409 # m3u8 download
1410 'skip_download': True,
1411 },
edfcf7ab
YCH
1412 },
1413 # Ooyala embed
1414 {
1415 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
1416 'info_dict': {
1417 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
1418 'ext': 'mp4',
cce9d15d 1419 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
edfcf7ab 1420 'title': 'This is what separates the Excel masters from the wannabes',
53e06b25 1421 'duration': 191.933,
edfcf7ab
YCH
1422 },
1423 'params': {
1424 # m3u8 downloads
1425 'skip_download': True,
1426 }
d6fd958c 1427 },
b26733ba
YCH
1428 # Brightcove URL in single quotes
1429 {
1430 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1431 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1432 'info_dict': {
1433 'id': '4255764656001',
1434 'ext': 'mp4',
1435 'title': 'SN Presents: Russell Martin, World Citizen',
1436 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
1437 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1438 'uploader_id': '1704050871',
1439 'upload_date': '20150525',
1440 'timestamp': 1432570283,
b26733ba 1441 },
756f574e
YCH
1442 },
1443 # Dailymotion Cloud video
1444 {
1445 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
7d52c052 1446 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
756f574e 1447 'info_dict': {
7d52c052 1448 'id': 'x2uy8t3',
756f574e 1449 'ext': 'mp4',
7d52c052
YCH
1450 'title': 'Sauvons les abeilles ! - Le débat',
1451 'description': 'md5:d9082128b1c5277987825d684939ca26',
ec85ded8 1452 'thumbnail': r're:^https?://.*\.jpe?g$',
7d52c052
YCH
1453 'timestamp': 1434970506,
1454 'upload_date': '20150622',
1455 'uploader': 'Public Sénat',
1456 'uploader_id': 'xa9gza',
756f574e 1457 }
a5158f38 1458 },
8084be78
S
1459 # OnionStudios embed
1460 {
1461 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1462 'info_dict': {
1463 'id': '2855',
1464 'ext': 'mp4',
1465 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1466 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1467 'uploader': 'ClickHole',
1468 'uploader_id': 'clickhole',
1469 }
1470 },
b8c1cc1a
S
1471 # SnagFilms embed
1472 {
1473 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1474 'info_dict': {
1475 'id': '74849a00-85a9-11e1-9660-123139220831',
1476 'ext': 'mp4',
1477 'title': '#whilewewatch',
1478 }
1479 },
a5158f38
YCH
1480 # AdobeTVVideo embed
1481 {
1482 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1483 'md5': '43662b577c018ad707a63766462b1e87',
1484 'info_dict': {
1485 'id': '2456',
1486 'ext': 'mp4',
1487 'title': 'New experience with Acrobat DC',
1488 'description': 'New experience with Acrobat DC',
1489 'duration': 248.667,
1490 },
1f812580 1491 },
ed126900 1492 # BrightcoveInPageEmbed embed
1493 {
1494 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1495 'info_dict': {
1496 'id': '4238694884001',
1497 'ext': 'flv',
1498 'title': 'Tabletop: Dread, Last Thoughts',
1499 'description': 'Tabletop: Dread, Last Thoughts',
1500 'duration': 51690,
1501 },
750b9ff0 1502 },
d10fe835
YCH
1503 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1504 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1505 {
1506 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1507 'info_dict': {
1508 'id': '4785848093001',
1509 'ext': 'mp4',
1510 'title': 'The Cardinal Pell Interview',
1511 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1512 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1513 'uploader_id': '2733773828001',
1514 'upload_date': '20160304',
1515 'timestamp': 1457083087,
d10fe835
YCH
1516 },
1517 'params': {
1518 # m3u8 downloads
1519 'skip_download': True,
1520 },
1521 },
9edf47df
S
1522 {
1523 # Brightcove embed with whitespace around attribute names
1524 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1525 'info_dict': {
1526 'id': '3167554373001',
1527 'ext': 'mp4',
1528 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1529 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1530 'uploader_id': '1079349493',
1531 'upload_date': '20140207',
1532 'timestamp': 1391810548,
1533 },
1534 'params': {
1535 'skip_download': True,
1536 },
1537 },
134c207e
YCH
1538 # Another form of arte.tv embed
1539 {
1540 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1541 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1542 'info_dict': {
1543 'id': '030273-562_PLUS7-F',
1544 'ext': 'mp4',
1545 'title': 'ARTE Reportage - Nulle part, en France',
1546 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1547 'upload_date': '20160409',
1548 },
1549 },
b8f67449
KM
1550 # LiveLeak embed
1551 {
1552 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1553 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1554 'info_dict': {
1555 'id': '874_1459135191',
1556 'ext': 'mp4',
1557 'title': 'Man shows poor quality of new apartment building',
1558 'description': 'The wall is like a sand pile.',
1559 'uploader': 'Lake8737',
09747ba7
YCH
1560 },
1561 'add_ie': [LiveLeakIE.ie_key()],
1562 },
1563 # Another LiveLeak embed pattern (#13336)
1564 {
1565 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1566 'info_dict': {
1567 'id': '2eb_1496309988',
1568 'ext': 'mp4',
1569 'title': 'Thief robs place where everyone was armed',
1570 'description': 'md5:694d73ee79e535953cf2488562288eee',
1571 'uploader': 'brazilwtf',
1572 },
1573 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1574 },
4a120778
YCH
1575 # Duplicated embedded video URLs
1576 {
1577 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1578 'info_dict': {
1579 'id': '149298443_480_16c25b74_2',
1580 'ext': 'mp4',
1581 'title': 'vs. Blue Orange Spring Game',
1582 'uploader': 'www.hudl.com',
1583 },
1584 },
371ddb14
S
1585 # twitter:player:stream embed
1586 {
1587 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1588 'info_dict': {
1589 'id': 'master',
1590 'ext': 'mp4',
1591 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1592 'uploader': 'www.rtl.be',
1593 },
1594 'params': {
1595 # m3u8 downloads
1596 'skip_download': True,
1597 },
1598 },
32917907
RA
1599 # twitter:player embed
1600 {
1601 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1602 'md5': 'a3e0df96369831de324f0778e126653c',
1603 'info_dict': {
1604 'id': '4909620399001',
1605 'ext': 'mp4',
1606 'title': 'What Do Black Holes Sound Like?',
1607 'description': 'what do black holes sound like',
1608 'upload_date': '20160524',
1609 'uploader_id': '29913724001',
1610 'timestamp': 1464107587,
1611 'uploader': 'TheAtlantic',
1612 },
1613 'add_ie': ['BrightcoveLegacy'],
fd6ca382 1614 },
4e826cd9
S
1615 # Nexx embed
1616 {
1617 'url': 'https://www.funk.net/serien/5940e15073f6120001657956/items/593efbb173f6120001657503',
1618 'info_dict': {
1619 'id': '247746',
1620 'ext': 'mp4',
1621 'title': "Yesterday's Jam (OV)",
1622 'description': 'md5:09bc0984723fed34e2581624a84e05f0',
1623 'timestamp': 1492594816,
1624 'upload_date': '20170419',
1625 },
1626 'params': {
1627 'format': 'bestvideo',
1628 'skip_download': True,
1629 },
1630 },
fd6ca382
YCH
1631 # Facebook <iframe> embed
1632 {
1633 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1634 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1635 'info_dict': {
1636 'id': '599637780109885',
1637 'ext': 'mp4',
1638 'title': 'Facebook video #599637780109885',
1639 },
1640 },
fd1c5fba
S
1641 # Facebook <iframe> embed, plugin video
1642 {
1643 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1644 'info_dict': {
1645 'id': '1754168231264132',
1646 'ext': 'mp4',
1647 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1648 'uploader': 'Tariq Ramadan (official)',
1649 'timestamp': 1496758379,
1650 'upload_date': '20170606',
1651 },
1652 'params': {
1653 'skip_download': True,
1654 },
1655 },
fd6ca382
YCH
1656 # Facebook API embed
1657 {
1658 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1659 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1660 'info_dict': {
1661 'id': '10153467542406923',
1662 'ext': 'mp4',
1663 'title': 'Facebook video #10153467542406923',
1664 },
7deef1ba
YCH
1665 },
1666 # Wordpress "YouTube Video Importer" plugin
1667 {
1668 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1669 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1670 'info_dict': {
1671 'id': 'HNTXWDXV9Is',
1672 'ext': 'mp4',
1673 'title': 'Blue Devils Drumline Stanford lot 2016',
1674 'upload_date': '20160627',
1675 'uploader_id': 'GENOCIDE8GENERAL10',
1676 'uploader': 'cylus cyrus',
1677 },
1678 },
81953d1a
RA
1679 {
1680 # video stored on custom kaltura server
1681 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1682 'md5': '537617d06e64dfed891fa1593c4b30cc',
1683 'info_dict': {
1684 'id': '0_1iotm5bh',
1685 'ext': 'mp4',
1686 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1687 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1688 'uploader_id': 'videos.expansion@el-mundo.net',
1689 'upload_date': '20150429',
1690 'timestamp': 1430303472,
1691 },
1692 'add_ie': ['Kaltura'],
1693 },
c03adf90
YCH
1694 {
1695 # Non-standard Vimeo embed
1696 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1697 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1698 'info_dict': {
1699 'id': '148867247',
1700 'ext': 'mp4',
1701 'title': 'Understanding the web - Teaser',
1702 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1703 'upload_date': '20151214',
1704 'uploader': 'OpenClassrooms',
1705 'uploader_id': 'openclassrooms',
1706 },
1707 'add_ie': ['Vimeo'],
1708 },
a5ff05df
S
1709 {
1710 # generic vimeo embed that requires original URL passed as Referer
1711 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1712 'only_matching': True,
1713 },
1979969f
S
1714 {
1715 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1716 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1717 'info_dict': {
1718 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1719 'ext': 'mp4',
1720 'title': 'Big Buck Bunny',
1721 'description': 'Royalty free test video',
1722 'timestamp': 1432816365,
1723 'upload_date': '20150528',
1724 'is_live': False,
1725 },
1726 'params': {
1727 'skip_download': True,
1728 },
1729 'add_ie': [ArkenaIE.ie_key()],
1730 },
2a1321a2
S
1731 {
1732 '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/',
1733 'info_dict': {
1734 'id': '1c7141f46c',
1735 'ext': 'mp4',
1736 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1737 },
1738 'params': {
1739 'skip_download': True,
1740 },
1741 'add_ie': [Vbox7IE.ie_key()],
1742 },
b0c8f2e9
DR
1743 {
1744 # DBTV embeds
1745 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1746 'info_dict': {
1747 'id': '43254897',
1748 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1749 },
b0c8f2e9
DR
1750 'playlist_mincount': 3,
1751 },
e186a9ec
S
1752 {
1753 # Videa embeds
1754 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1755 'info_dict': {
1756 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1757 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1758 },
1759 'playlist_mincount': 2,
1760 },
b687c85e
S
1761 {
1762 # 20 minuten embed
1763 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1764 'info_dict': {
1765 'id': '523629',
1766 'ext': 'mp4',
1767 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1768 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1769 },
1770 'params': {
1771 'skip_download': True,
1772 },
1773 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1774 },
1775 {
1776 # VideoPress embed
1777 'url': 'https://en.support.wordpress.com/videopress/',
1778 'info_dict': {
1779 'id': 'OcobLTqC',
1780 'ext': 'm4v',
1781 'title': 'IMG_5786',
1782 'timestamp': 1435711927,
1783 'upload_date': '20150701',
1784 },
1785 'params': {
1786 'skip_download': True,
1787 },
1788 'add_ie': [VideoPressIE.ie_key()],
fef51645 1789 },
eb3079b6
S
1790 {
1791 # Rutube embed
1792 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1793 'info_dict': {
1794 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1795 'ext': 'flv',
1796 'title': 'Магаззино: Казань 2',
1797 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1798 'uploader': 'Магаззино',
1799 'upload_date': '20170228',
1800 'uploader_id': '996642',
1801 },
1802 'params': {
1803 'skip_download': True,
1804 },
1805 'add_ie': [RutubeIE.ie_key()],
1806 },
fef51645
YCH
1807 {
1808 # ThePlatform embedded with whitespaces in URLs
1809 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1810 'only_matching': True,
1811 },
97952bdb
JH
1812 {
1813 # Senate ISVP iframe https
1814 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1815 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1816 'info_dict': {
1817 'id': 'govtaff020316',
1818 'ext': 'mp4',
1819 'title': 'Integrated Senate Video Player',
1820 },
1821 'add_ie': [SenateISVPIE.ie_key()],
1822 },
ab87c260
S
1823 {
1824 # Limelight embeds (1 channel embed + 4 media embeds)
1825 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1826 'info_dict': {
1827 'id': 'FacilitatorTraining2017',
1828 'title': 'Facilitator Training 2017',
1829 },
1830 'playlist_mincount': 5,
1831 },
eb02940c
S
1832 {
1833 # Limelight embed (LimelightPlayerUtil.embed)
1834 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1835 'info_dict': {
1836 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1837 'ext': 'mp4',
1838 'title': '07448641',
1839 'timestamp': 1499890639,
1840 'upload_date': '20170712',
1841 },
1842 'params': {
1843 'skip_download': True,
1844 },
1845 'add_ie': ['LimelightMedia'],
1846 },
7986c3ab
S
1847 {
1848 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1849 'info_dict': {
1850 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1851 'title': 'Standoff with Walnut Creek murder suspect ends',
1852 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1853 },
1854 'playlist_mincount': 4,
1855 },
55719459
JH
1856 {
1857 # WashingtonPost embed
1858 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1859 'info_dict': {
1860 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1861 'ext': 'mp4',
1862 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1863 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
1864 'timestamp': 1455216756,
1865 'uploader': 'The Washington Post',
1866 'upload_date': '20160211',
1867 },
1868 'add_ie': [WashingtonPostIE.ie_key()],
1869 },
2b8e6a68
S
1870 {
1871 # Mediaset embed
1872 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1873 'info_dict': {
1874 'id': '720642',
1875 'ext': 'mp4',
1876 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1877 },
1878 'params': {
1879 'skip_download': True,
1880 },
1881 'add_ie': [MediasetIE.ie_key()],
1882 },
73cf76a9
S
1883 {
1884 # JOJ.sk embeds
1885 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1886 'info_dict': {
1887 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1888 'title': 'Slovenskom sa prehnala vlna silných búrok',
1889 },
1890 'playlist_mincount': 5,
1891 'add_ie': [JojIE.ie_key()],
1892 },
4328ddf8
S
1893 {
1894 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1895 'url': 'https://tvrain.ru/amp/418921/',
1896 'md5': 'cc00413936695987e8de148b67d14f1d',
1897 'info_dict': {
1898 'id': '418921',
1899 'ext': 'mp4',
1900 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1901 },
1902 },
41918eaa 1903 {
1904 # vzaar embed
1663bd6e
S
1905 'url': 'http://help.vzaar.com/article/165-embedding-video',
1906 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1907 'info_dict': {
1663bd6e 1908 'id': '8707641',
41918eaa 1909 'ext': 'mp4',
1663bd6e 1910 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1911 },
1912 },
9ce1ac40 1913 {
1914 # multiple HTML5 videos on one page
1915 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1916 'info_dict': {
1917 'id': 'keyscenarios',
1918 'title': 'Rescue Kit 14 Free Edition - Getting started',
1919 },
1920 'playlist_count': 4,
1921 }
6e6b70d6
S
1922 # {
1923 # # TODO: find another test
1924 # # http://schema.org/VideoObject
1925 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
1926 # 'md5': '888dcf08b7ea671381f00fab74692755',
1927 # 'info_dict': {
1928 # 'id': 'nyvTSJMKId',
1929 # 'ext': 'mp4',
1930 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
1931 # 'description': '#love for cats.',
1932 # 'timestamp': 1461244995,
1933 # 'upload_date': '20160421',
1934 # },
1935 # 'params': {
1936 # 'force_generic_extractor': True,
1937 # },
1938 # }
cfe50f04 1939 ]
9b122384 1940
9b122384
PH
1941 def report_following_redirect(self, new_url):
1942 """Report information extraction."""
79649588 1943 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 1944
4fc946b5
PH
1945 def _extract_rss(self, url, video_id, doc):
1946 playlist_title = doc.find('./channel/title').text
1947 playlist_desc_el = doc.find('./channel/description')
1948 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
1949
76c73715
PH
1950 entries = []
1951 for it in doc.findall('./channel/item'):
1952 next_url = xpath_text(it, 'link', fatal=False)
1953 if not next_url:
1954 enclosure_nodes = it.findall('./enclosure')
1955 for e in enclosure_nodes:
1956 next_url = e.attrib.get('url')
1957 if next_url:
1958 break
1959
1960 if not next_url:
1961 continue
1962
1963 entries.append({
413c1f8e 1964 '_type': 'url_transparent',
76c73715
PH
1965 'url': next_url,
1966 'title': it.find('title').text,
1967 })
4fc946b5
PH
1968
1969 return {
1970 '_type': 'playlist',
1971 'id': url,
1972 'title': playlist_title,
1973 'description': playlist_desc,
1974 'entries': entries,
1975 }
1976
c8e9a235
PH
1977 def _extract_camtasia(self, url, video_id, webpage):
1978 """ Returns None if no camtasia video can be found. """
1979
1980 camtasia_cfg = self._search_regex(
1981 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
1982 webpage, 'camtasia configuration file', default=None)
1983 if camtasia_cfg is None:
1984 return None
1985
1986 title = self._html_search_meta('DC.title', webpage, fatal=True)
1987
1988 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
1989 camtasia_cfg = self._download_xml(
1990 camtasia_url, video_id,
1991 note='Downloading camtasia configuration',
1992 errnote='Failed to download camtasia configuration')
1993 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
1994
1995 entries = []
1996 for n in fileset_node.getchildren():
1997 url_n = n.find('./uri')
1998 if url_n is None:
1999 continue
2000
2001 entries.append({
2002 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2003 'title': '%s - %s' % (title, n.tag),
2004 'url': compat_urlparse.urljoin(url, url_n.text),
2005 'duration': float_or_none(n.find('./duration').text),
2006 })
2007
2008 return {
2009 '_type': 'playlist',
2010 'entries': entries,
2011 'title': title,
2012 }
2013
9b122384 2014 def _real_extract(self, url):
ebd3c7b3
PH
2015 if url.startswith('//'):
2016 return {
2017 '_type': 'url',
20991253 2018 'url': self.http_scheme() + url,
ebd3c7b3
PH
2019 }
2020
a7130543
JMF
2021 parsed_url = compat_urlparse.urlparse(url)
2022 if not parsed_url.scheme:
04b4d394
PH
2023 default_search = self._downloader.params.get('default_search')
2024 if default_search is None:
1f7ccb90 2025 default_search = 'fixup_error'
04b4d394 2026
1f7ccb90 2027 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2028 if '/' in url:
2029 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2030 return self.url_result('http://' + url)
1f7ccb90 2031 elif default_search != 'fixup_error':
9c1fc022 2032 if default_search == 'auto_warning':
0e67ab0d
PH
2033 if re.match(r'^(?:url|URL)$', url):
2034 raise ExtractorError(
2035 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2036 expected=True)
2037 else:
2038 self._downloader.report_warning(
7571c02c 2039 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2040 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2041
2042 if default_search in ('error', 'fixup_error'):
7571c02c 2043 raise ExtractorError(
b74e86f4
PH
2044 '%r is not a valid URL. '
2045 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2046 % (url, url), expected=True)
04b4d394 2047 else:
f2f2c0c2
PH
2048 if ':' not in default_search:
2049 default_search += ':'
04b4d394 2050 return self.url_result(default_search + url)
4d54ef20
PH
2051
2052 url, smuggled_data = unsmuggle_url(url)
2053 force_videoid = None
d6e6a422 2054 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2055 if smuggled_data and 'force_videoid' in smuggled_data:
2056 force_videoid = smuggled_data['force_videoid']
2057 video_id = force_videoid
2058 else:
9dcd6fd3 2059 video_id = self._generic_id(url)
3d83a1ae 2060
79649588 2061 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2062
ebab4520 2063 head_req = HEADRequest(url)
23be51d8 2064 head_response = self._request_webpage(
ebab4520
PH
2065 head_req, video_id,
2066 note=False, errnote='Could not send HEAD request to %s' % url,
2067 fatal=False)
42393ce2 2068
23be51d8 2069 if head_response is not False:
42393ce2 2070 # Check for redirect
5551d771 2071 new_url = compat_str(head_response.geturl())
42393ce2
PH
2072 if url != new_url:
2073 self.report_following_redirect(new_url)
4d54ef20
PH
2074 if force_videoid:
2075 new_url = smuggle_url(
2076 new_url, {'force_videoid': force_videoid})
cecaaf3f 2077 return self.url_result(new_url)
42393ce2 2078
23be51d8
PH
2079 full_response = None
2080 if head_response is False:
5c2266df 2081 request = sanitized_Request(url)
58bde34a
S
2082 request.add_header('Accept-Encoding', '*')
2083 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2084 head_response = full_response
2085
f930e0c7
S
2086 info_dict = {
2087 'id': video_id,
9dcd6fd3 2088 'title': self._generic_title(url),
303dcdb9 2089 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2090 }
2091
23be51d8 2092 # Check for direct link to a video
955737b2 2093 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2094 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2095 if m:
4e363703 2096 format_id = compat_str(m.group('format_id'))
f930e0c7 2097 if format_id.endswith('mpegurl'):
eadc3ccd 2098 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2099 elif format_id == 'f4m':
2100 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2101 else:
2102 formats = [{
4e363703 2103 'format_id': format_id,
eadc3ccd 2104 'url': url,
2105 'vcodec': 'none' if m.group('type') == 'audio' else None
2106 }]
de6c51e8 2107 info_dict['direct'] = True
19dbaeec 2108 self._sort_formats(formats)
de6c51e8 2109 info_dict['formats'] = formats
f930e0c7 2110 return info_dict
42393ce2 2111
d6e6a422 2112 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2113 force = self._downloader.params.get('force_generic_extractor', False)
2114 self._downloader.report_warning(
2115 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2116
4e262a88 2117 if not full_response:
5c2266df 2118 request = sanitized_Request(url)
58bde34a
S
2119 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2120 # making it impossible to download only chunk of the file (yet we need only 512kB to
2121 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2122 # that will always result in downloading the whole file that is not desirable.
2123 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2124 # to accept raw bytes and being able to download only a chunk.
2125 # It may probably better to solve this by checking Content-Type for application/octet-stream
2126 # after HEAD request finishes, but not sure if we can rely on this.
2127 request.add_header('Accept-Encoding', '*')
2128 full_response = self._request_webpage(request, video_id)
4e262a88 2129
5940862d
S
2130 first_bytes = full_response.read(512)
2131
2132 # Is it an M3U playlist?
0d769bcb 2133 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2134 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2135 self._sort_formats(info_dict['formats'])
5940862d
S
2136 return info_dict
2137
4e262a88
PH
2138 # Maybe it's a direct link to a video?
2139 # Be careful not to download the whole thing!
61ca9a80 2140 if not is_html(first_bytes):
4e262a88
PH
2141 self._downloader.report_warning(
2142 'URL could be a direct video link, returning it as such.')
f930e0c7 2143 info_dict.update({
4e262a88
PH
2144 'direct': True,
2145 'url': url,
f930e0c7
S
2146 })
2147 return info_dict
4e262a88
PH
2148
2149 webpage = self._webpage_read_content(
2150 full_response, url, video_id, prefix=first_bytes)
2151
9b122384 2152 self.report_extraction(video_id)
887c6acd 2153
1b840245 2154 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2155 try:
f7854627 2156 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2157 if doc.tag == 'rss':
2158 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2159 elif doc.tag == 'SmoothStreamingMedia':
2160 info_dict['formats'] = self._parse_ism_formats(doc, url)
2161 self._sort_formats(info_dict['formats'])
2162 return info_dict
e5e8d20a 2163 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2164 smil = self._parse_smil(doc, url, video_id)
2165 self._sort_formats(smil['formats'])
2166 return smil
729accb4
S
2167 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
2168 return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
1b840245 2169 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2170 info_dict['formats'] = self._parse_mpd_formats(
86f4d14f 2171 doc, video_id,
5551d771 2172 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2173 mpd_url=url)
19dbaeec 2174 self._sort_formats(info_dict['formats'])
f930e0c7
S
2175 return info_dict
2176 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2177 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2178 self._sort_formats(info_dict['formats'])
f930e0c7 2179 return info_dict
f7300c5c 2180 except compat_xml_parse_error:
4fc946b5
PH
2181 pass
2182
c8e9a235
PH
2183 # Is it a Camtasia project?
2184 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2185 if camtasia_res is not None:
2186 return camtasia_res
2187
14390730
S
2188 # Sometimes embedded video player is hidden behind percent encoding
2189 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2190 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2191 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2192
887c6acd
PH
2193 # it's tempting to parse this further, but you would
2194 # have to take into account all the variations like
2195 # Video Title - Site Name
2196 # Site Name | Video Title
2197 # Video Title - Tagline | Site Name
2198 # and so on and so forth; it's just not practical
6f41b2bc
S
2199 video_title = self._og_search_title(
2200 webpage, default=None) or self._html_search_regex(
79649588
PH
2201 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2202 default='video')
ef4fd848 2203
4d805e06
PH
2204 # Try to detect age limit automatically
2205 age_limit = self._rta_search(webpage)
2206 # And then there are the jokers who advertise that they use RTA,
2207 # but actually don't.
2208 AGE_LIMIT_MARKERS = [
2209 r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
2210 ]
2211 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2212 age_limit = 18
2213
ef4fd848
PH
2214 # video uploader is domain name
2215 video_uploader = self._search_regex(
79649588 2216 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2217
6f41b2bc
S
2218 video_description = self._og_search_description(webpage, default=None)
2219 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2220
b311b0ea
S
2221 info_dict.update({
2222 'title': video_title,
2223 'description': video_description,
2224 'thumbnail': video_thumbnail,
2225 'age_limit': age_limit,
2226 })
2227
1f4b722b 2228 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2229 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2230 if bc_urls:
99877772
PH
2231 entries = [{
2232 '_type': 'url',
2233 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2234 'ie_key': 'BrightcoveLegacy'
99877772
PH
2235 } for bc_url in bc_urls]
2236
2237 return {
2238 '_type': 'playlist',
2239 'title': video_title,
2240 'id': video_id,
2241 'entries': entries,
2242 }
cfe50f04 2243
f6519f89 2244 # Look for Brightcove New Studio embeds
0254f93b 2245 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2246 if bc_urls:
46b18f23 2247 return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
ed126900 2248
4e826cd9
S
2249 # Look for Nexx embeds
2250 nexx_urls = NexxIE._extract_urls(webpage)
2251 if nexx_urls:
2252 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2253
3f59b015
S
2254 # Look for Nexx iFrame embeds
2255 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2256 if nexx_embed_urls:
2257 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2258
4d8819d2
S
2259 # Look for ThePlatform embeds
2260 tp_urls = ThePlatformIE._extract_urls(webpage)
2261 if tp_urls:
46b18f23 2262 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2263
48a5eabc
S
2264 # Look for Vessel embeds
2265 vessel_urls = VesselIE._extract_urls(webpage)
2266 if vessel_urls:
46b18f23 2267 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2268
59b8ab58
PH
2269 # Look for embedded rtl.nl player
2270 matches = re.findall(
97b570a9 2271 r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
59b8ab58
PH
2272 webpage)
2273 if matches:
46b18f23 2274 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2275
09b9c45e
S
2276 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2277 if vimeo_urls:
46b18f23 2278 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2279
a1b85269
YCH
2280 vid_me_embed_url = self._search_regex(
2281 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2282 webpage, 'vid.me embed', default=None)
2283 if vid_me_embed_url is not None:
2284 return self.url_result(vid_me_embed_url, 'Vidme')
2285
66c9fa36
S
2286 # Look for YouTube embeds
2287 youtube_urls = YoutubeIE._extract_urls(webpage)
2288 if youtube_urls:
46b18f23 2289 return self.playlist_from_matches(
66c9fa36 2290 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2291
ad213a1d 2292 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2293 if matches:
46b18f23 2294 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2295
8489578d
NJ
2296 # Look for embedded Dailymotion playlist player (#3822)
2297 m = re.search(
2298 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2299 if m:
2300 playlists = re.findall(
2301 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2302 if playlists:
46b18f23
JH
2303 return self.playlist_from_matches(
2304 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2305
71a1db89
S
2306 # Look for DailyMail embeds
2307 dailymail_urls = DailyMailIE._extract_urls(webpage)
2308 if dailymail_urls:
2309 return self.playlist_from_matches(
2310 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2311
ef4fd848 2312 # Look for embedded Wistia player
58bb4402
S
2313 wistia_url = WistiaIE._extract_url(webpage)
2314 if wistia_url:
ef4fd848
PH
2315 return {
2316 '_type': 'url_transparent',
58bb4402
S
2317 'url': self._proto_relative_url(wistia_url),
2318 'ie_key': WistiaIE.ie_key(),
ef4fd848 2319 'uploader': video_uploader,
ef4fd848 2320 }
5f6a1245 2321
bab19a8e
S
2322 # Look for SVT player
2323 svt_url = SVTIE._extract_url(webpage)
2324 if svt_url:
2325 return self.url_result(svt_url, 'SVT')
2326
c19f7764
JMF
2327 # Look for Bandcamp pages with custom domain
2328 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2329 if mobj is not None:
2330 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2331 # Don't set the extractor because it can be a track url or an album
2332 return self.url_result(burl)
c19f7764 2333
f25571ff
PH
2334 # Look for embedded Vevo player
2335 mobj = re.search(
2336 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2337 if mobj is not None:
2338 return self.url_result(mobj.group('url'))
796df3c6
S
2339
2340 # Look for embedded Viddler player
cb454b33
S
2341 mobj = re.search(
2342 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2343 webpage)
796df3c6
S
2344 if mobj is not None:
2345 return self.url_result(mobj.group('url'))
f25571ff 2346
3378d67a
S
2347 # Look for NYTimes player
2348 mobj = re.search(
2349 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2350 webpage)
2351 if mobj is not None:
2352 return self.url_result(mobj.group('url'))
2353
cefdf970
S
2354 # Look for Libsyn player
2355 mobj = re.search(
2356 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2357 if mobj is not None:
2358 return self.url_result(mobj.group('url'))
2359
c0d0b01f 2360 # Look for Ooyala videos
8a37aa15 2361 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2362 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2363 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2364 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2365 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2366 if mobj is not None:
9837cb75
RA
2367 embed_token = self._search_regex(
2368 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2369 webpage, 'ooyala embed token', default=None)
2370 return OoyalaIE._build_url_result(smuggle_url(
2371 mobj.group('ec'), {
2372 'domain': url,
2373 'embed_token': embed_token,
2374 }))
c0d0b01f 2375
f076b638 2376 # Look for multiple Ooyala embeds on SBN network websites
2377 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2378 if mobj is not None:
2379 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2380 if embeds:
46b18f23
JH
2381 return self.playlist_from_matches(
2382 embeds, video_id, video_title,
2383 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2384
aa94a6d3 2385 # Look for Aparat videos
48099643 2386 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2387 if mobj is not None:
2388 return self.url_result(mobj.group(1), 'Aparat')
2389
c93c2ab1 2390 # Look for MPORA videos
c3f51436 2391 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2392 if mobj is not None:
2393 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2394
15c0e8e7 2395 # Look for embedded NovaMov-based player
8f89e687 2396 mobj = re.search(
8dfa187b 2397 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2398 (?P<url>http://(?:(?:embed|www)\.)?
2399 (?:novamov\.com|
2400 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2401 videoweed\.(?:es|com)|
2402 movshare\.(?:net|sx|ag)|
2403 divxstage\.(?:eu|net|ch|co|at|ag))
2404 /embed\.php.+?)\1''', webpage)
8f89e687 2405 if mobj is not None:
15c0e8e7 2406 return self.url_result(mobj.group('url'))
50f56607 2407
9834872b 2408 # Look for embedded Facebook player
0646e34c
S
2409 facebook_urls = FacebookIE._extract_urls(webpage)
2410 if facebook_urls:
2411 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2412
ca97a56e
S
2413 # Look for embedded VK player
2414 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2415 if mobj is not None:
2416 return self.url_result(mobj.group('url'), 'VK')
2417
33d4fdab
S
2418 # Look for embedded Odnoklassniki player
2419 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2420 if mobj is not None:
2421 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2422
0364fa8b
S
2423 # Look for embedded ivi player
2424 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2425 if mobj is not None:
2426 return self.url_result(mobj.group('url'), 'Ivi')
2427
db1f3888
PH
2428 # Look for embedded Huffington Post player
2429 mobj = re.search(
c3f51436 2430 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2431 if mobj is not None:
2432 return self.url_result(mobj.group('url'), 'HuffPost')
2433
1b86cc41 2434 # Look for embed.ly
2435 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2436 if mobj is not None:
2437 return self.url_result(mobj.group('url'))
2438 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2439 if mobj is not None:
f7e6f7fa 2440 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2441
60cc4dc4
PH
2442 # Look for funnyordie embed
2443 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2444 if matches:
46b18f23
JH
2445 return self.playlist_from_matches(
2446 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2447
db546cf8
S
2448 # Look for BBC iPlayer embed
2449 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2450 if matches:
46b18f23 2451 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2452
93d020dd
S
2453 # Look for embedded RUTV player
2454 rutv_url = RUTVIE._extract_url(webpage)
2455 if rutv_url:
2456 return self.url_result(rutv_url, 'RUTV')
2457
494f20cb 2458 # Look for embedded TVC player
b8599718
S
2459 tvc_url = TVCIE._extract_url(webpage)
2460 if tvc_url:
2461 return self.url_result(tvc_url, 'TVC')
494f20cb 2462
d40a3b5b
S
2463 # Look for embedded SportBox player
2464 sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
2465 if sportbox_urls:
46b18f23 2466 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
d40a3b5b 2467
2bb5b6d0
S
2468 # Look for embedded XHamster player
2469 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2470 if xhamster_urls:
46b18f23 2471 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2472
2c9ca782
S
2473 # Look for embedded TNAFlixNetwork player
2474 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2475 if tnaflix_urls:
46b18f23 2476 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2477
b52c9ef1
S
2478 # Look for embedded PornHub player
2479 pornhub_urls = PornHubIE._extract_urls(webpage)
2480 if pornhub_urls:
46b18f23 2481 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2482
37e7a71c
S
2483 # Look for embedded DrTuber player
2484 drtuber_urls = DrTuberIE._extract_urls(webpage)
2485 if drtuber_urls:
46b18f23 2486 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2487
e28ed498
S
2488 # Look for embedded RedTube player
2489 redtube_urls = RedTubeIE._extract_urls(webpage)
2490 if redtube_urls:
46b18f23 2491 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2492
9872d311
S
2493 # Look for embedded Tvigle player
2494 mobj = re.search(
2495 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2496 if mobj is not None:
2497 return self.url_result(mobj.group('url'), 'Tvigle')
2498
7e2ede98
JMF
2499 # Look for embedded TED player
2500 mobj = re.search(
d7cc31b6 2501 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2502 if mobj is not None:
2503 return self.url_result(mobj.group('url'), 'TED')
2504
5c386252 2505 # Look for embedded Ustream videos
d77ac737
YCH
2506 ustream_url = UstreamIE._extract_url(webpage)
2507 if ustream_url:
2508 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2509
893f8832
PH
2510 # Look for embedded arte.tv player
2511 mobj = re.search(
134c207e 2512 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2513 webpage)
2514 if mobj is not None:
2515 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2516
cbd55ade
S
2517 # Look for embedded francetv player
2518 mobj = re.search(
2519 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2520 webpage)
2521 if mobj is not None:
2522 return self.url_result(mobj.group('url'))
2523
cb3ac1c6
S
2524 # Look for embedded smotri.com player
2525 smotri_url = SmotriIE._extract_url(webpage)
2526 if smotri_url:
2527 return self.url_result(smotri_url, 'Smotri')
2528
e6c2d9ad 2529 # Look for embedded Myvi.ru player
6dd94d3a 2530 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2531 if myvi_url:
2532 return self.url_result(myvi_url)
2533
dfb1b146 2534 # Look for embedded soundcloud player
94aae015
S
2535 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2536 if soundcloud_urls:
46b18f23 2537 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2538
027e2312
S
2539 # Look for tunein player
2540 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2541 if tunein_urls:
46b18f23 2542 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2543
c5cd249e 2544 # Look for embedded mtvservices player
46fde8a1
S
2545 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2546 if mtvservices_url:
2547 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2548
49807b4a
S
2549 # Look for embedded yahoo player
2550 mobj = re.search(
2551 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2552 webpage)
2553 if mobj is not None:
2554 return self.url_result(mobj.group('url'), 'Yahoo')
2555
2ef6fcb5
PH
2556 # Look for embedded sbs.com.au player
2557 mobj = re.search(
e98b8e79
PH
2558 r'''(?x)
2559 (?:
2560 <meta\s+property="og:video"\s+content=|
2561 <iframe[^>]+?src=
2562 )
2563 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2564 webpage)
2565 if mobj is not None:
2566 return self.url_result(mobj.group('url'), 'SBS')
2567
42bdd9d0
PH
2568 # Look for embedded Cinchcast player
2569 mobj = re.search(
2570 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2571 webpage)
2572 if mobj is not None:
2573 return self.url_result(mobj.group('url'), 'Cinchcast')
2574
1a94ff68 2575 mobj = re.search(
5263cdfc 2576 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2577 webpage)
8001607e
YCH
2578 if not mobj:
2579 mobj = re.search(
2580 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2581 webpage)
1a94ff68
S
2582 if mobj is not None:
2583 return self.url_result(mobj.group('url'), 'MLB')
2584
1419fafd 2585 mobj = re.search(
dd467d33 2586 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2587 webpage)
2588 if mobj is not None:
2589 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2590
af63fed7 2591 mobj = re.search(
78d3b3e2 2592 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2593 webpage)
2594 if mobj is not None:
2595 return self.url_result(mobj.group('url'), 'Livestream')
2596
255fca5e
S
2597 # Look for Zapiks embed
2598 mobj = re.search(
2599 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2600 if mobj is not None:
2601 return self.url_result(mobj.group('url'), 'Zapiks')
2602
e3216b82 2603 # Look for Kaltura embeds
c287f2bc
S
2604 kaltura_url = KalturaIE._extract_url(webpage)
2605 if kaltura_url:
2606 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2607
665e9452 2608 # Look for EaglePlatform embeds
06a96da1
S
2609 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2610 if eagleplatform_url:
665e9452 2611 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2612
665e9452 2613 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2614 mobj = re.search(
2615 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2616 if mobj is not None:
2617 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2618
f8388757 2619 # Look for Pladform embeds
45dad7ba
S
2620 pladform_url = PladformIE._extract_url(webpage)
2621 if pladform_url:
2622 return self.url_result(pladform_url)
f8388757 2623
ff18735c
S
2624 # Look for Videomore embeds
2625 videomore_url = VideomoreIE._extract_url(webpage)
2626 if videomore_url:
2627 return self.url_result(videomore_url)
2628
83f1481b
S
2629 # Look for Webcaster embeds
2630 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2631 if webcaster_url:
2632 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2633
2dcc114f
S
2634 # Look for Playwire embeds
2635 mobj = re.search(
2636 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2637 if mobj is not None:
2638 return self.url_result(mobj.group('url'))
2639
ad320e9b
NJ
2640 # Look for 5min embeds
2641 mobj = re.search(
2642 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2643 if mobj is not None:
2644 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2645
18153f1b
S
2646 # Look for Crooks and Liars embeds
2647 mobj = re.search(
2648 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2649 if mobj is not None:
2650 return self.url_result(mobj.group('url'))
2651
a2edf2e7
YCH
2652 # Look for NBC Sports VPlayer embeds
2653 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2654 if nbc_sports_url:
2655 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2656
de3eb07e
YCH
2657 # Look for NBC News embeds
2658 nbc_news_embed_url = re.search(
2659 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2660 if nbc_news_embed_url:
2661 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2662
653789af 2663 # Look for Google Drive embeds
5b251628 2664 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2665 if google_drive_url:
2666 return self.url_result(google_drive_url, 'GoogleDrive')
2667
418c5cc3
YCH
2668 # Look for UDN embeds
2669 mobj = re.search(
c39fd7b1 2670 r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2671 if mobj is not None:
2672 return self.url_result(
0a160363 2673 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2674
2fe1b5bd
YCH
2675 # Look for Senate ISVP iframe
2676 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2677 if senate_isvp_url:
25c3a734 2678 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2679
756f574e
YCH
2680 # Look for Dailymotion Cloud videos
2681 dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
2682 if dmcloud_url:
2683 return self.url_result(dmcloud_url, 'DailymotionCloud')
2684
1ac1c4c2
S
2685 # Look for OnionStudios embeds
2686 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2687 if onionstudios_url:
2688 return self.url_result(onionstudios_url)
2689
67167920 2690 # Look for ViewLift embeds
2691 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2692 if viewlift_url:
2693 return self.url_result(viewlift_url)
eedd20ef 2694
7cb09524 2695 # Look for JWPlatform embeds
2696 jwplatform_url = JWPlatformIE._extract_url(webpage)
2697 if jwplatform_url:
2698 return self.url_result(jwplatform_url, 'JWPlatform')
2699
aecfcd4e
S
2700 # Look for Digiteka embeds
2701 digiteka_url = DigitekaIE._extract_url(webpage)
2702 if digiteka_url:
2703 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2704
1979969f
S
2705 # Look for Arkena embeds
2706 arkena_url = ArkenaIE._extract_url(webpage)
2707 if arkena_url:
2708 return self.url_result(arkena_url, ArkenaIE.ie_key())
2709
b1c35797
RA
2710 # Look for Piksel embeds
2711 piksel_url = PikselIE._extract_url(webpage)
2712 if piksel_url:
2713 return self.url_result(piksel_url, PikselIE.ie_key())
2714
1bf996fa 2715 # Look for Limelight embeds
e5d39886
S
2716 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2717 if limelight_urls:
2718 return self.playlist_result(
2719 limelight_urls, video_id, video_title, video_description)
2720
7986c3ab
S
2721 # Look for Anvato embeds
2722 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2723 if anvato_urls:
2724 return self.playlist_result(
2725 anvato_urls, video_id, video_title, video_description)
2726
a5158f38
YCH
2727 # Look for AdobeTVVideo embeds
2728 mobj = re.search(
2729 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2730 webpage)
2731 if mobj is not None:
2732 return self.url_result(
2733 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2734 'AdobeTVVideo')
2735
088e1aac
YCH
2736 # Look for Vine embeds
2737 mobj = re.search(
2738 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2739 webpage)
2740 if mobj is not None:
2741 return self.url_result(
2742 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2743
217d5ae0
RA
2744 # Look for VODPlatform embeds
2745 mobj = re.search(
93b84045 2746 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2747 webpage)
2748 if mobj is not None:
2749 return self.url_result(
93b84045 2750 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2751
7d273a38
RA
2752 # Look for Mangomolo embeds
2753 mobj = re.search(
d05ef09d 2754 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2755 (?:
2756 video\?.*?\bid=(?P<video_id>\d+)|
2757 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2758 ).+?)\1''', webpage)
2759 if mobj is not None:
2760 info = {
2761 '_type': 'url_transparent',
2762 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2763 'title': video_title,
2764 'description': video_description,
2765 'thumbnail': video_thumbnail,
2766 'uploader': video_uploader,
2767 }
2768 video_id = mobj.group('video_id')
2769 if video_id:
2770 info.update({
2771 'ie_key': 'MangomoloVideo',
2772 'id': video_id,
2773 })
2774 else:
2775 info.update({
2776 'ie_key': 'MangomoloLive',
2777 'id': mobj.group('channel_id'),
2778 })
2779 return info
2780
5a51775a
YCH
2781 # Look for Instagram embeds
2782 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2783 if instagram_embed_url is not None:
11e60fca
S
2784 return self.url_result(
2785 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2786
b8f67449 2787 # Look for LiveLeak embeds
09747ba7
YCH
2788 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2789 if liveleak_urls:
2790 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2791
5d39176f
S
2792 # Look for 3Q SDN embeds
2793 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2794 if threeqsdn_url:
6f41b2bc
S
2795 return {
2796 '_type': 'url_transparent',
2797 'ie_key': ThreeQSDNIE.ie_key(),
2798 'url': self._proto_relative_url(threeqsdn_url),
2799 'title': video_title,
2800 'description': video_description,
2801 'thumbnail': video_thumbnail,
2802 'uploader': video_uploader,
2803 }
5d39176f 2804
2a1321a2
S
2805 # Look for VBOX7 embeds
2806 vbox7_url = Vbox7IE._extract_url(webpage)
2807 if vbox7_url:
2808 return self.url_result(vbox7_url, Vbox7IE.ie_key())
2809
b0c8f2e9
DR
2810 # Look for DBTV embeds
2811 dbtv_urls = DBTVIE._extract_urls(webpage)
2812 if dbtv_urls:
46b18f23 2813 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 2814
e186a9ec
S
2815 # Look for Videa embeds
2816 videa_urls = VideaIE._extract_urls(webpage)
2817 if videa_urls:
46b18f23 2818 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 2819
b687c85e
S
2820 # Look for 20 minuten embeds
2821 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
2822 if twentymin_urls:
46b18f23
JH
2823 return self.playlist_from_matches(
2824 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 2825
17f8deeb
S
2826 # Look for Openload embeds
2827 openload_urls = OpenloadIE._extract_urls(webpage)
2828 if openload_urls:
46b18f23
JH
2829 return self.playlist_from_matches(
2830 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 2831
6ef3e65a
S
2832 # Look for VideoPress embeds
2833 videopress_urls = VideoPressIE._extract_urls(webpage)
2834 if videopress_urls:
46b18f23
JH
2835 return self.playlist_from_matches(
2836 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 2837
eb3079b6
S
2838 # Look for Rutube embeds
2839 rutube_urls = RutubeIE._extract_urls(webpage)
2840 if rutube_urls:
46b18f23 2841 return self.playlist_from_matches(
2583c0b5 2842 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 2843
55719459
JH
2844 # Look for WashingtonPost embeds
2845 wapo_urls = WashingtonPostIE._extract_urls(webpage)
2846 if wapo_urls:
2847 return self.playlist_from_matches(
2848 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
2849
5d29af3d
S
2850 # Look for Mediaset embeds
2851 mediaset_urls = MediasetIE._extract_urls(webpage)
2852 if mediaset_urls:
2853 return self.playlist_from_matches(
2854 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
2855
73cf76a9
S
2856 # Look for JOJ.sk embeds
2857 joj_urls = JojIE._extract_urls(webpage)
2858 if joj_urls:
2859 return self.playlist_from_matches(
2860 joj_urls, video_id, video_title, ie=JojIE.ie_key())
2861
24e966e8
PH
2862 # Look for megaphone.fm embeds
2863 mpfn_urls = MegaphoneIE._extract_urls(webpage)
2864 if mpfn_urls:
2865 return self.playlist_from_matches(
2866 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
2867
1663bd6e
S
2868 # Look for vzaar embeds
2869 vzaar_urls = VzaarIE._extract_urls(webpage)
2870 if vzaar_urls:
2871 return self.playlist_from_matches(
2872 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
2873
b311b0ea
S
2874 def merge_dicts(dict1, dict2):
2875 merged = {}
2876 for k, v in dict1.items():
2877 if v is not None:
2878 merged[k] = v
2879 for k, v in dict2.items():
2880 if v is None:
2881 continue
2882 if (k not in merged or
2883 (isinstance(v, compat_str) and v and
2884 isinstance(merged[k], compat_str) and
2885 not merged[k])):
2886 merged[k] = v
2887 return merged
2888
bd264412
YCH
2889 # Look for HTML5 media
2890 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
2891 if entries:
9ce1ac40 2892 if len(entries) == 1:
2893 entries[0].update({
bd264412
YCH
2894 'id': video_id,
2895 'title': video_title,
2896 })
9ce1ac40 2897 else:
2898 for num, entry in enumerate(entries, start=1):
2899 entry.update({
2900 'id': '%s-%s' % (video_id, num),
2901 'title': '%s (%d)' % (video_title, num),
2902 })
2903 for entry in entries:
bd264412 2904 self._sort_formats(entry['formats'])
9ce1ac40 2905 return self.playlist_result(entries, video_id, video_title)
bd264412 2906
c73e330e
RU
2907 jwplayer_data = self._find_jwplayer_data(
2908 webpage, video_id, transform_source=js_to_json)
2909 if jwplayer_data:
4f06c1c9 2910 info = self._parse_jwplayer_data(
3e943cfe 2911 jwplayer_data, video_id, require_title=False, base_url=url)
b311b0ea 2912 return merge_dicts(info, info_dict)
a4a554a7 2913
63d990d2
S
2914 # Video.js embed
2915 mobj = re.search(
c5b7014a 2916 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
2917 webpage)
2918 if mobj is not None:
2919 sources = self._parse_json(
2920 mobj.group(1), video_id, transform_source=js_to_json,
2921 fatal=False) or []
c5b7014a
S
2922 if not isinstance(sources, list):
2923 sources = [sources]
63d990d2
S
2924 formats = []
2925 for source in sources:
2926 src = source.get('src')
2927 if not src or not isinstance(src, compat_str):
2928 continue
2929 src = compat_urlparse.urljoin(url, src)
2930 src_type = source.get('type')
2931 if isinstance(src_type, compat_str):
2932 src_type = src_type.lower()
2933 ext = determine_ext(src).lower()
2934 if src_type == 'video/youtube':
2935 return self.url_result(src, YoutubeIE.ie_key())
2936 if src_type == 'application/dash+xml' or ext == 'mpd':
2937 formats.extend(self._extract_mpd_formats(
2938 src, video_id, mpd_id='dash', fatal=False))
2939 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
2940 formats.extend(self._extract_m3u8_formats(
2941 src, video_id, 'mp4', entry_protocol='m3u8_native',
2942 m3u8_id='hls', fatal=False))
2943 else:
2944 formats.append({
2945 'url': src,
2946 'ext': (mimetype2ext(src_type) or
2947 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
2948 })
2949 if formats:
2950 self._sort_formats(formats)
2951 info_dict['formats'] = formats
2952 return info_dict
2953
ff17be3a
S
2954 # Looking for http://schema.org/VideoObject
2955 json_ld = self._search_json_ld(
2956 webpage, video_id, default={}, expected_type='VideoObject')
2957 if json_ld.get('url'):
2958 return merge_dicts(json_ld, info_dict)
2959
ced659bb 2960 def check_video(vurl):
a0f71985
PH
2961 if YoutubeIE.suitable(vurl):
2962 return True
b7a8c1bc
S
2963 if RtmpIE.suitable(vurl):
2964 return True
ced659bb
S
2965 vpath = compat_urlparse.urlparse(vurl).path
2966 vext = determine_ext(vpath)
0ee79a37 2967 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
2968
2969 def filter_video(urls):
2970 return list(filter(check_video, urls))
2971
9b122384 2972 # Start with something easy: JW Player in SWFObject
ced659bb 2973 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 2974 if not found:
d981cef6 2975 # Look for gorilla-vid style embedding
ced659bb 2976 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
2977 (?:
2978 jw_plugins|
2979 JWPlayerOptions|
2980 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
2981 )
a0f71985
PH
2982 .*?
2983 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 2984 if not found:
9b122384 2985 # Broaden the search a little bit
ced659bb 2986 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
2987 if not found:
2988 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 2989 found = filter_video(re.findall(
54a9328b 2990 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
2991 if not found:
2992 # Flow player
ced659bb 2993 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
2994 flowplayer\("[^"]+",\s*
2995 \{[^}]+?\}\s*,
52585fd6 2996 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 2997 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 2998 ''', webpage))
501f13fb
PH
2999 if not found:
3000 # Cinerama player
3001 found = re.findall(
3002 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3003 if not found:
9b122384 3004 # Try to find twitter cards info
371ddb14
S
3005 # twitter:player:stream should be checked before twitter:player since
3006 # it is expected to contain a raw stream (see
3007 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3008 found = filter_video(re.findall(
3009 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3010 if not found:
9b122384
PH
3011 # We look for Open Graph info:
3012 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3013 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3014 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3015 if m_video_type is not None:
ced659bb 3016 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3017 if not found:
ed9a25dd 3018 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3019 found = re.search(
89ef304b 3020 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3021 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3022 webpage)
84f81016
S
3023 if not found:
3024 # Look also in Refresh HTTP header
3025 refresh_header = head_response.headers.get('Refresh')
3026 if refresh_header:
6c91a5a7
S
3027 # In python 2 response HTTP headers are bytestrings
3028 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3029 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3030 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3031 if found:
b37317d8 3032 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3033 if new_url != url:
3034 self.report_following_redirect(new_url)
3035 return {
3036 '_type': 'url',
3037 'url': new_url,
3038 }
3039 else:
3040 found = None
371ddb14
S
3041
3042 if not found:
3043 # twitter:player is a https URL to iframe player that may or may not
3044 # be supported by youtube-dl thus this is checked the very last (see
3045 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3046 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3047 if embed_url and embed_url != url:
371ddb14
S
3048 return self.url_result(embed_url)
3049
b30b8698 3050 if not found:
416c7fcb 3051 raise UnsupportedError(url)
9b122384 3052
b30b8698 3053 entries = []
4a120778 3054 for video_url in orderedSet(found):
949b6497 3055 video_url = unescapeHTML(video_url)
6cc37c69 3056 video_url = video_url.replace('\\/', '/')
b30b8698 3057 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3058 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3059
b30b8698
PH
3060 # Sometimes, jwplayer extraction will result in a YouTube URL
3061 if YoutubeIE.suitable(video_url):
3062 entries.append(self.url_result(video_url, 'Youtube'))
3063 continue
9b122384 3064
b30b8698
PH
3065 # here's a fun little line of code for you:
3066 video_id = os.path.splitext(video_id)[0]
fc9713a1 3067
28602e74
YCH
3068 entry_info_dict = {
3069 'id': video_id,
3070 'uploader': video_uploader,
3071 'title': video_title,
3072 'age_limit': age_limit,
3073 }
3074
5620f840
S
3075 if RtmpIE.suitable(video_url):
3076 entry_info_dict.update({
3077 '_type': 'url_transparent',
3078 'ie_key': RtmpIE.ie_key(),
3079 'url': video_url,
3080 })
3081 entries.append(entry_info_dict)
3082 continue
3083
729accb4
S
3084 ext = determine_ext(video_url)
3085 if ext == 'smil':
28602e74 3086 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3087 elif ext == 'xspf':
3088 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3089 elif ext == 'm3u8':
3090 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3091 elif ext == 'mpd':
3092 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3093 elif ext == 'f4m':
3094 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3095 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3096 # Just matching .ism/manifest is not enough to be reliably sure
3097 # whether it's actually an ISM manifest or some other streaming
3098 # manifest since there are various streaming URL formats
3099 # possible (see [1]) as well as some other shenanigans like
3100 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3101 # so on.
3102 # Thus the most reasonable way to solve this is to delegate
3103 # to generic extractor in order to look into the contents of
3104 # the manifest itself.
3105 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3106 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3107 entry_info_dict = self.url_result(
3108 smuggle_url(video_url, {'to_generic': True}),
3109 GenericIE.ie_key())
d6fd958c 3110 else:
28602e74
YCH
3111 entry_info_dict['url'] = video_url
3112
19dbaeec
S
3113 if entry_info_dict.get('formats'):
3114 self._sort_formats(entry_info_dict['formats'])
3115
28602e74 3116 entries.append(entry_info_dict)
b30b8698
PH
3117
3118 if len(entries) == 1:
669f0e7c 3119 return entries[0]
b30b8698
PH
3120 else:
3121 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3122 # 'url' results don't have a title
3123 if e.get('title') is not None:
3124 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3125 return {
3126 '_type': 'playlist',
3127 'entries': entries,
3128 }