]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/generic.py
[README.md] Add long lines policy to coding conventions
[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 25 KNOWN_EXTENSIONS,
6cc62232 26 merge_dicts,
63d990d2 27 mimetype2ext,
ed2d6a19 28 orderedSet,
5c2266df 29 sanitized_Request,
9d4660ca
PH
30 smuggle_url,
31 unescapeHTML,
42393ce2 32 unified_strdate,
4d54ef20 33 unsmuggle_url,
416c7fcb 34 UnsupportedError,
76c73715 35 xpath_text,
9b122384 36)
b7a8c1bc 37from .commonprotocols import RtmpIE
ed126900 38from .brightcove import (
4fcaa4f4 39 BrightcoveLegacyIE,
5c17f0a6 40 BrightcoveNewIE,
ed126900 41)
3f59b015
S
42from .nexx import (
43 NexxIE,
44 NexxEmbedIE,
45)
a2edf2e7 46from .nbc import NBCSportsVPlayerIE
c0d0b01f 47from .ooyala import OoyalaIE
93d020dd 48from .rutv import RUTVIE
954c1d05 49from .tvc import TVCIE
476cf548 50from .sportbox import SportBoxIE
cb3ac1c6 51from .smotri import SmotriIE
6dd94d3a 52from .myvi import MyviIE
1419fafd 53from .condenast import CondeNastIE
418c5cc3 54from .udn import UDNEmbedIE
2fe1b5bd 55from .senateisvp import SenateISVPIE
bab19a8e 56from .svt import SVTIE
65d161c4 57from .pornhub import PornHubIE
2bb5b6d0 58from .xhamster import XHamsterEmbedIE
2c9ca782 59from .tnaflix import TNAFlixNetworkEmbedIE
37e7a71c 60from .drtuber import DrTuberIE
e28ed498 61from .redtube import RedTubeIE
06993715 62from .tube8 import Tube8IE
b407e173 63from .vimeo import VimeoIE
3c4fbfec 64from .dailymotion import DailymotionIE
71a1db89 65from .dailymail import DailyMailIE
1ac1c4c2 66from .onionstudios import OnionStudiosIE
67167920 67from .viewlift import ViewLiftEmbedIE
46fde8a1 68from .mtv import MTVServicesEmbeddedIE
45dad7ba 69from .pladform import PladformIE
ff18735c 70from .videomore import VideomoreIE
83f1481b 71from .webcaster import WebcasterFeedIE
5b251628 72from .googledrive import GoogleDriveIE
7cb09524 73from .jwplatform import JWPlatformIE
aecfcd4e 74from .digiteka import DigitekaIE
1979969f 75from .arkena import ArkenaIE
5a51775a 76from .instagram import InstagramIE
b8f67449 77from .liveleak import LiveLeakIE
5d39176f 78from .threeqsdn import ThreeQSDNIE
4d8819d2 79from .theplatform import ThePlatformIE
48a5eabc 80from .vessel import VesselIE
c287f2bc 81from .kaltura import KalturaIE
06a96da1 82from .eagleplatform import EaglePlatformIE
fd6ca382 83from .facebook import FacebookIE
94aae015 84from .soundcloud import SoundcloudIE
027e2312 85from .tunein import TuneInBaseIE
2a1321a2 86from .vbox7 import Vbox7IE
b0c8f2e9 87from .dbtv import DBTVIE
b1c35797 88from .piksel import PikselIE
e186a9ec 89from .videa import VideaIE
b687c85e 90from .twentymin import TwentyMinutenIE
d77ac737 91from .ustream import UstreamIE
17f8deeb 92from .openload import OpenloadIE
6ef3e65a 93from .videopress import VideoPressIE
eb3079b6 94from .rutube import RutubeIE
e5d39886 95from .limelight import LimelightBaseIE
7986c3ab 96from .anvato import AnvatoIE
55719459 97from .washingtonpost import WashingtonPostIE
58bb4402 98from .wistia import WistiaIE
5d29af3d 99from .mediaset import MediasetIE
73cf76a9 100from .joj import JojIE
24e966e8 101from .megaphone import MegaphoneIE
41918eaa 102from .vzaar import VzaarIE
26bae2d9 103from .channel9 import Channel9IE
0987f2dd 104from .vshare import VShareIE
2ca7ed41 105from .mediasite import MediasiteIE
7d540621 106from .springboardplatform import SpringboardPlatformIE
4c780fbd 107from .yapfiles import YapFilesIE
86c8cfc5 108from .vice import ViceIE
178ee883 109from .xfileshare import XFileShareIE
660a230b 110from .cloudflarestream import CloudflareStreamIE
6bd499e8 111from .peertube import PeerTubeIE
5ee7ae5c 112from .teachable import TeachableIE
aee36ca8 113from .indavideo import IndavideoEmbedIE
cfd7f2a6 114from .apa import APAIE
f51f526b 115from .foxnews import FoxNewsIE
9d1b2138 116from .viqeo import ViqeoIE
57c68ec4 117from .expressen import ExpressenIE
83852e57 118from .zype import ZypeIE
9b122384 119
0838239e 120
9b122384 121class GenericIE(InfoExtractor):
79649588 122 IE_DESC = 'Generic downloader that works on some sites'
9b122384 123 _VALID_URL = r'.*'
79649588 124 IE_NAME = 'generic'
cfe50f04 125 _TESTS = [
c5fa81fe
S
126 # Direct link to a video
127 {
128 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
129 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
130 'info_dict': {
131 'id': 'trailer',
132 'ext': 'mp4',
133 'title': 'trailer',
134 'upload_date': '20100513',
135 }
136 },
c5138a7c 137 # Direct link to media delivered compressed (until Accept-Encoding is *)
c5fa81fe
S
138 {
139 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
140 'md5': '128c42e68b13950268b648275386fc74',
141 'info_dict': {
142 'id': 'FictionJunction-Parallel_Hearts',
143 'ext': 'flac',
144 'title': 'FictionJunction-Parallel_Hearts',
145 'upload_date': '20140522',
146 },
147 'expected_warnings': [
148 'URL could be a direct video link, returning it as such.'
39efc6e3
YCH
149 ],
150 'skip': 'URL invalid',
c5fa81fe
S
151 },
152 # Direct download with broken HEAD
153 {
154 'url': 'http://ai-radio.org:8000/radio.opus',
155 'info_dict': {
156 'id': 'radio',
157 'ext': 'opus',
158 'title': 'radio',
159 },
160 'params': {
161 'skip_download': True, # infinite live stream
162 },
163 'expected_warnings': [
ef0e4e7b
YCH
164 r'501.*Not Implemented',
165 r'400.*Bad Request',
c5fa81fe
S
166 ],
167 },
168 # Direct link with incorrect MIME type
169 {
170 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
171 'md5': '4ccbebe5f36706d85221f204d7eb5913',
172 'info_dict': {
173 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
174 'id': '5_Lennart_Poettering_-_Systemd',
175 'ext': 'webm',
176 'title': '5_Lennart_Poettering_-_Systemd',
177 'upload_date': '20141120',
178 },
179 'expected_warnings': [
180 'URL could be a direct video link, returning it as such.'
181 ]
182 },
183 # RSS feed
184 {
185 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
186 'info_dict': {
187 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
188 'title': 'Zero Punctuation',
189 'description': 're:.*groundbreaking video review series.*'
190 },
191 'playlist_mincount': 11,
192 },
193 # RSS feed with enclosure
194 {
195 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
196 'info_dict': {
197 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
198 'ext': 'm4v',
199 'upload_date': '20150228',
200 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
201 }
202 },
01aec848
BG
203 # RSS feed with enclosures and unsupported link URLs
204 {
205 'url': 'http://www.hellointernet.fm/podcast?format=rss',
206 'info_dict': {
207 'id': 'http://www.hellointernet.fm/podcast?format=rss',
208 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
209 'title': 'Hello Internet',
210 },
211 'playlist_mincount': 100,
212 },
8765222d
S
213 # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
214 {
215 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
216 'info_dict': {
217 'id': 'smil',
218 'ext': 'mp4',
219 'title': 'Automatics, robotics and biocybernetics',
220 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
e327b736 221 'upload_date': '20130627',
8765222d
S
222 'formats': 'mincount:16',
223 'subtitles': 'mincount:1',
224 },
225 'params': {
226 'force_generic_extractor': True,
227 'skip_download': True,
228 },
229 },
230 # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
231 {
232 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
233 'info_dict': {
234 'id': 'hds',
235 'ext': 'flv',
236 'title': 'hds',
237 'formats': 'mincount:1',
238 },
239 'params': {
240 'skip_download': True,
241 },
242 },
243 # SMIL from https://www.restudy.dk/video/play/id/1637
244 {
245 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
246 'info_dict': {
247 'id': 'video_1637',
248 'ext': 'flv',
249 'title': 'video_1637',
250 'formats': 'mincount:3',
251 },
252 'params': {
253 'skip_download': True,
254 },
255 },
256 # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
257 {
258 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
259 'info_dict': {
260 'id': 'smil-service',
261 'ext': 'flv',
262 'title': 'smil-service',
263 'formats': 'mincount:1',
264 },
265 'params': {
266 'skip_download': True,
267 },
268 },
269 # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
270 {
271 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
272 'info_dict': {
273 'id': '4719370',
274 'ext': 'mp4',
275 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
276 'formats': 'mincount:3',
277 },
278 'params': {
279 'skip_download': True,
280 },
281 },
1de5cd3b
S
282 # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
283 {
284 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
285 'info_dict': {
286 'id': 'mZlp2ctYIUEB',
287 'ext': 'mp4',
288 'title': 'Tikibad ontruimd wegens brand',
289 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
ec85ded8 290 'thumbnail': r're:^https?://.*\.jpg$',
1de5cd3b
S
291 'duration': 33,
292 },
293 'params': {
294 'skip_download': True,
295 },
296 },
9d939cec
S
297 # MPD from http://dash-mse-test.appspot.com/media.html
298 {
299 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
300 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
301 'info_dict': {
302 'id': 'car-20120827-manifest',
303 'ext': 'mp4',
304 'title': 'car-20120827-manifest',
305 'formats': 'mincount:9',
0738187f 306 'upload_date': '20130904',
9d939cec
S
307 },
308 'params': {
309 'format': 'bestvideo',
310 },
311 },
20938f76
S
312 # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
313 {
314 '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',
315 'info_dict': {
316 'id': 'content',
317 'ext': 'mp4',
318 'title': 'content',
319 'formats': 'mincount:8',
320 },
321 'params': {
322 # m3u8 downloads
323 'skip_download': True,
39efc6e3
YCH
324 },
325 'skip': 'video gone',
20938f76 326 },
edd9b71c
S
327 # m3u8 served with Content-Type: text/plain
328 {
329 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
330 'info_dict': {
331 'id': 'index',
332 'ext': 'mp4',
333 'title': 'index',
334 'upload_date': '20140720',
335 'formats': 'mincount:11',
336 },
337 'params': {
338 # m3u8 downloads
339 'skip_download': True,
39efc6e3
YCH
340 },
341 'skip': 'video gone',
edd9b71c 342 },
c5fa81fe
S
343 # google redirect
344 {
345 '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',
346 'info_dict': {
347 'id': 'cmQHVoWB5FY',
348 'ext': 'mp4',
349 'upload_date': '20130224',
350 'uploader_id': 'TheVerge',
ec85ded8 351 'description': r're:^Chris Ziegler takes a look at the\.*',
c5fa81fe
S
352 'uploader': 'The Verge',
353 'title': 'First Firefox OS phones side-by-side',
354 },
355 'params': {
356 'skip_download': False,
357 }
358 },
6c91a5a7
S
359 {
360 # redirect in Refresh HTTP header
361 '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',
362 'info_dict': {
363 'id': 'pO8h3EaFRdo',
364 'ext': 'mp4',
365 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
366 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
367 'upload_date': '20150917',
368 'uploader_id': 'brtvofficial',
369 'uploader': 'Boiler Room',
370 },
371 'params': {
372 'skip_download': False,
373 },
374 },
cfe50f04 375 {
79649588 376 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
d360a146 377 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
79649588 378 'info_dict': {
d360a146
S
379 'id': '13601338388002',
380 'ext': 'mp4',
79649588
PH
381 'uploader': 'www.hodiho.fr',
382 'title': 'R\u00e9gis plante sa Jeep',
cfe50f04
JMF
383 }
384 },
c19f7764
JMF
385 # bandcamp page with custom domain
386 {
79649588
PH
387 'add_ie': ['Bandcamp'],
388 'url': 'http://bronyrock.com/track/the-pony-mash',
79649588 389 'info_dict': {
fd50bf62
S
390 'id': '3235767654',
391 'ext': 'mp3',
79649588
PH
392 'title': 'The Pony Mash',
393 'uploader': 'M_Pallante',
c19f7764 394 },
79649588 395 'skip': 'There is a limit of 200 free downloads / month for the test song',
c19f7764 396 },
eeb165e6 397 {
53a664ed
S
398 # embedded brightcove video
399 # it also tests brightcove videos that need to set the 'Referer'
400 # in the http requests
3b7d9aa4 401 'add_ie': ['BrightcoveLegacy'],
79649588
PH
402 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
403 'info_dict': {
404 'id': '2765128793001',
405 'ext': 'mp4',
406 'title': 'Le cours de bourse : l’analyse technique',
407 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
408 'uploader': 'BFM BUSINESS',
eeb165e6 409 },
79649588
PH
410 'params': {
411 'skip_download': True,
eeb165e6
JMF
412 },
413 },
53a664ed
S
414 {
415 # embedded with itemprop embedURL and video id spelled as `idVideo`
416 'add_id': ['BrightcoveLegacy'],
417 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
418 'info_dict': {
419 'id': '5255628253001',
420 'ext': 'mp4',
421 'title': 'md5:37c519b1128915607601e75a87995fc0',
422 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
423 'uploader': 'BFM BUSINESS',
424 'uploader_id': '876450612001',
425 'timestamp': 1482255315,
426 'upload_date': '20161220',
427 },
428 'params': {
429 'skip_download': True,
430 },
431 },
17ab4d3b
PH
432 {
433 # https://github.com/rg3/youtube-dl/issues/2253
434 'url': 'http://bcove.me/i6nfkrc3',
17ab4d3b
PH
435 'md5': '0ba9446db037002366bab3b3eb30c88c',
436 'info_dict': {
fd50bf62
S
437 'id': '3101154703001',
438 'ext': 'mp4',
17ab4d3b
PH
439 'title': 'Still no power',
440 'uploader': 'thestar.com',
441 '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.',
442 },
3b7d9aa4 443 'add_ie': ['BrightcoveLegacy'],
39efc6e3 444 'skip': 'video gone',
17ab4d3b 445 },
0479c625
S
446 {
447 'url': 'http://www.championat.com/video/football/v/87/87499.html',
448 'md5': 'fb973ecf6e4a78a67453647444222983',
449 'info_dict': {
450 'id': '3414141473001',
451 'ext': 'mp4',
452 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
453 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
454 'uploader': 'Championat',
455 },
456 },
bdf97017 457 {
37aab278 458 # https://github.com/rg3/youtube-dl/issues/3541
3b7d9aa4 459 'add_ie': ['BrightcoveLegacy'],
bdf97017
NJ
460 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
461 'info_dict': {
462 'id': '3866516442001',
37aab278 463 'ext': 'mp4',
bdf97017
NJ
464 'title': 'Leer mij vrouwen kennen: Aflevering 1',
465 'description': 'Leer mij vrouwen kennen: Aflevering 1',
466 'uploader': 'SBS Broadcasting',
467 },
37aab278 468 'skip': 'Restricted to Netherlands',
bdf97017 469 'params': {
37aab278 470 'skip_download': True, # m3u8 download
bdf97017
NJ
471 },
472 },
06d0ad9a
YCH
473 {
474 # Brightcove video in <iframe>
475 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
476 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
477 'info_dict': {
478 'id': '5360463607001',
479 'ext': 'mp4',
480 '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',
481 '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。',
482 'uploader': 'United Nations',
483 'uploader_id': '1362235914001',
484 'timestamp': 1489593889,
485 'upload_date': '20170315',
486 },
487 'add_ie': ['BrightcoveLegacy'],
488 },
16e2c8f7
YCH
489 {
490 # Brightcove with alternative playerID key
491 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
492 'info_dict': {
493 'id': 'nmeth.2062_SV1',
494 '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',
495 },
496 'playlist': [{
497 'info_dict': {
498 'id': '2228375078001',
499 'ext': 'mp4',
500 'title': 'nmeth.2062-sv1',
501 'description': 'nmeth.2062-sv1',
502 'timestamp': 1363357591,
503 'upload_date': '20130315',
504 'uploader': 'Nature Publishing Group',
505 'uploader_id': '1964492299001',
506 },
507 }],
508 },
40158f55
JH
509 {
510 # Brightcove with UUID in videoPlayer
511 'url': 'http://www8.hp.com/cn/zh/home.html',
512 'info_dict': {
513 'id': '5255815316001',
514 'ext': 'mp4',
515 'title': 'Sprocket Video - China',
516 'description': 'Sprocket Video - China',
517 'uploader': 'HP-Video Gallery',
518 'timestamp': 1482263210,
519 'upload_date': '20161220',
520 'uploader_id': '1107601872001',
521 },
522 'params': {
523 'skip_download': True, # m3u8 download
524 },
525 'skip': 'video rotates...weekly?',
526 },
527 {
528 # Brightcove:new type [2].
529 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
530 'md5': '2b35148fcf48da41c9fb4591650784f3',
531 'info_dict': {
532 'id': '5348741021001',
533 'ext': 'mp4',
534 'upload_date': '20170306',
535 'uploader_id': '4191638492001',
536 'timestamp': 1488769918,
537 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
538
539 },
540 },
541 {
542 # Alternative brightcove <video> attributes
543 '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/',
544 'info_dict': {
545 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
546 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
547 },
548 'playlist': [{
549 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
550 'info_dict': {
551 'id': '5311302538001',
552 'ext': 'mp4',
553 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
554 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
555 'timestamp': 1486321708,
556 'upload_date': '20170205',
557 'uploader_id': '800000640001',
558 },
559 'only_matching': True,
560 }],
561 },
b68a812e
S
562 {
563 # Brightcove with UUID in videoPlayer
564 'url': 'http://www8.hp.com/cn/zh/home.html',
565 'info_dict': {
566 'id': '5255815316001',
567 'ext': 'mp4',
568 'title': 'Sprocket Video - China',
569 'description': 'Sprocket Video - China',
570 'uploader': 'HP-Video Gallery',
571 'timestamp': 1482263210,
572 'upload_date': '20161220',
573 'uploader_id': '1107601872001',
574 },
575 'params': {
576 'skip_download': True, # m3u8 download
577 },
578 },
c0d0b01f
JMF
579 # ooyala video
580 {
79649588 581 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
87830900 582 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
79649588
PH
583 'info_dict': {
584 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
585 'ext': 'mp4',
3486df38 586 'title': '2cc213299525360.mov', # that's what we get
53e06b25 587 'duration': 238.231,
c0d0b01f 588 },
87830900 589 'add_ie': ['Ooyala'],
c0d0b01f 590 },
bf94d763
S
591 {
592 # ooyala video embedded with http://player.ooyala.com/iframe.js
593 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
594 'info_dict': {
595 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
596 'ext': 'mp4',
597 'title': '"Steve Jobs: Man in the Machine" trailer',
598 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
53e06b25 599 'duration': 135.427,
bf94d763
S
600 },
601 'params': {
602 'skip_download': True,
603 },
39efc6e3 604 'skip': 'movie expired',
bf94d763 605 },
198d4cb4
GR
606 # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
607 {
608 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
609 'info_dict': {
610 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
611 'ext': 'mp4',
612 'title': 'Steampunk Fest Comes to Honesdale',
613 'duration': 43.276,
614 },
615 'params': {
616 'skip_download': True,
617 }
618 },
1b86cc41 619 # embed.ly video
620 {
621 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
622 'info_dict': {
623 'id': '9ODmcdjQcHQ',
624 'ext': 'mp4',
0a5bce56
PH
625 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
626 'upload_date': '20140225',
627 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
628 'uploader': 'Tested',
629 'uploader_id': 'testedcom',
1b86cc41 630 },
631 # No need to test YoutubeIE here
632 'params': {
633 'skip_download': True,
634 },
635 },
60cc4dc4
PH
636 # funnyordie embed
637 {
638 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
60cc4dc4
PH
639 'info_dict': {
640 'id': '18e820ec3f',
641 'ext': 'mp4',
642 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
643 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
93d020dd 644 },
39efc6e3
YCH
645 # HEAD requests lead to endless 301, while GET is OK
646 'expected_warnings': ['301'],
60cc4dc4 647 },
93d020dd
S
648 # RUTV embed
649 {
650 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
651 'info_dict': {
652 'id': '776940',
653 'ext': 'mp4',
654 'title': 'Охотское море стало целиком российским',
655 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
656 },
657 'params': {
658 # m3u8 download
659 'skip_download': True,
660 },
aab74fa1 661 },
f37bdbe5
S
662 # TVC embed
663 {
664 '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/',
665 'info_dict': {
666 'id': '55304',
667 'ext': 'mp4',
668 'title': 'Дошкольное воспитание',
669 },
670 },
b827a601
S
671 # SportBox embed
672 {
673 'url': 'http://www.vestifinance.ru/articles/25753',
674 'info_dict': {
675 'id': '25753',
05d1e7aa 676 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
b827a601
S
677 },
678 'playlist': [{
679 'info_dict': {
680 'id': '370908',
681 'title': 'Госзаказ. День 3',
682 'ext': 'mp4',
683 }
684 }, {
685 'info_dict': {
686 'id': '370905',
687 'title': 'Госзаказ. День 2',
688 'ext': 'mp4',
689 }
690 }, {
691 'info_dict': {
692 'id': '370902',
693 'title': 'Госзаказ. День 1',
694 'ext': 'mp4',
695 }
696 }],
697 'params': {
698 # m3u8 download
699 'skip_download': True,
700 },
701 },
bf20b9c5
S
702 # Myvi.ru embed
703 {
704 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
705 'info_dict': {
706 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
707 'ext': 'mp4',
708 'title': 'Ужастики, русский трейлер (2015)',
ec85ded8 709 'thumbnail': r're:^https?://.*\.jpg$',
bf20b9c5
S
710 'duration': 153,
711 }
712 },
c76799c5
S
713 # XHamster embed
714 {
715 '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',
716 'info_dict': {
717 'id': 'showthread',
718 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
719 },
720 'playlist_mincount': 7,
39efc6e3
YCH
721 # This forum does not allow <iframe> syntaxes anymore
722 # Now HTML tags are displayed as-is
723 'skip': 'No videos on this page',
c76799c5 724 },
aab74fa1
PH
725 # Embedded TED video
726 {
727 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
a8eb5a8e 728 'md5': '65fdff94098e4a607385a60c5177c638',
aab74fa1 729 'info_dict': {
a8eb5a8e 730 'id': '1969',
aab74fa1 731 'ext': 'mp4',
a8eb5a8e
PH
732 'title': 'Hidden miracles of the natural world',
733 'uploader': 'Louie Schwartzberg',
734 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
aab74fa1 735 }
60cc4dc4 736 },
d95e35d6
S
737 # nowvideo embed hidden behind percent encoding
738 {
739 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
740 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
741 'info_dict': {
742 'id': '06e53103ca9aa',
743 'ext': 'flv',
744 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
745 'description': 'No description',
746 },
0f2a2ba1 747 },
893f8832
PH
748 # arte embed
749 {
750 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
751 'md5': '7653032cbb25bf6c80d80f217055fa43',
752 'info_dict': {
753 'id': '048195-004_PLUS7-F',
754 'ext': 'flv',
755 'title': 'X:enius',
756 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
757 'upload_date': '20140320',
758 },
759 'params': {
760 'skip_download': 'Requires rtmpdump'
39efc6e3
YCH
761 },
762 'skip': 'video gone',
893f8832 763 },
cbd55ade
S
764 # francetv embed
765 {
766 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
767 'info_dict': {
768 'id': 'EV_30231',
769 'ext': 'mp4',
770 'title': 'Alcaline, le concert avec Calogero',
771 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
772 'upload_date': '20150226',
773 'timestamp': 1424989860,
774 'duration': 5400,
775 },
776 'params': {
777 # m3u8 downloads
778 'skip_download': True,
779 },
780 'expected_warnings': [
781 'Forbidden'
782 ]
783 },
fa35cdad
PH
784 # Condé Nast embed
785 {
786 'url': 'http://www.wired.com/2014/04/honda-asimo/',
787 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
788 'info_dict': {
789 'id': '53501be369702d3275860000',
790 'ext': 'mp4',
791 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
792 }
ebd3c7b3
PH
793 },
794 # Dailymotion embed
795 {
796 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
797 'md5': '441aeeb82eb72c422c7f14ec533999cd',
798 'info_dict': {
799 'id': 'k2mm4bCdJ6CQ2i7c8o2',
800 'ext': 'mp4',
801 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
0738187f 802 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
ebd3c7b3 803 'uploader': 'Spi0n',
0738187f
YCH
804 'uploader_id': 'xgditw',
805 'upload_date': '20140425',
806 'timestamp': 1398441542,
ebd3c7b3
PH
807 },
808 'add_ie': ['Dailymotion'],
2b88feed 809 },
71a1db89
S
810 # DailyMail embed
811 {
812 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
813 'info_dict': {
814 'id': '1495629',
815 'ext': 'mp4',
816 'title': 'Care worker punches elderly dementia patient in head 11 times',
817 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
818 },
819 'add_ie': ['DailyMail'],
820 'params': {
821 'skip_download': True,
822 },
823 },
2b88feed
PH
824 # YouTube embed
825 {
826 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
827 'info_dict': {
828 'id': 'FXRb4ykk4S0',
829 'ext': 'mp4',
830 'title': 'The NBL Auction 2014',
831 'uploader': 'BADMINTON England',
832 'uploader_id': 'BADMINTONEvents',
833 'upload_date': '20140603',
834 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
835 },
836 'add_ie': ['Youtube'],
837 'params': {
838 'skip_download': True,
839 }
840 },
c5cd249e
JMF
841 # MTVSercices embed
842 {
1fa309da
YCH
843 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
844 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
c5cd249e 845 'info_dict': {
1fa309da 846 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
c5cd249e 847 'ext': 'mp4',
1fa309da
YCH
848 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
849 'description': 'Two valets share their love for movie star Liam Neesons.',
05d1e7aa
YCH
850 'timestamp': 1349922600,
851 'upload_date': '20121011',
c5cd249e
JMF
852 },
853 },
61013473 854 # YouTube embed via <data-embed-url="">
855 {
856 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
61013473 857 'info_dict': {
a8eb5a8e 858 'id': '4vAffPZIT44',
61013473 859 'ext': 'mp4',
a8eb5a8e 860 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
ed2d6a19
PH
861 'uploader': 'Gameloft',
862 'uploader_id': 'gameloft',
a8eb5a8e
PH
863 'upload_date': '20140828',
864 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
ed2d6a19
PH
865 },
866 'params': {
867 'skip_download': True,
61013473 868 }
c8e9a235 869 },
61568e50
JH
870 # YouTube <object> embed
871 {
872 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
873 'md5': '516718101ec834f74318df76259fb3cc',
874 'info_dict': {
875 'id': 'msN87y-iEx0',
876 'ext': 'webm',
877 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
878 'upload_date': '20080526',
879 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
880 'uploader': 'Christopher Sykes',
881 'uploader_id': 'ChristopherJSykes',
882 },
883 'add_ie': ['Youtube'],
884 },
c8e9a235
PH
885 # Camtasia studio
886 {
887 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
888 'playlist': [{
889 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
890 'info_dict': {
891 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
892 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
893 'ext': 'flv',
894 'duration': 2235.90,
895 }
896 }, {
897 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
898 'info_dict': {
899 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
900 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
901 'ext': 'flv',
902 'duration': 2235.93,
903 }
904 }],
905 'info_dict': {
906 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
907 }
4d805e06
PH
908 },
909 # Flowplayer
910 {
911 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
912 'md5': '9d65602bf31c6e20014319c7d07fba27',
913 'info_dict': {
914 'id': '5123ea6d5e5a7',
915 'ext': 'mp4',
916 'age_limit': 18,
917 'uploader': 'www.handjobhub.com',
d6d9186f 918 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
4d805e06 919 }
0990305d 920 },
22a6f150
PH
921 # Multiple brightcove videos
922 # https://github.com/rg3/youtube-dl/issues/2283
923 {
924 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
925 'info_dict': {
926 'id': 'always-never',
927 'title': 'Always / Never - The New Yorker',
928 },
929 'playlist_count': 3,
930 'params': {
931 'extract_flat': False,
932 'skip_download': True,
933 }
1a94ff68
S
934 },
935 # MLB embed
936 {
937 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
938 'md5': '96f09a37e44da40dd083e12d9a683327',
939 'info_dict': {
940 'id': '33322633',
941 'ext': 'mp4',
942 'title': 'Ump changes call to ball',
943 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
944 'duration': 48,
945 'timestamp': 1401537900,
946 'upload_date': '20140531',
ec85ded8 947 'thumbnail': r're:^https?://.*\.jpg$',
1a94ff68
S
948 },
949 },
746c67d7
NJ
950 # Wistia embed
951 {
6c114b12
S
952 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
953 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
746c67d7 954 'info_dict': {
6c114b12 955 'id': '6e2wtrbdaf',
746c67d7 956 'ext': 'mov',
6c114b12
S
957 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
958 'description': 'a Paywall Videos video from Remilon',
959 'duration': 644.072,
960 'uploader': 'study.com',
961 'timestamp': 1459678540,
962 'upload_date': '20160403',
963 'filesize': 24687186,
746c67d7
NJ
964 },
965 },
52cffcb1 966 {
967 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
968 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
969 'info_dict': {
970 'id': 'uxjb0lwrcz',
971 'ext': 'mp4',
6c114b12 972 'title': 'Conversation about Hexagonal Rails Part 1',
0738187f 973 'description': 'a Martin Fowler video from ThoughtWorks',
52cffcb1 974 'duration': 1715.0,
85d7b765 975 'uploader': 'thoughtworks.wistia.com',
0738187f 976 'timestamp': 1401832161,
6c114b12 977 'upload_date': '20140603',
70b7e3fb 978 },
52cffcb1 979 },
7ded6545
S
980 # Wistia standard embed (async)
981 {
982 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
983 'info_dict': {
984 'id': '807fafadvk',
985 'ext': 'mp4',
986 'title': 'Drip Brennan Dunn Workshop',
987 'description': 'a JV Webinars video from getdrip-1',
988 'duration': 4986.95,
7ded6545 989 'timestamp': 1463607249,
6c114b12 990 'upload_date': '20160518',
7ded6545
S
991 },
992 'params': {
993 'skip_download': True,
994 }
995 },
ac645ac7
PH
996 # Soundcloud embed
997 {
998 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
999 'info_dict': {
1000 'id': '174391317',
1001 'ext': 'mp3',
1002 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
1003 'uploader': 'Sophos Security',
1004 'title': 'Chet Chat 171 - Oct 29, 2014',
1005 'upload_date': '20141029',
1006 }
af63fed7 1007 },
db19df6c
S
1008 # Soundcloud multiple embeds
1009 {
1010 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
1011 'info_dict': {
1012 'id': '52809',
1013 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
1014 },
1015 'playlist_mincount': 7,
1016 },
027e2312
S
1017 # TuneIn station embed
1018 {
1019 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
1020 'info_dict': {
1021 'id': '204146',
1022 'ext': 'mp3',
1023 'title': 'CNRV',
1024 'location': 'Paris, France',
1025 'is_live': True,
1026 },
1027 'params': {
1028 # Live stream
1029 'skip_download': True,
1030 },
1031 },
af63fed7
PH
1032 # Livestream embed
1033 {
1034 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
1035 'info_dict': {
1036 'id': '67864563',
1037 'ext': 'flv',
1038 'upload_date': '20141112',
1039 'title': 'Rosetta #CometLanding webcast HL 10',
1040 }
1041 },
78d3b3e2
YCH
1042 # Another Livestream embed, without 'new.' in URL
1043 {
1044 'url': 'https://www.freespeech.org/',
1045 'info_dict': {
1046 'id': '123537347',
1047 'ext': 'mp4',
1048 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
1049 },
1050 'params': {
1051 # Live stream
1052 'skip_download': True,
1053 },
1054 },
65f3a228
PH
1055 # LazyYT
1056 {
e8e4cc5a 1057 'url': 'https://skiplagged.com/',
65f3a228 1058 'info_dict': {
e8e4cc5a
JH
1059 'id': 'skiplagged',
1060 'title': 'Skiplagged: The smart way to find cheap flights',
65f3a228 1061 },
e8e4cc5a
JH
1062 'playlist_mincount': 1,
1063 'add_ie': ['Youtube'],
4e262a88 1064 },
42bdd9d0
PH
1065 # Cinchcast embed
1066 {
1067 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
1068 'info_dict': {
1069 'id': '7141703',
1070 'ext': 'mp3',
1071 'upload_date': '20141126',
1072 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
1073 }
1074 },
501f13fb
PH
1075 # Cinerama player
1076 {
1077 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
1078 'info_dict': {
1079 'id': '730m_DandD_1901_512k',
1080 'ext': 'mp4',
1081 'uploader': 'www.abc.net.au',
1082 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
1083 }
796df3c6
S
1084 },
1085 # embedded viddler video
1086 {
1087 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
1088 'info_dict': {
1089 'id': '4d03aad9',
1090 'ext': 'mp4',
1091 'uploader': 'deadspin',
1092 'title': 'WALL-TO-GORTAT',
1093 'timestamp': 1422285291,
1094 'upload_date': '20150126',
1095 },
1096 'add_ie': ['Viddler'],
a0f71985 1097 },
2051acde
S
1098 # Libsyn embed
1099 {
1100 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
1101 'info_dict': {
1102 'id': '3377616',
1103 'ext': 'mp3',
1104 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
1105 'description': 'md5:601cb790edd05908957dae8aaa866465',
1106 'upload_date': '20150220',
1107 },
326fa4e6 1108 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
2051acde 1109 },
a0f71985
PH
1110 # jwplayer YouTube
1111 {
1112 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
1113 'info_dict': {
1114 'id': 'Mrj4DVp2zeA',
1115 'ext': 'mp4',
f37e3f99 1116 'upload_date': '20150212',
a0f71985 1117 'uploader': 'The National Archives UK',
2637fadc 1118 'description': 'md5:8078af856dca76edc42910b61273dbbf',
a0f71985
PH
1119 'uploader_id': 'NationalArchives08',
1120 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
1121 },
59b8ab58 1122 },
5620f840
S
1123 # jwplayer rtmp
1124 {
6899b1d9 1125 'url': 'http://www.suffolk.edu/sjc/live.php',
5620f840 1126 'info_dict': {
6899b1d9 1127 'id': 'live',
5620f840
S
1128 'ext': 'flv',
1129 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
1130 'uploader': 'www.suffolk.edu',
1131 },
1132 'params': {
1133 'skip_download': True,
2637fadc 1134 },
6899b1d9 1135 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
5620f840 1136 },
a4a554a7
YCH
1137 # Complex jwplayer
1138 {
1139 'url': 'http://www.indiedb.com/games/king-machine/videos',
1140 'info_dict': {
1141 'id': 'videos',
1142 'ext': 'mp4',
1143 'title': 'king machine trailer 1',
2637fadc 1144 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
a4a554a7
YCH
1145 'thumbnail': r're:^https?://.*\.jpg$',
1146 },
1147 },
03486dbb
RU
1148 {
1149 # JWPlayer config passed as variable
1150 'url': 'http://www.txxx.com/videos/3326530/ariele/',
1151 'info_dict': {
1152 'id': '3326530_hq',
1153 'ext': 'mp4',
1154 'title': 'ARIELE | Tube Cup',
1155 'uploader': 'www.txxx.com',
1156 'age_limit': 18,
1157 },
1158 'params': {
1159 'skip_download': True,
1160 }
1161 },
939be9ad
JH
1162 {
1163 # JWPlatform iframe
1164 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
1165 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
1166 'info_dict': {
1167 'id': 'O0c5JcKT',
1168 'ext': 'mp4',
1169 'upload_date': '20171122',
1170 'timestamp': 1511366290,
1171 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
1172 },
805f5bf7 1173 'add_ie': [JWPlatformIE.ie_key()],
939be9ad 1174 },
63d990d2 1175 {
c5b7014a 1176 # Video.js embed, multiple formats
63d990d2
S
1177 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
1178 'info_dict': {
1179 'id': 'yygqldloqIk',
1180 'ext': 'mp4',
1181 'title': 'SolidWorks. Урок 6 Настройка чертежа',
1182 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
1183 'upload_date': '20130314',
1184 'uploader': 'PROстое3D',
1185 'uploader_id': 'PROstoe3D',
1186 },
1187 'params': {
1188 'skip_download': True,
1189 },
1190 },
c5b7014a
S
1191 {
1192 # Video.js embed, single format
1193 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
1194 'info_dict': {
1195 'id': 'watch',
1196 'ext': 'mp4',
1197 'title': 'Step 1 - Good Foundation',
1198 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
1199 },
1200 'params': {
1201 'skip_download': True,
1202 },
1203 },
59b8ab58
PH
1204 # rtl.nl embed
1205 {
1206 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
1207 'playlist_mincount': 5,
1208 'info_dict': {
1209 'id': 'aanslagen-kopenhagen',
2637fadc 1210 'title': 'Aanslagen Kopenhagen',
59b8ab58 1211 }
255fca5e
S
1212 },
1213 # Zapiks embed
1214 {
1215 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
1216 'info_dict': {
1217 'id': '118046',
1218 'ext': 'mp4',
1219 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
1220 }
1221 },
66e568de
S
1222 # Kaltura embed (different embed code)
1223 {
1224 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
1225 'info_dict': {
1226 'id': '1_a52wc67y',
1227 'ext': 'flv',
1228 'upload_date': '20150127',
1229 'uploader_id': 'PremierMedia',
1230 'timestamp': int,
1231 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
1232 },
1233 },
87703231
YCH
1234 # Kaltura embed with single quotes
1235 {
1236 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
1237 'info_dict': {
1238 'id': '0_izeg5utt',
1239 'ext': 'mp4',
1240 'title': '35871',
1241 'timestamp': 1355743100,
1242 'upload_date': '20121217',
e30991f9 1243 'uploader_id': 'cplapp@learn360.com',
87703231
YCH
1244 },
1245 'add_ie': ['Kaltura'],
1246 },
427cd050
S
1247 {
1248 # Kaltura embedded via quoted entry_id
1249 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
1250 'info_dict': {
1251 'id': '0_utuok90b',
1252 'ext': 'mp4',
1253 'title': '06_matthew_brender_raj_dutt',
1254 'timestamp': 1466638791,
1255 'upload_date': '20160622',
1256 },
1257 'add_ie': ['Kaltura'],
1258 'expected_warnings': [
1259 'Could not send HEAD request'
1260 ],
1261 'params': {
1262 'skip_download': True,
1263 }
1264 },
8ab7e6c4
YCH
1265 {
1266 # Kaltura embedded, some fileExt broken (#11480)
1267 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
1268 'info_dict': {
1269 'id': '1_sgtvehim',
1270 'ext': 'mp4',
1271 'title': 'Our "Standard Models" of particle physics and cosmology',
1272 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
1273 'timestamp': 1321158993,
1274 'upload_date': '20111113',
1275 'uploader_id': 'kps1',
1276 },
1277 'add_ie': ['Kaltura'],
1278 },
a01825a5
JH
1279 {
1280 # Kaltura iframe embed
1281 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
1282 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
1283 'info_dict': {
1284 'id': '0_f2cfbpwy',
1285 'ext': 'mp4',
1286 'title': 'I. M. Pei: A Centennial Celebration',
1287 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
1288 'upload_date': '20170403',
1289 'uploader_id': 'batchUser',
1290 'timestamp': 1491232186,
1291 },
1292 'add_ie': ['Kaltura'],
1293 },
c21692fa
S
1294 {
1295 # Kaltura iframe embed, more sophisticated
1296 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
1297 'info_dict': {
1298 'id': '1_9gzouybz',
1299 'ext': 'mp4',
1300 'title': 'lecture-05sep2017',
1301 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
1302 'upload_date': '20170913',
1303 'uploader_id': 'eps2',
1304 'timestamp': 1505340777,
1305 },
1306 'params': {
1307 'skip_download': True,
1308 },
1309 'add_ie': ['Kaltura'],
1310 },
e30991f9
S
1311 {
1312 # meta twitter:player
1313 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
1314 'info_dict': {
1315 'id': '0_01b42zps',
1316 'ext': 'mp4',
1317 'title': 'Main Twerk (Video)',
1318 'upload_date': '20171208',
1319 'uploader_id': 'sebastian.salinas@thechive.com',
1320 'timestamp': 1512713057,
1321 },
1322 'params': {
1323 'skip_download': True,
1324 },
1325 'add_ie': ['Kaltura'],
1326 },
250b042c
S
1327 # referrer protected EaglePlatform embed
1328 {
1329 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
1330 'info_dict': {
1331 'id': '582306',
1332 'ext': 'mp4',
1333 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1334 'thumbnail': r're:^https?://.*\.jpg$',
1335 'duration': 3382,
1336 'view_count': int,
1337 },
1338 'params': {
1339 'skip_download': True,
1340 },
135c9c42 1341 },
665e9452 1342 # ClipYou (EaglePlatform) embed (custom URL)
d47ae7f6
S
1343 {
1344 'url': 'http://muz-tv.ru/play/7129/',
4645432d 1345 # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
d47ae7f6
S
1346 'info_dict': {
1347 'id': '12820',
1348 'ext': 'mp4',
1349 'title': "'O Sole Mio",
ec85ded8 1350 'thumbnail': r're:^https?://.*\.jpg$',
d47ae7f6
S
1351 'duration': 216,
1352 'view_count': int,
1353 },
250b042c
S
1354 'params': {
1355 'skip_download': True,
1356 },
2637fadc 1357 'skip': 'This video is unavailable.',
d47ae7f6 1358 },
f8388757
S
1359 # Pladform embed
1360 {
1361 'url': 'http://muz-tv.ru/kinozal/view/7400/',
1362 'info_dict': {
1363 'id': '100183293',
1364 'ext': 'mp4',
62259846 1365 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
f8388757 1366 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
ec85ded8 1367 'thumbnail': r're:^https?://.*\.jpg$',
f8388757
S
1368 'duration': 694,
1369 'age_limit': 0,
1370 },
2637fadc 1371 'skip': 'HTTP Error 404: Not Found',
f8388757 1372 },
c798f15b
S
1373 # Playwire embed
1374 {
1375 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
1376 'info_dict': {
1377 'id': '3519514',
1378 'ext': 'mp4',
1379 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
ec85ded8 1380 'thumbnail': r're:^https?://.*\.png$',
c798f15b
S
1381 'duration': 45.115,
1382 },
1383 },
ad320e9b
NJ
1384 # 5min embed
1385 {
1386 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
1387 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
1388 'info_dict': {
1389 'id': '518726732',
1390 'ext': 'mp4',
1391 'title': 'Facebook Creates "On This Day" | Crunch Report',
2637fadc
RA
1392 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
1393 'timestamp': 1427237531,
1394 'uploader': 'Crunch Report',
1395 'upload_date': '20150324',
1396 },
1397 'params': {
1398 # m3u8 download
1399 'skip_download': True,
ad320e9b
NJ
1400 },
1401 },
a4257017
S
1402 # Crooks and Liars embed
1403 {
1404 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
1405 'info_dict': {
1406 'id': '8RUoRhRi',
1407 'ext': 'mp4',
1408 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
1409 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
1410 'timestamp': 1428207000,
1411 'upload_date': '20150405',
1412 'uploader': 'Heather',
1413 },
1414 },
1415 # Crooks and Liars external embed
1416 {
1417 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
1418 'info_dict': {
1419 'id': 'MTE3MjUtMzQ2MzA',
1420 'ext': 'mp4',
1421 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
1422 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
1423 'timestamp': 1265032391,
1424 'upload_date': '20100201',
1425 'uploader': 'Heather',
1426 },
1427 },
facecb84 1428 # NBC Sports vplayer embed
a2edf2e7 1429 {
facecb84 1430 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
a2edf2e7 1431 'info_dict': {
facecb84
S
1432 'id': 'ln7x1qSThw4k',
1433 'ext': 'flv',
1434 'title': "PFT Live: New leader in the 'new-look' defense",
1435 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
0738187f
YCH
1436 'uploader': 'NBCU-SPORTS',
1437 'upload_date': '20140107',
1438 'timestamp': 1389118457,
a2edf2e7 1439 },
2637fadc 1440 'skip': 'Invalid Page URL',
418c5cc3 1441 },
de3eb07e
YCH
1442 # NBC News embed
1443 {
1444 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
1445 'md5': '1aa589c675898ae6d37a17913cf68d66',
1446 'info_dict': {
2637fadc 1447 'id': 'x_dtl_oa_LettermanliftPR_160608',
de3eb07e 1448 'ext': 'mp4',
2637fadc 1449 'title': 'David Letterman: A Preview',
de3eb07e 1450 '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.',
2637fadc
RA
1451 'upload_date': '20160609',
1452 'timestamp': 1465431544,
1453 'uploader': 'NBCU-NEWS',
de3eb07e
YCH
1454 },
1455 },
418c5cc3
YCH
1456 # UDN embed
1457 {
811586eb 1458 'url': 'https://video.udn.com/news/300346',
01c58f84 1459 'md5': 'fd2060e988c326991037b9aff9df21a6',
418c5cc3 1460 'info_dict': {
01c58f84 1461 'id': '300346',
418c5cc3 1462 'ext': 'mp4',
01c58f84 1463 'title': '中一中男師變性 全校師生力挺',
ec85ded8 1464 'thumbnail': r're:^https?://.*\.jpg$',
811586eb
YCH
1465 },
1466 'params': {
1467 # m3u8 download
1468 'skip_download': True,
1469 },
2637fadc 1470 'expected_warnings': ['Failed to parse JSON Expecting value'],
edfcf7ab 1471 },
b26733ba
YCH
1472 # Brightcove URL in single quotes
1473 {
1474 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
1475 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
1476 'info_dict': {
1477 'id': '4255764656001',
1478 'ext': 'mp4',
1479 'title': 'SN Presents: Russell Martin, World Citizen',
1480 '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.',
1481 'uploader': 'Rogers Sportsnet',
0738187f
YCH
1482 'uploader_id': '1704050871',
1483 'upload_date': '20150525',
1484 'timestamp': 1432570283,
b26733ba 1485 },
756f574e 1486 },
8084be78
S
1487 # OnionStudios embed
1488 {
1489 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
1490 'info_dict': {
1491 'id': '2855',
1492 'ext': 'mp4',
1493 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
ec85ded8 1494 'thumbnail': r're:^https?://.*\.jpe?g$',
8084be78
S
1495 'uploader': 'ClickHole',
1496 'uploader_id': 'clickhole',
1497 }
1498 },
b8c1cc1a
S
1499 # SnagFilms embed
1500 {
1501 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
1502 'info_dict': {
1503 'id': '74849a00-85a9-11e1-9660-123139220831',
1504 'ext': 'mp4',
1505 'title': '#whilewewatch',
1506 }
1507 },
a5158f38
YCH
1508 # AdobeTVVideo embed
1509 {
1510 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
1511 'md5': '43662b577c018ad707a63766462b1e87',
1512 'info_dict': {
1513 'id': '2456',
1514 'ext': 'mp4',
1515 'title': 'New experience with Acrobat DC',
1516 'description': 'New experience with Acrobat DC',
1517 'duration': 248.667,
1518 },
1f812580 1519 },
ed126900 1520 # BrightcoveInPageEmbed embed
1521 {
1522 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
1523 'info_dict': {
1524 'id': '4238694884001',
1525 'ext': 'flv',
1526 'title': 'Tabletop: Dread, Last Thoughts',
1527 'description': 'Tabletop: Dread, Last Thoughts',
1528 'duration': 51690,
1529 },
750b9ff0 1530 },
d10fe835
YCH
1531 # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
1532 # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
1533 {
1534 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
1535 'info_dict': {
1536 'id': '4785848093001',
1537 'ext': 'mp4',
1538 'title': 'The Cardinal Pell Interview',
1539 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
1540 'uploader': 'GlobeCast Australia - GlobeStream',
0738187f
YCH
1541 'uploader_id': '2733773828001',
1542 'upload_date': '20160304',
1543 'timestamp': 1457083087,
d10fe835
YCH
1544 },
1545 'params': {
1546 # m3u8 downloads
1547 'skip_download': True,
1548 },
1549 },
9edf47df
S
1550 {
1551 # Brightcove embed with whitespace around attribute names
1552 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
1553 'info_dict': {
1554 'id': '3167554373001',
1555 'ext': 'mp4',
1556 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
1557 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
1558 'uploader_id': '1079349493',
1559 'upload_date': '20140207',
1560 'timestamp': 1391810548,
1561 },
1562 'params': {
1563 'skip_download': True,
1564 },
1565 },
134c207e
YCH
1566 # Another form of arte.tv embed
1567 {
1568 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
1569 'md5': '850bfe45417ddf221288c88a0cffe2e2',
1570 'info_dict': {
1571 'id': '030273-562_PLUS7-F',
1572 'ext': 'mp4',
1573 'title': 'ARTE Reportage - Nulle part, en France',
1574 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
1575 'upload_date': '20160409',
1576 },
1577 },
b8f67449
KM
1578 # LiveLeak embed
1579 {
1580 'url': 'http://www.wykop.pl/link/3088787/',
09747ba7 1581 'md5': '7619da8c820e835bef21a1efa2a0fc71',
b8f67449
KM
1582 'info_dict': {
1583 'id': '874_1459135191',
1584 'ext': 'mp4',
1585 'title': 'Man shows poor quality of new apartment building',
1586 'description': 'The wall is like a sand pile.',
1587 'uploader': 'Lake8737',
09747ba7
YCH
1588 },
1589 'add_ie': [LiveLeakIE.ie_key()],
1590 },
1591 # Another LiveLeak embed pattern (#13336)
1592 {
1593 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
1594 'info_dict': {
1595 'id': '2eb_1496309988',
1596 'ext': 'mp4',
1597 'title': 'Thief robs place where everyone was armed',
1598 'description': 'md5:694d73ee79e535953cf2488562288eee',
1599 'uploader': 'brazilwtf',
1600 },
1601 'add_ie': [LiveLeakIE.ie_key()],
b8f67449 1602 },
4a120778
YCH
1603 # Duplicated embedded video URLs
1604 {
1605 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
1606 'info_dict': {
1607 'id': '149298443_480_16c25b74_2',
1608 'ext': 'mp4',
1609 'title': 'vs. Blue Orange Spring Game',
1610 'uploader': 'www.hudl.com',
1611 },
1612 },
371ddb14
S
1613 # twitter:player:stream embed
1614 {
1615 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
1616 'info_dict': {
1617 'id': 'master',
1618 'ext': 'mp4',
1619 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
1620 'uploader': 'www.rtl.be',
1621 },
1622 'params': {
1623 # m3u8 downloads
1624 'skip_download': True,
1625 },
1626 },
32917907
RA
1627 # twitter:player embed
1628 {
1629 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
1630 'md5': 'a3e0df96369831de324f0778e126653c',
1631 'info_dict': {
1632 'id': '4909620399001',
1633 'ext': 'mp4',
1634 'title': 'What Do Black Holes Sound Like?',
1635 'description': 'what do black holes sound like',
1636 'upload_date': '20160524',
1637 'uploader_id': '29913724001',
1638 'timestamp': 1464107587,
1639 'uploader': 'TheAtlantic',
1640 },
1641 'add_ie': ['BrightcoveLegacy'],
fd6ca382
YCH
1642 },
1643 # Facebook <iframe> embed
1644 {
1645 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
dbf0157a 1646 'md5': 'fbcde74f534176ecb015849146dd3aee',
fd6ca382
YCH
1647 'info_dict': {
1648 'id': '599637780109885',
1649 'ext': 'mp4',
1650 'title': 'Facebook video #599637780109885',
1651 },
1652 },
fd1c5fba
S
1653 # Facebook <iframe> embed, plugin video
1654 {
1655 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
1656 'info_dict': {
1657 'id': '1754168231264132',
1658 'ext': 'mp4',
1659 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
1660 'uploader': 'Tariq Ramadan (official)',
1661 'timestamp': 1496758379,
1662 'upload_date': '20170606',
1663 },
1664 'params': {
1665 'skip_download': True,
1666 },
1667 },
fd6ca382
YCH
1668 # Facebook API embed
1669 {
1670 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
dbf0157a 1671 'md5': 'a47372ee61b39a7b90287094d447d94e',
fd6ca382
YCH
1672 'info_dict': {
1673 'id': '10153467542406923',
1674 'ext': 'mp4',
1675 'title': 'Facebook video #10153467542406923',
1676 },
7deef1ba
YCH
1677 },
1678 # Wordpress "YouTube Video Importer" plugin
1679 {
1680 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
dbf0157a 1681 'md5': 'd16797741b560b485194eddda8121b48',
7deef1ba
YCH
1682 'info_dict': {
1683 'id': 'HNTXWDXV9Is',
1684 'ext': 'mp4',
1685 'title': 'Blue Devils Drumline Stanford lot 2016',
1686 'upload_date': '20160627',
1687 'uploader_id': 'GENOCIDE8GENERAL10',
1688 'uploader': 'cylus cyrus',
1689 },
1690 },
81953d1a
RA
1691 {
1692 # video stored on custom kaltura server
1693 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
1694 'md5': '537617d06e64dfed891fa1593c4b30cc',
1695 'info_dict': {
1696 'id': '0_1iotm5bh',
1697 'ext': 'mp4',
1698 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
1699 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
1700 'uploader_id': 'videos.expansion@el-mundo.net',
1701 'upload_date': '20150429',
1702 'timestamp': 1430303472,
1703 },
1704 'add_ie': ['Kaltura'],
1705 },
c03adf90
YCH
1706 {
1707 # Non-standard Vimeo embed
1708 'url': 'https://openclassrooms.com/courses/understanding-the-web',
1709 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
1710 'info_dict': {
1711 'id': '148867247',
1712 'ext': 'mp4',
1713 'title': 'Understanding the web - Teaser',
1714 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
1715 'upload_date': '20151214',
1716 'uploader': 'OpenClassrooms',
1717 'uploader_id': 'openclassrooms',
1718 },
1719 'add_ie': ['Vimeo'],
1720 },
a5ff05df
S
1721 {
1722 # generic vimeo embed that requires original URL passed as Referer
1723 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
1724 'only_matching': True,
1725 },
1979969f
S
1726 {
1727 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
1728 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
1729 'info_dict': {
1730 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
1731 'ext': 'mp4',
1732 'title': 'Big Buck Bunny',
1733 'description': 'Royalty free test video',
1734 'timestamp': 1432816365,
1735 'upload_date': '20150528',
1736 'is_live': False,
1737 },
1738 'params': {
1739 'skip_download': True,
1740 },
1741 'add_ie': [ArkenaIE.ie_key()],
1742 },
2a1321a2
S
1743 {
1744 '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/',
1745 'info_dict': {
1746 'id': '1c7141f46c',
1747 'ext': 'mp4',
1748 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
1749 },
1750 'params': {
1751 'skip_download': True,
1752 },
1753 'add_ie': [Vbox7IE.ie_key()],
1754 },
b0c8f2e9
DR
1755 {
1756 # DBTV embeds
1757 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
fd3ec986
S
1758 'info_dict': {
1759 'id': '43254897',
1760 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
1761 },
b0c8f2e9
DR
1762 'playlist_mincount': 3,
1763 },
e186a9ec
S
1764 {
1765 # Videa embeds
1766 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
1767 'info_dict': {
1768 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
1769 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
1770 },
1771 'playlist_mincount': 2,
1772 },
b687c85e
S
1773 {
1774 # 20 minuten embed
1775 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
1776 'info_dict': {
1777 'id': '523629',
1778 'ext': 'mp4',
1779 'title': 'So kommen Sie bei Eis und Schnee sicher an',
1780 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
1781 },
1782 'params': {
1783 'skip_download': True,
1784 },
1785 'add_ie': [TwentyMinutenIE.ie_key()],
6ef3e65a
S
1786 },
1787 {
1788 # VideoPress embed
1789 'url': 'https://en.support.wordpress.com/videopress/',
1790 'info_dict': {
1791 'id': 'OcobLTqC',
1792 'ext': 'm4v',
1793 'title': 'IMG_5786',
1794 'timestamp': 1435711927,
1795 'upload_date': '20150701',
1796 },
1797 'params': {
1798 'skip_download': True,
1799 },
1800 'add_ie': [VideoPressIE.ie_key()],
fef51645 1801 },
eb3079b6
S
1802 {
1803 # Rutube embed
1804 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
1805 'info_dict': {
1806 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
1807 'ext': 'flv',
1808 'title': 'Магаззино: Казань 2',
1809 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
1810 'uploader': 'Магаззино',
1811 'upload_date': '20170228',
1812 'uploader_id': '996642',
1813 },
1814 'params': {
1815 'skip_download': True,
1816 },
1817 'add_ie': [RutubeIE.ie_key()],
1818 },
fef51645
YCH
1819 {
1820 # ThePlatform embedded with whitespaces in URLs
1821 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
1822 'only_matching': True,
1823 },
97952bdb
JH
1824 {
1825 # Senate ISVP iframe https
1826 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
1827 'md5': 'fb8c70b0b515e5037981a2492099aab8',
1828 'info_dict': {
1829 'id': 'govtaff020316',
1830 'ext': 'mp4',
1831 'title': 'Integrated Senate Video Player',
1832 },
1833 'add_ie': [SenateISVPIE.ie_key()],
1834 },
ab87c260
S
1835 {
1836 # Limelight embeds (1 channel embed + 4 media embeds)
1837 'url': 'http://www.sedona.com/FacilitatorTraining2017',
1838 'info_dict': {
1839 'id': 'FacilitatorTraining2017',
1840 'title': 'Facilitator Training 2017',
1841 },
1842 'playlist_mincount': 5,
1843 },
eb02940c
S
1844 {
1845 # Limelight embed (LimelightPlayerUtil.embed)
1846 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
1847 'info_dict': {
1848 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
1849 'ext': 'mp4',
1850 'title': '07448641',
1851 'timestamp': 1499890639,
1852 'upload_date': '20170712',
1853 },
1854 'params': {
1855 'skip_download': True,
1856 },
1857 'add_ie': ['LimelightMedia'],
1858 },
7986c3ab
S
1859 {
1860 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
1861 'info_dict': {
1862 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
1863 'title': 'Standoff with Walnut Creek murder suspect ends',
1864 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
1865 },
1866 'playlist_mincount': 4,
1867 },
55719459
JH
1868 {
1869 # WashingtonPost embed
1870 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
1871 'info_dict': {
1872 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
1873 'ext': 'mp4',
1874 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
1875 '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.',
1876 'timestamp': 1455216756,
1877 'uploader': 'The Washington Post',
1878 'upload_date': '20160211',
1879 },
1880 'add_ie': [WashingtonPostIE.ie_key()],
1881 },
2b8e6a68
S
1882 {
1883 # Mediaset embed
1884 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
1885 'info_dict': {
1886 'id': '720642',
1887 'ext': 'mp4',
1888 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
1889 },
1890 'params': {
1891 'skip_download': True,
1892 },
1893 'add_ie': [MediasetIE.ie_key()],
1894 },
73cf76a9
S
1895 {
1896 # JOJ.sk embeds
1897 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1898 'info_dict': {
1899 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
1900 'title': 'Slovenskom sa prehnala vlna silných búrok',
1901 },
1902 'playlist_mincount': 5,
1903 'add_ie': [JojIE.ie_key()],
1904 },
4328ddf8
S
1905 {
1906 # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
1907 'url': 'https://tvrain.ru/amp/418921/',
1908 'md5': 'cc00413936695987e8de148b67d14f1d',
1909 'info_dict': {
1910 'id': '418921',
1911 'ext': 'mp4',
1912 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
1913 },
1914 },
41918eaa 1915 {
1916 # vzaar embed
1663bd6e
S
1917 'url': 'http://help.vzaar.com/article/165-embedding-video',
1918 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
41918eaa 1919 'info_dict': {
1663bd6e 1920 'id': '8707641',
41918eaa 1921 'ext': 'mp4',
1663bd6e 1922 'title': 'Building A Business Online: Principal Chairs Q & A',
41918eaa 1923 },
1924 },
9ce1ac40 1925 {
1926 # multiple HTML5 videos on one page
1927 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
1928 'info_dict': {
1929 'id': 'keyscenarios',
1930 'title': 'Rescue Kit 14 Free Edition - Getting started',
1931 },
1932 'playlist_count': 4,
0987f2dd
T
1933 },
1934 {
1935 # vshare embed
1936 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
1937 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
1938 'info_dict': {
1939 'id': '0f64ce6',
1940 'title': 'vl14062007715967',
1941 'ext': 'mp4',
1942 }
2ca7ed41
S
1943 },
1944 {
1945 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
1946 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
1947 'info_dict': {
1948 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
1949 'ext': 'mp4',
1950 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
1951 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
1952 'timestamp': 1474354800,
1953 'upload_date': '20160920',
1954 }
7d540621
S
1955 },
1956 {
1957 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
1958 'info_dict': {
1959 'id': '1731611',
1960 'ext': 'mp4',
1961 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
1962 'description': 'md5:eb5f23826a027ba95277d105f248b825',
1963 'timestamp': 1516100691,
1964 'upload_date': '20180116',
1965 },
1966 'params': {
1967 'skip_download': True,
1968 },
1969 'add_ie': [SpringboardPlatformIE.ie_key()],
ea696249
S
1970 },
1971 {
1972 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1973 'info_dict': {
1974 'id': 'uPDB5I9wfp8',
1975 'ext': 'webm',
1976 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1977 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1978 'upload_date': '20160219',
1979 'uploader': 'Pocoyo - Português (BR)',
1980 'uploader_id': 'PocoyoBrazil',
1981 },
1982 'add_ie': [YoutubeIE.ie_key()],
1983 'params': {
1984 'skip_download': True,
1985 },
4c780fbd
S
1986 },
1987 {
1988 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
1989 'info_dict': {
1990 'id': 'vMDE4NzI1Mjgt690b',
1991 'ext': 'mp4',
1992 'title': 'Котята',
1993 },
1994 'add_ie': [YapFilesIE.ie_key()],
1995 'params': {
1996 'skip_download': True,
1997 },
1fc37ca3 1998 },
660a230b
S
1999 {
2000 # CloudflareStream embed
2001 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
2002 'info_dict': {
2003 'id': '31c9291ab41fac05471db4e73aa11717',
2004 'ext': 'mp4',
2005 'title': '31c9291ab41fac05471db4e73aa11717',
2006 },
2007 'add_ie': [CloudflareStreamIE.ie_key()],
2008 'params': {
2009 'skip_download': True,
2010 },
2011 },
6bd499e8
S
2012 {
2013 # PeerTube embed
2014 'url': 'https://joinpeertube.org/fr/home/',
2015 'info_dict': {
2016 'id': 'home',
2017 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
2018 },
2019 'playlist_count': 2,
2020 },
aee36ca8
S
2021 {
2022 # Indavideo embed
2023 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
2024 'info_dict': {
2025 'id': '1693903',
2026 'ext': 'mp4',
2027 'title': 'Így kell otthon hamburgert sütni',
2028 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
2029 'timestamp': 1426330212,
2030 'upload_date': '20150314',
2031 'uploader': 'StreetKitchen',
2032 'uploader_id': '546363',
2033 },
2034 'add_ie': [IndavideoEmbedIE.ie_key()],
2035 'params': {
2036 'skip_download': True,
2037 },
2038 },
cfd7f2a6
S
2039 {
2040 # APA embed via JWPlatform embed
2041 'url': 'http://www.vol.at/blue-man-group/5593454',
2042 'info_dict': {
2043 'id': 'jjv85FdZ',
2044 'ext': 'mp4',
2045 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
2046 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2047 'thumbnail': r're:^https?://.*\.jpg$',
2048 'duration': 254,
2049 'timestamp': 1519211149,
2050 'upload_date': '20180221',
2051 },
2052 'params': {
2053 'skip_download': True,
2054 },
2055 },
1fc37ca3
SO
2056 {
2057 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
2058 'md5': 'b68d276de422ab07ee1d49388103f457',
2059 'info_dict': {
2060 'id': '83645793',
2061 'title': 'Lock up and get excited',
1fc37ca3 2062 'ext': 'mp4'
d3431dcb
S
2063 },
2064 'skip': 'TODO: fix nested playlists processing in tests',
2065 },
9d1b2138
S
2066 {
2067 # Viqeo embeds
2068 'url': 'https://viqeo.tv/',
2069 'info_dict': {
2070 'id': 'viqeo',
2071 'title': 'All-new video platform',
2072 },
2073 'playlist_count': 6,
2074 },
83852e57
S
2075 {
2076 # Zype embed
2077 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
2078 'info_dict': {
2079 'id': '5b400b834b32992a310622b9',
2080 'ext': 'mp4',
2081 'title': 'Smoky Barbecue Favorites',
2082 'thumbnail': r're:^https?://.*\.jpe?g',
2083 },
2084 'add_ie': [ZypeIE.ie_key()],
2085 'params': {
2086 'skip_download': True,
2087 },
2088 },
e0b6e988
S
2089 {
2090 # videojs embed
2091 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
2092 'info_dict': {
2093 'id': 'shell',
2094 'ext': 'mp4',
2095 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
2096 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
2097 'thumbnail': r're:^https?://.*\.jpg$',
2098 },
2099 'params': {
2100 'skip_download': True,
2101 },
2102 'expected_warnings': ['Failed to download MPD manifest'],
2103 },
6e6b70d6
S
2104 # {
2105 # # TODO: find another test
2106 # # http://schema.org/VideoObject
2107 # 'url': 'https://flipagram.com/f/nyvTSJMKId',
2108 # 'md5': '888dcf08b7ea671381f00fab74692755',
2109 # 'info_dict': {
2110 # 'id': 'nyvTSJMKId',
2111 # 'ext': 'mp4',
2112 # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
2113 # 'description': '#love for cats.',
2114 # 'timestamp': 1461244995,
2115 # 'upload_date': '20160421',
2116 # },
2117 # 'params': {
2118 # 'force_generic_extractor': True,
2119 # },
2120 # }
cfe50f04 2121 ]
9b122384 2122
9b122384
PH
2123 def report_following_redirect(self, new_url):
2124 """Report information extraction."""
79649588 2125 self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
9b122384 2126
4fc946b5
PH
2127 def _extract_rss(self, url, video_id, doc):
2128 playlist_title = doc.find('./channel/title').text
2129 playlist_desc_el = doc.find('./channel/description')
2130 playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
2131
76c73715
PH
2132 entries = []
2133 for it in doc.findall('./channel/item'):
01aec848
BG
2134 next_url = None
2135 enclosure_nodes = it.findall('./enclosure')
2136 for e in enclosure_nodes:
2137 next_url = e.attrib.get('url')
2138 if next_url:
2139 break
2140
76c73715 2141 if not next_url:
01aec848 2142 next_url = xpath_text(it, 'link', fatal=False)
76c73715
PH
2143
2144 if not next_url:
2145 continue
2146
2147 entries.append({
413c1f8e 2148 '_type': 'url_transparent',
76c73715
PH
2149 'url': next_url,
2150 'title': it.find('title').text,
2151 })
4fc946b5
PH
2152
2153 return {
2154 '_type': 'playlist',
2155 'id': url,
2156 'title': playlist_title,
2157 'description': playlist_desc,
2158 'entries': entries,
2159 }
2160
c8e9a235
PH
2161 def _extract_camtasia(self, url, video_id, webpage):
2162 """ Returns None if no camtasia video can be found. """
2163
2164 camtasia_cfg = self._search_regex(
2165 r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
2166 webpage, 'camtasia configuration file', default=None)
2167 if camtasia_cfg is None:
2168 return None
2169
2170 title = self._html_search_meta('DC.title', webpage, fatal=True)
2171
2172 camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
2173 camtasia_cfg = self._download_xml(
2174 camtasia_url, video_id,
2175 note='Downloading camtasia configuration',
2176 errnote='Failed to download camtasia configuration')
2177 fileset_node = camtasia_cfg.find('./playlist/array/fileset')
2178
2179 entries = []
2180 for n in fileset_node.getchildren():
2181 url_n = n.find('./uri')
2182 if url_n is None:
2183 continue
2184
2185 entries.append({
2186 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
2187 'title': '%s - %s' % (title, n.tag),
2188 'url': compat_urlparse.urljoin(url, url_n.text),
2189 'duration': float_or_none(n.find('./duration').text),
2190 })
2191
2192 return {
2193 '_type': 'playlist',
2194 'entries': entries,
2195 'title': title,
2196 }
2197
9b122384 2198 def _real_extract(self, url):
ebd3c7b3
PH
2199 if url.startswith('//'):
2200 return {
2201 '_type': 'url',
20991253 2202 'url': self.http_scheme() + url,
ebd3c7b3
PH
2203 }
2204
a7130543
JMF
2205 parsed_url = compat_urlparse.urlparse(url)
2206 if not parsed_url.scheme:
04b4d394
PH
2207 default_search = self._downloader.params.get('default_search')
2208 if default_search is None:
1f7ccb90 2209 default_search = 'fixup_error'
04b4d394 2210
1f7ccb90 2211 if default_search in ('auto', 'auto_warning', 'fixup_error'):
04b4d394
PH
2212 if '/' in url:
2213 self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
2214 return self.url_result('http://' + url)
1f7ccb90 2215 elif default_search != 'fixup_error':
9c1fc022 2216 if default_search == 'auto_warning':
0e67ab0d
PH
2217 if re.match(r'^(?:url|URL)$', url):
2218 raise ExtractorError(
2219 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
2220 expected=True)
2221 else:
2222 self._downloader.report_warning(
7571c02c 2223 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
04b4d394 2224 return self.url_result('ytsearch:' + url)
1f7ccb90
PH
2225
2226 if default_search in ('error', 'fixup_error'):
7571c02c 2227 raise ExtractorError(
b74e86f4
PH
2228 '%r is not a valid URL. '
2229 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
2230 % (url, url), expected=True)
04b4d394 2231 else:
f2f2c0c2
PH
2232 if ':' not in default_search:
2233 default_search += ':'
04b4d394 2234 return self.url_result(default_search + url)
4d54ef20
PH
2235
2236 url, smuggled_data = unsmuggle_url(url)
2237 force_videoid = None
d6e6a422 2238 is_intentional = smuggled_data and smuggled_data.get('to_generic')
4d54ef20
PH
2239 if smuggled_data and 'force_videoid' in smuggled_data:
2240 force_videoid = smuggled_data['force_videoid']
2241 video_id = force_videoid
2242 else:
9dcd6fd3 2243 video_id = self._generic_id(url)
3d83a1ae 2244
79649588 2245 self.to_screen('%s: Requesting header' % video_id)
c1d1facd 2246
ebab4520 2247 head_req = HEADRequest(url)
23be51d8 2248 head_response = self._request_webpage(
ebab4520
PH
2249 head_req, video_id,
2250 note=False, errnote='Could not send HEAD request to %s' % url,
2251 fatal=False)
42393ce2 2252
23be51d8 2253 if head_response is not False:
42393ce2 2254 # Check for redirect
5551d771 2255 new_url = compat_str(head_response.geturl())
42393ce2
PH
2256 if url != new_url:
2257 self.report_following_redirect(new_url)
4d54ef20
PH
2258 if force_videoid:
2259 new_url = smuggle_url(
2260 new_url, {'force_videoid': force_videoid})
cecaaf3f 2261 return self.url_result(new_url)
42393ce2 2262
23be51d8
PH
2263 full_response = None
2264 if head_response is False:
5c2266df 2265 request = sanitized_Request(url)
58bde34a
S
2266 request.add_header('Accept-Encoding', '*')
2267 full_response = self._request_webpage(request, video_id)
23be51d8
PH
2268 head_response = full_response
2269
f930e0c7
S
2270 info_dict = {
2271 'id': video_id,
9dcd6fd3 2272 'title': self._generic_title(url),
303dcdb9 2273 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
f930e0c7
S
2274 }
2275
23be51d8 2276 # Check for direct link to a video
955737b2 2277 content_type = head_response.headers.get('Content-Type', '').lower()
263eff95 2278 m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
23be51d8 2279 if m:
4e363703 2280 format_id = compat_str(m.group('format_id'))
f930e0c7 2281 if format_id.endswith('mpegurl'):
eadc3ccd 2282 formats = self._extract_m3u8_formats(url, video_id, 'mp4')
f930e0c7
S
2283 elif format_id == 'f4m':
2284 formats = self._extract_f4m_formats(url, video_id)
eadc3ccd 2285 else:
2286 formats = [{
4e363703 2287 'format_id': format_id,
eadc3ccd 2288 'url': url,
2289 'vcodec': 'none' if m.group('type') == 'audio' else None
2290 }]
de6c51e8 2291 info_dict['direct'] = True
19dbaeec 2292 self._sort_formats(formats)
de6c51e8 2293 info_dict['formats'] = formats
f930e0c7 2294 return info_dict
42393ce2 2295
d6e6a422 2296 if not self._downloader.params.get('test', False) and not is_intentional:
2fece970
S
2297 force = self._downloader.params.get('force_generic_extractor', False)
2298 self._downloader.report_warning(
2299 '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
d6e6a422 2300
4e262a88 2301 if not full_response:
5c2266df 2302 request = sanitized_Request(url)
58bde34a
S
2303 # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
2304 # making it impossible to download only chunk of the file (yet we need only 512kB to
2305 # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
2306 # that will always result in downloading the whole file that is not desirable.
2307 # Therefore for extraction pass we have to override Accept-Encoding to any in order
2308 # to accept raw bytes and being able to download only a chunk.
2309 # It may probably better to solve this by checking Content-Type for application/octet-stream
2310 # after HEAD request finishes, but not sure if we can rely on this.
2311 request.add_header('Accept-Encoding', '*')
2312 full_response = self._request_webpage(request, video_id)
4e262a88 2313
5940862d
S
2314 first_bytes = full_response.read(512)
2315
2316 # Is it an M3U playlist?
0d769bcb 2317 if first_bytes.startswith(b'#EXTM3U'):
5940862d 2318 info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
19dbaeec 2319 self._sort_formats(info_dict['formats'])
5940862d
S
2320 return info_dict
2321
4e262a88
PH
2322 # Maybe it's a direct link to a video?
2323 # Be careful not to download the whole thing!
61ca9a80 2324 if not is_html(first_bytes):
4e262a88
PH
2325 self._downloader.report_warning(
2326 'URL could be a direct video link, returning it as such.')
f930e0c7 2327 info_dict.update({
4e262a88
PH
2328 'direct': True,
2329 'url': url,
f930e0c7
S
2330 })
2331 return info_dict
4e262a88
PH
2332
2333 webpage = self._webpage_read_content(
2334 full_response, url, video_id, prefix=first_bytes)
2335
9b122384 2336 self.report_extraction(video_id)
887c6acd 2337
1b840245 2338 # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
4fc946b5 2339 try:
f7854627 2340 doc = compat_etree_fromstring(webpage.encode('utf-8'))
4fc946b5
PH
2341 if doc.tag == 'rss':
2342 return self._extract_rss(url, video_id, doc)
cc99a77a
S
2343 elif doc.tag == 'SmoothStreamingMedia':
2344 info_dict['formats'] = self._parse_ism_formats(doc, url)
2345 self._sort_formats(info_dict['formats'])
2346 return info_dict
e5e8d20a 2347 elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
19dbaeec
S
2348 smil = self._parse_smil(doc, url, video_id)
2349 self._sort_formats(smil['formats'])
2350 return smil
729accb4 2351 elif doc.tag == '{http://xspf.org/ns/0/}playlist':
96b8b9ab 2352 return self.playlist_result(
47a5cb77
S
2353 self._parse_xspf(
2354 doc, video_id, xspf_url=url,
2355 xspf_base_url=compat_str(full_response.geturl())),
96b8b9ab 2356 video_id)
1b840245 2357 elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
f930e0c7 2358 info_dict['formats'] = self._parse_mpd_formats(
d3f8b76b 2359 doc,
5551d771 2360 mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
86f4d14f 2361 mpd_url=url)
19dbaeec 2362 self._sort_formats(info_dict['formats'])
f930e0c7
S
2363 return info_dict
2364 elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
2365 info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
19dbaeec 2366 self._sort_formats(info_dict['formats'])
f930e0c7 2367 return info_dict
f7300c5c 2368 except compat_xml_parse_error:
4fc946b5
PH
2369 pass
2370
c8e9a235
PH
2371 # Is it a Camtasia project?
2372 camtasia_res = self._extract_camtasia(url, video_id, webpage)
2373 if camtasia_res is not None:
2374 return camtasia_res
2375
14390730
S
2376 # Sometimes embedded video player is hidden behind percent encoding
2377 # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
2378 # Unescaping the whole page allows to handle those cases in a generic way
45eedbe5 2379 webpage = compat_urllib_parse_unquote(webpage)
1f7659db 2380
887c6acd
PH
2381 # it's tempting to parse this further, but you would
2382 # have to take into account all the variations like
2383 # Video Title - Site Name
2384 # Site Name | Video Title
2385 # Video Title - Tagline | Site Name
2386 # and so on and so forth; it's just not practical
6f41b2bc
S
2387 video_title = self._og_search_title(
2388 webpage, default=None) or self._html_search_regex(
79649588
PH
2389 r'(?s)<title>(.*?)</title>', webpage, 'video title',
2390 default='video')
ef4fd848 2391
4d805e06
PH
2392 # Try to detect age limit automatically
2393 age_limit = self._rta_search(webpage)
2394 # And then there are the jokers who advertise that they use RTA,
2395 # but actually don't.
2396 AGE_LIMIT_MARKERS = [
197224b7 2397 r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
4d805e06
PH
2398 ]
2399 if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
2400 age_limit = 18
2401
ef4fd848
PH
2402 # video uploader is domain name
2403 video_uploader = self._search_regex(
79649588 2404 r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
887c6acd 2405
6f41b2bc
S
2406 video_description = self._og_search_description(webpage, default=None)
2407 video_thumbnail = self._og_search_thumbnail(webpage, default=None)
2408
b311b0ea
S
2409 info_dict.update({
2410 'title': video_title,
2411 'description': video_description,
2412 'thumbnail': video_thumbnail,
2413 'age_limit': age_limit,
2414 })
2415
1f4b722b 2416 # Look for Brightcove Legacy Studio embeds
4fcaa4f4 2417 bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
99877772 2418 if bc_urls:
99877772
PH
2419 entries = [{
2420 '_type': 'url',
2421 'url': smuggle_url(bc_url, {'Referer': url}),
3b7d9aa4 2422 'ie_key': 'BrightcoveLegacy'
99877772
PH
2423 } for bc_url in bc_urls]
2424
2425 return {
2426 '_type': 'playlist',
2427 'title': video_title,
2428 'id': video_id,
2429 'entries': entries,
2430 }
cfe50f04 2431
f6519f89 2432 # Look for Brightcove New Studio embeds
0254f93b 2433 bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
f6519f89 2434 if bc_urls:
5399ab3f
S
2435 return self.playlist_from_matches(
2436 bc_urls, video_id, video_title,
2437 getter=lambda x: smuggle_url(x, {'referrer': url}),
2438 ie='BrightcoveNew')
ed126900 2439
4e826cd9
S
2440 # Look for Nexx embeds
2441 nexx_urls = NexxIE._extract_urls(webpage)
2442 if nexx_urls:
2443 return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
2444
3f59b015
S
2445 # Look for Nexx iFrame embeds
2446 nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
2447 if nexx_embed_urls:
2448 return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
2449
4d8819d2
S
2450 # Look for ThePlatform embeds
2451 tp_urls = ThePlatformIE._extract_urls(webpage)
2452 if tp_urls:
46b18f23 2453 return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
4d8819d2 2454
48a5eabc
S
2455 # Look for Vessel embeds
2456 vessel_urls = VesselIE._extract_urls(webpage)
2457 if vessel_urls:
46b18f23 2458 return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
48a5eabc 2459
59b8ab58
PH
2460 # Look for embedded rtl.nl player
2461 matches = re.findall(
2637fadc 2462 r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
59b8ab58
PH
2463 webpage)
2464 if matches:
46b18f23 2465 return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
59b8ab58 2466
09b9c45e
S
2467 vimeo_urls = VimeoIE._extract_urls(url, webpage)
2468 if vimeo_urls:
46b18f23 2469 return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
7115ca84 2470
a1b85269
YCH
2471 vid_me_embed_url = self._search_regex(
2472 r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
2473 webpage, 'vid.me embed', default=None)
2474 if vid_me_embed_url is not None:
2475 return self.url_result(vid_me_embed_url, 'Vidme')
2476
66c9fa36
S
2477 # Look for YouTube embeds
2478 youtube_urls = YoutubeIE._extract_urls(webpage)
2479 if youtube_urls:
46b18f23 2480 return self.playlist_from_matches(
66c9fa36 2481 youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
7deef1ba 2482
ad213a1d 2483 matches = DailymotionIE._extract_urls(webpage)
355e4fd0 2484 if matches:
46b18f23 2485 return self.playlist_from_matches(matches, video_id, video_title)
355e4fd0 2486
8489578d
NJ
2487 # Look for embedded Dailymotion playlist player (#3822)
2488 m = re.search(
2489 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
2490 if m:
2491 playlists = re.findall(
2492 r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
2493 if playlists:
46b18f23
JH
2494 return self.playlist_from_matches(
2495 playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
8489578d 2496
71a1db89
S
2497 # Look for DailyMail embeds
2498 dailymail_urls = DailyMailIE._extract_urls(webpage)
2499 if dailymail_urls:
2500 return self.playlist_from_matches(
2501 dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
2502
ef4fd848 2503 # Look for embedded Wistia player
58bb4402
S
2504 wistia_url = WistiaIE._extract_url(webpage)
2505 if wistia_url:
ef4fd848
PH
2506 return {
2507 '_type': 'url_transparent',
58bb4402
S
2508 'url': self._proto_relative_url(wistia_url),
2509 'ie_key': WistiaIE.ie_key(),
ef4fd848 2510 'uploader': video_uploader,
ef4fd848 2511 }
5f6a1245 2512
bab19a8e
S
2513 # Look for SVT player
2514 svt_url = SVTIE._extract_url(webpage)
2515 if svt_url:
2516 return self.url_result(svt_url, 'SVT')
2517
c19f7764
JMF
2518 # Look for Bandcamp pages with custom domain
2519 mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
2520 if mobj is not None:
2521 burl = unescapeHTML(mobj.group(1))
09804265
JMF
2522 # Don't set the extractor because it can be a track url or an album
2523 return self.url_result(burl)
c19f7764 2524
f25571ff
PH
2525 # Look for embedded Vevo player
2526 mobj = re.search(
2527 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
2528 if mobj is not None:
2529 return self.url_result(mobj.group('url'))
796df3c6
S
2530
2531 # Look for embedded Viddler player
cb454b33
S
2532 mobj = re.search(
2533 r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
2534 webpage)
796df3c6
S
2535 if mobj is not None:
2536 return self.url_result(mobj.group('url'))
f25571ff 2537
3378d67a
S
2538 # Look for NYTimes player
2539 mobj = re.search(
2540 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
2541 webpage)
2542 if mobj is not None:
2543 return self.url_result(mobj.group('url'))
2544
cefdf970
S
2545 # Look for Libsyn player
2546 mobj = re.search(
2547 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
2548 if mobj is not None:
2549 return self.url_result(mobj.group('url'))
2550
c0d0b01f 2551 # Look for Ooyala videos
8a37aa15 2552 mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
f076b638 2553 re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
198d4cb4 2554 re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
edfcf7ab
YCH
2555 re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
2556 re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
c0d0b01f 2557 if mobj is not None:
9837cb75
RA
2558 embed_token = self._search_regex(
2559 r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
2560 webpage, 'ooyala embed token', default=None)
2561 return OoyalaIE._build_url_result(smuggle_url(
2562 mobj.group('ec'), {
2563 'domain': url,
2564 'embed_token': embed_token,
2565 }))
c0d0b01f 2566
f076b638 2567 # Look for multiple Ooyala embeds on SBN network websites
2568 mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
2569 if mobj is not None:
2570 embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
2571 if embeds:
46b18f23
JH
2572 return self.playlist_from_matches(
2573 embeds, video_id, video_title,
2574 getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
f076b638 2575
aa94a6d3 2576 # Look for Aparat videos
48099643 2577 mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
aa94a6d3
PH
2578 if mobj is not None:
2579 return self.url_result(mobj.group(1), 'Aparat')
2580
c93c2ab1 2581 # Look for MPORA videos
c3f51436 2582 mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
c93c2ab1
PH
2583 if mobj is not None:
2584 return self.url_result(mobj.group(1), 'Mpora')
5f59ee79 2585
15c0e8e7 2586 # Look for embedded NovaMov-based player
8f89e687 2587 mobj = re.search(
8dfa187b 2588 r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
15c0e8e7
S
2589 (?P<url>http://(?:(?:embed|www)\.)?
2590 (?:novamov\.com|
2591 nowvideo\.(?:ch|sx|eu|at|ag|co)|
2592 videoweed\.(?:es|com)|
2593 movshare\.(?:net|sx|ag)|
2594 divxstage\.(?:eu|net|ch|co|at|ag))
2595 /embed\.php.+?)\1''', webpage)
8f89e687 2596 if mobj is not None:
15c0e8e7 2597 return self.url_result(mobj.group('url'))
50f56607 2598
9834872b 2599 # Look for embedded Facebook player
0646e34c
S
2600 facebook_urls = FacebookIE._extract_urls(webpage)
2601 if facebook_urls:
2602 return self.playlist_from_matches(facebook_urls, video_id, video_title)
9834872b 2603
ca97a56e
S
2604 # Look for embedded VK player
2605 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
2606 if mobj is not None:
2607 return self.url_result(mobj.group('url'), 'VK')
2608
33d4fdab
S
2609 # Look for embedded Odnoklassniki player
2610 mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
2611 if mobj is not None:
2612 return self.url_result(mobj.group('url'), 'Odnoklassniki')
2613
0364fa8b
S
2614 # Look for embedded ivi player
2615 mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
2616 if mobj is not None:
2617 return self.url_result(mobj.group('url'), 'Ivi')
2618
db1f3888
PH
2619 # Look for embedded Huffington Post player
2620 mobj = re.search(
c3f51436 2621 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
db1f3888
PH
2622 if mobj is not None:
2623 return self.url_result(mobj.group('url'), 'HuffPost')
2624
1b86cc41 2625 # Look for embed.ly
2626 mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
2627 if mobj is not None:
2628 return self.url_result(mobj.group('url'))
2629 mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
2630 if mobj is not None:
f7e6f7fa 2631 return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
1b86cc41 2632
60cc4dc4
PH
2633 # Look for funnyordie embed
2634 matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
2635 if matches:
46b18f23
JH
2636 return self.playlist_from_matches(
2637 matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
60cc4dc4 2638
db546cf8
S
2639 # Look for BBC iPlayer embed
2640 matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
2641 if matches:
46b18f23 2642 return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
db546cf8 2643
93d020dd
S
2644 # Look for embedded RUTV player
2645 rutv_url = RUTVIE._extract_url(webpage)
2646 if rutv_url:
2647 return self.url_result(rutv_url, 'RUTV')
2648
494f20cb 2649 # Look for embedded TVC player
b8599718
S
2650 tvc_url = TVCIE._extract_url(webpage)
2651 if tvc_url:
2652 return self.url_result(tvc_url, 'TVC')
494f20cb 2653
d40a3b5b 2654 # Look for embedded SportBox player
476cf548 2655 sportbox_urls = SportBoxIE._extract_urls(webpage)
d40a3b5b 2656 if sportbox_urls:
476cf548 2657 return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
d40a3b5b 2658
2bb5b6d0
S
2659 # Look for embedded XHamster player
2660 xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
2661 if xhamster_urls:
46b18f23 2662 return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
2bb5b6d0 2663
2c9ca782
S
2664 # Look for embedded TNAFlixNetwork player
2665 tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
2666 if tnaflix_urls:
46b18f23 2667 return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
2c9ca782 2668
b52c9ef1
S
2669 # Look for embedded PornHub player
2670 pornhub_urls = PornHubIE._extract_urls(webpage)
2671 if pornhub_urls:
46b18f23 2672 return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
b52c9ef1 2673
37e7a71c
S
2674 # Look for embedded DrTuber player
2675 drtuber_urls = DrTuberIE._extract_urls(webpage)
2676 if drtuber_urls:
46b18f23 2677 return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
37e7a71c 2678
e28ed498
S
2679 # Look for embedded RedTube player
2680 redtube_urls = RedTubeIE._extract_urls(webpage)
2681 if redtube_urls:
46b18f23 2682 return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
e28ed498 2683
06993715
S
2684 # Look for embedded Tube8 player
2685 tube8_urls = Tube8IE._extract_urls(webpage)
2686 if tube8_urls:
2687 return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
2688
9872d311
S
2689 # Look for embedded Tvigle player
2690 mobj = re.search(
2691 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
2692 if mobj is not None:
2693 return self.url_result(mobj.group('url'), 'Tvigle')
2694
7e2ede98
JMF
2695 # Look for embedded TED player
2696 mobj = re.search(
d7cc31b6 2697 r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
7e2ede98
JMF
2698 if mobj is not None:
2699 return self.url_result(mobj.group('url'), 'TED')
2700
5c386252 2701 # Look for embedded Ustream videos
d77ac737
YCH
2702 ustream_url = UstreamIE._extract_url(webpage)
2703 if ustream_url:
2704 return self.url_result(ustream_url, UstreamIE.ie_key())
5c386252 2705
893f8832
PH
2706 # Look for embedded arte.tv player
2707 mobj = re.search(
134c207e 2708 r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
893f8832
PH
2709 webpage)
2710 if mobj is not None:
2711 return self.url_result(mobj.group('url'), 'ArteTVEmbed')
2712
cbd55ade
S
2713 # Look for embedded francetv player
2714 mobj = re.search(
2715 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
2716 webpage)
2717 if mobj is not None:
2718 return self.url_result(mobj.group('url'))
2719
cb3ac1c6
S
2720 # Look for embedded smotri.com player
2721 smotri_url = SmotriIE._extract_url(webpage)
2722 if smotri_url:
2723 return self.url_result(smotri_url, 'Smotri')
2724
e6c2d9ad 2725 # Look for embedded Myvi.ru player
6dd94d3a 2726 myvi_url = MyviIE._extract_url(webpage)
e6c2d9ad
S
2727 if myvi_url:
2728 return self.url_result(myvi_url)
2729
dfb1b146 2730 # Look for embedded soundcloud player
94aae015
S
2731 soundcloud_urls = SoundcloudIE._extract_urls(webpage)
2732 if soundcloud_urls:
46b18f23 2733 return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
20991253 2734
027e2312
S
2735 # Look for tunein player
2736 tunein_urls = TuneInBaseIE._extract_urls(webpage)
2737 if tunein_urls:
46b18f23 2738 return self.playlist_from_matches(tunein_urls, video_id, video_title)
027e2312 2739
c5cd249e 2740 # Look for embedded mtvservices player
46fde8a1
S
2741 mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
2742 if mtvservices_url:
2743 return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
c5cd249e 2744
49807b4a
S
2745 # Look for embedded yahoo player
2746 mobj = re.search(
2747 r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
2748 webpage)
2749 if mobj is not None:
2750 return self.url_result(mobj.group('url'), 'Yahoo')
2751
2ef6fcb5
PH
2752 # Look for embedded sbs.com.au player
2753 mobj = re.search(
e98b8e79
PH
2754 r'''(?x)
2755 (?:
2756 <meta\s+property="og:video"\s+content=|
2757 <iframe[^>]+?src=
2758 )
2759 (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
2ef6fcb5
PH
2760 webpage)
2761 if mobj is not None:
2762 return self.url_result(mobj.group('url'), 'SBS')
2763
42bdd9d0
PH
2764 # Look for embedded Cinchcast player
2765 mobj = re.search(
2766 r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
2767 webpage)
2768 if mobj is not None:
2769 return self.url_result(mobj.group('url'), 'Cinchcast')
2770
1a94ff68 2771 mobj = re.search(
5263cdfc 2772 r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
1a94ff68 2773 webpage)
8001607e
YCH
2774 if not mobj:
2775 mobj = re.search(
2776 r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
2777 webpage)
1a94ff68
S
2778 if mobj is not None:
2779 return self.url_result(mobj.group('url'), 'MLB')
2780
1419fafd 2781 mobj = re.search(
dd467d33 2782 r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
1419fafd
S
2783 webpage)
2784 if mobj is not None:
2785 return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
2786
af63fed7 2787 mobj = re.search(
78d3b3e2 2788 r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
af63fed7
PH
2789 webpage)
2790 if mobj is not None:
2791 return self.url_result(mobj.group('url'), 'Livestream')
2792
255fca5e
S
2793 # Look for Zapiks embed
2794 mobj = re.search(
2795 r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
2796 if mobj is not None:
2797 return self.url_result(mobj.group('url'), 'Zapiks')
2798
e3216b82 2799 # Look for Kaltura embeds
c287f2bc
S
2800 kaltura_url = KalturaIE._extract_url(webpage)
2801 if kaltura_url:
2802 return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
e3216b82 2803
665e9452 2804 # Look for EaglePlatform embeds
06a96da1
S
2805 eagleplatform_url = EaglePlatformIE._extract_url(webpage)
2806 if eagleplatform_url:
665e9452 2807 return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
135c9c42 2808
665e9452 2809 # Look for ClipYou (uses EaglePlatform) embeds
d47ae7f6
S
2810 mobj = re.search(
2811 r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
2812 if mobj is not None:
2813 return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
2814
f8388757 2815 # Look for Pladform embeds
45dad7ba
S
2816 pladform_url = PladformIE._extract_url(webpage)
2817 if pladform_url:
2818 return self.url_result(pladform_url)
f8388757 2819
ff18735c
S
2820 # Look for Videomore embeds
2821 videomore_url = VideomoreIE._extract_url(webpage)
2822 if videomore_url:
2823 return self.url_result(videomore_url)
2824
83f1481b
S
2825 # Look for Webcaster embeds
2826 webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
2827 if webcaster_url:
2828 return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
2829
2dcc114f
S
2830 # Look for Playwire embeds
2831 mobj = re.search(
2832 r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
2833 if mobj is not None:
2834 return self.url_result(mobj.group('url'))
2835
ad320e9b
NJ
2836 # Look for 5min embeds
2837 mobj = re.search(
2838 r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
2839 if mobj is not None:
2840 return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
2841
18153f1b
S
2842 # Look for Crooks and Liars embeds
2843 mobj = re.search(
2844 r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
2845 if mobj is not None:
2846 return self.url_result(mobj.group('url'))
2847
a2edf2e7
YCH
2848 # Look for NBC Sports VPlayer embeds
2849 nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
2850 if nbc_sports_url:
2851 return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
2852
de3eb07e
YCH
2853 # Look for NBC News embeds
2854 nbc_news_embed_url = re.search(
2855 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
2856 if nbc_news_embed_url:
2857 return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
2858
653789af 2859 # Look for Google Drive embeds
5b251628 2860 google_drive_url = GoogleDriveIE._extract_url(webpage)
653789af 2861 if google_drive_url:
2862 return self.url_result(google_drive_url, 'GoogleDrive')
2863
418c5cc3
YCH
2864 # Look for UDN embeds
2865 mobj = re.search(
2637fadc 2866 r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
418c5cc3
YCH
2867 if mobj is not None:
2868 return self.url_result(
0a160363 2869 compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
418c5cc3 2870
2fe1b5bd
YCH
2871 # Look for Senate ISVP iframe
2872 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
2873 if senate_isvp_url:
25c3a734 2874 return self.url_result(senate_isvp_url, 'SenateISVP')
2fe1b5bd 2875
1ac1c4c2
S
2876 # Look for OnionStudios embeds
2877 onionstudios_url = OnionStudiosIE._extract_url(webpage)
2878 if onionstudios_url:
2879 return self.url_result(onionstudios_url)
2880
67167920 2881 # Look for ViewLift embeds
2882 viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
2883 if viewlift_url:
2884 return self.url_result(viewlift_url)
eedd20ef 2885
7cb09524 2886 # Look for JWPlatform embeds
b0ead0e0
S
2887 jwplatform_urls = JWPlatformIE._extract_urls(webpage)
2888 if jwplatform_urls:
2889 return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
7cb09524 2890
aecfcd4e
S
2891 # Look for Digiteka embeds
2892 digiteka_url = DigitekaIE._extract_url(webpage)
2893 if digiteka_url:
2894 return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
6aeba407 2895
1979969f
S
2896 # Look for Arkena embeds
2897 arkena_url = ArkenaIE._extract_url(webpage)
2898 if arkena_url:
2899 return self.url_result(arkena_url, ArkenaIE.ie_key())
2900
b1c35797
RA
2901 # Look for Piksel embeds
2902 piksel_url = PikselIE._extract_url(webpage)
2903 if piksel_url:
2904 return self.url_result(piksel_url, PikselIE.ie_key())
2905
1bf996fa 2906 # Look for Limelight embeds
e5d39886
S
2907 limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
2908 if limelight_urls:
2909 return self.playlist_result(
2910 limelight_urls, video_id, video_title, video_description)
2911
7986c3ab
S
2912 # Look for Anvato embeds
2913 anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
2914 if anvato_urls:
2915 return self.playlist_result(
2916 anvato_urls, video_id, video_title, video_description)
2917
a5158f38
YCH
2918 # Look for AdobeTVVideo embeds
2919 mobj = re.search(
2920 r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
2921 webpage)
2922 if mobj is not None:
2923 return self.url_result(
2924 self._proto_relative_url(unescapeHTML(mobj.group(1))),
2925 'AdobeTVVideo')
2926
088e1aac
YCH
2927 # Look for Vine embeds
2928 mobj = re.search(
2929 r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
2930 webpage)
2931 if mobj is not None:
2932 return self.url_result(
2933 self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
2934
217d5ae0
RA
2935 # Look for VODPlatform embeds
2936 mobj = re.search(
93b84045 2937 r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
217d5ae0
RA
2938 webpage)
2939 if mobj is not None:
2940 return self.url_result(
93b84045 2941 self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
217d5ae0 2942
7d273a38
RA
2943 # Look for Mangomolo embeds
2944 mobj = re.search(
d05ef09d 2945 r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
7d273a38
RA
2946 (?:
2947 video\?.*?\bid=(?P<video_id>\d+)|
2948 index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
2949 ).+?)\1''', webpage)
2950 if mobj is not None:
2951 info = {
2952 '_type': 'url_transparent',
2953 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
2954 'title': video_title,
2955 'description': video_description,
2956 'thumbnail': video_thumbnail,
2957 'uploader': video_uploader,
2958 }
2959 video_id = mobj.group('video_id')
2960 if video_id:
2961 info.update({
2962 'ie_key': 'MangomoloVideo',
2963 'id': video_id,
2964 })
2965 else:
2966 info.update({
2967 'ie_key': 'MangomoloLive',
2968 'id': mobj.group('channel_id'),
2969 })
2970 return info
2971
5a51775a
YCH
2972 # Look for Instagram embeds
2973 instagram_embed_url = InstagramIE._extract_embed_url(webpage)
2974 if instagram_embed_url is not None:
11e60fca
S
2975 return self.url_result(
2976 self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
5a51775a 2977
b8f67449 2978 # Look for LiveLeak embeds
09747ba7
YCH
2979 liveleak_urls = LiveLeakIE._extract_urls(webpage)
2980 if liveleak_urls:
2981 return self.playlist_from_matches(liveleak_urls, video_id, video_title)
b8f67449 2982
5d39176f
S
2983 # Look for 3Q SDN embeds
2984 threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
2985 if threeqsdn_url:
6f41b2bc
S
2986 return {
2987 '_type': 'url_transparent',
2988 'ie_key': ThreeQSDNIE.ie_key(),
2989 'url': self._proto_relative_url(threeqsdn_url),
2990 'title': video_title,
2991 'description': video_description,
2992 'thumbnail': video_thumbnail,
2993 'uploader': video_uploader,
2994 }
5d39176f 2995
2a1321a2
S
2996 # Look for VBOX7 embeds
2997 vbox7_url = Vbox7IE._extract_url(webpage)
2998 if vbox7_url:
2999 return self.url_result(vbox7_url, Vbox7IE.ie_key())
3000
b0c8f2e9
DR
3001 # Look for DBTV embeds
3002 dbtv_urls = DBTVIE._extract_urls(webpage)
3003 if dbtv_urls:
46b18f23 3004 return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
b0c8f2e9 3005
e186a9ec
S
3006 # Look for Videa embeds
3007 videa_urls = VideaIE._extract_urls(webpage)
3008 if videa_urls:
46b18f23 3009 return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
e186a9ec 3010
b687c85e
S
3011 # Look for 20 minuten embeds
3012 twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
3013 if twentymin_urls:
46b18f23
JH
3014 return self.playlist_from_matches(
3015 twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
b687c85e 3016
17f8deeb
S
3017 # Look for Openload embeds
3018 openload_urls = OpenloadIE._extract_urls(webpage)
3019 if openload_urls:
46b18f23
JH
3020 return self.playlist_from_matches(
3021 openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
17f8deeb 3022
6ef3e65a
S
3023 # Look for VideoPress embeds
3024 videopress_urls = VideoPressIE._extract_urls(webpage)
3025 if videopress_urls:
46b18f23
JH
3026 return self.playlist_from_matches(
3027 videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
6ef3e65a 3028
eb3079b6
S
3029 # Look for Rutube embeds
3030 rutube_urls = RutubeIE._extract_urls(webpage)
3031 if rutube_urls:
46b18f23 3032 return self.playlist_from_matches(
2583c0b5 3033 rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
6ef3e65a 3034
55719459
JH
3035 # Look for WashingtonPost embeds
3036 wapo_urls = WashingtonPostIE._extract_urls(webpage)
3037 if wapo_urls:
3038 return self.playlist_from_matches(
3039 wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
3040
5d29af3d 3041 # Look for Mediaset embeds
8fd12a08 3042 mediaset_urls = MediasetIE._extract_urls(self, webpage)
5d29af3d
S
3043 if mediaset_urls:
3044 return self.playlist_from_matches(
3045 mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
3046
73cf76a9
S
3047 # Look for JOJ.sk embeds
3048 joj_urls = JojIE._extract_urls(webpage)
3049 if joj_urls:
3050 return self.playlist_from_matches(
3051 joj_urls, video_id, video_title, ie=JojIE.ie_key())
3052
24e966e8
PH
3053 # Look for megaphone.fm embeds
3054 mpfn_urls = MegaphoneIE._extract_urls(webpage)
3055 if mpfn_urls:
3056 return self.playlist_from_matches(
3057 mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
3058
1663bd6e
S
3059 # Look for vzaar embeds
3060 vzaar_urls = VzaarIE._extract_urls(webpage)
3061 if vzaar_urls:
3062 return self.playlist_from_matches(
3063 vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
3064
26bae2d9
S
3065 channel9_urls = Channel9IE._extract_urls(webpage)
3066 if channel9_urls:
3067 return self.playlist_from_matches(
3068 channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
3069
0987f2dd
T
3070 vshare_urls = VShareIE._extract_urls(webpage)
3071 if vshare_urls:
3072 return self.playlist_from_matches(
3073 vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
3074
8056c854 3075 # Look for Mediasite embeds
2ca7ed41
S
3076 mediasite_urls = MediasiteIE._extract_urls(webpage)
3077 if mediasite_urls:
3078 entries = [
3079 self.url_result(smuggle_url(
3080 compat_urlparse.urljoin(url, mediasite_url),
3081 {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
3082 for mediasite_url in mediasite_urls]
3083 return self.playlist_result(entries, video_id, video_title)
8056c854 3084
7d540621
S
3085 springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
3086 if springboardplatform_urls:
3087 return self.playlist_from_matches(
3088 springboardplatform_urls, video_id, video_title,
3089 ie=SpringboardPlatformIE.ie_key())
3090
4c780fbd
S
3091 yapfiles_urls = YapFilesIE._extract_urls(webpage)
3092 if yapfiles_urls:
3093 return self.playlist_from_matches(
3094 yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
3095
86c8cfc5
S
3096 vice_urls = ViceIE._extract_urls(webpage)
3097 if vice_urls:
3098 return self.playlist_from_matches(
3099 vice_urls, video_id, video_title, ie=ViceIE.ie_key())
3100
178ee883
S
3101 xfileshare_urls = XFileShareIE._extract_urls(webpage)
3102 if xfileshare_urls:
3103 return self.playlist_from_matches(
3104 xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
3105
660a230b
S
3106 cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
3107 if cloudflarestream_urls:
3108 return self.playlist_from_matches(
3109 cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
3110
8b4b400a 3111 peertube_urls = PeerTubeIE._extract_urls(webpage, url)
6bd499e8
S
3112 if peertube_urls:
3113 return self.playlist_from_matches(
3114 peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
3115
5ee7ae5c
S
3116 teachable_url = TeachableIE._extract_url(webpage, url)
3117 if teachable_url:
3118 return self.url_result(teachable_url)
3119
aee36ca8
S
3120 indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
3121 if indavideo_urls:
3122 return self.playlist_from_matches(
3123 indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
3124
cfd7f2a6
S
3125 apa_urls = APAIE._extract_urls(webpage)
3126 if apa_urls:
3127 return self.playlist_from_matches(
3128 apa_urls, video_id, video_title, ie=APAIE.ie_key())
3129
f51f526b
S
3130 foxnews_urls = FoxNewsIE._extract_urls(webpage)
3131 if foxnews_urls:
3132 return self.playlist_from_matches(
3133 foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
3134
2e4350ee 3135 sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
d3431dcb
S
3136 r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
3137 webpage)]
3138 if sharevideos_urls:
3139 return self.playlist_from_matches(
3140 sharevideos_urls, video_id, video_title)
3141
9d1b2138
S
3142 viqeo_urls = ViqeoIE._extract_urls(webpage)
3143 if viqeo_urls:
3144 return self.playlist_from_matches(
3145 viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
57c68ec4
S
3146
3147 expressen_urls = ExpressenIE._extract_urls(webpage)
3148 if expressen_urls:
3149 return self.playlist_from_matches(
3150 expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
9d1b2138 3151
83852e57
S
3152 zype_urls = ZypeIE._extract_urls(webpage)
3153 if zype_urls:
3154 return self.playlist_from_matches(
3155 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
3156
bd264412
YCH
3157 # Look for HTML5 media
3158 entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
3159 if entries:
9ce1ac40 3160 if len(entries) == 1:
3161 entries[0].update({
bd264412
YCH
3162 'id': video_id,
3163 'title': video_title,
3164 })
9ce1ac40 3165 else:
3166 for num, entry in enumerate(entries, start=1):
3167 entry.update({
3168 'id': '%s-%s' % (video_id, num),
3169 'title': '%s (%d)' % (video_title, num),
3170 })
3171 for entry in entries:
bd264412 3172 self._sort_formats(entry['formats'])
9ce1ac40 3173 return self.playlist_result(entries, video_id, video_title)
bd264412 3174
c73e330e
RU
3175 jwplayer_data = self._find_jwplayer_data(
3176 webpage, video_id, transform_source=js_to_json)
3177 if jwplayer_data:
3d08f63d
MYM
3178 try:
3179 info = self._parse_jwplayer_data(
3180 jwplayer_data, video_id, require_title=False, base_url=url)
3181 return merge_dicts(info, info_dict)
3182 except ExtractorError:
3183 # See https://github.com/rg3/youtube-dl/pull/16735
3184 pass
a4a554a7 3185
63d990d2
S
3186 # Video.js embed
3187 mobj = re.search(
c5b7014a 3188 r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
63d990d2
S
3189 webpage)
3190 if mobj is not None:
3191 sources = self._parse_json(
3192 mobj.group(1), video_id, transform_source=js_to_json,
3193 fatal=False) or []
c5b7014a
S
3194 if not isinstance(sources, list):
3195 sources = [sources]
63d990d2
S
3196 formats = []
3197 for source in sources:
e0b6e988
S
3198 src = source.get('src')
3199 if not src or not isinstance(src, compat_str):
63d990d2
S
3200 continue
3201 src = compat_urlparse.urljoin(url, src)
3202 src_type = source.get('type')
3203 if isinstance(src_type, compat_str):
3204 src_type = src_type.lower()
3205 ext = determine_ext(src).lower()
3206 if src_type == 'video/youtube':
3207 return self.url_result(src, YoutubeIE.ie_key())
3208 if src_type == 'application/dash+xml' or ext == 'mpd':
3209 formats.extend(self._extract_mpd_formats(
3210 src, video_id, mpd_id='dash', fatal=False))
3211 elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
3212 formats.extend(self._extract_m3u8_formats(
3213 src, video_id, 'mp4', entry_protocol='m3u8_native',
3214 m3u8_id='hls', fatal=False))
3215 else:
3216 formats.append({
3217 'url': src,
3218 'ext': (mimetype2ext(src_type) or
3219 ext if ext in KNOWN_EXTENSIONS else 'mp4'),
3220 })
3221 if formats:
3222 self._sort_formats(formats)
3223 info_dict['formats'] = formats
3224 return info_dict
3225
ff17be3a
S
3226 # Looking for http://schema.org/VideoObject
3227 json_ld = self._search_json_ld(
3228 webpage, video_id, default={}, expected_type='VideoObject')
3229 if json_ld.get('url'):
3230 return merge_dicts(json_ld, info_dict)
3231
ced659bb 3232 def check_video(vurl):
a0f71985
PH
3233 if YoutubeIE.suitable(vurl):
3234 return True
b7a8c1bc
S
3235 if RtmpIE.suitable(vurl):
3236 return True
ced659bb
S
3237 vpath = compat_urlparse.urlparse(vurl).path
3238 vext = determine_ext(vpath)
0ee79a37 3239 return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
ced659bb
S
3240
3241 def filter_video(urls):
3242 return list(filter(check_video, urls))
3243
9b122384 3244 # Start with something easy: JW Player in SWFObject
ced659bb 3245 found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
b30b8698 3246 if not found:
d981cef6 3247 # Look for gorilla-vid style embedding
ced659bb 3248 found = filter_video(re.findall(r'''(?sx)
c0292e8a
PH
3249 (?:
3250 jw_plugins|
3251 JWPlayerOptions|
3252 jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
3253 )
a0f71985
PH
3254 .*?
3255 ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
b30b8698 3256 if not found:
9b122384 3257 # Broaden the search a little bit
ced659bb 3258 found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
b30b8698
PH
3259 if not found:
3260 # Broaden the findall a little bit: JWPlayer JS loader
ced659bb 3261 found = filter_video(re.findall(
54a9328b 3262 r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
4d805e06
PH
3263 if not found:
3264 # Flow player
ced659bb 3265 found = filter_video(re.findall(r'''(?xs)
4d805e06
PH
3266 flowplayer\("[^"]+",\s*
3267 \{[^}]+?\}\s*,
52585fd6 3268 \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
4d805e06 3269 ["']?url["']?\s*:\s*["']([^"']+)["']
ced659bb 3270 ''', webpage))
501f13fb
PH
3271 if not found:
3272 # Cinerama player
3273 found = re.findall(
3274 r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
b30b8698 3275 if not found:
9b122384 3276 # Try to find twitter cards info
371ddb14
S
3277 # twitter:player:stream should be checked before twitter:player since
3278 # it is expected to contain a raw stream (see
3279 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
ced659bb
S
3280 found = filter_video(re.findall(
3281 r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
b30b8698 3282 if not found:
9b122384
PH
3283 # We look for Open Graph info:
3284 # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
b30b8698 3285 m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
9b122384
PH
3286 # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
3287 if m_video_type is not None:
ced659bb 3288 found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
b30b8698 3289 if not found:
ed9a25dd 3290 REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
a5a45015 3291 found = re.search(
89ef304b 3292 r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
ed9a25dd 3293 r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
89ef304b 3294 webpage)
84f81016
S
3295 if not found:
3296 # Look also in Refresh HTTP header
3297 refresh_header = head_response.headers.get('Refresh')
3298 if refresh_header:
6c91a5a7
S
3299 # In python 2 response HTTP headers are bytestrings
3300 if sys.version_info < (3, 0) and isinstance(refresh_header, str):
3301 refresh_header = refresh_header.decode('iso-8859-1')
ed9a25dd 3302 found = re.search(REDIRECT_REGEX, refresh_header)
b30b8698 3303 if found:
b37317d8 3304 new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
54b960f3
S
3305 if new_url != url:
3306 self.report_following_redirect(new_url)
3307 return {
3308 '_type': 'url',
3309 'url': new_url,
3310 }
3311 else:
3312 found = None
371ddb14
S
3313
3314 if not found:
3315 # twitter:player is a https URL to iframe player that may or may not
3316 # be supported by youtube-dl thus this is checked the very last (see
3317 # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
3318 embed_url = self._html_search_meta('twitter:player', webpage, default=None)
02d01e15 3319 if embed_url and embed_url != url:
371ddb14
S
3320 return self.url_result(embed_url)
3321
b30b8698 3322 if not found:
416c7fcb 3323 raise UnsupportedError(url)
9b122384 3324
b30b8698 3325 entries = []
4a120778 3326 for video_url in orderedSet(found):
949b6497 3327 video_url = unescapeHTML(video_url)
6cc37c69 3328 video_url = video_url.replace('\\/', '/')
b30b8698 3329 video_url = compat_urlparse.urljoin(url, video_url)
f7e6f7fa 3330 video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
9b122384 3331
b30b8698
PH
3332 # Sometimes, jwplayer extraction will result in a YouTube URL
3333 if YoutubeIE.suitable(video_url):
3334 entries.append(self.url_result(video_url, 'Youtube'))
3335 continue
9b122384 3336
b30b8698
PH
3337 # here's a fun little line of code for you:
3338 video_id = os.path.splitext(video_id)[0]
fc9713a1 3339
28602e74
YCH
3340 entry_info_dict = {
3341 'id': video_id,
3342 'uploader': video_uploader,
3343 'title': video_title,
3344 'age_limit': age_limit,
3345 }
3346
5620f840
S
3347 if RtmpIE.suitable(video_url):
3348 entry_info_dict.update({
3349 '_type': 'url_transparent',
3350 'ie_key': RtmpIE.ie_key(),
3351 'url': video_url,
3352 })
3353 entries.append(entry_info_dict)
3354 continue
3355
729accb4
S
3356 ext = determine_ext(video_url)
3357 if ext == 'smil':
28602e74 3358 entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
729accb4
S
3359 elif ext == 'xspf':
3360 return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
750b9ff0
YCH
3361 elif ext == 'm3u8':
3362 entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
79a35085
S
3363 elif ext == 'mpd':
3364 entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
3f2f4a94
S
3365 elif ext == 'f4m':
3366 entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
4119a96c 3367 elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
26aae566
S
3368 # Just matching .ism/manifest is not enough to be reliably sure
3369 # whether it's actually an ISM manifest or some other streaming
3370 # manifest since there are various streaming URL formats
3371 # possible (see [1]) as well as some other shenanigans like
3372 # .smil/manifest URLs that actually serve an ISM (see [2]) and
3373 # so on.
3374 # Thus the most reasonable way to solve this is to delegate
3375 # to generic extractor in order to look into the contents of
3376 # the manifest itself.
3377 # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
3378 # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
3379 entry_info_dict = self.url_result(
3380 smuggle_url(video_url, {'to_generic': True}),
3381 GenericIE.ie_key())
d6fd958c 3382 else:
28602e74
YCH
3383 entry_info_dict['url'] = video_url
3384
19dbaeec
S
3385 if entry_info_dict.get('formats'):
3386 self._sort_formats(entry_info_dict['formats'])
3387
28602e74 3388 entries.append(entry_info_dict)
b30b8698
PH
3389
3390 if len(entries) == 1:
669f0e7c 3391 return entries[0]
b30b8698
PH
3392 else:
3393 for num, e in enumerate(entries, start=1):
13d8fbef
JMF
3394 # 'url' results don't have a title
3395 if e.get('title') is not None:
3396 e['title'] = '%s (%d)' % (e['title'], num)
b30b8698
PH
3397 return {
3398 '_type': 'playlist',
3399 'entries': entries,
3400 }