generic.py 107 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681
  1. # coding: utf-8
  2. from __future__ import unicode_literals
  3. import os
  4. import re
  5. import sys
  6. from .common import InfoExtractor
  7. from .youtube import YoutubeIE
  8. from ..compat import (
  9. compat_etree_fromstring,
  10. compat_urllib_parse_unquote,
  11. compat_urlparse,
  12. compat_xml_parse_error,
  13. )
  14. from ..utils import (
  15. determine_ext,
  16. ExtractorError,
  17. float_or_none,
  18. HEADRequest,
  19. is_html,
  20. js_to_json,
  21. orderedSet,
  22. sanitized_Request,
  23. smuggle_url,
  24. unescapeHTML,
  25. unified_strdate,
  26. unsmuggle_url,
  27. UnsupportedError,
  28. xpath_text,
  29. )
  30. from .commonprotocols import RtmpIE
  31. from .brightcove import (
  32. BrightcoveLegacyIE,
  33. BrightcoveNewIE,
  34. )
  35. from .nbc import NBCSportsVPlayerIE
  36. from .ooyala import OoyalaIE
  37. from .rutv import RUTVIE
  38. from .tvc import TVCIE
  39. from .sportbox import SportBoxEmbedIE
  40. from .smotri import SmotriIE
  41. from .myvi import MyviIE
  42. from .condenast import CondeNastIE
  43. from .udn import UDNEmbedIE
  44. from .senateisvp import SenateISVPIE
  45. from .svt import SVTIE
  46. from .pornhub import PornHubIE
  47. from .xhamster import XHamsterEmbedIE
  48. from .tnaflix import TNAFlixNetworkEmbedIE
  49. from .drtuber import DrTuberIE
  50. from .redtube import RedTubeIE
  51. from .vimeo import VimeoIE
  52. from .dailymotion import (
  53. DailymotionIE,
  54. DailymotionCloudIE,
  55. )
  56. from .onionstudios import OnionStudiosIE
  57. from .viewlift import ViewLiftEmbedIE
  58. from .mtv import MTVServicesEmbeddedIE
  59. from .pladform import PladformIE
  60. from .videomore import VideomoreIE
  61. from .webcaster import WebcasterFeedIE
  62. from .googledrive import GoogleDriveIE
  63. from .jwplatform import JWPlatformIE
  64. from .digiteka import DigitekaIE
  65. from .arkena import ArkenaIE
  66. from .instagram import InstagramIE
  67. from .liveleak import LiveLeakIE
  68. from .threeqsdn import ThreeQSDNIE
  69. from .theplatform import ThePlatformIE
  70. from .vessel import VesselIE
  71. from .kaltura import KalturaIE
  72. from .eagleplatform import EaglePlatformIE
  73. from .facebook import FacebookIE
  74. from .soundcloud import SoundcloudIE
  75. from .tunein import TuneInBaseIE
  76. from .vbox7 import Vbox7IE
  77. from .dbtv import DBTVIE
  78. from .piksel import PikselIE
  79. from .videa import VideaIE
  80. from .twentymin import TwentyMinutenIE
  81. from .ustream import UstreamIE
  82. from .openload import OpenloadIE
  83. from .videopress import VideoPressIE
  84. class GenericIE(InfoExtractor):
  85. IE_DESC = 'Generic downloader that works on some sites'
  86. _VALID_URL = r'.*'
  87. IE_NAME = 'generic'
  88. _TESTS = [
  89. # Direct link to a video
  90. {
  91. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  92. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  93. 'info_dict': {
  94. 'id': 'trailer',
  95. 'ext': 'mp4',
  96. 'title': 'trailer',
  97. 'upload_date': '20100513',
  98. }
  99. },
  100. # Direct link to media delivered compressed (until Accept-Encoding is *)
  101. {
  102. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  103. 'md5': '128c42e68b13950268b648275386fc74',
  104. 'info_dict': {
  105. 'id': 'FictionJunction-Parallel_Hearts',
  106. 'ext': 'flac',
  107. 'title': 'FictionJunction-Parallel_Hearts',
  108. 'upload_date': '20140522',
  109. },
  110. 'expected_warnings': [
  111. 'URL could be a direct video link, returning it as such.'
  112. ],
  113. 'skip': 'URL invalid',
  114. },
  115. # Direct download with broken HEAD
  116. {
  117. 'url': 'http://ai-radio.org:8000/radio.opus',
  118. 'info_dict': {
  119. 'id': 'radio',
  120. 'ext': 'opus',
  121. 'title': 'radio',
  122. },
  123. 'params': {
  124. 'skip_download': True, # infinite live stream
  125. },
  126. 'expected_warnings': [
  127. r'501.*Not Implemented',
  128. r'400.*Bad Request',
  129. ],
  130. },
  131. # Direct link with incorrect MIME type
  132. {
  133. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  134. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  135. 'info_dict': {
  136. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  137. 'id': '5_Lennart_Poettering_-_Systemd',
  138. 'ext': 'webm',
  139. 'title': '5_Lennart_Poettering_-_Systemd',
  140. 'upload_date': '20141120',
  141. },
  142. 'expected_warnings': [
  143. 'URL could be a direct video link, returning it as such.'
  144. ]
  145. },
  146. # RSS feed
  147. {
  148. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  149. 'info_dict': {
  150. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  151. 'title': 'Zero Punctuation',
  152. 'description': 're:.*groundbreaking video review series.*'
  153. },
  154. 'playlist_mincount': 11,
  155. },
  156. # RSS feed with enclosure
  157. {
  158. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  159. 'info_dict': {
  160. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  161. 'ext': 'm4v',
  162. 'upload_date': '20150228',
  163. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  164. }
  165. },
  166. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  167. {
  168. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  169. 'info_dict': {
  170. 'id': 'smil',
  171. 'ext': 'mp4',
  172. 'title': 'Automatics, robotics and biocybernetics',
  173. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  174. 'upload_date': '20130627',
  175. 'formats': 'mincount:16',
  176. 'subtitles': 'mincount:1',
  177. },
  178. 'params': {
  179. 'force_generic_extractor': True,
  180. 'skip_download': True,
  181. },
  182. },
  183. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  184. {
  185. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  186. 'info_dict': {
  187. 'id': 'hds',
  188. 'ext': 'flv',
  189. 'title': 'hds',
  190. 'formats': 'mincount:1',
  191. },
  192. 'params': {
  193. 'skip_download': True,
  194. },
  195. },
  196. # SMIL from https://www.restudy.dk/video/play/id/1637
  197. {
  198. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  199. 'info_dict': {
  200. 'id': 'video_1637',
  201. 'ext': 'flv',
  202. 'title': 'video_1637',
  203. 'formats': 'mincount:3',
  204. },
  205. 'params': {
  206. 'skip_download': True,
  207. },
  208. },
  209. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  210. {
  211. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  212. 'info_dict': {
  213. 'id': 'smil-service',
  214. 'ext': 'flv',
  215. 'title': 'smil-service',
  216. 'formats': 'mincount:1',
  217. },
  218. 'params': {
  219. 'skip_download': True,
  220. },
  221. },
  222. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  223. {
  224. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  225. 'info_dict': {
  226. 'id': '4719370',
  227. 'ext': 'mp4',
  228. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  229. 'formats': 'mincount:3',
  230. },
  231. 'params': {
  232. 'skip_download': True,
  233. },
  234. },
  235. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  236. {
  237. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  238. 'info_dict': {
  239. 'id': 'mZlp2ctYIUEB',
  240. 'ext': 'mp4',
  241. 'title': 'Tikibad ontruimd wegens brand',
  242. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  243. 'thumbnail': r're:^https?://.*\.jpg$',
  244. 'duration': 33,
  245. },
  246. 'params': {
  247. 'skip_download': True,
  248. },
  249. },
  250. # MPD from http://dash-mse-test.appspot.com/media.html
  251. {
  252. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  253. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  254. 'info_dict': {
  255. 'id': 'car-20120827-manifest',
  256. 'ext': 'mp4',
  257. 'title': 'car-20120827-manifest',
  258. 'formats': 'mincount:9',
  259. 'upload_date': '20130904',
  260. },
  261. 'params': {
  262. 'format': 'bestvideo',
  263. },
  264. },
  265. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  266. {
  267. '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',
  268. 'info_dict': {
  269. 'id': 'content',
  270. 'ext': 'mp4',
  271. 'title': 'content',
  272. 'formats': 'mincount:8',
  273. },
  274. 'params': {
  275. # m3u8 downloads
  276. 'skip_download': True,
  277. },
  278. 'skip': 'video gone',
  279. },
  280. # m3u8 served with Content-Type: text/plain
  281. {
  282. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  283. 'info_dict': {
  284. 'id': 'index',
  285. 'ext': 'mp4',
  286. 'title': 'index',
  287. 'upload_date': '20140720',
  288. 'formats': 'mincount:11',
  289. },
  290. 'params': {
  291. # m3u8 downloads
  292. 'skip_download': True,
  293. },
  294. 'skip': 'video gone',
  295. },
  296. # google redirect
  297. {
  298. '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',
  299. 'info_dict': {
  300. 'id': 'cmQHVoWB5FY',
  301. 'ext': 'mp4',
  302. 'upload_date': '20130224',
  303. 'uploader_id': 'TheVerge',
  304. 'description': r're:^Chris Ziegler takes a look at the\.*',
  305. 'uploader': 'The Verge',
  306. 'title': 'First Firefox OS phones side-by-side',
  307. },
  308. 'params': {
  309. 'skip_download': False,
  310. }
  311. },
  312. {
  313. # redirect in Refresh HTTP header
  314. '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',
  315. 'info_dict': {
  316. 'id': 'pO8h3EaFRdo',
  317. 'ext': 'mp4',
  318. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  319. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  320. 'upload_date': '20150917',
  321. 'uploader_id': 'brtvofficial',
  322. 'uploader': 'Boiler Room',
  323. },
  324. 'params': {
  325. 'skip_download': False,
  326. },
  327. },
  328. {
  329. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  330. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  331. 'info_dict': {
  332. 'id': '13601338388002',
  333. 'ext': 'mp4',
  334. 'uploader': 'www.hodiho.fr',
  335. 'title': 'R\u00e9gis plante sa Jeep',
  336. }
  337. },
  338. # bandcamp page with custom domain
  339. {
  340. 'add_ie': ['Bandcamp'],
  341. 'url': 'http://bronyrock.com/track/the-pony-mash',
  342. 'info_dict': {
  343. 'id': '3235767654',
  344. 'ext': 'mp3',
  345. 'title': 'The Pony Mash',
  346. 'uploader': 'M_Pallante',
  347. },
  348. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  349. },
  350. {
  351. # embedded brightcove video
  352. # it also tests brightcove videos that need to set the 'Referer'
  353. # in the http requests
  354. 'add_ie': ['BrightcoveLegacy'],
  355. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  356. 'info_dict': {
  357. 'id': '2765128793001',
  358. 'ext': 'mp4',
  359. 'title': 'Le cours de bourse : l’analyse technique',
  360. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  361. 'uploader': 'BFM BUSINESS',
  362. },
  363. 'params': {
  364. 'skip_download': True,
  365. },
  366. },
  367. {
  368. # embedded with itemprop embedURL and video id spelled as `idVideo`
  369. 'add_id': ['BrightcoveLegacy'],
  370. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  371. 'info_dict': {
  372. 'id': '5255628253001',
  373. 'ext': 'mp4',
  374. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  375. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  376. 'uploader': 'BFM BUSINESS',
  377. 'uploader_id': '876450612001',
  378. 'timestamp': 1482255315,
  379. 'upload_date': '20161220',
  380. },
  381. 'params': {
  382. 'skip_download': True,
  383. },
  384. },
  385. {
  386. # https://github.com/rg3/youtube-dl/issues/2253
  387. 'url': 'http://bcove.me/i6nfkrc3',
  388. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  389. 'info_dict': {
  390. 'id': '3101154703001',
  391. 'ext': 'mp4',
  392. 'title': 'Still no power',
  393. 'uploader': 'thestar.com',
  394. '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.',
  395. },
  396. 'add_ie': ['BrightcoveLegacy'],
  397. 'skip': 'video gone',
  398. },
  399. {
  400. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  401. 'md5': 'fb973ecf6e4a78a67453647444222983',
  402. 'info_dict': {
  403. 'id': '3414141473001',
  404. 'ext': 'mp4',
  405. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  406. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  407. 'uploader': 'Championat',
  408. },
  409. },
  410. {
  411. # https://github.com/rg3/youtube-dl/issues/3541
  412. 'add_ie': ['BrightcoveLegacy'],
  413. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  414. 'info_dict': {
  415. 'id': '3866516442001',
  416. 'ext': 'mp4',
  417. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  418. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  419. 'uploader': 'SBS Broadcasting',
  420. },
  421. 'skip': 'Restricted to Netherlands',
  422. 'params': {
  423. 'skip_download': True, # m3u8 download
  424. },
  425. },
  426. {
  427. # Brightcove with alternative playerID key
  428. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  429. 'info_dict': {
  430. 'id': 'nmeth.2062_SV1',
  431. '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',
  432. },
  433. 'playlist': [{
  434. 'info_dict': {
  435. 'id': '2228375078001',
  436. 'ext': 'mp4',
  437. 'title': 'nmeth.2062-sv1',
  438. 'description': 'nmeth.2062-sv1',
  439. 'timestamp': 1363357591,
  440. 'upload_date': '20130315',
  441. 'uploader': 'Nature Publishing Group',
  442. 'uploader_id': '1964492299001',
  443. },
  444. }],
  445. },
  446. # ooyala video
  447. {
  448. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  449. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  450. 'info_dict': {
  451. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  452. 'ext': 'mp4',
  453. 'title': '2cc213299525360.mov', # that's what we get
  454. 'duration': 238.231,
  455. },
  456. 'add_ie': ['Ooyala'],
  457. },
  458. {
  459. # ooyala video embedded with http://player.ooyala.com/iframe.js
  460. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  461. 'info_dict': {
  462. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  463. 'ext': 'mp4',
  464. 'title': '"Steve Jobs: Man in the Machine" trailer',
  465. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  466. 'duration': 135.427,
  467. },
  468. 'params': {
  469. 'skip_download': True,
  470. },
  471. 'skip': 'movie expired',
  472. },
  473. # embed.ly video
  474. {
  475. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  476. 'info_dict': {
  477. 'id': '9ODmcdjQcHQ',
  478. 'ext': 'mp4',
  479. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  480. 'upload_date': '20140225',
  481. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  482. 'uploader': 'Tested',
  483. 'uploader_id': 'testedcom',
  484. },
  485. # No need to test YoutubeIE here
  486. 'params': {
  487. 'skip_download': True,
  488. },
  489. },
  490. # funnyordie embed
  491. {
  492. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  493. 'info_dict': {
  494. 'id': '18e820ec3f',
  495. 'ext': 'mp4',
  496. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  497. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  498. },
  499. # HEAD requests lead to endless 301, while GET is OK
  500. 'expected_warnings': ['301'],
  501. },
  502. # RUTV embed
  503. {
  504. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  505. 'info_dict': {
  506. 'id': '776940',
  507. 'ext': 'mp4',
  508. 'title': 'Охотское море стало целиком российским',
  509. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  510. },
  511. 'params': {
  512. # m3u8 download
  513. 'skip_download': True,
  514. },
  515. },
  516. # TVC embed
  517. {
  518. '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/',
  519. 'info_dict': {
  520. 'id': '55304',
  521. 'ext': 'mp4',
  522. 'title': 'Дошкольное воспитание',
  523. },
  524. },
  525. # SportBox embed
  526. {
  527. 'url': 'http://www.vestifinance.ru/articles/25753',
  528. 'info_dict': {
  529. 'id': '25753',
  530. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  531. },
  532. 'playlist': [{
  533. 'info_dict': {
  534. 'id': '370908',
  535. 'title': 'Госзаказ. День 3',
  536. 'ext': 'mp4',
  537. }
  538. }, {
  539. 'info_dict': {
  540. 'id': '370905',
  541. 'title': 'Госзаказ. День 2',
  542. 'ext': 'mp4',
  543. }
  544. }, {
  545. 'info_dict': {
  546. 'id': '370902',
  547. 'title': 'Госзаказ. День 1',
  548. 'ext': 'mp4',
  549. }
  550. }],
  551. 'params': {
  552. # m3u8 download
  553. 'skip_download': True,
  554. },
  555. },
  556. # Myvi.ru embed
  557. {
  558. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  559. 'info_dict': {
  560. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  561. 'ext': 'mp4',
  562. 'title': 'Ужастики, русский трейлер (2015)',
  563. 'thumbnail': r're:^https?://.*\.jpg$',
  564. 'duration': 153,
  565. }
  566. },
  567. # XHamster embed
  568. {
  569. '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',
  570. 'info_dict': {
  571. 'id': 'showthread',
  572. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  573. },
  574. 'playlist_mincount': 7,
  575. # This forum does not allow <iframe> syntaxes anymore
  576. # Now HTML tags are displayed as-is
  577. 'skip': 'No videos on this page',
  578. },
  579. # Embedded TED video
  580. {
  581. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  582. 'md5': '65fdff94098e4a607385a60c5177c638',
  583. 'info_dict': {
  584. 'id': '1969',
  585. 'ext': 'mp4',
  586. 'title': 'Hidden miracles of the natural world',
  587. 'uploader': 'Louie Schwartzberg',
  588. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  589. }
  590. },
  591. # nowvideo embed hidden behind percent encoding
  592. {
  593. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  594. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  595. 'info_dict': {
  596. 'id': '06e53103ca9aa',
  597. 'ext': 'flv',
  598. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  599. 'description': 'No description',
  600. },
  601. },
  602. # arte embed
  603. {
  604. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  605. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  606. 'info_dict': {
  607. 'id': '048195-004_PLUS7-F',
  608. 'ext': 'flv',
  609. 'title': 'X:enius',
  610. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  611. 'upload_date': '20140320',
  612. },
  613. 'params': {
  614. 'skip_download': 'Requires rtmpdump'
  615. },
  616. 'skip': 'video gone',
  617. },
  618. # francetv embed
  619. {
  620. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  621. 'info_dict': {
  622. 'id': 'EV_30231',
  623. 'ext': 'mp4',
  624. 'title': 'Alcaline, le concert avec Calogero',
  625. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  626. 'upload_date': '20150226',
  627. 'timestamp': 1424989860,
  628. 'duration': 5400,
  629. },
  630. 'params': {
  631. # m3u8 downloads
  632. 'skip_download': True,
  633. },
  634. 'expected_warnings': [
  635. 'Forbidden'
  636. ]
  637. },
  638. # Condé Nast embed
  639. {
  640. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  641. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  642. 'info_dict': {
  643. 'id': '53501be369702d3275860000',
  644. 'ext': 'mp4',
  645. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  646. }
  647. },
  648. # Dailymotion embed
  649. {
  650. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  651. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  652. 'info_dict': {
  653. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  654. 'ext': 'mp4',
  655. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  656. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  657. 'uploader': 'Spi0n',
  658. 'uploader_id': 'xgditw',
  659. 'upload_date': '20140425',
  660. 'timestamp': 1398441542,
  661. },
  662. 'add_ie': ['Dailymotion'],
  663. },
  664. # YouTube embed
  665. {
  666. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  667. 'info_dict': {
  668. 'id': 'FXRb4ykk4S0',
  669. 'ext': 'mp4',
  670. 'title': 'The NBL Auction 2014',
  671. 'uploader': 'BADMINTON England',
  672. 'uploader_id': 'BADMINTONEvents',
  673. 'upload_date': '20140603',
  674. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  675. },
  676. 'add_ie': ['Youtube'],
  677. 'params': {
  678. 'skip_download': True,
  679. }
  680. },
  681. # MTVSercices embed
  682. {
  683. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  684. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  685. 'info_dict': {
  686. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  687. 'ext': 'mp4',
  688. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  689. 'description': 'Two valets share their love for movie star Liam Neesons.',
  690. 'timestamp': 1349922600,
  691. 'upload_date': '20121011',
  692. },
  693. },
  694. # YouTube embed via <data-embed-url="">
  695. {
  696. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  697. 'info_dict': {
  698. 'id': '4vAffPZIT44',
  699. 'ext': 'mp4',
  700. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  701. 'uploader': 'Gameloft',
  702. 'uploader_id': 'gameloft',
  703. 'upload_date': '20140828',
  704. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  705. },
  706. 'params': {
  707. 'skip_download': True,
  708. }
  709. },
  710. # Camtasia studio
  711. {
  712. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  713. 'playlist': [{
  714. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  715. 'info_dict': {
  716. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  717. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  718. 'ext': 'flv',
  719. 'duration': 2235.90,
  720. }
  721. }, {
  722. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  723. 'info_dict': {
  724. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  725. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  726. 'ext': 'flv',
  727. 'duration': 2235.93,
  728. }
  729. }],
  730. 'info_dict': {
  731. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  732. }
  733. },
  734. # Flowplayer
  735. {
  736. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  737. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  738. 'info_dict': {
  739. 'id': '5123ea6d5e5a7',
  740. 'ext': 'mp4',
  741. 'age_limit': 18,
  742. 'uploader': 'www.handjobhub.com',
  743. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  744. }
  745. },
  746. # Multiple brightcove videos
  747. # https://github.com/rg3/youtube-dl/issues/2283
  748. {
  749. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  750. 'info_dict': {
  751. 'id': 'always-never',
  752. 'title': 'Always / Never - The New Yorker',
  753. },
  754. 'playlist_count': 3,
  755. 'params': {
  756. 'extract_flat': False,
  757. 'skip_download': True,
  758. }
  759. },
  760. # MLB embed
  761. {
  762. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  763. 'md5': '96f09a37e44da40dd083e12d9a683327',
  764. 'info_dict': {
  765. 'id': '33322633',
  766. 'ext': 'mp4',
  767. 'title': 'Ump changes call to ball',
  768. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  769. 'duration': 48,
  770. 'timestamp': 1401537900,
  771. 'upload_date': '20140531',
  772. 'thumbnail': r're:^https?://.*\.jpg$',
  773. },
  774. },
  775. # Wistia embed
  776. {
  777. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  778. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  779. 'info_dict': {
  780. 'id': '6e2wtrbdaf',
  781. 'ext': 'mov',
  782. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  783. 'description': 'a Paywall Videos video from Remilon',
  784. 'duration': 644.072,
  785. 'uploader': 'study.com',
  786. 'timestamp': 1459678540,
  787. 'upload_date': '20160403',
  788. 'filesize': 24687186,
  789. },
  790. },
  791. {
  792. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  793. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  794. 'info_dict': {
  795. 'id': 'uxjb0lwrcz',
  796. 'ext': 'mp4',
  797. 'title': 'Conversation about Hexagonal Rails Part 1',
  798. 'description': 'a Martin Fowler video from ThoughtWorks',
  799. 'duration': 1715.0,
  800. 'uploader': 'thoughtworks.wistia.com',
  801. 'timestamp': 1401832161,
  802. 'upload_date': '20140603',
  803. },
  804. },
  805. # Wistia standard embed (async)
  806. {
  807. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  808. 'info_dict': {
  809. 'id': '807fafadvk',
  810. 'ext': 'mp4',
  811. 'title': 'Drip Brennan Dunn Workshop',
  812. 'description': 'a JV Webinars video from getdrip-1',
  813. 'duration': 4986.95,
  814. 'timestamp': 1463607249,
  815. 'upload_date': '20160518',
  816. },
  817. 'params': {
  818. 'skip_download': True,
  819. }
  820. },
  821. # Soundcloud embed
  822. {
  823. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  824. 'info_dict': {
  825. 'id': '174391317',
  826. 'ext': 'mp3',
  827. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  828. 'uploader': 'Sophos Security',
  829. 'title': 'Chet Chat 171 - Oct 29, 2014',
  830. 'upload_date': '20141029',
  831. }
  832. },
  833. # Soundcloud multiple embeds
  834. {
  835. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  836. 'info_dict': {
  837. 'id': '52809',
  838. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  839. },
  840. 'playlist_mincount': 7,
  841. },
  842. # TuneIn station embed
  843. {
  844. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  845. 'info_dict': {
  846. 'id': '204146',
  847. 'ext': 'mp3',
  848. 'title': 'CNRV',
  849. 'location': 'Paris, France',
  850. 'is_live': True,
  851. },
  852. 'params': {
  853. # Live stream
  854. 'skip_download': True,
  855. },
  856. },
  857. # Livestream embed
  858. {
  859. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  860. 'info_dict': {
  861. 'id': '67864563',
  862. 'ext': 'flv',
  863. 'upload_date': '20141112',
  864. 'title': 'Rosetta #CometLanding webcast HL 10',
  865. }
  866. },
  867. # Another Livestream embed, without 'new.' in URL
  868. {
  869. 'url': 'https://www.freespeech.org/',
  870. 'info_dict': {
  871. 'id': '123537347',
  872. 'ext': 'mp4',
  873. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  874. },
  875. 'params': {
  876. # Live stream
  877. 'skip_download': True,
  878. },
  879. },
  880. # LazyYT
  881. {
  882. 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
  883. 'info_dict': {
  884. 'id': '1986',
  885. 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
  886. },
  887. 'playlist_mincount': 2,
  888. },
  889. # Cinchcast embed
  890. {
  891. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  892. 'info_dict': {
  893. 'id': '7141703',
  894. 'ext': 'mp3',
  895. 'upload_date': '20141126',
  896. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  897. }
  898. },
  899. # Cinerama player
  900. {
  901. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  902. 'info_dict': {
  903. 'id': '730m_DandD_1901_512k',
  904. 'ext': 'mp4',
  905. 'uploader': 'www.abc.net.au',
  906. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  907. }
  908. },
  909. # embedded viddler video
  910. {
  911. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  912. 'info_dict': {
  913. 'id': '4d03aad9',
  914. 'ext': 'mp4',
  915. 'uploader': 'deadspin',
  916. 'title': 'WALL-TO-GORTAT',
  917. 'timestamp': 1422285291,
  918. 'upload_date': '20150126',
  919. },
  920. 'add_ie': ['Viddler'],
  921. },
  922. # Libsyn embed
  923. {
  924. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  925. 'info_dict': {
  926. 'id': '3377616',
  927. 'ext': 'mp3',
  928. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  929. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  930. 'upload_date': '20150220',
  931. },
  932. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  933. },
  934. # jwplayer YouTube
  935. {
  936. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  937. 'info_dict': {
  938. 'id': 'Mrj4DVp2zeA',
  939. 'ext': 'mp4',
  940. 'upload_date': '20150212',
  941. 'uploader': 'The National Archives UK',
  942. 'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
  943. 'uploader_id': 'NationalArchives08',
  944. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  945. },
  946. },
  947. # jwplayer rtmp
  948. {
  949. 'url': 'http://www.suffolk.edu/sjc/',
  950. 'info_dict': {
  951. 'id': 'sjclive',
  952. 'ext': 'flv',
  953. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  954. 'uploader': 'www.suffolk.edu',
  955. },
  956. 'params': {
  957. 'skip_download': True,
  958. }
  959. },
  960. # Complex jwplayer
  961. {
  962. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  963. 'info_dict': {
  964. 'id': 'videos',
  965. 'ext': 'mp4',
  966. 'title': 'king machine trailer 1',
  967. 'thumbnail': r're:^https?://.*\.jpg$',
  968. },
  969. },
  970. # rtl.nl embed
  971. {
  972. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  973. 'playlist_mincount': 5,
  974. 'info_dict': {
  975. 'id': 'aanslagen-kopenhagen',
  976. 'title': 'Aanslagen Kopenhagen | RTL Nieuws',
  977. }
  978. },
  979. # Zapiks embed
  980. {
  981. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  982. 'info_dict': {
  983. 'id': '118046',
  984. 'ext': 'mp4',
  985. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  986. }
  987. },
  988. # Kaltura embed (different embed code)
  989. {
  990. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  991. 'info_dict': {
  992. 'id': '1_a52wc67y',
  993. 'ext': 'flv',
  994. 'upload_date': '20150127',
  995. 'uploader_id': 'PremierMedia',
  996. 'timestamp': int,
  997. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  998. },
  999. },
  1000. # Kaltura embed with single quotes
  1001. {
  1002. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1003. 'info_dict': {
  1004. 'id': '0_izeg5utt',
  1005. 'ext': 'mp4',
  1006. 'title': '35871',
  1007. 'timestamp': 1355743100,
  1008. 'upload_date': '20121217',
  1009. 'uploader_id': 'batchUser',
  1010. },
  1011. 'add_ie': ['Kaltura'],
  1012. },
  1013. {
  1014. # Kaltura embedded via quoted entry_id
  1015. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1016. 'info_dict': {
  1017. 'id': '0_utuok90b',
  1018. 'ext': 'mp4',
  1019. 'title': '06_matthew_brender_raj_dutt',
  1020. 'timestamp': 1466638791,
  1021. 'upload_date': '20160622',
  1022. },
  1023. 'add_ie': ['Kaltura'],
  1024. 'expected_warnings': [
  1025. 'Could not send HEAD request'
  1026. ],
  1027. 'params': {
  1028. 'skip_download': True,
  1029. }
  1030. },
  1031. {
  1032. # Kaltura embedded, some fileExt broken (#11480)
  1033. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1034. 'info_dict': {
  1035. 'id': '1_sgtvehim',
  1036. 'ext': 'mp4',
  1037. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1038. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1039. 'timestamp': 1321158993,
  1040. 'upload_date': '20111113',
  1041. 'uploader_id': 'kps1',
  1042. },
  1043. 'add_ie': ['Kaltura'],
  1044. },
  1045. # Eagle.Platform embed (generic URL)
  1046. {
  1047. 'url': 'http://lenta.ru/news/2015/03/06/navalny/',
  1048. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1049. 'info_dict': {
  1050. 'id': '227304',
  1051. 'ext': 'mp4',
  1052. 'title': 'Навальный вышел на свободу',
  1053. 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
  1054. 'thumbnail': r're:^https?://.*\.jpg$',
  1055. 'duration': 87,
  1056. 'view_count': int,
  1057. 'age_limit': 0,
  1058. },
  1059. },
  1060. # ClipYou (Eagle.Platform) embed (custom URL)
  1061. {
  1062. 'url': 'http://muz-tv.ru/play/7129/',
  1063. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1064. 'info_dict': {
  1065. 'id': '12820',
  1066. 'ext': 'mp4',
  1067. 'title': "'O Sole Mio",
  1068. 'thumbnail': r're:^https?://.*\.jpg$',
  1069. 'duration': 216,
  1070. 'view_count': int,
  1071. },
  1072. },
  1073. # Pladform embed
  1074. {
  1075. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1076. 'info_dict': {
  1077. 'id': '100183293',
  1078. 'ext': 'mp4',
  1079. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1080. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1081. 'thumbnail': r're:^https?://.*\.jpg$',
  1082. 'duration': 694,
  1083. 'age_limit': 0,
  1084. },
  1085. },
  1086. # Playwire embed
  1087. {
  1088. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1089. 'info_dict': {
  1090. 'id': '3519514',
  1091. 'ext': 'mp4',
  1092. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1093. 'thumbnail': r're:^https?://.*\.png$',
  1094. 'duration': 45.115,
  1095. },
  1096. },
  1097. # 5min embed
  1098. {
  1099. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1100. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1101. 'info_dict': {
  1102. 'id': '518726732',
  1103. 'ext': 'mp4',
  1104. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1105. },
  1106. },
  1107. # SVT embed
  1108. {
  1109. 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
  1110. 'info_dict': {
  1111. 'id': '2900353',
  1112. 'ext': 'flv',
  1113. 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)',
  1114. 'duration': 27,
  1115. 'age_limit': 0,
  1116. },
  1117. },
  1118. # Crooks and Liars embed
  1119. {
  1120. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1121. 'info_dict': {
  1122. 'id': '8RUoRhRi',
  1123. 'ext': 'mp4',
  1124. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1125. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1126. 'timestamp': 1428207000,
  1127. 'upload_date': '20150405',
  1128. 'uploader': 'Heather',
  1129. },
  1130. },
  1131. # Crooks and Liars external embed
  1132. {
  1133. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1134. 'info_dict': {
  1135. 'id': 'MTE3MjUtMzQ2MzA',
  1136. 'ext': 'mp4',
  1137. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1138. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1139. 'timestamp': 1265032391,
  1140. 'upload_date': '20100201',
  1141. 'uploader': 'Heather',
  1142. },
  1143. },
  1144. # NBC Sports vplayer embed
  1145. {
  1146. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1147. 'info_dict': {
  1148. 'id': 'ln7x1qSThw4k',
  1149. 'ext': 'flv',
  1150. 'title': "PFT Live: New leader in the 'new-look' defense",
  1151. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1152. 'uploader': 'NBCU-SPORTS',
  1153. 'upload_date': '20140107',
  1154. 'timestamp': 1389118457,
  1155. },
  1156. },
  1157. # NBC News embed
  1158. {
  1159. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1160. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1161. 'info_dict': {
  1162. 'id': '701714499682',
  1163. 'ext': 'mp4',
  1164. 'title': 'PREVIEW: On Assignment: David Letterman',
  1165. '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.',
  1166. },
  1167. },
  1168. # UDN embed
  1169. {
  1170. 'url': 'https://video.udn.com/news/300346',
  1171. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1172. 'info_dict': {
  1173. 'id': '300346',
  1174. 'ext': 'mp4',
  1175. 'title': '中一中男師變性 全校師生力挺',
  1176. 'thumbnail': r're:^https?://.*\.jpg$',
  1177. },
  1178. 'params': {
  1179. # m3u8 download
  1180. 'skip_download': True,
  1181. },
  1182. },
  1183. # Ooyala embed
  1184. {
  1185. 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
  1186. 'info_dict': {
  1187. 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
  1188. 'ext': 'mp4',
  1189. 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.',
  1190. 'title': 'This is what separates the Excel masters from the wannabes',
  1191. 'duration': 191.933,
  1192. },
  1193. 'params': {
  1194. # m3u8 downloads
  1195. 'skip_download': True,
  1196. }
  1197. },
  1198. # Brightcove URL in single quotes
  1199. {
  1200. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1201. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1202. 'info_dict': {
  1203. 'id': '4255764656001',
  1204. 'ext': 'mp4',
  1205. 'title': 'SN Presents: Russell Martin, World Citizen',
  1206. '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.',
  1207. 'uploader': 'Rogers Sportsnet',
  1208. 'uploader_id': '1704050871',
  1209. 'upload_date': '20150525',
  1210. 'timestamp': 1432570283,
  1211. },
  1212. },
  1213. # Dailymotion Cloud video
  1214. {
  1215. 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
  1216. 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38',
  1217. 'info_dict': {
  1218. 'id': 'x2uy8t3',
  1219. 'ext': 'mp4',
  1220. 'title': 'Sauvons les abeilles ! - Le débat',
  1221. 'description': 'md5:d9082128b1c5277987825d684939ca26',
  1222. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1223. 'timestamp': 1434970506,
  1224. 'upload_date': '20150622',
  1225. 'uploader': 'Public Sénat',
  1226. 'uploader_id': 'xa9gza',
  1227. }
  1228. },
  1229. # OnionStudios embed
  1230. {
  1231. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1232. 'info_dict': {
  1233. 'id': '2855',
  1234. 'ext': 'mp4',
  1235. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1236. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1237. 'uploader': 'ClickHole',
  1238. 'uploader_id': 'clickhole',
  1239. }
  1240. },
  1241. # SnagFilms embed
  1242. {
  1243. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1244. 'info_dict': {
  1245. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1246. 'ext': 'mp4',
  1247. 'title': '#whilewewatch',
  1248. }
  1249. },
  1250. # AdobeTVVideo embed
  1251. {
  1252. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1253. 'md5': '43662b577c018ad707a63766462b1e87',
  1254. 'info_dict': {
  1255. 'id': '2456',
  1256. 'ext': 'mp4',
  1257. 'title': 'New experience with Acrobat DC',
  1258. 'description': 'New experience with Acrobat DC',
  1259. 'duration': 248.667,
  1260. },
  1261. },
  1262. # BrightcoveInPageEmbed embed
  1263. {
  1264. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1265. 'info_dict': {
  1266. 'id': '4238694884001',
  1267. 'ext': 'flv',
  1268. 'title': 'Tabletop: Dread, Last Thoughts',
  1269. 'description': 'Tabletop: Dread, Last Thoughts',
  1270. 'duration': 51690,
  1271. },
  1272. },
  1273. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1274. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1275. {
  1276. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1277. 'info_dict': {
  1278. 'id': '4785848093001',
  1279. 'ext': 'mp4',
  1280. 'title': 'The Cardinal Pell Interview',
  1281. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1282. 'uploader': 'GlobeCast Australia - GlobeStream',
  1283. 'uploader_id': '2733773828001',
  1284. 'upload_date': '20160304',
  1285. 'timestamp': 1457083087,
  1286. },
  1287. 'params': {
  1288. # m3u8 downloads
  1289. 'skip_download': True,
  1290. },
  1291. },
  1292. # Another form of arte.tv embed
  1293. {
  1294. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1295. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1296. 'info_dict': {
  1297. 'id': '030273-562_PLUS7-F',
  1298. 'ext': 'mp4',
  1299. 'title': 'ARTE Reportage - Nulle part, en France',
  1300. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1301. 'upload_date': '20160409',
  1302. },
  1303. },
  1304. # LiveLeak embed
  1305. {
  1306. 'url': 'http://www.wykop.pl/link/3088787/',
  1307. 'md5': 'ace83b9ed19b21f68e1b50e844fdf95d',
  1308. 'info_dict': {
  1309. 'id': '874_1459135191',
  1310. 'ext': 'mp4',
  1311. 'title': 'Man shows poor quality of new apartment building',
  1312. 'description': 'The wall is like a sand pile.',
  1313. 'uploader': 'Lake8737',
  1314. }
  1315. },
  1316. # Duplicated embedded video URLs
  1317. {
  1318. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1319. 'info_dict': {
  1320. 'id': '149298443_480_16c25b74_2',
  1321. 'ext': 'mp4',
  1322. 'title': 'vs. Blue Orange Spring Game',
  1323. 'uploader': 'www.hudl.com',
  1324. },
  1325. },
  1326. # twitter:player:stream embed
  1327. {
  1328. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1329. 'info_dict': {
  1330. 'id': 'master',
  1331. 'ext': 'mp4',
  1332. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1333. 'uploader': 'www.rtl.be',
  1334. },
  1335. 'params': {
  1336. # m3u8 downloads
  1337. 'skip_download': True,
  1338. },
  1339. },
  1340. # twitter:player embed
  1341. {
  1342. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1343. 'md5': 'a3e0df96369831de324f0778e126653c',
  1344. 'info_dict': {
  1345. 'id': '4909620399001',
  1346. 'ext': 'mp4',
  1347. 'title': 'What Do Black Holes Sound Like?',
  1348. 'description': 'what do black holes sound like',
  1349. 'upload_date': '20160524',
  1350. 'uploader_id': '29913724001',
  1351. 'timestamp': 1464107587,
  1352. 'uploader': 'TheAtlantic',
  1353. },
  1354. 'add_ie': ['BrightcoveLegacy'],
  1355. },
  1356. # Facebook <iframe> embed
  1357. {
  1358. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1359. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1360. 'info_dict': {
  1361. 'id': '599637780109885',
  1362. 'ext': 'mp4',
  1363. 'title': 'Facebook video #599637780109885',
  1364. },
  1365. },
  1366. # Facebook API embed
  1367. {
  1368. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1369. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1370. 'info_dict': {
  1371. 'id': '10153467542406923',
  1372. 'ext': 'mp4',
  1373. 'title': 'Facebook video #10153467542406923',
  1374. },
  1375. },
  1376. # Wordpress "YouTube Video Importer" plugin
  1377. {
  1378. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1379. 'md5': 'd16797741b560b485194eddda8121b48',
  1380. 'info_dict': {
  1381. 'id': 'HNTXWDXV9Is',
  1382. 'ext': 'mp4',
  1383. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1384. 'upload_date': '20160627',
  1385. 'uploader_id': 'GENOCIDE8GENERAL10',
  1386. 'uploader': 'cylus cyrus',
  1387. },
  1388. },
  1389. {
  1390. # video stored on custom kaltura server
  1391. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1392. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1393. 'info_dict': {
  1394. 'id': '0_1iotm5bh',
  1395. 'ext': 'mp4',
  1396. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1397. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1398. 'uploader_id': 'videos.expansion@el-mundo.net',
  1399. 'upload_date': '20150429',
  1400. 'timestamp': 1430303472,
  1401. },
  1402. 'add_ie': ['Kaltura'],
  1403. },
  1404. {
  1405. # Non-standard Vimeo embed
  1406. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1407. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1408. 'info_dict': {
  1409. 'id': '148867247',
  1410. 'ext': 'mp4',
  1411. 'title': 'Understanding the web - Teaser',
  1412. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1413. 'upload_date': '20151214',
  1414. 'uploader': 'OpenClassrooms',
  1415. 'uploader_id': 'openclassrooms',
  1416. },
  1417. 'add_ie': ['Vimeo'],
  1418. },
  1419. {
  1420. # generic vimeo embed that requires original URL passed as Referer
  1421. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1422. 'only_matching': True,
  1423. },
  1424. {
  1425. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1426. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1427. 'info_dict': {
  1428. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1429. 'ext': 'mp4',
  1430. 'title': 'Big Buck Bunny',
  1431. 'description': 'Royalty free test video',
  1432. 'timestamp': 1432816365,
  1433. 'upload_date': '20150528',
  1434. 'is_live': False,
  1435. },
  1436. 'params': {
  1437. 'skip_download': True,
  1438. },
  1439. 'add_ie': [ArkenaIE.ie_key()],
  1440. },
  1441. {
  1442. '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/',
  1443. 'info_dict': {
  1444. 'id': '1c7141f46c',
  1445. 'ext': 'mp4',
  1446. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1447. },
  1448. 'params': {
  1449. 'skip_download': True,
  1450. },
  1451. 'add_ie': [Vbox7IE.ie_key()],
  1452. },
  1453. {
  1454. # DBTV embeds
  1455. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1456. 'info_dict': {
  1457. 'id': '43254897',
  1458. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1459. },
  1460. 'playlist_mincount': 3,
  1461. },
  1462. {
  1463. # Videa embeds
  1464. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1465. 'info_dict': {
  1466. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1467. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1468. },
  1469. 'playlist_mincount': 2,
  1470. },
  1471. {
  1472. # 20 minuten embed
  1473. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1474. 'info_dict': {
  1475. 'id': '523629',
  1476. 'ext': 'mp4',
  1477. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1478. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1479. },
  1480. 'params': {
  1481. 'skip_download': True,
  1482. },
  1483. 'add_ie': [TwentyMinutenIE.ie_key()],
  1484. },
  1485. {
  1486. # VideoPress embed
  1487. 'url': 'https://en.support.wordpress.com/videopress/',
  1488. 'info_dict': {
  1489. 'id': 'OcobLTqC',
  1490. 'ext': 'm4v',
  1491. 'title': 'IMG_5786',
  1492. 'timestamp': 1435711927,
  1493. 'upload_date': '20150701',
  1494. },
  1495. 'params': {
  1496. 'skip_download': True,
  1497. },
  1498. 'add_ie': [VideoPressIE.ie_key()],
  1499. },
  1500. {
  1501. # ThePlatform embedded with whitespaces in URLs
  1502. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1503. 'only_matching': True,
  1504. },
  1505. # {
  1506. # # TODO: find another test
  1507. # # http://schema.org/VideoObject
  1508. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  1509. # 'md5': '888dcf08b7ea671381f00fab74692755',
  1510. # 'info_dict': {
  1511. # 'id': 'nyvTSJMKId',
  1512. # 'ext': 'mp4',
  1513. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  1514. # 'description': '#love for cats.',
  1515. # 'timestamp': 1461244995,
  1516. # 'upload_date': '20160421',
  1517. # },
  1518. # 'params': {
  1519. # 'force_generic_extractor': True,
  1520. # },
  1521. # }
  1522. ]
  1523. def report_following_redirect(self, new_url):
  1524. """Report information extraction."""
  1525. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  1526. def _extract_rss(self, url, video_id, doc):
  1527. playlist_title = doc.find('./channel/title').text
  1528. playlist_desc_el = doc.find('./channel/description')
  1529. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  1530. entries = []
  1531. for it in doc.findall('./channel/item'):
  1532. next_url = xpath_text(it, 'link', fatal=False)
  1533. if not next_url:
  1534. enclosure_nodes = it.findall('./enclosure')
  1535. for e in enclosure_nodes:
  1536. next_url = e.attrib.get('url')
  1537. if next_url:
  1538. break
  1539. if not next_url:
  1540. continue
  1541. entries.append({
  1542. '_type': 'url',
  1543. 'url': next_url,
  1544. 'title': it.find('title').text,
  1545. })
  1546. return {
  1547. '_type': 'playlist',
  1548. 'id': url,
  1549. 'title': playlist_title,
  1550. 'description': playlist_desc,
  1551. 'entries': entries,
  1552. }
  1553. def _extract_camtasia(self, url, video_id, webpage):
  1554. """ Returns None if no camtasia video can be found. """
  1555. camtasia_cfg = self._search_regex(
  1556. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  1557. webpage, 'camtasia configuration file', default=None)
  1558. if camtasia_cfg is None:
  1559. return None
  1560. title = self._html_search_meta('DC.title', webpage, fatal=True)
  1561. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  1562. camtasia_cfg = self._download_xml(
  1563. camtasia_url, video_id,
  1564. note='Downloading camtasia configuration',
  1565. errnote='Failed to download camtasia configuration')
  1566. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  1567. entries = []
  1568. for n in fileset_node.getchildren():
  1569. url_n = n.find('./uri')
  1570. if url_n is None:
  1571. continue
  1572. entries.append({
  1573. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  1574. 'title': '%s - %s' % (title, n.tag),
  1575. 'url': compat_urlparse.urljoin(url, url_n.text),
  1576. 'duration': float_or_none(n.find('./duration').text),
  1577. })
  1578. return {
  1579. '_type': 'playlist',
  1580. 'entries': entries,
  1581. 'title': title,
  1582. }
  1583. def _real_extract(self, url):
  1584. if url.startswith('//'):
  1585. return {
  1586. '_type': 'url',
  1587. 'url': self.http_scheme() + url,
  1588. }
  1589. parsed_url = compat_urlparse.urlparse(url)
  1590. if not parsed_url.scheme:
  1591. default_search = self._downloader.params.get('default_search')
  1592. if default_search is None:
  1593. default_search = 'fixup_error'
  1594. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  1595. if '/' in url:
  1596. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  1597. return self.url_result('http://' + url)
  1598. elif default_search != 'fixup_error':
  1599. if default_search == 'auto_warning':
  1600. if re.match(r'^(?:url|URL)$', url):
  1601. raise ExtractorError(
  1602. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  1603. expected=True)
  1604. else:
  1605. self._downloader.report_warning(
  1606. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  1607. return self.url_result('ytsearch:' + url)
  1608. if default_search in ('error', 'fixup_error'):
  1609. raise ExtractorError(
  1610. '%r is not a valid URL. '
  1611. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  1612. % (url, url), expected=True)
  1613. else:
  1614. if ':' not in default_search:
  1615. default_search += ':'
  1616. return self.url_result(default_search + url)
  1617. url, smuggled_data = unsmuggle_url(url)
  1618. force_videoid = None
  1619. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  1620. if smuggled_data and 'force_videoid' in smuggled_data:
  1621. force_videoid = smuggled_data['force_videoid']
  1622. video_id = force_videoid
  1623. else:
  1624. video_id = self._generic_id(url)
  1625. self.to_screen('%s: Requesting header' % video_id)
  1626. head_req = HEADRequest(url)
  1627. head_response = self._request_webpage(
  1628. head_req, video_id,
  1629. note=False, errnote='Could not send HEAD request to %s' % url,
  1630. fatal=False)
  1631. if head_response is not False:
  1632. # Check for redirect
  1633. new_url = head_response.geturl()
  1634. if url != new_url:
  1635. self.report_following_redirect(new_url)
  1636. if force_videoid:
  1637. new_url = smuggle_url(
  1638. new_url, {'force_videoid': force_videoid})
  1639. return self.url_result(new_url)
  1640. full_response = None
  1641. if head_response is False:
  1642. request = sanitized_Request(url)
  1643. request.add_header('Accept-Encoding', '*')
  1644. full_response = self._request_webpage(request, video_id)
  1645. head_response = full_response
  1646. info_dict = {
  1647. 'id': video_id,
  1648. 'title': self._generic_title(url),
  1649. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  1650. }
  1651. # Check for direct link to a video
  1652. content_type = head_response.headers.get('Content-Type', '').lower()
  1653. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  1654. if m:
  1655. format_id = m.group('format_id')
  1656. if format_id.endswith('mpegurl'):
  1657. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  1658. elif format_id == 'f4m':
  1659. formats = self._extract_f4m_formats(url, video_id)
  1660. else:
  1661. formats = [{
  1662. 'format_id': m.group('format_id'),
  1663. 'url': url,
  1664. 'vcodec': 'none' if m.group('type') == 'audio' else None
  1665. }]
  1666. info_dict['direct'] = True
  1667. self._sort_formats(formats)
  1668. info_dict['formats'] = formats
  1669. return info_dict
  1670. if not self._downloader.params.get('test', False) and not is_intentional:
  1671. force = self._downloader.params.get('force_generic_extractor', False)
  1672. self._downloader.report_warning(
  1673. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  1674. if not full_response:
  1675. request = sanitized_Request(url)
  1676. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  1677. # making it impossible to download only chunk of the file (yet we need only 512kB to
  1678. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  1679. # that will always result in downloading the whole file that is not desirable.
  1680. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  1681. # to accept raw bytes and being able to download only a chunk.
  1682. # It may probably better to solve this by checking Content-Type for application/octet-stream
  1683. # after HEAD request finishes, but not sure if we can rely on this.
  1684. request.add_header('Accept-Encoding', '*')
  1685. full_response = self._request_webpage(request, video_id)
  1686. first_bytes = full_response.read(512)
  1687. # Is it an M3U playlist?
  1688. if first_bytes.startswith(b'#EXTM3U'):
  1689. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  1690. self._sort_formats(info_dict['formats'])
  1691. return info_dict
  1692. # Maybe it's a direct link to a video?
  1693. # Be careful not to download the whole thing!
  1694. if not is_html(first_bytes):
  1695. self._downloader.report_warning(
  1696. 'URL could be a direct video link, returning it as such.')
  1697. info_dict.update({
  1698. 'direct': True,
  1699. 'url': url,
  1700. })
  1701. return info_dict
  1702. webpage = self._webpage_read_content(
  1703. full_response, url, video_id, prefix=first_bytes)
  1704. self.report_extraction(video_id)
  1705. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  1706. try:
  1707. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  1708. if doc.tag == 'rss':
  1709. return self._extract_rss(url, video_id, doc)
  1710. elif doc.tag == 'SmoothStreamingMedia':
  1711. info_dict['formats'] = self._parse_ism_formats(doc, url)
  1712. self._sort_formats(info_dict['formats'])
  1713. return info_dict
  1714. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  1715. smil = self._parse_smil(doc, url, video_id)
  1716. self._sort_formats(smil['formats'])
  1717. return smil
  1718. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  1719. return self.playlist_result(self._parse_xspf(doc, video_id), video_id)
  1720. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  1721. info_dict['formats'] = self._parse_mpd_formats(
  1722. doc, video_id,
  1723. mpd_base_url=full_response.geturl().rpartition('/')[0],
  1724. mpd_url=url)
  1725. self._sort_formats(info_dict['formats'])
  1726. return info_dict
  1727. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  1728. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  1729. self._sort_formats(info_dict['formats'])
  1730. return info_dict
  1731. except compat_xml_parse_error:
  1732. pass
  1733. # Is it a Camtasia project?
  1734. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  1735. if camtasia_res is not None:
  1736. return camtasia_res
  1737. # Sometimes embedded video player is hidden behind percent encoding
  1738. # (e.g. https://github.com/rg3/youtube-dl/issues/2448)
  1739. # Unescaping the whole page allows to handle those cases in a generic way
  1740. webpage = compat_urllib_parse_unquote(webpage)
  1741. # it's tempting to parse this further, but you would
  1742. # have to take into account all the variations like
  1743. # Video Title - Site Name
  1744. # Site Name | Video Title
  1745. # Video Title - Tagline | Site Name
  1746. # and so on and so forth; it's just not practical
  1747. video_title = self._og_search_title(
  1748. webpage, default=None) or self._html_search_regex(
  1749. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  1750. default='video')
  1751. # Try to detect age limit automatically
  1752. age_limit = self._rta_search(webpage)
  1753. # And then there are the jokers who advertise that they use RTA,
  1754. # but actually don't.
  1755. AGE_LIMIT_MARKERS = [
  1756. r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
  1757. ]
  1758. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  1759. age_limit = 18
  1760. # video uploader is domain name
  1761. video_uploader = self._search_regex(
  1762. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  1763. video_description = self._og_search_description(webpage, default=None)
  1764. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  1765. # Helper method
  1766. def _playlist_from_matches(matches, getter=None, ie=None):
  1767. urlrs = orderedSet(
  1768. self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
  1769. for m in matches)
  1770. return self.playlist_result(
  1771. urlrs, playlist_id=video_id, playlist_title=video_title)
  1772. # Look for Brightcove Legacy Studio embeds
  1773. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  1774. if bc_urls:
  1775. self.to_screen('Brightcove video detected.')
  1776. entries = [{
  1777. '_type': 'url',
  1778. 'url': smuggle_url(bc_url, {'Referer': url}),
  1779. 'ie_key': 'BrightcoveLegacy'
  1780. } for bc_url in bc_urls]
  1781. return {
  1782. '_type': 'playlist',
  1783. 'title': video_title,
  1784. 'id': video_id,
  1785. 'entries': entries,
  1786. }
  1787. # Look for Brightcove New Studio embeds
  1788. bc_urls = BrightcoveNewIE._extract_urls(webpage)
  1789. if bc_urls:
  1790. return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
  1791. # Look for ThePlatform embeds
  1792. tp_urls = ThePlatformIE._extract_urls(webpage)
  1793. if tp_urls:
  1794. return _playlist_from_matches(tp_urls, ie='ThePlatform')
  1795. # Look for Vessel embeds
  1796. vessel_urls = VesselIE._extract_urls(webpage)
  1797. if vessel_urls:
  1798. return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
  1799. # Look for embedded rtl.nl player
  1800. matches = re.findall(
  1801. r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
  1802. webpage)
  1803. if matches:
  1804. return _playlist_from_matches(matches, ie='RtlNl')
  1805. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  1806. if vimeo_urls:
  1807. return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
  1808. vid_me_embed_url = self._search_regex(
  1809. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  1810. webpage, 'vid.me embed', default=None)
  1811. if vid_me_embed_url is not None:
  1812. return self.url_result(vid_me_embed_url, 'Vidme')
  1813. # Look for embedded YouTube player
  1814. matches = re.findall(r'''(?x)
  1815. (?:
  1816. <iframe[^>]+?src=|
  1817. data-video-url=|
  1818. <embed[^>]+?src=|
  1819. embedSWF\(?:\s*|
  1820. new\s+SWFObject\(
  1821. )
  1822. (["\'])
  1823. (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
  1824. (?:embed|v|p)/.+?)
  1825. \1''', webpage)
  1826. if matches:
  1827. return _playlist_from_matches(
  1828. matches, lambda m: unescapeHTML(m[1]))
  1829. # Look for lazyYT YouTube embed
  1830. matches = re.findall(
  1831. r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
  1832. if matches:
  1833. return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
  1834. # Look for Wordpress "YouTube Video Importer" plugin
  1835. matches = re.findall(r'''(?x)<div[^>]+
  1836. class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
  1837. data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
  1838. if matches:
  1839. return _playlist_from_matches(matches, lambda m: m[-1])
  1840. matches = DailymotionIE._extract_urls(webpage)
  1841. if matches:
  1842. return _playlist_from_matches(matches)
  1843. # Look for embedded Dailymotion playlist player (#3822)
  1844. m = re.search(
  1845. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  1846. if m:
  1847. playlists = re.findall(
  1848. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  1849. if playlists:
  1850. return _playlist_from_matches(
  1851. playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
  1852. # Look for embedded Wistia player
  1853. match = re.search(
  1854. r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
  1855. if match:
  1856. embed_url = self._proto_relative_url(
  1857. unescapeHTML(match.group('url')))
  1858. return {
  1859. '_type': 'url_transparent',
  1860. 'url': embed_url,
  1861. 'ie_key': 'Wistia',
  1862. 'uploader': video_uploader,
  1863. }
  1864. match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
  1865. if match:
  1866. return {
  1867. '_type': 'url_transparent',
  1868. 'url': 'wistia:%s' % match.group('id'),
  1869. 'ie_key': 'Wistia',
  1870. 'uploader': video_uploader,
  1871. }
  1872. match = re.search(
  1873. r'''(?sx)
  1874. <script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
  1875. <div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
  1876. ''', webpage)
  1877. if match:
  1878. return self.url_result(self._proto_relative_url(
  1879. 'wistia:%s' % match.group('id')), 'Wistia')
  1880. # Look for SVT player
  1881. svt_url = SVTIE._extract_url(webpage)
  1882. if svt_url:
  1883. return self.url_result(svt_url, 'SVT')
  1884. # Look for embedded condenast player
  1885. matches = re.findall(
  1886. r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
  1887. webpage)
  1888. if matches:
  1889. return {
  1890. '_type': 'playlist',
  1891. 'entries': [{
  1892. '_type': 'url',
  1893. 'ie_key': 'CondeNast',
  1894. 'url': ma,
  1895. } for ma in matches],
  1896. 'title': video_title,
  1897. 'id': video_id,
  1898. }
  1899. # Look for Bandcamp pages with custom domain
  1900. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  1901. if mobj is not None:
  1902. burl = unescapeHTML(mobj.group(1))
  1903. # Don't set the extractor because it can be a track url or an album
  1904. return self.url_result(burl)
  1905. # Look for embedded Vevo player
  1906. mobj = re.search(
  1907. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  1908. if mobj is not None:
  1909. return self.url_result(mobj.group('url'))
  1910. # Look for embedded Viddler player
  1911. mobj = re.search(
  1912. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  1913. webpage)
  1914. if mobj is not None:
  1915. return self.url_result(mobj.group('url'))
  1916. # Look for NYTimes player
  1917. mobj = re.search(
  1918. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  1919. webpage)
  1920. if mobj is not None:
  1921. return self.url_result(mobj.group('url'))
  1922. # Look for Libsyn player
  1923. mobj = re.search(
  1924. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  1925. if mobj is not None:
  1926. return self.url_result(mobj.group('url'))
  1927. # Look for Ooyala videos
  1928. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
  1929. re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
  1930. re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
  1931. re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  1932. if mobj is not None:
  1933. embed_token = self._search_regex(
  1934. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  1935. webpage, 'ooyala embed token', default=None)
  1936. return OoyalaIE._build_url_result(smuggle_url(
  1937. mobj.group('ec'), {
  1938. 'domain': url,
  1939. 'embed_token': embed_token,
  1940. }))
  1941. # Look for multiple Ooyala embeds on SBN network websites
  1942. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  1943. if mobj is not None:
  1944. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  1945. if embeds:
  1946. return _playlist_from_matches(
  1947. embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  1948. # Look for Aparat videos
  1949. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  1950. if mobj is not None:
  1951. return self.url_result(mobj.group(1), 'Aparat')
  1952. # Look for MPORA videos
  1953. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  1954. if mobj is not None:
  1955. return self.url_result(mobj.group(1), 'Mpora')
  1956. # Look for embedded NovaMov-based player
  1957. mobj = re.search(
  1958. r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
  1959. (?P<url>http://(?:(?:embed|www)\.)?
  1960. (?:novamov\.com|
  1961. nowvideo\.(?:ch|sx|eu|at|ag|co)|
  1962. videoweed\.(?:es|com)|
  1963. movshare\.(?:net|sx|ag)|
  1964. divxstage\.(?:eu|net|ch|co|at|ag))
  1965. /embed\.php.+?)\1''', webpage)
  1966. if mobj is not None:
  1967. return self.url_result(mobj.group('url'))
  1968. # Look for embedded Facebook player
  1969. facebook_url = FacebookIE._extract_url(webpage)
  1970. if facebook_url is not None:
  1971. return self.url_result(facebook_url, 'Facebook')
  1972. # Look for embedded VK player
  1973. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  1974. if mobj is not None:
  1975. return self.url_result(mobj.group('url'), 'VK')
  1976. # Look for embedded Odnoklassniki player
  1977. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
  1978. if mobj is not None:
  1979. return self.url_result(mobj.group('url'), 'Odnoklassniki')
  1980. # Look for embedded ivi player
  1981. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  1982. if mobj is not None:
  1983. return self.url_result(mobj.group('url'), 'Ivi')
  1984. # Look for embedded Huffington Post player
  1985. mobj = re.search(
  1986. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  1987. if mobj is not None:
  1988. return self.url_result(mobj.group('url'), 'HuffPost')
  1989. # Look for embed.ly
  1990. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  1991. if mobj is not None:
  1992. return self.url_result(mobj.group('url'))
  1993. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  1994. if mobj is not None:
  1995. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  1996. # Look for funnyordie embed
  1997. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  1998. if matches:
  1999. return _playlist_from_matches(
  2000. matches, getter=unescapeHTML, ie='FunnyOrDie')
  2001. # Look for BBC iPlayer embed
  2002. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2003. if matches:
  2004. return _playlist_from_matches(matches, ie='BBCCoUk')
  2005. # Look for embedded RUTV player
  2006. rutv_url = RUTVIE._extract_url(webpage)
  2007. if rutv_url:
  2008. return self.url_result(rutv_url, 'RUTV')
  2009. # Look for embedded TVC player
  2010. tvc_url = TVCIE._extract_url(webpage)
  2011. if tvc_url:
  2012. return self.url_result(tvc_url, 'TVC')
  2013. # Look for embedded SportBox player
  2014. sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
  2015. if sportbox_urls:
  2016. return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
  2017. # Look for embedded XHamster player
  2018. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2019. if xhamster_urls:
  2020. return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
  2021. # Look for embedded TNAFlixNetwork player
  2022. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2023. if tnaflix_urls:
  2024. return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
  2025. # Look for embedded PornHub player
  2026. pornhub_urls = PornHubIE._extract_urls(webpage)
  2027. if pornhub_urls:
  2028. return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
  2029. # Look for embedded DrTuber player
  2030. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2031. if drtuber_urls:
  2032. return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
  2033. # Look for embedded RedTube player
  2034. redtube_urls = RedTubeIE._extract_urls(webpage)
  2035. if redtube_urls:
  2036. return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
  2037. # Look for embedded Tvigle player
  2038. mobj = re.search(
  2039. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2040. if mobj is not None:
  2041. return self.url_result(mobj.group('url'), 'Tvigle')
  2042. # Look for embedded TED player
  2043. mobj = re.search(
  2044. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2045. if mobj is not None:
  2046. return self.url_result(mobj.group('url'), 'TED')
  2047. # Look for embedded Ustream videos
  2048. ustream_url = UstreamIE._extract_url(webpage)
  2049. if ustream_url:
  2050. return self.url_result(ustream_url, UstreamIE.ie_key())
  2051. # Look for embedded arte.tv player
  2052. mobj = re.search(
  2053. r'<(?:script|iframe) [^>]*?src="(?P<url>http://www\.arte\.tv/(?:playerv2/embed|arte_vp/index)[^"]+)"',
  2054. webpage)
  2055. if mobj is not None:
  2056. return self.url_result(mobj.group('url'), 'ArteTVEmbed')
  2057. # Look for embedded francetv player
  2058. mobj = re.search(
  2059. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2060. webpage)
  2061. if mobj is not None:
  2062. return self.url_result(mobj.group('url'))
  2063. # Look for embedded smotri.com player
  2064. smotri_url = SmotriIE._extract_url(webpage)
  2065. if smotri_url:
  2066. return self.url_result(smotri_url, 'Smotri')
  2067. # Look for embedded Myvi.ru player
  2068. myvi_url = MyviIE._extract_url(webpage)
  2069. if myvi_url:
  2070. return self.url_result(myvi_url)
  2071. # Look for embedded soundcloud player
  2072. soundcloud_urls = SoundcloudIE._extract_urls(webpage)
  2073. if soundcloud_urls:
  2074. return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
  2075. # Look for tunein player
  2076. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2077. if tunein_urls:
  2078. return _playlist_from_matches(tunein_urls)
  2079. # Look for embedded mtvservices player
  2080. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2081. if mtvservices_url:
  2082. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2083. # Look for embedded yahoo player
  2084. mobj = re.search(
  2085. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2086. webpage)
  2087. if mobj is not None:
  2088. return self.url_result(mobj.group('url'), 'Yahoo')
  2089. # Look for embedded sbs.com.au player
  2090. mobj = re.search(
  2091. r'''(?x)
  2092. (?:
  2093. <meta\s+property="og:video"\s+content=|
  2094. <iframe[^>]+?src=
  2095. )
  2096. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2097. webpage)
  2098. if mobj is not None:
  2099. return self.url_result(mobj.group('url'), 'SBS')
  2100. # Look for embedded Cinchcast player
  2101. mobj = re.search(
  2102. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2103. webpage)
  2104. if mobj is not None:
  2105. return self.url_result(mobj.group('url'), 'Cinchcast')
  2106. mobj = re.search(
  2107. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2108. webpage)
  2109. if not mobj:
  2110. mobj = re.search(
  2111. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2112. webpage)
  2113. if mobj is not None:
  2114. return self.url_result(mobj.group('url'), 'MLB')
  2115. mobj = re.search(
  2116. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2117. webpage)
  2118. if mobj is not None:
  2119. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2120. mobj = re.search(
  2121. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2122. webpage)
  2123. if mobj is not None:
  2124. return self.url_result(mobj.group('url'), 'Livestream')
  2125. # Look for Zapiks embed
  2126. mobj = re.search(
  2127. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2128. if mobj is not None:
  2129. return self.url_result(mobj.group('url'), 'Zapiks')
  2130. # Look for Kaltura embeds
  2131. kaltura_url = KalturaIE._extract_url(webpage)
  2132. if kaltura_url:
  2133. return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
  2134. # Look for Eagle.Platform embeds
  2135. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2136. if eagleplatform_url:
  2137. return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
  2138. # Look for ClipYou (uses Eagle.Platform) embeds
  2139. mobj = re.search(
  2140. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2141. if mobj is not None:
  2142. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2143. # Look for Pladform embeds
  2144. pladform_url = PladformIE._extract_url(webpage)
  2145. if pladform_url:
  2146. return self.url_result(pladform_url)
  2147. # Look for Videomore embeds
  2148. videomore_url = VideomoreIE._extract_url(webpage)
  2149. if videomore_url:
  2150. return self.url_result(videomore_url)
  2151. # Look for Webcaster embeds
  2152. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2153. if webcaster_url:
  2154. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2155. # Look for Playwire embeds
  2156. mobj = re.search(
  2157. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2158. if mobj is not None:
  2159. return self.url_result(mobj.group('url'))
  2160. # Look for 5min embeds
  2161. mobj = re.search(
  2162. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2163. if mobj is not None:
  2164. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2165. # Look for Crooks and Liars embeds
  2166. mobj = re.search(
  2167. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2168. if mobj is not None:
  2169. return self.url_result(mobj.group('url'))
  2170. # Look for NBC Sports VPlayer embeds
  2171. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2172. if nbc_sports_url:
  2173. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2174. # Look for NBC News embeds
  2175. nbc_news_embed_url = re.search(
  2176. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2177. if nbc_news_embed_url:
  2178. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2179. # Look for Google Drive embeds
  2180. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2181. if google_drive_url:
  2182. return self.url_result(google_drive_url, 'GoogleDrive')
  2183. # Look for UDN embeds
  2184. mobj = re.search(
  2185. r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2186. if mobj is not None:
  2187. return self.url_result(
  2188. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2189. # Look for Senate ISVP iframe
  2190. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2191. if senate_isvp_url:
  2192. return self.url_result(senate_isvp_url, 'SenateISVP')
  2193. # Look for Dailymotion Cloud videos
  2194. dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
  2195. if dmcloud_url:
  2196. return self.url_result(dmcloud_url, 'DailymotionCloud')
  2197. # Look for OnionStudios embeds
  2198. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2199. if onionstudios_url:
  2200. return self.url_result(onionstudios_url)
  2201. # Look for ViewLift embeds
  2202. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2203. if viewlift_url:
  2204. return self.url_result(viewlift_url)
  2205. # Look for JWPlatform embeds
  2206. jwplatform_url = JWPlatformIE._extract_url(webpage)
  2207. if jwplatform_url:
  2208. return self.url_result(jwplatform_url, 'JWPlatform')
  2209. # Look for Digiteka embeds
  2210. digiteka_url = DigitekaIE._extract_url(webpage)
  2211. if digiteka_url:
  2212. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2213. # Look for Arkena embeds
  2214. arkena_url = ArkenaIE._extract_url(webpage)
  2215. if arkena_url:
  2216. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2217. # Look for Piksel embeds
  2218. piksel_url = PikselIE._extract_url(webpage)
  2219. if piksel_url:
  2220. return self.url_result(piksel_url, PikselIE.ie_key())
  2221. # Look for Limelight embeds
  2222. mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
  2223. if mobj:
  2224. lm = {
  2225. 'Media': 'media',
  2226. 'Channel': 'channel',
  2227. 'ChannelList': 'channel_list',
  2228. }
  2229. return self.url_result(smuggle_url('limelight:%s:%s' % (
  2230. lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
  2231. 'Limelight%s' % mobj.group(1), mobj.group(2))
  2232. mobj = re.search(
  2233. r'''(?sx)
  2234. <object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
  2235. <param[^>]+
  2236. name=(["\'])flashVars\2[^>]+
  2237. value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
  2238. ''', webpage)
  2239. if mobj:
  2240. return self.url_result(smuggle_url(
  2241. 'limelight:media:%s' % mobj.group('id'),
  2242. {'source_url': url}), 'LimelightMedia', mobj.group('id'))
  2243. # Look for AdobeTVVideo embeds
  2244. mobj = re.search(
  2245. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2246. webpage)
  2247. if mobj is not None:
  2248. return self.url_result(
  2249. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2250. 'AdobeTVVideo')
  2251. # Look for Vine embeds
  2252. mobj = re.search(
  2253. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2254. webpage)
  2255. if mobj is not None:
  2256. return self.url_result(
  2257. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2258. # Look for VODPlatform embeds
  2259. mobj = re.search(
  2260. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
  2261. webpage)
  2262. if mobj is not None:
  2263. return self.url_result(
  2264. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2265. # Look for Mangomolo embeds
  2266. mobj = re.search(
  2267. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
  2268. (?:
  2269. video\?.*?\bid=(?P<video_id>\d+)|
  2270. index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2271. ).+?)\1''', webpage)
  2272. if mobj is not None:
  2273. info = {
  2274. '_type': 'url_transparent',
  2275. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2276. 'title': video_title,
  2277. 'description': video_description,
  2278. 'thumbnail': video_thumbnail,
  2279. 'uploader': video_uploader,
  2280. }
  2281. video_id = mobj.group('video_id')
  2282. if video_id:
  2283. info.update({
  2284. 'ie_key': 'MangomoloVideo',
  2285. 'id': video_id,
  2286. })
  2287. else:
  2288. info.update({
  2289. 'ie_key': 'MangomoloLive',
  2290. 'id': mobj.group('channel_id'),
  2291. })
  2292. return info
  2293. # Look for Instagram embeds
  2294. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2295. if instagram_embed_url is not None:
  2296. return self.url_result(
  2297. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2298. # Look for LiveLeak embeds
  2299. liveleak_url = LiveLeakIE._extract_url(webpage)
  2300. if liveleak_url:
  2301. return self.url_result(liveleak_url, 'LiveLeak')
  2302. # Look for 3Q SDN embeds
  2303. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2304. if threeqsdn_url:
  2305. return {
  2306. '_type': 'url_transparent',
  2307. 'ie_key': ThreeQSDNIE.ie_key(),
  2308. 'url': self._proto_relative_url(threeqsdn_url),
  2309. 'title': video_title,
  2310. 'description': video_description,
  2311. 'thumbnail': video_thumbnail,
  2312. 'uploader': video_uploader,
  2313. }
  2314. # Look for VBOX7 embeds
  2315. vbox7_url = Vbox7IE._extract_url(webpage)
  2316. if vbox7_url:
  2317. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2318. # Look for DBTV embeds
  2319. dbtv_urls = DBTVIE._extract_urls(webpage)
  2320. if dbtv_urls:
  2321. return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
  2322. # Look for Videa embeds
  2323. videa_urls = VideaIE._extract_urls(webpage)
  2324. if videa_urls:
  2325. return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
  2326. # Look for 20 minuten embeds
  2327. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2328. if twentymin_urls:
  2329. return _playlist_from_matches(
  2330. twentymin_urls, ie=TwentyMinutenIE.ie_key())
  2331. # Look for Openload embeds
  2332. openload_urls = OpenloadIE._extract_urls(webpage)
  2333. if openload_urls:
  2334. return _playlist_from_matches(
  2335. openload_urls, ie=OpenloadIE.ie_key())
  2336. # Look for VideoPress embeds
  2337. videopress_urls = VideoPressIE._extract_urls(webpage)
  2338. if videopress_urls:
  2339. return _playlist_from_matches(
  2340. videopress_urls, ie=VideoPressIE.ie_key())
  2341. # Looking for http://schema.org/VideoObject
  2342. json_ld = self._search_json_ld(
  2343. webpage, video_id, default={}, expected_type='VideoObject')
  2344. if json_ld.get('url'):
  2345. info_dict.update({
  2346. 'title': video_title or info_dict['title'],
  2347. 'description': video_description,
  2348. 'thumbnail': video_thumbnail,
  2349. 'age_limit': age_limit
  2350. })
  2351. info_dict.update(json_ld)
  2352. return info_dict
  2353. # Look for HTML5 media
  2354. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  2355. if entries:
  2356. for entry in entries:
  2357. entry.update({
  2358. 'id': video_id,
  2359. 'title': video_title,
  2360. })
  2361. self._sort_formats(entry['formats'])
  2362. return self.playlist_result(entries)
  2363. jwplayer_data_str = self._find_jwplayer_data(webpage)
  2364. if jwplayer_data_str:
  2365. try:
  2366. jwplayer_data = self._parse_json(
  2367. jwplayer_data_str, video_id, transform_source=js_to_json)
  2368. return self._parse_jwplayer_data(jwplayer_data, video_id)
  2369. except ExtractorError:
  2370. pass
  2371. def check_video(vurl):
  2372. if YoutubeIE.suitable(vurl):
  2373. return True
  2374. if RtmpIE.suitable(vurl):
  2375. return True
  2376. vpath = compat_urlparse.urlparse(vurl).path
  2377. vext = determine_ext(vpath)
  2378. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
  2379. def filter_video(urls):
  2380. return list(filter(check_video, urls))
  2381. # Start with something easy: JW Player in SWFObject
  2382. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  2383. if not found:
  2384. # Look for gorilla-vid style embedding
  2385. found = filter_video(re.findall(r'''(?sx)
  2386. (?:
  2387. jw_plugins|
  2388. JWPlayerOptions|
  2389. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  2390. )
  2391. .*?
  2392. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  2393. if not found:
  2394. # Broaden the search a little bit
  2395. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  2396. if not found:
  2397. # Broaden the findall a little bit: JWPlayer JS loader
  2398. found = filter_video(re.findall(
  2399. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  2400. if not found:
  2401. # Flow player
  2402. found = filter_video(re.findall(r'''(?xs)
  2403. flowplayer\("[^"]+",\s*
  2404. \{[^}]+?\}\s*,
  2405. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  2406. ["']?url["']?\s*:\s*["']([^"']+)["']
  2407. ''', webpage))
  2408. if not found:
  2409. # Cinerama player
  2410. found = re.findall(
  2411. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  2412. if not found:
  2413. # Try to find twitter cards info
  2414. # twitter:player:stream should be checked before twitter:player since
  2415. # it is expected to contain a raw stream (see
  2416. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2417. found = filter_video(re.findall(
  2418. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  2419. if not found:
  2420. # We look for Open Graph info:
  2421. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  2422. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  2423. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  2424. if m_video_type is not None:
  2425. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  2426. if not found:
  2427. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  2428. found = re.search(
  2429. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  2430. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  2431. webpage)
  2432. if not found:
  2433. # Look also in Refresh HTTP header
  2434. refresh_header = head_response.headers.get('Refresh')
  2435. if refresh_header:
  2436. # In python 2 response HTTP headers are bytestrings
  2437. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  2438. refresh_header = refresh_header.decode('iso-8859-1')
  2439. found = re.search(REDIRECT_REGEX, refresh_header)
  2440. if found:
  2441. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  2442. self.report_following_redirect(new_url)
  2443. return {
  2444. '_type': 'url',
  2445. 'url': new_url,
  2446. }
  2447. if not found:
  2448. # twitter:player is a https URL to iframe player that may or may not
  2449. # be supported by youtube-dl thus this is checked the very last (see
  2450. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  2451. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  2452. if embed_url:
  2453. return self.url_result(embed_url)
  2454. if not found:
  2455. raise UnsupportedError(url)
  2456. entries = []
  2457. for video_url in orderedSet(found):
  2458. video_url = unescapeHTML(video_url)
  2459. video_url = video_url.replace('\\/', '/')
  2460. video_url = compat_urlparse.urljoin(url, video_url)
  2461. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  2462. # Sometimes, jwplayer extraction will result in a YouTube URL
  2463. if YoutubeIE.suitable(video_url):
  2464. entries.append(self.url_result(video_url, 'Youtube'))
  2465. continue
  2466. # here's a fun little line of code for you:
  2467. video_id = os.path.splitext(video_id)[0]
  2468. entry_info_dict = {
  2469. 'id': video_id,
  2470. 'uploader': video_uploader,
  2471. 'title': video_title,
  2472. 'age_limit': age_limit,
  2473. }
  2474. if RtmpIE.suitable(video_url):
  2475. entry_info_dict.update({
  2476. '_type': 'url_transparent',
  2477. 'ie_key': RtmpIE.ie_key(),
  2478. 'url': video_url,
  2479. })
  2480. entries.append(entry_info_dict)
  2481. continue
  2482. ext = determine_ext(video_url)
  2483. if ext == 'smil':
  2484. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  2485. elif ext == 'xspf':
  2486. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  2487. elif ext == 'm3u8':
  2488. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  2489. elif ext == 'mpd':
  2490. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  2491. elif ext == 'f4m':
  2492. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  2493. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  2494. # Just matching .ism/manifest is not enough to be reliably sure
  2495. # whether it's actually an ISM manifest or some other streaming
  2496. # manifest since there are various streaming URL formats
  2497. # possible (see [1]) as well as some other shenanigans like
  2498. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  2499. # so on.
  2500. # Thus the most reasonable way to solve this is to delegate
  2501. # to generic extractor in order to look into the contents of
  2502. # the manifest itself.
  2503. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  2504. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  2505. entry_info_dict = self.url_result(
  2506. smuggle_url(video_url, {'to_generic': True}),
  2507. GenericIE.ie_key())
  2508. else:
  2509. entry_info_dict['url'] = video_url
  2510. if entry_info_dict.get('formats'):
  2511. self._sort_formats(entry_info_dict['formats'])
  2512. entries.append(entry_info_dict)
  2513. if len(entries) == 1:
  2514. return entries[0]
  2515. else:
  2516. for num, e in enumerate(entries, start=1):
  2517. # 'url' results don't have a title
  2518. if e.get('title') is not None:
  2519. e['title'] = '%s (%d)' % (e['title'], num)
  2520. return {
  2521. '_type': 'playlist',
  2522. 'entries': entries,
  2523. }