generic.py 139 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458
  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_str,
  11. compat_urllib_parse_unquote,
  12. compat_urlparse,
  13. compat_xml_parse_error,
  14. )
  15. from ..utils import (
  16. determine_ext,
  17. ExtractorError,
  18. float_or_none,
  19. HEADRequest,
  20. is_html,
  21. js_to_json,
  22. KNOWN_EXTENSIONS,
  23. merge_dicts,
  24. mimetype2ext,
  25. orderedSet,
  26. sanitized_Request,
  27. smuggle_url,
  28. unescapeHTML,
  29. unified_strdate,
  30. unsmuggle_url,
  31. UnsupportedError,
  32. xpath_text,
  33. )
  34. from .commonprotocols import RtmpIE
  35. from .brightcove import (
  36. BrightcoveLegacyIE,
  37. BrightcoveNewIE,
  38. )
  39. from .nexx import (
  40. NexxIE,
  41. NexxEmbedIE,
  42. )
  43. from .nbc import NBCSportsVPlayerIE
  44. from .ooyala import OoyalaIE
  45. from .rutv import RUTVIE
  46. from .tvc import TVCIE
  47. from .sportbox import SportBoxIE
  48. from .smotri import SmotriIE
  49. from .myvi import MyviIE
  50. from .condenast import CondeNastIE
  51. from .udn import UDNEmbedIE
  52. from .senateisvp import SenateISVPIE
  53. from .svt import SVTIE
  54. from .pornhub import PornHubIE
  55. from .xhamster import XHamsterEmbedIE
  56. from .tnaflix import TNAFlixNetworkEmbedIE
  57. from .drtuber import DrTuberIE
  58. from .redtube import RedTubeIE
  59. from .tube8 import Tube8IE
  60. from .mofosex import MofosexEmbedIE
  61. from .spankwire import SpankwireIE
  62. from .youporn import YouPornIE
  63. from .vimeo import VimeoIE
  64. from .dailymotion import DailymotionIE
  65. from .dailymail import DailyMailIE
  66. from .onionstudios import OnionStudiosIE
  67. from .viewlift import ViewLiftEmbedIE
  68. from .mtv import MTVServicesEmbeddedIE
  69. from .pladform import PladformIE
  70. from .videomore import VideomoreIE
  71. from .webcaster import WebcasterFeedIE
  72. from .googledrive import GoogleDriveIE
  73. from .jwplatform import JWPlatformIE
  74. from .digiteka import DigitekaIE
  75. from .arkena import ArkenaIE
  76. from .instagram import InstagramIE
  77. from .liveleak import LiveLeakIE
  78. from .threeqsdn import ThreeQSDNIE
  79. from .theplatform import ThePlatformIE
  80. from .kaltura import KalturaIE
  81. from .eagleplatform import EaglePlatformIE
  82. from .facebook import FacebookIE
  83. from .soundcloud import SoundcloudEmbedIE
  84. from .tunein import TuneInBaseIE
  85. from .vbox7 import Vbox7IE
  86. from .dbtv import DBTVIE
  87. from .piksel import PikselIE
  88. from .videa import VideaIE
  89. from .twentymin import TwentyMinutenIE
  90. from .ustream import UstreamIE
  91. from .arte import ArteTVEmbedIE
  92. from .videopress import VideoPressIE
  93. from .rutube import RutubeIE
  94. from .limelight import LimelightBaseIE
  95. from .anvato import AnvatoIE
  96. from .washingtonpost import WashingtonPostIE
  97. from .wistia import WistiaIE
  98. from .mediaset import MediasetIE
  99. from .joj import JojIE
  100. from .megaphone import MegaphoneIE
  101. from .vzaar import VzaarIE
  102. from .channel9 import Channel9IE
  103. from .vshare import VShareIE
  104. from .mediasite import MediasiteIE
  105. from .springboardplatform import SpringboardPlatformIE
  106. from .yapfiles import YapFilesIE
  107. from .vice import ViceIE
  108. from .xfileshare import XFileShareIE
  109. from .cloudflarestream import CloudflareStreamIE
  110. from .peertube import PeerTubeIE
  111. from .teachable import TeachableIE
  112. from .indavideo import IndavideoEmbedIE
  113. from .apa import APAIE
  114. from .foxnews import FoxNewsIE
  115. from .viqeo import ViqeoIE
  116. from .expressen import ExpressenIE
  117. from .zype import ZypeIE
  118. from .odnoklassniki import OdnoklassnikiIE
  119. from .kinja import KinjaEmbedIE
  120. class GenericIE(InfoExtractor):
  121. IE_DESC = 'Generic downloader that works on some sites'
  122. _VALID_URL = r'.*'
  123. IE_NAME = 'generic'
  124. _TESTS = [
  125. # Direct link to a video
  126. {
  127. 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4',
  128. 'md5': '67d406c2bcb6af27fa886f31aa934bbe',
  129. 'info_dict': {
  130. 'id': 'trailer',
  131. 'ext': 'mp4',
  132. 'title': 'trailer',
  133. 'upload_date': '20100513',
  134. }
  135. },
  136. # Direct link to media delivered compressed (until Accept-Encoding is *)
  137. {
  138. 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac',
  139. 'md5': '128c42e68b13950268b648275386fc74',
  140. 'info_dict': {
  141. 'id': 'FictionJunction-Parallel_Hearts',
  142. 'ext': 'flac',
  143. 'title': 'FictionJunction-Parallel_Hearts',
  144. 'upload_date': '20140522',
  145. },
  146. 'expected_warnings': [
  147. 'URL could be a direct video link, returning it as such.'
  148. ],
  149. 'skip': 'URL invalid',
  150. },
  151. # Direct download with broken HEAD
  152. {
  153. 'url': 'http://ai-radio.org:8000/radio.opus',
  154. 'info_dict': {
  155. 'id': 'radio',
  156. 'ext': 'opus',
  157. 'title': 'radio',
  158. },
  159. 'params': {
  160. 'skip_download': True, # infinite live stream
  161. },
  162. 'expected_warnings': [
  163. r'501.*Not Implemented',
  164. r'400.*Bad Request',
  165. ],
  166. },
  167. # Direct link with incorrect MIME type
  168. {
  169. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  170. 'md5': '4ccbebe5f36706d85221f204d7eb5913',
  171. 'info_dict': {
  172. 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm',
  173. 'id': '5_Lennart_Poettering_-_Systemd',
  174. 'ext': 'webm',
  175. 'title': '5_Lennart_Poettering_-_Systemd',
  176. 'upload_date': '20141120',
  177. },
  178. 'expected_warnings': [
  179. 'URL could be a direct video link, returning it as such.'
  180. ]
  181. },
  182. # RSS feed
  183. {
  184. 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  185. 'info_dict': {
  186. 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
  187. 'title': 'Zero Punctuation',
  188. 'description': 're:.*groundbreaking video review series.*'
  189. },
  190. 'playlist_mincount': 11,
  191. },
  192. # RSS feed with enclosure
  193. {
  194. 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
  195. 'info_dict': {
  196. 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  197. 'ext': 'm4v',
  198. 'upload_date': '20150228',
  199. 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
  200. }
  201. },
  202. # RSS feed with enclosures and unsupported link URLs
  203. {
  204. 'url': 'http://www.hellointernet.fm/podcast?format=rss',
  205. 'info_dict': {
  206. 'id': 'http://www.hellointernet.fm/podcast?format=rss',
  207. 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.',
  208. 'title': 'Hello Internet',
  209. },
  210. 'playlist_mincount': 100,
  211. },
  212. # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
  213. {
  214. 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
  215. 'info_dict': {
  216. 'id': 'smil',
  217. 'ext': 'mp4',
  218. 'title': 'Automatics, robotics and biocybernetics',
  219. 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
  220. 'upload_date': '20130627',
  221. 'formats': 'mincount:16',
  222. 'subtitles': 'mincount:1',
  223. },
  224. 'params': {
  225. 'force_generic_extractor': True,
  226. 'skip_download': True,
  227. },
  228. },
  229. # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html
  230. {
  231. 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil',
  232. 'info_dict': {
  233. 'id': 'hds',
  234. 'ext': 'flv',
  235. 'title': 'hds',
  236. 'formats': 'mincount:1',
  237. },
  238. 'params': {
  239. 'skip_download': True,
  240. },
  241. },
  242. # SMIL from https://www.restudy.dk/video/play/id/1637
  243. {
  244. 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml',
  245. 'info_dict': {
  246. 'id': 'video_1637',
  247. 'ext': 'flv',
  248. 'title': 'video_1637',
  249. 'formats': 'mincount:3',
  250. },
  251. 'params': {
  252. 'skip_download': True,
  253. },
  254. },
  255. # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm
  256. {
  257. 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil',
  258. 'info_dict': {
  259. 'id': 'smil-service',
  260. 'ext': 'flv',
  261. 'title': 'smil-service',
  262. 'formats': 'mincount:1',
  263. },
  264. 'params': {
  265. 'skip_download': True,
  266. },
  267. },
  268. # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370
  269. {
  270. 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil',
  271. 'info_dict': {
  272. 'id': '4719370',
  273. 'ext': 'mp4',
  274. 'title': '571de1fd-47bc-48db-abf9-238872a58d1f',
  275. 'formats': 'mincount:3',
  276. },
  277. 'params': {
  278. 'skip_download': True,
  279. },
  280. },
  281. # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html
  282. {
  283. 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf',
  284. 'info_dict': {
  285. 'id': 'mZlp2ctYIUEB',
  286. 'ext': 'mp4',
  287. 'title': 'Tikibad ontruimd wegens brand',
  288. 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
  289. 'thumbnail': r're:^https?://.*\.jpg$',
  290. 'duration': 33,
  291. },
  292. 'params': {
  293. 'skip_download': True,
  294. },
  295. },
  296. # MPD from http://dash-mse-test.appspot.com/media.html
  297. {
  298. 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd',
  299. 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53',
  300. 'info_dict': {
  301. 'id': 'car-20120827-manifest',
  302. 'ext': 'mp4',
  303. 'title': 'car-20120827-manifest',
  304. 'formats': 'mincount:9',
  305. 'upload_date': '20130904',
  306. },
  307. 'params': {
  308. 'format': 'bestvideo',
  309. },
  310. },
  311. # m3u8 served with Content-Type: audio/x-mpegURL; charset=utf-8
  312. {
  313. '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',
  314. 'info_dict': {
  315. 'id': 'content',
  316. 'ext': 'mp4',
  317. 'title': 'content',
  318. 'formats': 'mincount:8',
  319. },
  320. 'params': {
  321. # m3u8 downloads
  322. 'skip_download': True,
  323. },
  324. 'skip': 'video gone',
  325. },
  326. # m3u8 served with Content-Type: text/plain
  327. {
  328. 'url': 'http://www.nacentapps.com/m3u8/index.m3u8',
  329. 'info_dict': {
  330. 'id': 'index',
  331. 'ext': 'mp4',
  332. 'title': 'index',
  333. 'upload_date': '20140720',
  334. 'formats': 'mincount:11',
  335. },
  336. 'params': {
  337. # m3u8 downloads
  338. 'skip_download': True,
  339. },
  340. 'skip': 'video gone',
  341. },
  342. # google redirect
  343. {
  344. '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',
  345. 'info_dict': {
  346. 'id': 'cmQHVoWB5FY',
  347. 'ext': 'mp4',
  348. 'upload_date': '20130224',
  349. 'uploader_id': 'TheVerge',
  350. 'description': r're:^Chris Ziegler takes a look at the\.*',
  351. 'uploader': 'The Verge',
  352. 'title': 'First Firefox OS phones side-by-side',
  353. },
  354. 'params': {
  355. 'skip_download': False,
  356. }
  357. },
  358. {
  359. # redirect in Refresh HTTP header
  360. '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',
  361. 'info_dict': {
  362. 'id': 'pO8h3EaFRdo',
  363. 'ext': 'mp4',
  364. 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set',
  365. 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5',
  366. 'upload_date': '20150917',
  367. 'uploader_id': 'brtvofficial',
  368. 'uploader': 'Boiler Room',
  369. },
  370. 'params': {
  371. 'skip_download': False,
  372. },
  373. },
  374. {
  375. 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
  376. 'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
  377. 'info_dict': {
  378. 'id': '13601338388002',
  379. 'ext': 'mp4',
  380. 'uploader': 'www.hodiho.fr',
  381. 'title': 'R\u00e9gis plante sa Jeep',
  382. }
  383. },
  384. # bandcamp page with custom domain
  385. {
  386. 'add_ie': ['Bandcamp'],
  387. 'url': 'http://bronyrock.com/track/the-pony-mash',
  388. 'info_dict': {
  389. 'id': '3235767654',
  390. 'ext': 'mp3',
  391. 'title': 'The Pony Mash',
  392. 'uploader': 'M_Pallante',
  393. },
  394. 'skip': 'There is a limit of 200 free downloads / month for the test song',
  395. },
  396. {
  397. # embedded brightcove video
  398. # it also tests brightcove videos that need to set the 'Referer'
  399. # in the http requests
  400. 'add_ie': ['BrightcoveLegacy'],
  401. 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
  402. 'info_dict': {
  403. 'id': '2765128793001',
  404. 'ext': 'mp4',
  405. 'title': 'Le cours de bourse : l’analyse technique',
  406. 'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
  407. 'uploader': 'BFM BUSINESS',
  408. },
  409. 'params': {
  410. 'skip_download': True,
  411. },
  412. },
  413. {
  414. # embedded with itemprop embedURL and video id spelled as `idVideo`
  415. 'add_id': ['BrightcoveLegacy'],
  416. 'url': 'http://bfmbusiness.bfmtv.com/mediaplayer/chroniques/olivier-delamarche/',
  417. 'info_dict': {
  418. 'id': '5255628253001',
  419. 'ext': 'mp4',
  420. 'title': 'md5:37c519b1128915607601e75a87995fc0',
  421. 'description': 'md5:37f7f888b434bb8f8cc8dbd4f7a4cf26',
  422. 'uploader': 'BFM BUSINESS',
  423. 'uploader_id': '876450612001',
  424. 'timestamp': 1482255315,
  425. 'upload_date': '20161220',
  426. },
  427. 'params': {
  428. 'skip_download': True,
  429. },
  430. },
  431. {
  432. # https://github.com/ytdl-org/youtube-dl/issues/2253
  433. 'url': 'http://bcove.me/i6nfkrc3',
  434. 'md5': '0ba9446db037002366bab3b3eb30c88c',
  435. 'info_dict': {
  436. 'id': '3101154703001',
  437. 'ext': 'mp4',
  438. 'title': 'Still no power',
  439. 'uploader': 'thestar.com',
  440. '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.',
  441. },
  442. 'add_ie': ['BrightcoveLegacy'],
  443. 'skip': 'video gone',
  444. },
  445. {
  446. 'url': 'http://www.championat.com/video/football/v/87/87499.html',
  447. 'md5': 'fb973ecf6e4a78a67453647444222983',
  448. 'info_dict': {
  449. 'id': '3414141473001',
  450. 'ext': 'mp4',
  451. 'title': 'Видео. Удаление Дзагоева (ЦСКА)',
  452. 'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
  453. 'uploader': 'Championat',
  454. },
  455. },
  456. {
  457. # https://github.com/ytdl-org/youtube-dl/issues/3541
  458. 'add_ie': ['BrightcoveLegacy'],
  459. 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
  460. 'info_dict': {
  461. 'id': '3866516442001',
  462. 'ext': 'mp4',
  463. 'title': 'Leer mij vrouwen kennen: Aflevering 1',
  464. 'description': 'Leer mij vrouwen kennen: Aflevering 1',
  465. 'uploader': 'SBS Broadcasting',
  466. },
  467. 'skip': 'Restricted to Netherlands',
  468. 'params': {
  469. 'skip_download': True, # m3u8 download
  470. },
  471. },
  472. {
  473. # Brightcove video in <iframe>
  474. 'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
  475. 'md5': '36d74ef5e37c8b4a2ce92880d208b968',
  476. 'info_dict': {
  477. 'id': '5360463607001',
  478. 'ext': 'mp4',
  479. 'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
  480. 'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼(Zade Dirani)在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》(HEARTBEAT),为受到六年冲突影响的叙利亚儿童发出强烈呐喊,呼吁世界做出共同努力,使叙利亚儿童重新获得享有正常童年生活的权利。',
  481. 'uploader': 'United Nations',
  482. 'uploader_id': '1362235914001',
  483. 'timestamp': 1489593889,
  484. 'upload_date': '20170315',
  485. },
  486. 'add_ie': ['BrightcoveLegacy'],
  487. },
  488. {
  489. # Brightcove with alternative playerID key
  490. 'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
  491. 'info_dict': {
  492. 'id': 'nmeth.2062_SV1',
  493. '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',
  494. },
  495. 'playlist': [{
  496. 'info_dict': {
  497. 'id': '2228375078001',
  498. 'ext': 'mp4',
  499. 'title': 'nmeth.2062-sv1',
  500. 'description': 'nmeth.2062-sv1',
  501. 'timestamp': 1363357591,
  502. 'upload_date': '20130315',
  503. 'uploader': 'Nature Publishing Group',
  504. 'uploader_id': '1964492299001',
  505. },
  506. }],
  507. },
  508. {
  509. # Brightcove with UUID in videoPlayer
  510. 'url': 'http://www8.hp.com/cn/zh/home.html',
  511. 'info_dict': {
  512. 'id': '5255815316001',
  513. 'ext': 'mp4',
  514. 'title': 'Sprocket Video - China',
  515. 'description': 'Sprocket Video - China',
  516. 'uploader': 'HP-Video Gallery',
  517. 'timestamp': 1482263210,
  518. 'upload_date': '20161220',
  519. 'uploader_id': '1107601872001',
  520. },
  521. 'params': {
  522. 'skip_download': True, # m3u8 download
  523. },
  524. 'skip': 'video rotates...weekly?',
  525. },
  526. {
  527. # Brightcove:new type [2].
  528. 'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
  529. 'md5': '2b35148fcf48da41c9fb4591650784f3',
  530. 'info_dict': {
  531. 'id': '5348741021001',
  532. 'ext': 'mp4',
  533. 'upload_date': '20170306',
  534. 'uploader_id': '4191638492001',
  535. 'timestamp': 1488769918,
  536. 'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
  537. },
  538. },
  539. {
  540. # Alternative brightcove <video> attributes
  541. 'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
  542. 'info_dict': {
  543. 'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
  544. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
  545. },
  546. 'playlist': [{
  547. 'md5': '732d22ba3d33f2f3fc253c39f8f36523',
  548. 'info_dict': {
  549. 'id': '5311302538001',
  550. 'ext': 'mp4',
  551. 'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
  552. 'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
  553. 'timestamp': 1486321708,
  554. 'upload_date': '20170205',
  555. 'uploader_id': '800000640001',
  556. },
  557. 'only_matching': True,
  558. }],
  559. },
  560. {
  561. # Brightcove with UUID in videoPlayer
  562. 'url': 'http://www8.hp.com/cn/zh/home.html',
  563. 'info_dict': {
  564. 'id': '5255815316001',
  565. 'ext': 'mp4',
  566. 'title': 'Sprocket Video - China',
  567. 'description': 'Sprocket Video - China',
  568. 'uploader': 'HP-Video Gallery',
  569. 'timestamp': 1482263210,
  570. 'upload_date': '20161220',
  571. 'uploader_id': '1107601872001',
  572. },
  573. 'params': {
  574. 'skip_download': True, # m3u8 download
  575. },
  576. },
  577. # ooyala video
  578. {
  579. 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
  580. 'md5': '166dd577b433b4d4ebfee10b0824d8ff',
  581. 'info_dict': {
  582. 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
  583. 'ext': 'mp4',
  584. 'title': '2cc213299525360.mov', # that's what we get
  585. 'duration': 238.231,
  586. },
  587. 'add_ie': ['Ooyala'],
  588. },
  589. {
  590. # ooyala video embedded with http://player.ooyala.com/iframe.js
  591. 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/',
  592. 'info_dict': {
  593. 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB',
  594. 'ext': 'mp4',
  595. 'title': '"Steve Jobs: Man in the Machine" trailer',
  596. 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."',
  597. 'duration': 135.427,
  598. },
  599. 'params': {
  600. 'skip_download': True,
  601. },
  602. 'skip': 'movie expired',
  603. },
  604. # ooyala video embedded with http://player.ooyala.com/static/v4/production/latest/core.min.js
  605. {
  606. 'url': 'http://wnep.com/2017/07/22/steampunk-fest-comes-to-honesdale/',
  607. 'info_dict': {
  608. 'id': 'lwYWYxYzE6V5uJMjNGyKtwwiw9ZJD7t2',
  609. 'ext': 'mp4',
  610. 'title': 'Steampunk Fest Comes to Honesdale',
  611. 'duration': 43.276,
  612. },
  613. 'params': {
  614. 'skip_download': True,
  615. }
  616. },
  617. # embed.ly video
  618. {
  619. 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
  620. 'info_dict': {
  621. 'id': '9ODmcdjQcHQ',
  622. 'ext': 'mp4',
  623. 'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
  624. 'upload_date': '20140225',
  625. 'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
  626. 'uploader': 'Tested',
  627. 'uploader_id': 'testedcom',
  628. },
  629. # No need to test YoutubeIE here
  630. 'params': {
  631. 'skip_download': True,
  632. },
  633. },
  634. # funnyordie embed
  635. {
  636. 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
  637. 'info_dict': {
  638. 'id': '18e820ec3f',
  639. 'ext': 'mp4',
  640. 'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
  641. 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
  642. },
  643. # HEAD requests lead to endless 301, while GET is OK
  644. 'expected_warnings': ['301'],
  645. },
  646. # RUTV embed
  647. {
  648. 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html',
  649. 'info_dict': {
  650. 'id': '776940',
  651. 'ext': 'mp4',
  652. 'title': 'Охотское море стало целиком российским',
  653. 'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
  654. },
  655. 'params': {
  656. # m3u8 download
  657. 'skip_download': True,
  658. },
  659. },
  660. # TVC embed
  661. {
  662. '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/',
  663. 'info_dict': {
  664. 'id': '55304',
  665. 'ext': 'mp4',
  666. 'title': 'Дошкольное воспитание',
  667. },
  668. },
  669. # SportBox embed
  670. {
  671. 'url': 'http://www.vestifinance.ru/articles/25753',
  672. 'info_dict': {
  673. 'id': '25753',
  674. 'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
  675. },
  676. 'playlist': [{
  677. 'info_dict': {
  678. 'id': '370908',
  679. 'title': 'Госзаказ. День 3',
  680. 'ext': 'mp4',
  681. }
  682. }, {
  683. 'info_dict': {
  684. 'id': '370905',
  685. 'title': 'Госзаказ. День 2',
  686. 'ext': 'mp4',
  687. }
  688. }, {
  689. 'info_dict': {
  690. 'id': '370902',
  691. 'title': 'Госзаказ. День 1',
  692. 'ext': 'mp4',
  693. }
  694. }],
  695. 'params': {
  696. # m3u8 download
  697. 'skip_download': True,
  698. },
  699. },
  700. # Myvi.ru embed
  701. {
  702. 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1',
  703. 'info_dict': {
  704. 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e',
  705. 'ext': 'mp4',
  706. 'title': 'Ужастики, русский трейлер (2015)',
  707. 'thumbnail': r're:^https?://.*\.jpg$',
  708. 'duration': 153,
  709. }
  710. },
  711. # XHamster embed
  712. {
  713. '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',
  714. 'info_dict': {
  715. 'id': 'showthread',
  716. 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
  717. },
  718. 'playlist_mincount': 7,
  719. # This forum does not allow <iframe> syntaxes anymore
  720. # Now HTML tags are displayed as-is
  721. 'skip': 'No videos on this page',
  722. },
  723. # Embedded TED video
  724. {
  725. 'url': 'http://en.support.wordpress.com/videos/ted-talks/',
  726. 'md5': '65fdff94098e4a607385a60c5177c638',
  727. 'info_dict': {
  728. 'id': '1969',
  729. 'ext': 'mp4',
  730. 'title': 'Hidden miracles of the natural world',
  731. 'uploader': 'Louie Schwartzberg',
  732. 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
  733. }
  734. },
  735. # nowvideo embed hidden behind percent encoding
  736. {
  737. 'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
  738. 'md5': '2baf4ddd70f697d94b1c18cf796d5107',
  739. 'info_dict': {
  740. 'id': '06e53103ca9aa',
  741. 'ext': 'flv',
  742. 'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
  743. 'description': 'No description',
  744. },
  745. },
  746. # arte embed
  747. {
  748. 'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
  749. 'md5': '7653032cbb25bf6c80d80f217055fa43',
  750. 'info_dict': {
  751. 'id': '048195-004_PLUS7-F',
  752. 'ext': 'flv',
  753. 'title': 'X:enius',
  754. 'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
  755. 'upload_date': '20140320',
  756. },
  757. 'params': {
  758. 'skip_download': 'Requires rtmpdump'
  759. },
  760. 'skip': 'video gone',
  761. },
  762. # francetv embed
  763. {
  764. 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero',
  765. 'info_dict': {
  766. 'id': 'EV_30231',
  767. 'ext': 'mp4',
  768. 'title': 'Alcaline, le concert avec Calogero',
  769. 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
  770. 'upload_date': '20150226',
  771. 'timestamp': 1424989860,
  772. 'duration': 5400,
  773. },
  774. 'params': {
  775. # m3u8 downloads
  776. 'skip_download': True,
  777. },
  778. 'expected_warnings': [
  779. 'Forbidden'
  780. ]
  781. },
  782. # Condé Nast embed
  783. {
  784. 'url': 'http://www.wired.com/2014/04/honda-asimo/',
  785. 'md5': 'ba0dfe966fa007657bd1443ee672db0f',
  786. 'info_dict': {
  787. 'id': '53501be369702d3275860000',
  788. 'ext': 'mp4',
  789. 'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
  790. }
  791. },
  792. # Dailymotion embed
  793. {
  794. 'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
  795. 'md5': '441aeeb82eb72c422c7f14ec533999cd',
  796. 'info_dict': {
  797. 'id': 'k2mm4bCdJ6CQ2i7c8o2',
  798. 'ext': 'mp4',
  799. 'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
  800. 'description': 'md5:faf028e48a461b8b7fad38f1e104b119',
  801. 'uploader': 'Spi0n',
  802. 'uploader_id': 'xgditw',
  803. 'upload_date': '20140425',
  804. 'timestamp': 1398441542,
  805. },
  806. 'add_ie': ['Dailymotion'],
  807. },
  808. # DailyMail embed
  809. {
  810. 'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
  811. 'info_dict': {
  812. 'id': '1495629',
  813. 'ext': 'mp4',
  814. 'title': 'Care worker punches elderly dementia patient in head 11 times',
  815. 'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
  816. },
  817. 'add_ie': ['DailyMail'],
  818. 'params': {
  819. 'skip_download': True,
  820. },
  821. },
  822. # YouTube embed
  823. {
  824. 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
  825. 'info_dict': {
  826. 'id': 'FXRb4ykk4S0',
  827. 'ext': 'mp4',
  828. 'title': 'The NBL Auction 2014',
  829. 'uploader': 'BADMINTON England',
  830. 'uploader_id': 'BADMINTONEvents',
  831. 'upload_date': '20140603',
  832. 'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
  833. },
  834. 'add_ie': ['Youtube'],
  835. 'params': {
  836. 'skip_download': True,
  837. }
  838. },
  839. # MTVServices embed
  840. {
  841. 'url': 'http://www.vulture.com/2016/06/new-key-peele-sketches-released.html',
  842. 'md5': 'ca1aef97695ef2c1d6973256a57e5252',
  843. 'info_dict': {
  844. 'id': '769f7ec0-0692-4d62-9b45-0d88074bffc1',
  845. 'ext': 'mp4',
  846. 'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
  847. 'description': 'Two valets share their love for movie star Liam Neesons.',
  848. 'timestamp': 1349922600,
  849. 'upload_date': '20121011',
  850. },
  851. },
  852. # YouTube embed via <data-embed-url="">
  853. {
  854. 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
  855. 'info_dict': {
  856. 'id': '4vAffPZIT44',
  857. 'ext': 'mp4',
  858. 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
  859. 'uploader': 'Gameloft',
  860. 'uploader_id': 'gameloft',
  861. 'upload_date': '20140828',
  862. 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
  863. },
  864. 'params': {
  865. 'skip_download': True,
  866. }
  867. },
  868. # YouTube <object> embed
  869. {
  870. 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
  871. 'md5': '516718101ec834f74318df76259fb3cc',
  872. 'info_dict': {
  873. 'id': 'msN87y-iEx0',
  874. 'ext': 'webm',
  875. 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
  876. 'upload_date': '20080526',
  877. 'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
  878. 'uploader': 'Christopher Sykes',
  879. 'uploader_id': 'ChristopherJSykes',
  880. },
  881. 'add_ie': ['Youtube'],
  882. },
  883. # Camtasia studio
  884. {
  885. 'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
  886. 'playlist': [{
  887. 'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
  888. 'info_dict': {
  889. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  890. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
  891. 'ext': 'flv',
  892. 'duration': 2235.90,
  893. }
  894. }, {
  895. 'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
  896. 'info_dict': {
  897. 'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
  898. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
  899. 'ext': 'flv',
  900. 'duration': 2235.93,
  901. }
  902. }],
  903. 'info_dict': {
  904. 'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
  905. }
  906. },
  907. # Flowplayer
  908. {
  909. 'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
  910. 'md5': '9d65602bf31c6e20014319c7d07fba27',
  911. 'info_dict': {
  912. 'id': '5123ea6d5e5a7',
  913. 'ext': 'mp4',
  914. 'age_limit': 18,
  915. 'uploader': 'www.handjobhub.com',
  916. 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
  917. }
  918. },
  919. # Multiple brightcove videos
  920. # https://github.com/ytdl-org/youtube-dl/issues/2283
  921. {
  922. 'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
  923. 'info_dict': {
  924. 'id': 'always-never',
  925. 'title': 'Always / Never - The New Yorker',
  926. },
  927. 'playlist_count': 3,
  928. 'params': {
  929. 'extract_flat': False,
  930. 'skip_download': True,
  931. }
  932. },
  933. # MLB embed
  934. {
  935. 'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
  936. 'md5': '96f09a37e44da40dd083e12d9a683327',
  937. 'info_dict': {
  938. 'id': '33322633',
  939. 'ext': 'mp4',
  940. 'title': 'Ump changes call to ball',
  941. 'description': 'md5:71c11215384298a172a6dcb4c2e20685',
  942. 'duration': 48,
  943. 'timestamp': 1401537900,
  944. 'upload_date': '20140531',
  945. 'thumbnail': r're:^https?://.*\.jpg$',
  946. },
  947. },
  948. # Wistia embed
  949. {
  950. 'url': 'http://study.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
  951. 'md5': '1953f3a698ab51cfc948ed3992a0b7ff',
  952. 'info_dict': {
  953. 'id': '6e2wtrbdaf',
  954. 'ext': 'mov',
  955. 'title': 'paywall_north-american-exploration-failed-colonies-of-spain-france-england',
  956. 'description': 'a Paywall Videos video from Remilon',
  957. 'duration': 644.072,
  958. 'uploader': 'study.com',
  959. 'timestamp': 1459678540,
  960. 'upload_date': '20160403',
  961. 'filesize': 24687186,
  962. },
  963. },
  964. {
  965. 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
  966. 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
  967. 'info_dict': {
  968. 'id': 'uxjb0lwrcz',
  969. 'ext': 'mp4',
  970. 'title': 'Conversation about Hexagonal Rails Part 1',
  971. 'description': 'a Martin Fowler video from ThoughtWorks',
  972. 'duration': 1715.0,
  973. 'uploader': 'thoughtworks.wistia.com',
  974. 'timestamp': 1401832161,
  975. 'upload_date': '20140603',
  976. },
  977. },
  978. # Wistia standard embed (async)
  979. {
  980. 'url': 'https://www.getdrip.com/university/brennan-dunn-drip-workshop/',
  981. 'info_dict': {
  982. 'id': '807fafadvk',
  983. 'ext': 'mp4',
  984. 'title': 'Drip Brennan Dunn Workshop',
  985. 'description': 'a JV Webinars video from getdrip-1',
  986. 'duration': 4986.95,
  987. 'timestamp': 1463607249,
  988. 'upload_date': '20160518',
  989. },
  990. 'params': {
  991. 'skip_download': True,
  992. }
  993. },
  994. # Soundcloud embed
  995. {
  996. 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
  997. 'info_dict': {
  998. 'id': '174391317',
  999. 'ext': 'mp3',
  1000. 'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
  1001. 'uploader': 'Sophos Security',
  1002. 'title': 'Chet Chat 171 - Oct 29, 2014',
  1003. 'upload_date': '20141029',
  1004. }
  1005. },
  1006. # Soundcloud multiple embeds
  1007. {
  1008. 'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
  1009. 'info_dict': {
  1010. 'id': '52809',
  1011. 'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
  1012. },
  1013. 'playlist_mincount': 7,
  1014. },
  1015. # TuneIn station embed
  1016. {
  1017. 'url': 'http://radiocnrv.com/promouvoir-radio-cnrv/',
  1018. 'info_dict': {
  1019. 'id': '204146',
  1020. 'ext': 'mp3',
  1021. 'title': 'CNRV',
  1022. 'location': 'Paris, France',
  1023. 'is_live': True,
  1024. },
  1025. 'params': {
  1026. # Live stream
  1027. 'skip_download': True,
  1028. },
  1029. },
  1030. # Livestream embed
  1031. {
  1032. 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
  1033. 'info_dict': {
  1034. 'id': '67864563',
  1035. 'ext': 'flv',
  1036. 'upload_date': '20141112',
  1037. 'title': 'Rosetta #CometLanding webcast HL 10',
  1038. }
  1039. },
  1040. # Another Livestream embed, without 'new.' in URL
  1041. {
  1042. 'url': 'https://www.freespeech.org/',
  1043. 'info_dict': {
  1044. 'id': '123537347',
  1045. 'ext': 'mp4',
  1046. 'title': 're:^FSTV [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  1047. },
  1048. 'params': {
  1049. # Live stream
  1050. 'skip_download': True,
  1051. },
  1052. },
  1053. # LazyYT
  1054. {
  1055. 'url': 'https://skiplagged.com/',
  1056. 'info_dict': {
  1057. 'id': 'skiplagged',
  1058. 'title': 'Skiplagged: The smart way to find cheap flights',
  1059. },
  1060. 'playlist_mincount': 1,
  1061. 'add_ie': ['Youtube'],
  1062. },
  1063. # Cinchcast embed
  1064. {
  1065. 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
  1066. 'info_dict': {
  1067. 'id': '7141703',
  1068. 'ext': 'mp3',
  1069. 'upload_date': '20141126',
  1070. 'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
  1071. }
  1072. },
  1073. # Cinerama player
  1074. {
  1075. 'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
  1076. 'info_dict': {
  1077. 'id': '730m_DandD_1901_512k',
  1078. 'ext': 'mp4',
  1079. 'uploader': 'www.abc.net.au',
  1080. 'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
  1081. }
  1082. },
  1083. # embedded viddler video
  1084. {
  1085. 'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
  1086. 'info_dict': {
  1087. 'id': '4d03aad9',
  1088. 'ext': 'mp4',
  1089. 'uploader': 'deadspin',
  1090. 'title': 'WALL-TO-GORTAT',
  1091. 'timestamp': 1422285291,
  1092. 'upload_date': '20150126',
  1093. },
  1094. 'add_ie': ['Viddler'],
  1095. },
  1096. # Libsyn embed
  1097. {
  1098. 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
  1099. 'info_dict': {
  1100. 'id': '3377616',
  1101. 'ext': 'mp3',
  1102. 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
  1103. 'description': 'md5:601cb790edd05908957dae8aaa866465',
  1104. 'upload_date': '20150220',
  1105. },
  1106. 'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
  1107. },
  1108. # jwplayer YouTube
  1109. {
  1110. 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
  1111. 'info_dict': {
  1112. 'id': 'Mrj4DVp2zeA',
  1113. 'ext': 'mp4',
  1114. 'upload_date': '20150212',
  1115. 'uploader': 'The National Archives UK',
  1116. 'description': 'md5:8078af856dca76edc42910b61273dbbf',
  1117. 'uploader_id': 'NationalArchives08',
  1118. 'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
  1119. },
  1120. },
  1121. # jwplayer rtmp
  1122. {
  1123. 'url': 'http://www.suffolk.edu/sjc/live.php',
  1124. 'info_dict': {
  1125. 'id': 'live',
  1126. 'ext': 'flv',
  1127. 'title': 'Massachusetts Supreme Judicial Court Oral Arguments',
  1128. 'uploader': 'www.suffolk.edu',
  1129. },
  1130. 'params': {
  1131. 'skip_download': True,
  1132. },
  1133. 'skip': 'Only has video a few mornings per month, see http://www.suffolk.edu/sjc/',
  1134. },
  1135. # Complex jwplayer
  1136. {
  1137. 'url': 'http://www.indiedb.com/games/king-machine/videos',
  1138. 'info_dict': {
  1139. 'id': 'videos',
  1140. 'ext': 'mp4',
  1141. 'title': 'king machine trailer 1',
  1142. 'description': 'Browse King Machine videos & audio for sweet media. Your eyes will thank you.',
  1143. 'thumbnail': r're:^https?://.*\.jpg$',
  1144. },
  1145. },
  1146. {
  1147. # JWPlayer config passed as variable
  1148. 'url': 'http://www.txxx.com/videos/3326530/ariele/',
  1149. 'info_dict': {
  1150. 'id': '3326530_hq',
  1151. 'ext': 'mp4',
  1152. 'title': 'ARIELE | Tube Cup',
  1153. 'uploader': 'www.txxx.com',
  1154. 'age_limit': 18,
  1155. },
  1156. 'params': {
  1157. 'skip_download': True,
  1158. }
  1159. },
  1160. {
  1161. # JWPlatform iframe
  1162. 'url': 'https://www.mediaite.com/tv/dem-senator-claims-gary-cohn-faked-a-bad-connection-during-trump-call-to-get-him-off-the-phone/',
  1163. 'md5': 'ca00a040364b5b439230e7ebfd02c4e9',
  1164. 'info_dict': {
  1165. 'id': 'O0c5JcKT',
  1166. 'ext': 'mp4',
  1167. 'upload_date': '20171122',
  1168. 'timestamp': 1511366290,
  1169. 'title': 'Dem Senator Claims Gary Cohn Faked a Bad Connection During Trump Call to Get Him Off the Phone',
  1170. },
  1171. 'add_ie': [JWPlatformIE.ie_key()],
  1172. },
  1173. {
  1174. # Video.js embed, multiple formats
  1175. 'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
  1176. 'info_dict': {
  1177. 'id': 'yygqldloqIk',
  1178. 'ext': 'mp4',
  1179. 'title': 'SolidWorks. Урок 6 Настройка чертежа',
  1180. 'description': 'md5:baf95267792646afdbf030e4d06b2ab3',
  1181. 'upload_date': '20130314',
  1182. 'uploader': 'PROстое3D',
  1183. 'uploader_id': 'PROstoe3D',
  1184. },
  1185. 'params': {
  1186. 'skip_download': True,
  1187. },
  1188. },
  1189. {
  1190. # Video.js embed, single format
  1191. 'url': 'https://www.vooplayer.com/v3/watch/watch.php?v=NzgwNTg=',
  1192. 'info_dict': {
  1193. 'id': 'watch',
  1194. 'ext': 'mp4',
  1195. 'title': 'Step 1 - Good Foundation',
  1196. 'description': 'md5:d1e7ff33a29fc3eb1673d6c270d344f4',
  1197. },
  1198. 'params': {
  1199. 'skip_download': True,
  1200. },
  1201. },
  1202. # rtl.nl embed
  1203. {
  1204. 'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
  1205. 'playlist_mincount': 5,
  1206. 'info_dict': {
  1207. 'id': 'aanslagen-kopenhagen',
  1208. 'title': 'Aanslagen Kopenhagen',
  1209. }
  1210. },
  1211. # Zapiks embed
  1212. {
  1213. 'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
  1214. 'info_dict': {
  1215. 'id': '118046',
  1216. 'ext': 'mp4',
  1217. 'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
  1218. }
  1219. },
  1220. # Kaltura embed (different embed code)
  1221. {
  1222. 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014',
  1223. 'info_dict': {
  1224. 'id': '1_a52wc67y',
  1225. 'ext': 'flv',
  1226. 'upload_date': '20150127',
  1227. 'uploader_id': 'PremierMedia',
  1228. 'timestamp': int,
  1229. 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014',
  1230. },
  1231. },
  1232. # Kaltura embed with single quotes
  1233. {
  1234. 'url': 'http://fod.infobase.com/p_ViewPlaylist.aspx?AssignmentID=NUN8ZY',
  1235. 'info_dict': {
  1236. 'id': '0_izeg5utt',
  1237. 'ext': 'mp4',
  1238. 'title': '35871',
  1239. 'timestamp': 1355743100,
  1240. 'upload_date': '20121217',
  1241. 'uploader_id': 'cplapp@learn360.com',
  1242. },
  1243. 'add_ie': ['Kaltura'],
  1244. },
  1245. {
  1246. # Kaltura embedded via quoted entry_id
  1247. 'url': 'https://www.oreilly.com/ideas/my-cloud-makes-pretty-pictures',
  1248. 'info_dict': {
  1249. 'id': '0_utuok90b',
  1250. 'ext': 'mp4',
  1251. 'title': '06_matthew_brender_raj_dutt',
  1252. 'timestamp': 1466638791,
  1253. 'upload_date': '20160622',
  1254. },
  1255. 'add_ie': ['Kaltura'],
  1256. 'expected_warnings': [
  1257. 'Could not send HEAD request'
  1258. ],
  1259. 'params': {
  1260. 'skip_download': True,
  1261. }
  1262. },
  1263. {
  1264. # Kaltura embedded, some fileExt broken (#11480)
  1265. 'url': 'http://www.cornell.edu/video/nima-arkani-hamed-standard-models-of-particle-physics',
  1266. 'info_dict': {
  1267. 'id': '1_sgtvehim',
  1268. 'ext': 'mp4',
  1269. 'title': 'Our "Standard Models" of particle physics and cosmology',
  1270. 'description': 'md5:67ea74807b8c4fea92a6f38d6d323861',
  1271. 'timestamp': 1321158993,
  1272. 'upload_date': '20111113',
  1273. 'uploader_id': 'kps1',
  1274. },
  1275. 'add_ie': ['Kaltura'],
  1276. },
  1277. {
  1278. # Kaltura iframe embed
  1279. 'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
  1280. 'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
  1281. 'info_dict': {
  1282. 'id': '0_f2cfbpwy',
  1283. 'ext': 'mp4',
  1284. 'title': 'I. M. Pei: A Centennial Celebration',
  1285. 'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
  1286. 'upload_date': '20170403',
  1287. 'uploader_id': 'batchUser',
  1288. 'timestamp': 1491232186,
  1289. },
  1290. 'add_ie': ['Kaltura'],
  1291. },
  1292. {
  1293. # Kaltura iframe embed, more sophisticated
  1294. 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html',
  1295. 'info_dict': {
  1296. 'id': '1_9gzouybz',
  1297. 'ext': 'mp4',
  1298. 'title': 'lecture-05sep2017',
  1299. 'description': 'md5:40f347d91fd4ba047e511c5321064b49',
  1300. 'upload_date': '20170913',
  1301. 'uploader_id': 'eps2',
  1302. 'timestamp': 1505340777,
  1303. },
  1304. 'params': {
  1305. 'skip_download': True,
  1306. },
  1307. 'add_ie': ['Kaltura'],
  1308. },
  1309. {
  1310. # meta twitter:player
  1311. 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/',
  1312. 'info_dict': {
  1313. 'id': '0_01b42zps',
  1314. 'ext': 'mp4',
  1315. 'title': 'Main Twerk (Video)',
  1316. 'upload_date': '20171208',
  1317. 'uploader_id': 'sebastian.salinas@thechive.com',
  1318. 'timestamp': 1512713057,
  1319. },
  1320. 'params': {
  1321. 'skip_download': True,
  1322. },
  1323. 'add_ie': ['Kaltura'],
  1324. },
  1325. # referrer protected EaglePlatform embed
  1326. {
  1327. 'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
  1328. 'info_dict': {
  1329. 'id': '582306',
  1330. 'ext': 'mp4',
  1331. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1332. 'thumbnail': r're:^https?://.*\.jpg$',
  1333. 'duration': 3382,
  1334. 'view_count': int,
  1335. },
  1336. 'params': {
  1337. 'skip_download': True,
  1338. },
  1339. },
  1340. # ClipYou (EaglePlatform) embed (custom URL)
  1341. {
  1342. 'url': 'http://muz-tv.ru/play/7129/',
  1343. # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
  1344. 'info_dict': {
  1345. 'id': '12820',
  1346. 'ext': 'mp4',
  1347. 'title': "'O Sole Mio",
  1348. 'thumbnail': r're:^https?://.*\.jpg$',
  1349. 'duration': 216,
  1350. 'view_count': int,
  1351. },
  1352. 'params': {
  1353. 'skip_download': True,
  1354. },
  1355. 'skip': 'This video is unavailable.',
  1356. },
  1357. # Pladform embed
  1358. {
  1359. 'url': 'http://muz-tv.ru/kinozal/view/7400/',
  1360. 'info_dict': {
  1361. 'id': '100183293',
  1362. 'ext': 'mp4',
  1363. 'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
  1364. 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
  1365. 'thumbnail': r're:^https?://.*\.jpg$',
  1366. 'duration': 694,
  1367. 'age_limit': 0,
  1368. },
  1369. 'skip': 'HTTP Error 404: Not Found',
  1370. },
  1371. # Playwire embed
  1372. {
  1373. 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
  1374. 'info_dict': {
  1375. 'id': '3519514',
  1376. 'ext': 'mp4',
  1377. 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
  1378. 'thumbnail': r're:^https?://.*\.png$',
  1379. 'duration': 45.115,
  1380. },
  1381. },
  1382. # 5min embed
  1383. {
  1384. 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
  1385. 'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
  1386. 'info_dict': {
  1387. 'id': '518726732',
  1388. 'ext': 'mp4',
  1389. 'title': 'Facebook Creates "On This Day" | Crunch Report',
  1390. 'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
  1391. 'timestamp': 1427237531,
  1392. 'uploader': 'Crunch Report',
  1393. 'upload_date': '20150324',
  1394. },
  1395. 'params': {
  1396. # m3u8 download
  1397. 'skip_download': True,
  1398. },
  1399. },
  1400. # Crooks and Liars embed
  1401. {
  1402. 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
  1403. 'info_dict': {
  1404. 'id': '8RUoRhRi',
  1405. 'ext': 'mp4',
  1406. 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
  1407. 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
  1408. 'timestamp': 1428207000,
  1409. 'upload_date': '20150405',
  1410. 'uploader': 'Heather',
  1411. },
  1412. },
  1413. # Crooks and Liars external embed
  1414. {
  1415. 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
  1416. 'info_dict': {
  1417. 'id': 'MTE3MjUtMzQ2MzA',
  1418. 'ext': 'mp4',
  1419. 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
  1420. 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
  1421. 'timestamp': 1265032391,
  1422. 'upload_date': '20100201',
  1423. 'uploader': 'Heather',
  1424. },
  1425. },
  1426. # NBC Sports vplayer embed
  1427. {
  1428. 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
  1429. 'info_dict': {
  1430. 'id': 'ln7x1qSThw4k',
  1431. 'ext': 'flv',
  1432. 'title': "PFT Live: New leader in the 'new-look' defense",
  1433. 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
  1434. 'uploader': 'NBCU-SPORTS',
  1435. 'upload_date': '20140107',
  1436. 'timestamp': 1389118457,
  1437. },
  1438. 'skip': 'Invalid Page URL',
  1439. },
  1440. # NBC News embed
  1441. {
  1442. 'url': 'http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html',
  1443. 'md5': '1aa589c675898ae6d37a17913cf68d66',
  1444. 'info_dict': {
  1445. 'id': 'x_dtl_oa_LettermanliftPR_160608',
  1446. 'ext': 'mp4',
  1447. 'title': 'David Letterman: A Preview',
  1448. '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.',
  1449. 'upload_date': '20160609',
  1450. 'timestamp': 1465431544,
  1451. 'uploader': 'NBCU-NEWS',
  1452. },
  1453. },
  1454. # UDN embed
  1455. {
  1456. 'url': 'https://video.udn.com/news/300346',
  1457. 'md5': 'fd2060e988c326991037b9aff9df21a6',
  1458. 'info_dict': {
  1459. 'id': '300346',
  1460. 'ext': 'mp4',
  1461. 'title': '中一中男師變性 全校師生力挺',
  1462. 'thumbnail': r're:^https?://.*\.jpg$',
  1463. },
  1464. 'params': {
  1465. # m3u8 download
  1466. 'skip_download': True,
  1467. },
  1468. 'expected_warnings': ['Failed to parse JSON Expecting value'],
  1469. },
  1470. # Brightcove URL in single quotes
  1471. {
  1472. 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
  1473. 'md5': '4ae374f1f8b91c889c4b9203c8c752af',
  1474. 'info_dict': {
  1475. 'id': '4255764656001',
  1476. 'ext': 'mp4',
  1477. 'title': 'SN Presents: Russell Martin, World Citizen',
  1478. '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.',
  1479. 'uploader': 'Rogers Sportsnet',
  1480. 'uploader_id': '1704050871',
  1481. 'upload_date': '20150525',
  1482. 'timestamp': 1432570283,
  1483. },
  1484. },
  1485. # Kinja embed
  1486. {
  1487. 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
  1488. 'info_dict': {
  1489. 'id': '106351',
  1490. 'ext': 'mp4',
  1491. 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
  1492. 'description': 'Migrated from OnionStudios',
  1493. 'thumbnail': r're:^https?://.*\.jpe?g$',
  1494. 'uploader': 'clickhole',
  1495. 'upload_date': '20150527',
  1496. 'timestamp': 1432744860,
  1497. }
  1498. },
  1499. # SnagFilms embed
  1500. {
  1501. 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html',
  1502. 'info_dict': {
  1503. 'id': '74849a00-85a9-11e1-9660-123139220831',
  1504. 'ext': 'mp4',
  1505. 'title': '#whilewewatch',
  1506. }
  1507. },
  1508. # AdobeTVVideo embed
  1509. {
  1510. 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners',
  1511. 'md5': '43662b577c018ad707a63766462b1e87',
  1512. 'info_dict': {
  1513. 'id': '2456',
  1514. 'ext': 'mp4',
  1515. 'title': 'New experience with Acrobat DC',
  1516. 'description': 'New experience with Acrobat DC',
  1517. 'duration': 248.667,
  1518. },
  1519. },
  1520. # BrightcoveInPageEmbed embed
  1521. {
  1522. 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/',
  1523. 'info_dict': {
  1524. 'id': '4238694884001',
  1525. 'ext': 'flv',
  1526. 'title': 'Tabletop: Dread, Last Thoughts',
  1527. 'description': 'Tabletop: Dread, Last Thoughts',
  1528. 'duration': 51690,
  1529. },
  1530. },
  1531. # Brightcove embed, with no valid 'renditions' but valid 'IOSRenditions'
  1532. # This video can't be played in browsers if Flash disabled and UA set to iPhone, which is actually a false alarm
  1533. {
  1534. 'url': 'https://dl.dropboxusercontent.com/u/29092637/interview.html',
  1535. 'info_dict': {
  1536. 'id': '4785848093001',
  1537. 'ext': 'mp4',
  1538. 'title': 'The Cardinal Pell Interview',
  1539. 'description': 'Sky News Contributor Andrew Bolt interviews George Pell in Rome, following the Cardinal\'s evidence before the Royal Commission into Child Abuse. ',
  1540. 'uploader': 'GlobeCast Australia - GlobeStream',
  1541. 'uploader_id': '2733773828001',
  1542. 'upload_date': '20160304',
  1543. 'timestamp': 1457083087,
  1544. },
  1545. 'params': {
  1546. # m3u8 downloads
  1547. 'skip_download': True,
  1548. },
  1549. },
  1550. {
  1551. # Brightcove embed with whitespace around attribute names
  1552. 'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
  1553. 'info_dict': {
  1554. 'id': '3167554373001',
  1555. 'ext': 'mp4',
  1556. 'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
  1557. 'description': 'md5:57bacb0e0f29349de4972bfda3191713',
  1558. 'uploader_id': '1079349493',
  1559. 'upload_date': '20140207',
  1560. 'timestamp': 1391810548,
  1561. },
  1562. 'params': {
  1563. 'skip_download': True,
  1564. },
  1565. },
  1566. # Another form of arte.tv embed
  1567. {
  1568. 'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
  1569. 'md5': '850bfe45417ddf221288c88a0cffe2e2',
  1570. 'info_dict': {
  1571. 'id': '030273-562_PLUS7-F',
  1572. 'ext': 'mp4',
  1573. 'title': 'ARTE Reportage - Nulle part, en France',
  1574. 'description': 'md5:e3a0e8868ed7303ed509b9e3af2b870d',
  1575. 'upload_date': '20160409',
  1576. },
  1577. },
  1578. # LiveLeak embed
  1579. {
  1580. 'url': 'http://www.wykop.pl/link/3088787/',
  1581. 'md5': '7619da8c820e835bef21a1efa2a0fc71',
  1582. 'info_dict': {
  1583. 'id': '874_1459135191',
  1584. 'ext': 'mp4',
  1585. 'title': 'Man shows poor quality of new apartment building',
  1586. 'description': 'The wall is like a sand pile.',
  1587. 'uploader': 'Lake8737',
  1588. },
  1589. 'add_ie': [LiveLeakIE.ie_key()],
  1590. },
  1591. # Another LiveLeak embed pattern (#13336)
  1592. {
  1593. 'url': 'https://milo.yiannopoulos.net/2017/06/concealed-carry-robbery/',
  1594. 'info_dict': {
  1595. 'id': '2eb_1496309988',
  1596. 'ext': 'mp4',
  1597. 'title': 'Thief robs place where everyone was armed',
  1598. 'description': 'md5:694d73ee79e535953cf2488562288eee',
  1599. 'uploader': 'brazilwtf',
  1600. },
  1601. 'add_ie': [LiveLeakIE.ie_key()],
  1602. },
  1603. # Duplicated embedded video URLs
  1604. {
  1605. 'url': 'http://www.hudl.com/athlete/2538180/highlights/149298443',
  1606. 'info_dict': {
  1607. 'id': '149298443_480_16c25b74_2',
  1608. 'ext': 'mp4',
  1609. 'title': 'vs. Blue Orange Spring Game',
  1610. 'uploader': 'www.hudl.com',
  1611. },
  1612. },
  1613. # twitter:player:stream embed
  1614. {
  1615. 'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
  1616. 'info_dict': {
  1617. 'id': 'master',
  1618. 'ext': 'mp4',
  1619. 'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
  1620. 'uploader': 'www.rtl.be',
  1621. },
  1622. 'params': {
  1623. # m3u8 downloads
  1624. 'skip_download': True,
  1625. },
  1626. },
  1627. # twitter:player embed
  1628. {
  1629. 'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
  1630. 'md5': 'a3e0df96369831de324f0778e126653c',
  1631. 'info_dict': {
  1632. 'id': '4909620399001',
  1633. 'ext': 'mp4',
  1634. 'title': 'What Do Black Holes Sound Like?',
  1635. 'description': 'what do black holes sound like',
  1636. 'upload_date': '20160524',
  1637. 'uploader_id': '29913724001',
  1638. 'timestamp': 1464107587,
  1639. 'uploader': 'TheAtlantic',
  1640. },
  1641. 'add_ie': ['BrightcoveLegacy'],
  1642. },
  1643. # Facebook <iframe> embed
  1644. {
  1645. 'url': 'https://www.hostblogger.de/blog/archives/6181-Auto-jagt-Betonmischer.html',
  1646. 'md5': 'fbcde74f534176ecb015849146dd3aee',
  1647. 'info_dict': {
  1648. 'id': '599637780109885',
  1649. 'ext': 'mp4',
  1650. 'title': 'Facebook video #599637780109885',
  1651. },
  1652. },
  1653. # Facebook <iframe> embed, plugin video
  1654. {
  1655. 'url': 'http://5pillarsuk.com/2017/06/07/tariq-ramadan-disagrees-with-pr-exercise-by-imams-refusing-funeral-prayers-for-london-attackers/',
  1656. 'info_dict': {
  1657. 'id': '1754168231264132',
  1658. 'ext': 'mp4',
  1659. 'title': 'About the Imams and Religious leaders refusing to perform funeral prayers for...',
  1660. 'uploader': 'Tariq Ramadan (official)',
  1661. 'timestamp': 1496758379,
  1662. 'upload_date': '20170606',
  1663. },
  1664. 'params': {
  1665. 'skip_download': True,
  1666. },
  1667. },
  1668. # Facebook API embed
  1669. {
  1670. 'url': 'http://www.lothype.com/blue-stars-2016-preview-standstill-full-show/',
  1671. 'md5': 'a47372ee61b39a7b90287094d447d94e',
  1672. 'info_dict': {
  1673. 'id': '10153467542406923',
  1674. 'ext': 'mp4',
  1675. 'title': 'Facebook video #10153467542406923',
  1676. },
  1677. },
  1678. # Wordpress "YouTube Video Importer" plugin
  1679. {
  1680. 'url': 'http://www.lothype.com/blue-devils-drumline-stanford-lot-2016/',
  1681. 'md5': 'd16797741b560b485194eddda8121b48',
  1682. 'info_dict': {
  1683. 'id': 'HNTXWDXV9Is',
  1684. 'ext': 'mp4',
  1685. 'title': 'Blue Devils Drumline Stanford lot 2016',
  1686. 'upload_date': '20160627',
  1687. 'uploader_id': 'GENOCIDE8GENERAL10',
  1688. 'uploader': 'cylus cyrus',
  1689. },
  1690. },
  1691. {
  1692. # video stored on custom kaltura server
  1693. 'url': 'http://www.expansion.com/multimedia/videos.html?media=EQcM30NHIPv',
  1694. 'md5': '537617d06e64dfed891fa1593c4b30cc',
  1695. 'info_dict': {
  1696. 'id': '0_1iotm5bh',
  1697. 'ext': 'mp4',
  1698. 'title': 'Elecciones británicas: 5 lecciones para Rajoy',
  1699. 'description': 'md5:435a89d68b9760b92ce67ed227055f16',
  1700. 'uploader_id': 'videos.expansion@el-mundo.net',
  1701. 'upload_date': '20150429',
  1702. 'timestamp': 1430303472,
  1703. },
  1704. 'add_ie': ['Kaltura'],
  1705. },
  1706. {
  1707. # multiple kaltura embeds, nsfw
  1708. 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
  1709. 'info_dict': {
  1710. 'id': 'kamila-avec-video-jaime-sadomie',
  1711. 'title': "Kamila avec vídeo “J'aime sadomie”",
  1712. },
  1713. 'playlist_count': 8,
  1714. },
  1715. {
  1716. # Non-standard Vimeo embed
  1717. 'url': 'https://openclassrooms.com/courses/understanding-the-web',
  1718. 'md5': '64d86f1c7d369afd9a78b38cbb88d80a',
  1719. 'info_dict': {
  1720. 'id': '148867247',
  1721. 'ext': 'mp4',
  1722. 'title': 'Understanding the web - Teaser',
  1723. 'description': 'This is "Understanding the web - Teaser" by openclassrooms on Vimeo, the home for high quality videos and the people who love them.',
  1724. 'upload_date': '20151214',
  1725. 'uploader': 'OpenClassrooms',
  1726. 'uploader_id': 'openclassrooms',
  1727. },
  1728. 'add_ie': ['Vimeo'],
  1729. },
  1730. {
  1731. # generic vimeo embed that requires original URL passed as Referer
  1732. 'url': 'http://racing4everyone.eu/2016/07/30/formula-1-2016-round12-germany/',
  1733. 'only_matching': True,
  1734. },
  1735. {
  1736. 'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
  1737. 'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
  1738. 'info_dict': {
  1739. 'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
  1740. 'ext': 'mp4',
  1741. 'title': 'Big Buck Bunny',
  1742. 'description': 'Royalty free test video',
  1743. 'timestamp': 1432816365,
  1744. 'upload_date': '20150528',
  1745. 'is_live': False,
  1746. },
  1747. 'params': {
  1748. 'skip_download': True,
  1749. },
  1750. 'add_ie': [ArkenaIE.ie_key()],
  1751. },
  1752. {
  1753. '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/',
  1754. 'info_dict': {
  1755. 'id': '1c7141f46c',
  1756. 'ext': 'mp4',
  1757. 'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
  1758. },
  1759. 'params': {
  1760. 'skip_download': True,
  1761. },
  1762. 'add_ie': [Vbox7IE.ie_key()],
  1763. },
  1764. {
  1765. # DBTV embeds
  1766. 'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
  1767. 'info_dict': {
  1768. 'id': '43254897',
  1769. 'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
  1770. },
  1771. 'playlist_mincount': 3,
  1772. },
  1773. {
  1774. # Videa embeds
  1775. 'url': 'http://forum.dvdtalk.com/movie-talk/623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style.html',
  1776. 'info_dict': {
  1777. 'id': '623756-deleted-magic-star-wars-ot-deleted-alt-scenes-docu-style',
  1778. 'title': 'Deleted Magic - Star Wars: OT Deleted / Alt. Scenes Docu. Style - DVD Talk Forum',
  1779. },
  1780. 'playlist_mincount': 2,
  1781. },
  1782. {
  1783. # 20 minuten embed
  1784. 'url': 'http://www.20min.ch/schweiz/news/story/So-kommen-Sie-bei-Eis-und-Schnee-sicher-an-27032552',
  1785. 'info_dict': {
  1786. 'id': '523629',
  1787. 'ext': 'mp4',
  1788. 'title': 'So kommen Sie bei Eis und Schnee sicher an',
  1789. 'description': 'md5:117c212f64b25e3d95747e5276863f7d',
  1790. },
  1791. 'params': {
  1792. 'skip_download': True,
  1793. },
  1794. 'add_ie': [TwentyMinutenIE.ie_key()],
  1795. },
  1796. {
  1797. # VideoPress embed
  1798. 'url': 'https://en.support.wordpress.com/videopress/',
  1799. 'info_dict': {
  1800. 'id': 'OcobLTqC',
  1801. 'ext': 'm4v',
  1802. 'title': 'IMG_5786',
  1803. 'timestamp': 1435711927,
  1804. 'upload_date': '20150701',
  1805. },
  1806. 'params': {
  1807. 'skip_download': True,
  1808. },
  1809. 'add_ie': [VideoPressIE.ie_key()],
  1810. },
  1811. {
  1812. # Rutube embed
  1813. 'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
  1814. 'info_dict': {
  1815. 'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
  1816. 'ext': 'flv',
  1817. 'title': 'Магаззино: Казань 2',
  1818. 'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
  1819. 'uploader': 'Магаззино',
  1820. 'upload_date': '20170228',
  1821. 'uploader_id': '996642',
  1822. },
  1823. 'params': {
  1824. 'skip_download': True,
  1825. },
  1826. 'add_ie': [RutubeIE.ie_key()],
  1827. },
  1828. {
  1829. # ThePlatform embedded with whitespaces in URLs
  1830. 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
  1831. 'only_matching': True,
  1832. },
  1833. {
  1834. # Senate ISVP iframe https
  1835. 'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
  1836. 'md5': 'fb8c70b0b515e5037981a2492099aab8',
  1837. 'info_dict': {
  1838. 'id': 'govtaff020316',
  1839. 'ext': 'mp4',
  1840. 'title': 'Integrated Senate Video Player',
  1841. },
  1842. 'add_ie': [SenateISVPIE.ie_key()],
  1843. },
  1844. {
  1845. # Limelight embeds (1 channel embed + 4 media embeds)
  1846. 'url': 'http://www.sedona.com/FacilitatorTraining2017',
  1847. 'info_dict': {
  1848. 'id': 'FacilitatorTraining2017',
  1849. 'title': 'Facilitator Training 2017',
  1850. },
  1851. 'playlist_mincount': 5,
  1852. },
  1853. {
  1854. # Limelight embed (LimelightPlayerUtil.embed)
  1855. 'url': 'https://tv5.ca/videos?v=xuu8qowr291ri',
  1856. 'info_dict': {
  1857. 'id': '95d035dc5c8a401588e9c0e6bd1e9c92',
  1858. 'ext': 'mp4',
  1859. 'title': '07448641',
  1860. 'timestamp': 1499890639,
  1861. 'upload_date': '20170712',
  1862. },
  1863. 'params': {
  1864. 'skip_download': True,
  1865. },
  1866. 'add_ie': ['LimelightMedia'],
  1867. },
  1868. {
  1869. 'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
  1870. 'info_dict': {
  1871. 'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
  1872. 'title': 'Standoff with Walnut Creek murder suspect ends',
  1873. 'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
  1874. },
  1875. 'playlist_mincount': 4,
  1876. },
  1877. {
  1878. # WashingtonPost embed
  1879. 'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
  1880. 'info_dict': {
  1881. 'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
  1882. 'ext': 'mp4',
  1883. 'title': "No one has seen the drama series based on Trump's life \u2014 until now",
  1884. 'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
  1885. 'timestamp': 1455216756,
  1886. 'uploader': 'The Washington Post',
  1887. 'upload_date': '20160211',
  1888. },
  1889. 'add_ie': [WashingtonPostIE.ie_key()],
  1890. },
  1891. {
  1892. # Mediaset embed
  1893. 'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
  1894. 'info_dict': {
  1895. 'id': '720642',
  1896. 'ext': 'mp4',
  1897. 'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
  1898. },
  1899. 'params': {
  1900. 'skip_download': True,
  1901. },
  1902. 'add_ie': [MediasetIE.ie_key()],
  1903. },
  1904. {
  1905. # JOJ.sk embeds
  1906. 'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1907. 'info_dict': {
  1908. 'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
  1909. 'title': 'Slovenskom sa prehnala vlna silných búrok',
  1910. },
  1911. 'playlist_mincount': 5,
  1912. 'add_ie': [JojIE.ie_key()],
  1913. },
  1914. {
  1915. # AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
  1916. 'url': 'https://tvrain.ru/amp/418921/',
  1917. 'md5': 'cc00413936695987e8de148b67d14f1d',
  1918. 'info_dict': {
  1919. 'id': '418921',
  1920. 'ext': 'mp4',
  1921. 'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
  1922. },
  1923. },
  1924. {
  1925. # vzaar embed
  1926. 'url': 'http://help.vzaar.com/article/165-embedding-video',
  1927. 'md5': '7e3919d9d2620b89e3e00bec7fe8c9d4',
  1928. 'info_dict': {
  1929. 'id': '8707641',
  1930. 'ext': 'mp4',
  1931. 'title': 'Building A Business Online: Principal Chairs Q & A',
  1932. },
  1933. },
  1934. {
  1935. # multiple HTML5 videos on one page
  1936. 'url': 'https://www.paragon-software.com/home/rk-free/keyscenarios.html',
  1937. 'info_dict': {
  1938. 'id': 'keyscenarios',
  1939. 'title': 'Rescue Kit 14 Free Edition - Getting started',
  1940. },
  1941. 'playlist_count': 4,
  1942. },
  1943. {
  1944. # vshare embed
  1945. 'url': 'https://youtube-dl-demo.neocities.org/vshare.html',
  1946. 'md5': '17b39f55b5497ae8b59f5fbce8e35886',
  1947. 'info_dict': {
  1948. 'id': '0f64ce6',
  1949. 'title': 'vl14062007715967',
  1950. 'ext': 'mp4',
  1951. }
  1952. },
  1953. {
  1954. 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/',
  1955. 'md5': 'aecd089f55b1cb5a59032cb049d3a356',
  1956. 'info_dict': {
  1957. 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d',
  1958. 'ext': 'mp4',
  1959. 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare',
  1960. 'description': 'md5:5a51db84a62def7b7054df2ade403c6c',
  1961. 'timestamp': 1474354800,
  1962. 'upload_date': '20160920',
  1963. }
  1964. },
  1965. {
  1966. 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton',
  1967. 'info_dict': {
  1968. 'id': '1731611',
  1969. 'ext': 'mp4',
  1970. 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!',
  1971. 'description': 'md5:eb5f23826a027ba95277d105f248b825',
  1972. 'timestamp': 1516100691,
  1973. 'upload_date': '20180116',
  1974. },
  1975. 'params': {
  1976. 'skip_download': True,
  1977. },
  1978. 'add_ie': [SpringboardPlatformIE.ie_key()],
  1979. },
  1980. {
  1981. 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
  1982. 'info_dict': {
  1983. 'id': 'uPDB5I9wfp8',
  1984. 'ext': 'webm',
  1985. 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
  1986. 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
  1987. 'upload_date': '20160219',
  1988. 'uploader': 'Pocoyo - Português (BR)',
  1989. 'uploader_id': 'PocoyoBrazil',
  1990. },
  1991. 'add_ie': [YoutubeIE.ie_key()],
  1992. 'params': {
  1993. 'skip_download': True,
  1994. },
  1995. },
  1996. {
  1997. 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
  1998. 'info_dict': {
  1999. 'id': 'vMDE4NzI1Mjgt690b',
  2000. 'ext': 'mp4',
  2001. 'title': 'Котята',
  2002. },
  2003. 'add_ie': [YapFilesIE.ie_key()],
  2004. 'params': {
  2005. 'skip_download': True,
  2006. },
  2007. },
  2008. {
  2009. # CloudflareStream embed
  2010. 'url': 'https://www.cloudflare.com/products/cloudflare-stream/',
  2011. 'info_dict': {
  2012. 'id': '31c9291ab41fac05471db4e73aa11717',
  2013. 'ext': 'mp4',
  2014. 'title': '31c9291ab41fac05471db4e73aa11717',
  2015. },
  2016. 'add_ie': [CloudflareStreamIE.ie_key()],
  2017. 'params': {
  2018. 'skip_download': True,
  2019. },
  2020. },
  2021. {
  2022. # PeerTube embed
  2023. 'url': 'https://joinpeertube.org/fr/home/',
  2024. 'info_dict': {
  2025. 'id': 'home',
  2026. 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube',
  2027. },
  2028. 'playlist_count': 2,
  2029. },
  2030. {
  2031. # Indavideo embed
  2032. 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/',
  2033. 'info_dict': {
  2034. 'id': '1693903',
  2035. 'ext': 'mp4',
  2036. 'title': 'Így kell otthon hamburgert sütni',
  2037. 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7',
  2038. 'timestamp': 1426330212,
  2039. 'upload_date': '20150314',
  2040. 'uploader': 'StreetKitchen',
  2041. 'uploader_id': '546363',
  2042. },
  2043. 'add_ie': [IndavideoEmbedIE.ie_key()],
  2044. 'params': {
  2045. 'skip_download': True,
  2046. },
  2047. },
  2048. {
  2049. # APA embed via JWPlatform embed
  2050. 'url': 'http://www.vol.at/blue-man-group/5593454',
  2051. 'info_dict': {
  2052. 'id': 'jjv85FdZ',
  2053. 'ext': 'mp4',
  2054. 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
  2055. 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  2056. 'thumbnail': r're:^https?://.*\.jpg$',
  2057. 'duration': 254,
  2058. 'timestamp': 1519211149,
  2059. 'upload_date': '20180221',
  2060. },
  2061. 'params': {
  2062. 'skip_download': True,
  2063. },
  2064. },
  2065. {
  2066. 'url': 'http://share-videos.se/auto/video/83645793?uid=13',
  2067. 'md5': 'b68d276de422ab07ee1d49388103f457',
  2068. 'info_dict': {
  2069. 'id': '83645793',
  2070. 'title': 'Lock up and get excited',
  2071. 'ext': 'mp4'
  2072. },
  2073. 'skip': 'TODO: fix nested playlists processing in tests',
  2074. },
  2075. {
  2076. # Viqeo embeds
  2077. 'url': 'https://viqeo.tv/',
  2078. 'info_dict': {
  2079. 'id': 'viqeo',
  2080. 'title': 'All-new video platform',
  2081. },
  2082. 'playlist_count': 6,
  2083. },
  2084. {
  2085. # Squarespace video embed, 2019-08-28
  2086. 'url': 'http://ootboxford.com',
  2087. 'info_dict': {
  2088. 'id': 'Tc7b_JGdZfw',
  2089. 'title': 'Out of the Blue, at Childish Things 10',
  2090. 'ext': 'mp4',
  2091. 'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
  2092. 'uploader_id': 'helendouglashouse',
  2093. 'uploader': 'Helen & Douglas House',
  2094. 'upload_date': '20140328',
  2095. },
  2096. 'params': {
  2097. 'skip_download': True,
  2098. },
  2099. },
  2100. {
  2101. # Zype embed
  2102. 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
  2103. 'info_dict': {
  2104. 'id': '5b400b834b32992a310622b9',
  2105. 'ext': 'mp4',
  2106. 'title': 'Smoky Barbecue Favorites',
  2107. 'thumbnail': r're:^https?://.*\.jpe?g',
  2108. 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
  2109. 'upload_date': '20170909',
  2110. 'timestamp': 1504915200,
  2111. },
  2112. 'add_ie': [ZypeIE.ie_key()],
  2113. 'params': {
  2114. 'skip_download': True,
  2115. },
  2116. },
  2117. {
  2118. # videojs embed
  2119. 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
  2120. 'info_dict': {
  2121. 'id': 'shell',
  2122. 'ext': 'mp4',
  2123. 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано',
  2124. 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1',
  2125. 'thumbnail': r're:^https?://.*\.jpg$',
  2126. },
  2127. 'params': {
  2128. 'skip_download': True,
  2129. },
  2130. 'expected_warnings': ['Failed to download MPD manifest'],
  2131. },
  2132. {
  2133. # DailyMotion embed with DM.player
  2134. 'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
  2135. 'info_dict': {
  2136. 'id': 'k6aKkGHd9FJs4mtJN39',
  2137. 'ext': 'mp4',
  2138. 'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
  2139. 'description': 'This video is private.',
  2140. 'uploader_id': 'x1jf30l',
  2141. 'uploader': 'beIN SPORTS USA',
  2142. 'upload_date': '20190528',
  2143. 'timestamp': 1559062971,
  2144. },
  2145. 'params': {
  2146. 'skip_download': True,
  2147. },
  2148. },
  2149. # {
  2150. # # TODO: find another test
  2151. # # http://schema.org/VideoObject
  2152. # 'url': 'https://flipagram.com/f/nyvTSJMKId',
  2153. # 'md5': '888dcf08b7ea671381f00fab74692755',
  2154. # 'info_dict': {
  2155. # 'id': 'nyvTSJMKId',
  2156. # 'ext': 'mp4',
  2157. # 'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
  2158. # 'description': '#love for cats.',
  2159. # 'timestamp': 1461244995,
  2160. # 'upload_date': '20160421',
  2161. # },
  2162. # 'params': {
  2163. # 'force_generic_extractor': True,
  2164. # },
  2165. # }
  2166. ]
  2167. def report_following_redirect(self, new_url):
  2168. """Report information extraction."""
  2169. self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
  2170. def _extract_rss(self, url, video_id, doc):
  2171. playlist_title = doc.find('./channel/title').text
  2172. playlist_desc_el = doc.find('./channel/description')
  2173. playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
  2174. entries = []
  2175. for it in doc.findall('./channel/item'):
  2176. next_url = None
  2177. enclosure_nodes = it.findall('./enclosure')
  2178. for e in enclosure_nodes:
  2179. next_url = e.attrib.get('url')
  2180. if next_url:
  2181. break
  2182. if not next_url:
  2183. next_url = xpath_text(it, 'link', fatal=False)
  2184. if not next_url:
  2185. continue
  2186. entries.append({
  2187. '_type': 'url_transparent',
  2188. 'url': next_url,
  2189. 'title': it.find('title').text,
  2190. })
  2191. return {
  2192. '_type': 'playlist',
  2193. 'id': url,
  2194. 'title': playlist_title,
  2195. 'description': playlist_desc,
  2196. 'entries': entries,
  2197. }
  2198. def _extract_camtasia(self, url, video_id, webpage):
  2199. """ Returns None if no camtasia video can be found. """
  2200. camtasia_cfg = self._search_regex(
  2201. r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
  2202. webpage, 'camtasia configuration file', default=None)
  2203. if camtasia_cfg is None:
  2204. return None
  2205. title = self._html_search_meta('DC.title', webpage, fatal=True)
  2206. camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
  2207. camtasia_cfg = self._download_xml(
  2208. camtasia_url, video_id,
  2209. note='Downloading camtasia configuration',
  2210. errnote='Failed to download camtasia configuration')
  2211. fileset_node = camtasia_cfg.find('./playlist/array/fileset')
  2212. entries = []
  2213. for n in fileset_node.getchildren():
  2214. url_n = n.find('./uri')
  2215. if url_n is None:
  2216. continue
  2217. entries.append({
  2218. 'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
  2219. 'title': '%s - %s' % (title, n.tag),
  2220. 'url': compat_urlparse.urljoin(url, url_n.text),
  2221. 'duration': float_or_none(n.find('./duration').text),
  2222. })
  2223. return {
  2224. '_type': 'playlist',
  2225. 'entries': entries,
  2226. 'title': title,
  2227. }
  2228. def _real_extract(self, url):
  2229. if url.startswith('//'):
  2230. return self.url_result(self.http_scheme() + url)
  2231. parsed_url = compat_urlparse.urlparse(url)
  2232. if not parsed_url.scheme:
  2233. default_search = self._downloader.params.get('default_search')
  2234. if default_search is None:
  2235. default_search = 'fixup_error'
  2236. if default_search in ('auto', 'auto_warning', 'fixup_error'):
  2237. if re.match(r'^[^\s/]+\.[^\s/]+/', url):
  2238. self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
  2239. return self.url_result('http://' + url)
  2240. elif default_search != 'fixup_error':
  2241. if default_search == 'auto_warning':
  2242. if re.match(r'^(?:url|URL)$', url):
  2243. raise ExtractorError(
  2244. 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
  2245. expected=True)
  2246. else:
  2247. self._downloader.report_warning(
  2248. 'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
  2249. return self.url_result('ytsearch:' + url)
  2250. if default_search in ('error', 'fixup_error'):
  2251. raise ExtractorError(
  2252. '%r is not a valid URL. '
  2253. 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
  2254. % (url, url), expected=True)
  2255. else:
  2256. if ':' not in default_search:
  2257. default_search += ':'
  2258. return self.url_result(default_search + url)
  2259. url, smuggled_data = unsmuggle_url(url)
  2260. force_videoid = None
  2261. is_intentional = smuggled_data and smuggled_data.get('to_generic')
  2262. if smuggled_data and 'force_videoid' in smuggled_data:
  2263. force_videoid = smuggled_data['force_videoid']
  2264. video_id = force_videoid
  2265. else:
  2266. video_id = self._generic_id(url)
  2267. self.to_screen('%s: Requesting header' % video_id)
  2268. head_req = HEADRequest(url)
  2269. head_response = self._request_webpage(
  2270. head_req, video_id,
  2271. note=False, errnote='Could not send HEAD request to %s' % url,
  2272. fatal=False)
  2273. if head_response is not False:
  2274. # Check for redirect
  2275. new_url = head_response.geturl()
  2276. if url != new_url:
  2277. self.report_following_redirect(new_url)
  2278. if force_videoid:
  2279. new_url = smuggle_url(
  2280. new_url, {'force_videoid': force_videoid})
  2281. return self.url_result(new_url)
  2282. full_response = None
  2283. if head_response is False:
  2284. request = sanitized_Request(url)
  2285. request.add_header('Accept-Encoding', '*')
  2286. full_response = self._request_webpage(request, video_id)
  2287. head_response = full_response
  2288. info_dict = {
  2289. 'id': video_id,
  2290. 'title': self._generic_title(url),
  2291. 'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
  2292. }
  2293. # Check for direct link to a video
  2294. content_type = head_response.headers.get('Content-Type', '').lower()
  2295. m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
  2296. if m:
  2297. format_id = compat_str(m.group('format_id'))
  2298. if format_id.endswith('mpegurl'):
  2299. formats = self._extract_m3u8_formats(url, video_id, 'mp4')
  2300. elif format_id == 'f4m':
  2301. formats = self._extract_f4m_formats(url, video_id)
  2302. else:
  2303. formats = [{
  2304. 'format_id': format_id,
  2305. 'url': url,
  2306. 'vcodec': 'none' if m.group('type') == 'audio' else None
  2307. }]
  2308. info_dict['direct'] = True
  2309. self._sort_formats(formats)
  2310. info_dict['formats'] = formats
  2311. return info_dict
  2312. if not self._downloader.params.get('test', False) and not is_intentional:
  2313. force = self._downloader.params.get('force_generic_extractor', False)
  2314. self._downloader.report_warning(
  2315. '%s on generic information extractor.' % ('Forcing' if force else 'Falling back'))
  2316. if not full_response:
  2317. request = sanitized_Request(url)
  2318. # Some webservers may serve compressed content of rather big size (e.g. gzipped flac)
  2319. # making it impossible to download only chunk of the file (yet we need only 512kB to
  2320. # test whether it's HTML or not). According to youtube-dl default Accept-Encoding
  2321. # that will always result in downloading the whole file that is not desirable.
  2322. # Therefore for extraction pass we have to override Accept-Encoding to any in order
  2323. # to accept raw bytes and being able to download only a chunk.
  2324. # It may probably better to solve this by checking Content-Type for application/octet-stream
  2325. # after HEAD request finishes, but not sure if we can rely on this.
  2326. request.add_header('Accept-Encoding', '*')
  2327. full_response = self._request_webpage(request, video_id)
  2328. first_bytes = full_response.read(512)
  2329. # Is it an M3U playlist?
  2330. if first_bytes.startswith(b'#EXTM3U'):
  2331. info_dict['formats'] = self._extract_m3u8_formats(url, video_id, 'mp4')
  2332. self._sort_formats(info_dict['formats'])
  2333. return info_dict
  2334. # Maybe it's a direct link to a video?
  2335. # Be careful not to download the whole thing!
  2336. if not is_html(first_bytes):
  2337. self._downloader.report_warning(
  2338. 'URL could be a direct video link, returning it as such.')
  2339. info_dict.update({
  2340. 'direct': True,
  2341. 'url': url,
  2342. })
  2343. return info_dict
  2344. webpage = self._webpage_read_content(
  2345. full_response, url, video_id, prefix=first_bytes)
  2346. self.report_extraction(video_id)
  2347. # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
  2348. try:
  2349. doc = compat_etree_fromstring(webpage.encode('utf-8'))
  2350. if doc.tag == 'rss':
  2351. return self._extract_rss(url, video_id, doc)
  2352. elif doc.tag == 'SmoothStreamingMedia':
  2353. info_dict['formats'] = self._parse_ism_formats(doc, url)
  2354. self._sort_formats(info_dict['formats'])
  2355. return info_dict
  2356. elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):
  2357. smil = self._parse_smil(doc, url, video_id)
  2358. self._sort_formats(smil['formats'])
  2359. return smil
  2360. elif doc.tag == '{http://xspf.org/ns/0/}playlist':
  2361. return self.playlist_result(
  2362. self._parse_xspf(
  2363. doc, video_id, xspf_url=url,
  2364. xspf_base_url=full_response.geturl()),
  2365. video_id)
  2366. elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
  2367. info_dict['formats'] = self._parse_mpd_formats(
  2368. doc,
  2369. mpd_base_url=full_response.geturl().rpartition('/')[0],
  2370. mpd_url=url)
  2371. self._sort_formats(info_dict['formats'])
  2372. return info_dict
  2373. elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag):
  2374. info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id)
  2375. self._sort_formats(info_dict['formats'])
  2376. return info_dict
  2377. except compat_xml_parse_error:
  2378. pass
  2379. # Is it a Camtasia project?
  2380. camtasia_res = self._extract_camtasia(url, video_id, webpage)
  2381. if camtasia_res is not None:
  2382. return camtasia_res
  2383. # Sometimes embedded video player is hidden behind percent encoding
  2384. # (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
  2385. # Unescaping the whole page allows to handle those cases in a generic way
  2386. webpage = compat_urllib_parse_unquote(webpage)
  2387. # Unescape squarespace embeds to be detected by generic extractor,
  2388. # see https://github.com/ytdl-org/youtube-dl/issues/21294
  2389. webpage = re.sub(
  2390. r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
  2391. lambda x: unescapeHTML(x.group(0)), webpage)
  2392. # it's tempting to parse this further, but you would
  2393. # have to take into account all the variations like
  2394. # Video Title - Site Name
  2395. # Site Name | Video Title
  2396. # Video Title - Tagline | Site Name
  2397. # and so on and so forth; it's just not practical
  2398. video_title = self._og_search_title(
  2399. webpage, default=None) or self._html_search_regex(
  2400. r'(?s)<title>(.*?)</title>', webpage, 'video title',
  2401. default='video')
  2402. # Try to detect age limit automatically
  2403. age_limit = self._rta_search(webpage)
  2404. # And then there are the jokers who advertise that they use RTA,
  2405. # but actually don't.
  2406. AGE_LIMIT_MARKERS = [
  2407. r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
  2408. ]
  2409. if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
  2410. age_limit = 18
  2411. # video uploader is domain name
  2412. video_uploader = self._search_regex(
  2413. r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
  2414. video_description = self._og_search_description(webpage, default=None)
  2415. video_thumbnail = self._og_search_thumbnail(webpage, default=None)
  2416. info_dict.update({
  2417. 'title': video_title,
  2418. 'description': video_description,
  2419. 'thumbnail': video_thumbnail,
  2420. 'age_limit': age_limit,
  2421. })
  2422. # Look for Brightcove Legacy Studio embeds
  2423. bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
  2424. if bc_urls:
  2425. entries = [{
  2426. '_type': 'url',
  2427. 'url': smuggle_url(bc_url, {'Referer': url}),
  2428. 'ie_key': 'BrightcoveLegacy'
  2429. } for bc_url in bc_urls]
  2430. return {
  2431. '_type': 'playlist',
  2432. 'title': video_title,
  2433. 'id': video_id,
  2434. 'entries': entries,
  2435. }
  2436. # Look for Brightcove New Studio embeds
  2437. bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
  2438. if bc_urls:
  2439. return self.playlist_from_matches(
  2440. bc_urls, video_id, video_title,
  2441. getter=lambda x: smuggle_url(x, {'referrer': url}),
  2442. ie='BrightcoveNew')
  2443. # Look for Nexx embeds
  2444. nexx_urls = NexxIE._extract_urls(webpage)
  2445. if nexx_urls:
  2446. return self.playlist_from_matches(nexx_urls, video_id, video_title, ie=NexxIE.ie_key())
  2447. # Look for Nexx iFrame embeds
  2448. nexx_embed_urls = NexxEmbedIE._extract_urls(webpage)
  2449. if nexx_embed_urls:
  2450. return self.playlist_from_matches(nexx_embed_urls, video_id, video_title, ie=NexxEmbedIE.ie_key())
  2451. # Look for ThePlatform embeds
  2452. tp_urls = ThePlatformIE._extract_urls(webpage)
  2453. if tp_urls:
  2454. return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
  2455. # Look for embedded rtl.nl player
  2456. matches = re.findall(
  2457. r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
  2458. webpage)
  2459. if matches:
  2460. return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
  2461. vimeo_urls = VimeoIE._extract_urls(url, webpage)
  2462. if vimeo_urls:
  2463. return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
  2464. vid_me_embed_url = self._search_regex(
  2465. r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
  2466. webpage, 'vid.me embed', default=None)
  2467. if vid_me_embed_url is not None:
  2468. return self.url_result(vid_me_embed_url, 'Vidme')
  2469. # Look for YouTube embeds
  2470. youtube_urls = YoutubeIE._extract_urls(webpage)
  2471. if youtube_urls:
  2472. return self.playlist_from_matches(
  2473. youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())
  2474. matches = DailymotionIE._extract_urls(webpage)
  2475. if matches:
  2476. return self.playlist_from_matches(matches, video_id, video_title)
  2477. # Look for embedded Dailymotion playlist player (#3822)
  2478. m = re.search(
  2479. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
  2480. if m:
  2481. playlists = re.findall(
  2482. r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
  2483. if playlists:
  2484. return self.playlist_from_matches(
  2485. playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
  2486. # Look for DailyMail embeds
  2487. dailymail_urls = DailyMailIE._extract_urls(webpage)
  2488. if dailymail_urls:
  2489. return self.playlist_from_matches(
  2490. dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
  2491. # Look for Teachable embeds, must be before Wistia
  2492. teachable_url = TeachableIE._extract_url(webpage, url)
  2493. if teachable_url:
  2494. return self.url_result(teachable_url)
  2495. # Look for embedded Wistia player
  2496. wistia_urls = WistiaIE._extract_urls(webpage)
  2497. if wistia_urls:
  2498. playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
  2499. for entry in playlist['entries']:
  2500. entry.update({
  2501. '_type': 'url_transparent',
  2502. 'uploader': video_uploader,
  2503. })
  2504. return playlist
  2505. # Look for SVT player
  2506. svt_url = SVTIE._extract_url(webpage)
  2507. if svt_url:
  2508. return self.url_result(svt_url, 'SVT')
  2509. # Look for Bandcamp pages with custom domain
  2510. mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
  2511. if mobj is not None:
  2512. burl = unescapeHTML(mobj.group(1))
  2513. # Don't set the extractor because it can be a track url or an album
  2514. return self.url_result(burl)
  2515. # Look for embedded Vevo player
  2516. mobj = re.search(
  2517. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
  2518. if mobj is not None:
  2519. return self.url_result(mobj.group('url'))
  2520. # Look for embedded Viddler player
  2521. mobj = re.search(
  2522. r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
  2523. webpage)
  2524. if mobj is not None:
  2525. return self.url_result(mobj.group('url'))
  2526. # Look for NYTimes player
  2527. mobj = re.search(
  2528. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
  2529. webpage)
  2530. if mobj is not None:
  2531. return self.url_result(mobj.group('url'))
  2532. # Look for Libsyn player
  2533. mobj = re.search(
  2534. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
  2535. if mobj is not None:
  2536. return self.url_result(mobj.group('url'))
  2537. # Look for Ooyala videos
  2538. mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage)
  2539. or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2540. or re.search(r'OO\.Player\.create\.apply\(\s*OO\.Player\s*,\s*op\(\s*\[\s*[\'"][^\'"]*[\'"]\s*,\s*[\'"](?P<ec>.{32})[\'"]', webpage)
  2541. or re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage)
  2542. or re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
  2543. if mobj is not None:
  2544. embed_token = self._search_regex(
  2545. r'embedToken[\'"]?\s*:\s*[\'"]([^\'"]+)',
  2546. webpage, 'ooyala embed token', default=None)
  2547. return OoyalaIE._build_url_result(smuggle_url(
  2548. mobj.group('ec'), {
  2549. 'domain': url,
  2550. 'embed_token': embed_token,
  2551. }))
  2552. # Look for multiple Ooyala embeds on SBN network websites
  2553. mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
  2554. if mobj is not None:
  2555. embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
  2556. if embeds:
  2557. return self.playlist_from_matches(
  2558. embeds, video_id, video_title,
  2559. getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
  2560. # Look for Aparat videos
  2561. mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
  2562. if mobj is not None:
  2563. return self.url_result(mobj.group(1), 'Aparat')
  2564. # Look for MPORA videos
  2565. mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
  2566. if mobj is not None:
  2567. return self.url_result(mobj.group(1), 'Mpora')
  2568. # Look for embedded Facebook player
  2569. facebook_urls = FacebookIE._extract_urls(webpage)
  2570. if facebook_urls:
  2571. return self.playlist_from_matches(facebook_urls, video_id, video_title)
  2572. # Look for embedded VK player
  2573. mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
  2574. if mobj is not None:
  2575. return self.url_result(mobj.group('url'), 'VK')
  2576. # Look for embedded Odnoklassniki player
  2577. odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
  2578. if odnoklassniki_url:
  2579. return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
  2580. # Look for embedded ivi player
  2581. mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
  2582. if mobj is not None:
  2583. return self.url_result(mobj.group('url'), 'Ivi')
  2584. # Look for embedded Huffington Post player
  2585. mobj = re.search(
  2586. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
  2587. if mobj is not None:
  2588. return self.url_result(mobj.group('url'), 'HuffPost')
  2589. # Look for embed.ly
  2590. mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
  2591. if mobj is not None:
  2592. return self.url_result(mobj.group('url'))
  2593. mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
  2594. if mobj is not None:
  2595. return self.url_result(compat_urllib_parse_unquote(mobj.group('url')))
  2596. # Look for funnyordie embed
  2597. matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
  2598. if matches:
  2599. return self.playlist_from_matches(
  2600. matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
  2601. # Look for BBC iPlayer embed
  2602. matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
  2603. if matches:
  2604. return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
  2605. # Look for embedded RUTV player
  2606. rutv_url = RUTVIE._extract_url(webpage)
  2607. if rutv_url:
  2608. return self.url_result(rutv_url, 'RUTV')
  2609. # Look for embedded TVC player
  2610. tvc_url = TVCIE._extract_url(webpage)
  2611. if tvc_url:
  2612. return self.url_result(tvc_url, 'TVC')
  2613. # Look for embedded SportBox player
  2614. sportbox_urls = SportBoxIE._extract_urls(webpage)
  2615. if sportbox_urls:
  2616. return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key())
  2617. # Look for embedded XHamster player
  2618. xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
  2619. if xhamster_urls:
  2620. return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
  2621. # Look for embedded TNAFlixNetwork player
  2622. tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
  2623. if tnaflix_urls:
  2624. return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
  2625. # Look for embedded PornHub player
  2626. pornhub_urls = PornHubIE._extract_urls(webpage)
  2627. if pornhub_urls:
  2628. return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
  2629. # Look for embedded DrTuber player
  2630. drtuber_urls = DrTuberIE._extract_urls(webpage)
  2631. if drtuber_urls:
  2632. return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
  2633. # Look for embedded RedTube player
  2634. redtube_urls = RedTubeIE._extract_urls(webpage)
  2635. if redtube_urls:
  2636. return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
  2637. # Look for embedded Tube8 player
  2638. tube8_urls = Tube8IE._extract_urls(webpage)
  2639. if tube8_urls:
  2640. return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key())
  2641. # Look for embedded Mofosex player
  2642. mofosex_urls = MofosexEmbedIE._extract_urls(webpage)
  2643. if mofosex_urls:
  2644. return self.playlist_from_matches(mofosex_urls, video_id, video_title, ie=MofosexEmbedIE.ie_key())
  2645. # Look for embedded Spankwire player
  2646. spankwire_urls = SpankwireIE._extract_urls(webpage)
  2647. if spankwire_urls:
  2648. return self.playlist_from_matches(spankwire_urls, video_id, video_title, ie=SpankwireIE.ie_key())
  2649. # Look for embedded YouPorn player
  2650. youporn_urls = YouPornIE._extract_urls(webpage)
  2651. if youporn_urls:
  2652. return self.playlist_from_matches(youporn_urls, video_id, video_title, ie=YouPornIE.ie_key())
  2653. # Look for embedded Tvigle player
  2654. mobj = re.search(
  2655. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
  2656. if mobj is not None:
  2657. return self.url_result(mobj.group('url'), 'Tvigle')
  2658. # Look for embedded TED player
  2659. mobj = re.search(
  2660. r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
  2661. if mobj is not None:
  2662. return self.url_result(mobj.group('url'), 'TED')
  2663. # Look for embedded Ustream videos
  2664. ustream_url = UstreamIE._extract_url(webpage)
  2665. if ustream_url:
  2666. return self.url_result(ustream_url, UstreamIE.ie_key())
  2667. # Look for embedded arte.tv player
  2668. arte_urls = ArteTVEmbedIE._extract_urls(webpage)
  2669. if arte_urls:
  2670. return self.playlist_from_matches(arte_urls, video_id, video_title)
  2671. # Look for embedded francetv player
  2672. mobj = re.search(
  2673. r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?://)?embed\.francetv\.fr/\?ue=.+?)\1',
  2674. webpage)
  2675. if mobj is not None:
  2676. return self.url_result(mobj.group('url'))
  2677. # Look for embedded smotri.com player
  2678. smotri_url = SmotriIE._extract_url(webpage)
  2679. if smotri_url:
  2680. return self.url_result(smotri_url, 'Smotri')
  2681. # Look for embedded Myvi.ru player
  2682. myvi_url = MyviIE._extract_url(webpage)
  2683. if myvi_url:
  2684. return self.url_result(myvi_url)
  2685. # Look for embedded soundcloud player
  2686. soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
  2687. if soundcloud_urls:
  2688. return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
  2689. # Look for tunein player
  2690. tunein_urls = TuneInBaseIE._extract_urls(webpage)
  2691. if tunein_urls:
  2692. return self.playlist_from_matches(tunein_urls, video_id, video_title)
  2693. # Look for embedded mtvservices player
  2694. mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
  2695. if mtvservices_url:
  2696. return self.url_result(mtvservices_url, ie='MTVServicesEmbedded')
  2697. # Look for embedded yahoo player
  2698. mobj = re.search(
  2699. r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
  2700. webpage)
  2701. if mobj is not None:
  2702. return self.url_result(mobj.group('url'), 'Yahoo')
  2703. # Look for embedded sbs.com.au player
  2704. mobj = re.search(
  2705. r'''(?x)
  2706. (?:
  2707. <meta\s+property="og:video"\s+content=|
  2708. <iframe[^>]+?src=
  2709. )
  2710. (["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
  2711. webpage)
  2712. if mobj is not None:
  2713. return self.url_result(mobj.group('url'), 'SBS')
  2714. # Look for embedded Cinchcast player
  2715. mobj = re.search(
  2716. r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
  2717. webpage)
  2718. if mobj is not None:
  2719. return self.url_result(mobj.group('url'), 'Cinchcast')
  2720. mobj = re.search(
  2721. r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
  2722. webpage)
  2723. if not mobj:
  2724. mobj = re.search(
  2725. r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
  2726. webpage)
  2727. if mobj is not None:
  2728. return self.url_result(mobj.group('url'), 'MLB')
  2729. mobj = re.search(
  2730. r'<(?:iframe|script)[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
  2731. webpage)
  2732. if mobj is not None:
  2733. return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
  2734. mobj = re.search(
  2735. r'<iframe[^>]+src="(?P<url>https?://(?:new\.)?livestream\.com/[^"]+/player[^"]+)"',
  2736. webpage)
  2737. if mobj is not None:
  2738. return self.url_result(mobj.group('url'), 'Livestream')
  2739. # Look for Zapiks embed
  2740. mobj = re.search(
  2741. r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
  2742. if mobj is not None:
  2743. return self.url_result(mobj.group('url'), 'Zapiks')
  2744. # Look for Kaltura embeds
  2745. kaltura_urls = KalturaIE._extract_urls(webpage)
  2746. if kaltura_urls:
  2747. return self.playlist_from_matches(
  2748. kaltura_urls, video_id, video_title,
  2749. getter=lambda x: smuggle_url(x, {'source_url': url}),
  2750. ie=KalturaIE.ie_key())
  2751. # Look for EaglePlatform embeds
  2752. eagleplatform_url = EaglePlatformIE._extract_url(webpage)
  2753. if eagleplatform_url:
  2754. return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
  2755. # Look for ClipYou (uses EaglePlatform) embeds
  2756. mobj = re.search(
  2757. r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
  2758. if mobj is not None:
  2759. return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
  2760. # Look for Pladform embeds
  2761. pladform_url = PladformIE._extract_url(webpage)
  2762. if pladform_url:
  2763. return self.url_result(pladform_url)
  2764. # Look for Videomore embeds
  2765. videomore_url = VideomoreIE._extract_url(webpage)
  2766. if videomore_url:
  2767. return self.url_result(videomore_url)
  2768. # Look for Webcaster embeds
  2769. webcaster_url = WebcasterFeedIE._extract_url(self, webpage)
  2770. if webcaster_url:
  2771. return self.url_result(webcaster_url, ie=WebcasterFeedIE.ie_key())
  2772. # Look for Playwire embeds
  2773. mobj = re.search(
  2774. r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
  2775. if mobj is not None:
  2776. return self.url_result(mobj.group('url'))
  2777. # Look for 5min embeds
  2778. mobj = re.search(
  2779. r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
  2780. if mobj is not None:
  2781. return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
  2782. # Look for Crooks and Liars embeds
  2783. mobj = re.search(
  2784. r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
  2785. if mobj is not None:
  2786. return self.url_result(mobj.group('url'))
  2787. # Look for NBC Sports VPlayer embeds
  2788. nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
  2789. if nbc_sports_url:
  2790. return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
  2791. # Look for NBC News embeds
  2792. nbc_news_embed_url = re.search(
  2793. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//www\.nbcnews\.com/widget/video-embed/[^"\']+)\1', webpage)
  2794. if nbc_news_embed_url:
  2795. return self.url_result(nbc_news_embed_url.group('url'), 'NBCNews')
  2796. # Look for Google Drive embeds
  2797. google_drive_url = GoogleDriveIE._extract_url(webpage)
  2798. if google_drive_url:
  2799. return self.url_result(google_drive_url, 'GoogleDrive')
  2800. # Look for UDN embeds
  2801. mobj = re.search(
  2802. r'<iframe[^>]+src="(?:https?:)?(?P<url>%s)"' % UDNEmbedIE._PROTOCOL_RELATIVE_VALID_URL, webpage)
  2803. if mobj is not None:
  2804. return self.url_result(
  2805. compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
  2806. # Look for Senate ISVP iframe
  2807. senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  2808. if senate_isvp_url:
  2809. return self.url_result(senate_isvp_url, 'SenateISVP')
  2810. # Look for Kinja embeds
  2811. kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
  2812. if kinja_embed_urls:
  2813. return self.playlist_from_matches(
  2814. kinja_embed_urls, video_id, video_title)
  2815. # Look for OnionStudios embeds
  2816. onionstudios_url = OnionStudiosIE._extract_url(webpage)
  2817. if onionstudios_url:
  2818. return self.url_result(onionstudios_url)
  2819. # Look for ViewLift embeds
  2820. viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
  2821. if viewlift_url:
  2822. return self.url_result(viewlift_url)
  2823. # Look for JWPlatform embeds
  2824. jwplatform_urls = JWPlatformIE._extract_urls(webpage)
  2825. if jwplatform_urls:
  2826. return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key())
  2827. # Look for Digiteka embeds
  2828. digiteka_url = DigitekaIE._extract_url(webpage)
  2829. if digiteka_url:
  2830. return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
  2831. # Look for Arkena embeds
  2832. arkena_url = ArkenaIE._extract_url(webpage)
  2833. if arkena_url:
  2834. return self.url_result(arkena_url, ArkenaIE.ie_key())
  2835. # Look for Piksel embeds
  2836. piksel_url = PikselIE._extract_url(webpage)
  2837. if piksel_url:
  2838. return self.url_result(piksel_url, PikselIE.ie_key())
  2839. # Look for Limelight embeds
  2840. limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
  2841. if limelight_urls:
  2842. return self.playlist_result(
  2843. limelight_urls, video_id, video_title, video_description)
  2844. # Look for Anvato embeds
  2845. anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
  2846. if anvato_urls:
  2847. return self.playlist_result(
  2848. anvato_urls, video_id, video_title, video_description)
  2849. # Look for AdobeTVVideo embeds
  2850. mobj = re.search(
  2851. r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
  2852. webpage)
  2853. if mobj is not None:
  2854. return self.url_result(
  2855. self._proto_relative_url(unescapeHTML(mobj.group(1))),
  2856. 'AdobeTVVideo')
  2857. # Look for Vine embeds
  2858. mobj = re.search(
  2859. r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vine\.co/v/[^/]+/embed/(?:simple|postcard))',
  2860. webpage)
  2861. if mobj is not None:
  2862. return self.url_result(
  2863. self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
  2864. # Look for VODPlatform embeds
  2865. mobj = re.search(
  2866. r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
  2867. webpage)
  2868. if mobj is not None:
  2869. return self.url_result(
  2870. self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
  2871. # Look for Mangomolo embeds
  2872. mobj = re.search(
  2873. r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
  2874. (?:
  2875. admin\.mangomolo\.com/analytics/index\.php/customers/embed|
  2876. player\.mangomolo\.com/v1
  2877. )/
  2878. (?:
  2879. video\?.*?\bid=(?P<video_id>\d+)|
  2880. (?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
  2881. ).+?)\1''', webpage)
  2882. if mobj is not None:
  2883. info = {
  2884. '_type': 'url_transparent',
  2885. 'url': self._proto_relative_url(unescapeHTML(mobj.group('url'))),
  2886. 'title': video_title,
  2887. 'description': video_description,
  2888. 'thumbnail': video_thumbnail,
  2889. 'uploader': video_uploader,
  2890. }
  2891. video_id = mobj.group('video_id')
  2892. if video_id:
  2893. info.update({
  2894. 'ie_key': 'MangomoloVideo',
  2895. 'id': video_id,
  2896. })
  2897. else:
  2898. info.update({
  2899. 'ie_key': 'MangomoloLive',
  2900. 'id': mobj.group('channel_id'),
  2901. })
  2902. return info
  2903. # Look for Instagram embeds
  2904. instagram_embed_url = InstagramIE._extract_embed_url(webpage)
  2905. if instagram_embed_url is not None:
  2906. return self.url_result(
  2907. self._proto_relative_url(instagram_embed_url), InstagramIE.ie_key())
  2908. # Look for LiveLeak embeds
  2909. liveleak_urls = LiveLeakIE._extract_urls(webpage)
  2910. if liveleak_urls:
  2911. return self.playlist_from_matches(liveleak_urls, video_id, video_title)
  2912. # Look for 3Q SDN embeds
  2913. threeqsdn_url = ThreeQSDNIE._extract_url(webpage)
  2914. if threeqsdn_url:
  2915. return {
  2916. '_type': 'url_transparent',
  2917. 'ie_key': ThreeQSDNIE.ie_key(),
  2918. 'url': self._proto_relative_url(threeqsdn_url),
  2919. 'title': video_title,
  2920. 'description': video_description,
  2921. 'thumbnail': video_thumbnail,
  2922. 'uploader': video_uploader,
  2923. }
  2924. # Look for VBOX7 embeds
  2925. vbox7_url = Vbox7IE._extract_url(webpage)
  2926. if vbox7_url:
  2927. return self.url_result(vbox7_url, Vbox7IE.ie_key())
  2928. # Look for DBTV embeds
  2929. dbtv_urls = DBTVIE._extract_urls(webpage)
  2930. if dbtv_urls:
  2931. return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
  2932. # Look for Videa embeds
  2933. videa_urls = VideaIE._extract_urls(webpage)
  2934. if videa_urls:
  2935. return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
  2936. # Look for 20 minuten embeds
  2937. twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
  2938. if twentymin_urls:
  2939. return self.playlist_from_matches(
  2940. twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
  2941. # Look for VideoPress embeds
  2942. videopress_urls = VideoPressIE._extract_urls(webpage)
  2943. if videopress_urls:
  2944. return self.playlist_from_matches(
  2945. videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
  2946. # Look for Rutube embeds
  2947. rutube_urls = RutubeIE._extract_urls(webpage)
  2948. if rutube_urls:
  2949. return self.playlist_from_matches(
  2950. rutube_urls, video_id, video_title, ie=RutubeIE.ie_key())
  2951. # Look for WashingtonPost embeds
  2952. wapo_urls = WashingtonPostIE._extract_urls(webpage)
  2953. if wapo_urls:
  2954. return self.playlist_from_matches(
  2955. wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
  2956. # Look for Mediaset embeds
  2957. mediaset_urls = MediasetIE._extract_urls(self, webpage)
  2958. if mediaset_urls:
  2959. return self.playlist_from_matches(
  2960. mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
  2961. # Look for JOJ.sk embeds
  2962. joj_urls = JojIE._extract_urls(webpage)
  2963. if joj_urls:
  2964. return self.playlist_from_matches(
  2965. joj_urls, video_id, video_title, ie=JojIE.ie_key())
  2966. # Look for megaphone.fm embeds
  2967. mpfn_urls = MegaphoneIE._extract_urls(webpage)
  2968. if mpfn_urls:
  2969. return self.playlist_from_matches(
  2970. mpfn_urls, video_id, video_title, ie=MegaphoneIE.ie_key())
  2971. # Look for vzaar embeds
  2972. vzaar_urls = VzaarIE._extract_urls(webpage)
  2973. if vzaar_urls:
  2974. return self.playlist_from_matches(
  2975. vzaar_urls, video_id, video_title, ie=VzaarIE.ie_key())
  2976. channel9_urls = Channel9IE._extract_urls(webpage)
  2977. if channel9_urls:
  2978. return self.playlist_from_matches(
  2979. channel9_urls, video_id, video_title, ie=Channel9IE.ie_key())
  2980. vshare_urls = VShareIE._extract_urls(webpage)
  2981. if vshare_urls:
  2982. return self.playlist_from_matches(
  2983. vshare_urls, video_id, video_title, ie=VShareIE.ie_key())
  2984. # Look for Mediasite embeds
  2985. mediasite_urls = MediasiteIE._extract_urls(webpage)
  2986. if mediasite_urls:
  2987. entries = [
  2988. self.url_result(smuggle_url(
  2989. compat_urlparse.urljoin(url, mediasite_url),
  2990. {'UrlReferrer': url}), ie=MediasiteIE.ie_key())
  2991. for mediasite_url in mediasite_urls]
  2992. return self.playlist_result(entries, video_id, video_title)
  2993. springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage)
  2994. if springboardplatform_urls:
  2995. return self.playlist_from_matches(
  2996. springboardplatform_urls, video_id, video_title,
  2997. ie=SpringboardPlatformIE.ie_key())
  2998. yapfiles_urls = YapFilesIE._extract_urls(webpage)
  2999. if yapfiles_urls:
  3000. return self.playlist_from_matches(
  3001. yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
  3002. vice_urls = ViceIE._extract_urls(webpage)
  3003. if vice_urls:
  3004. return self.playlist_from_matches(
  3005. vice_urls, video_id, video_title, ie=ViceIE.ie_key())
  3006. xfileshare_urls = XFileShareIE._extract_urls(webpage)
  3007. if xfileshare_urls:
  3008. return self.playlist_from_matches(
  3009. xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key())
  3010. cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage)
  3011. if cloudflarestream_urls:
  3012. return self.playlist_from_matches(
  3013. cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key())
  3014. peertube_urls = PeerTubeIE._extract_urls(webpage, url)
  3015. if peertube_urls:
  3016. return self.playlist_from_matches(
  3017. peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
  3018. indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
  3019. if indavideo_urls:
  3020. return self.playlist_from_matches(
  3021. indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key())
  3022. apa_urls = APAIE._extract_urls(webpage)
  3023. if apa_urls:
  3024. return self.playlist_from_matches(
  3025. apa_urls, video_id, video_title, ie=APAIE.ie_key())
  3026. foxnews_urls = FoxNewsIE._extract_urls(webpage)
  3027. if foxnews_urls:
  3028. return self.playlist_from_matches(
  3029. foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
  3030. sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
  3031. r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
  3032. webpage)]
  3033. if sharevideos_urls:
  3034. return self.playlist_from_matches(
  3035. sharevideos_urls, video_id, video_title)
  3036. viqeo_urls = ViqeoIE._extract_urls(webpage)
  3037. if viqeo_urls:
  3038. return self.playlist_from_matches(
  3039. viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key())
  3040. expressen_urls = ExpressenIE._extract_urls(webpage)
  3041. if expressen_urls:
  3042. return self.playlist_from_matches(
  3043. expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key())
  3044. zype_urls = ZypeIE._extract_urls(webpage)
  3045. if zype_urls:
  3046. return self.playlist_from_matches(
  3047. zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
  3048. # Look for HTML5 media
  3049. entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
  3050. if entries:
  3051. if len(entries) == 1:
  3052. entries[0].update({
  3053. 'id': video_id,
  3054. 'title': video_title,
  3055. })
  3056. else:
  3057. for num, entry in enumerate(entries, start=1):
  3058. entry.update({
  3059. 'id': '%s-%s' % (video_id, num),
  3060. 'title': '%s (%d)' % (video_title, num),
  3061. })
  3062. for entry in entries:
  3063. self._sort_formats(entry['formats'])
  3064. return self.playlist_result(entries, video_id, video_title)
  3065. jwplayer_data = self._find_jwplayer_data(
  3066. webpage, video_id, transform_source=js_to_json)
  3067. if jwplayer_data:
  3068. try:
  3069. info = self._parse_jwplayer_data(
  3070. jwplayer_data, video_id, require_title=False, base_url=url)
  3071. return merge_dicts(info, info_dict)
  3072. except ExtractorError:
  3073. # See https://github.com/ytdl-org/youtube-dl/pull/16735
  3074. pass
  3075. # Video.js embed
  3076. mobj = re.search(
  3077. r'(?s)\bvideojs\s*\(.+?\.src\s*\(\s*((?:\[.+?\]|{.+?}))\s*\)\s*;',
  3078. webpage)
  3079. if mobj is not None:
  3080. sources = self._parse_json(
  3081. mobj.group(1), video_id, transform_source=js_to_json,
  3082. fatal=False) or []
  3083. if not isinstance(sources, list):
  3084. sources = [sources]
  3085. formats = []
  3086. for source in sources:
  3087. src = source.get('src')
  3088. if not src or not isinstance(src, compat_str):
  3089. continue
  3090. src = compat_urlparse.urljoin(url, src)
  3091. src_type = source.get('type')
  3092. if isinstance(src_type, compat_str):
  3093. src_type = src_type.lower()
  3094. ext = determine_ext(src).lower()
  3095. if src_type == 'video/youtube':
  3096. return self.url_result(src, YoutubeIE.ie_key())
  3097. if src_type == 'application/dash+xml' or ext == 'mpd':
  3098. formats.extend(self._extract_mpd_formats(
  3099. src, video_id, mpd_id='dash', fatal=False))
  3100. elif src_type == 'application/x-mpegurl' or ext == 'm3u8':
  3101. formats.extend(self._extract_m3u8_formats(
  3102. src, video_id, 'mp4', entry_protocol='m3u8_native',
  3103. m3u8_id='hls', fatal=False))
  3104. else:
  3105. formats.append({
  3106. 'url': src,
  3107. 'ext': (mimetype2ext(src_type)
  3108. or ext if ext in KNOWN_EXTENSIONS else 'mp4'),
  3109. })
  3110. if formats:
  3111. self._sort_formats(formats)
  3112. info_dict['formats'] = formats
  3113. return info_dict
  3114. # Looking for http://schema.org/VideoObject
  3115. json_ld = self._search_json_ld(
  3116. webpage, video_id, default={}, expected_type='VideoObject')
  3117. if json_ld.get('url'):
  3118. return merge_dicts(json_ld, info_dict)
  3119. def check_video(vurl):
  3120. if YoutubeIE.suitable(vurl):
  3121. return True
  3122. if RtmpIE.suitable(vurl):
  3123. return True
  3124. vpath = compat_urlparse.urlparse(vurl).path
  3125. vext = determine_ext(vpath)
  3126. return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
  3127. def filter_video(urls):
  3128. return list(filter(check_video, urls))
  3129. # Start with something easy: JW Player in SWFObject
  3130. found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
  3131. if not found:
  3132. # Look for gorilla-vid style embedding
  3133. found = filter_video(re.findall(r'''(?sx)
  3134. (?:
  3135. jw_plugins|
  3136. JWPlayerOptions|
  3137. jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
  3138. )
  3139. .*?
  3140. ['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
  3141. if not found:
  3142. # Broaden the search a little bit
  3143. found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
  3144. if not found:
  3145. # Broaden the findall a little bit: JWPlayer JS loader
  3146. found = filter_video(re.findall(
  3147. r'[^A-Za-z0-9]?(?:file|video_url)["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
  3148. if not found:
  3149. # Flow player
  3150. found = filter_video(re.findall(r'''(?xs)
  3151. flowplayer\("[^"]+",\s*
  3152. \{[^}]+?\}\s*,
  3153. \s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
  3154. ["']?url["']?\s*:\s*["']([^"']+)["']
  3155. ''', webpage))
  3156. if not found:
  3157. # Cinerama player
  3158. found = re.findall(
  3159. r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
  3160. if not found:
  3161. # Try to find twitter cards info
  3162. # twitter:player:stream should be checked before twitter:player since
  3163. # it is expected to contain a raw stream (see
  3164. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3165. found = filter_video(re.findall(
  3166. r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
  3167. if not found:
  3168. # We look for Open Graph info:
  3169. # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
  3170. m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
  3171. # We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
  3172. if m_video_type is not None:
  3173. found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
  3174. if not found:
  3175. REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
  3176. found = re.search(
  3177. r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
  3178. r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
  3179. webpage)
  3180. if not found:
  3181. # Look also in Refresh HTTP header
  3182. refresh_header = head_response.headers.get('Refresh')
  3183. if refresh_header:
  3184. # In python 2 response HTTP headers are bytestrings
  3185. if sys.version_info < (3, 0) and isinstance(refresh_header, str):
  3186. refresh_header = refresh_header.decode('iso-8859-1')
  3187. found = re.search(REDIRECT_REGEX, refresh_header)
  3188. if found:
  3189. new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
  3190. if new_url != url:
  3191. self.report_following_redirect(new_url)
  3192. return {
  3193. '_type': 'url',
  3194. 'url': new_url,
  3195. }
  3196. else:
  3197. found = None
  3198. if not found:
  3199. # twitter:player is a https URL to iframe player that may or may not
  3200. # be supported by youtube-dl thus this is checked the very last (see
  3201. # https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
  3202. embed_url = self._html_search_meta('twitter:player', webpage, default=None)
  3203. if embed_url and embed_url != url:
  3204. return self.url_result(embed_url)
  3205. if not found:
  3206. raise UnsupportedError(url)
  3207. entries = []
  3208. for video_url in orderedSet(found):
  3209. video_url = unescapeHTML(video_url)
  3210. video_url = video_url.replace('\\/', '/')
  3211. video_url = compat_urlparse.urljoin(url, video_url)
  3212. video_id = compat_urllib_parse_unquote(os.path.basename(video_url))
  3213. # Sometimes, jwplayer extraction will result in a YouTube URL
  3214. if YoutubeIE.suitable(video_url):
  3215. entries.append(self.url_result(video_url, 'Youtube'))
  3216. continue
  3217. # here's a fun little line of code for you:
  3218. video_id = os.path.splitext(video_id)[0]
  3219. entry_info_dict = {
  3220. 'id': video_id,
  3221. 'uploader': video_uploader,
  3222. 'title': video_title,
  3223. 'age_limit': age_limit,
  3224. }
  3225. if RtmpIE.suitable(video_url):
  3226. entry_info_dict.update({
  3227. '_type': 'url_transparent',
  3228. 'ie_key': RtmpIE.ie_key(),
  3229. 'url': video_url,
  3230. })
  3231. entries.append(entry_info_dict)
  3232. continue
  3233. ext = determine_ext(video_url)
  3234. if ext == 'smil':
  3235. entry_info_dict['formats'] = self._extract_smil_formats(video_url, video_id)
  3236. elif ext == 'xspf':
  3237. return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
  3238. elif ext == 'm3u8':
  3239. entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4')
  3240. elif ext == 'mpd':
  3241. entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id)
  3242. elif ext == 'f4m':
  3243. entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
  3244. elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
  3245. # Just matching .ism/manifest is not enough to be reliably sure
  3246. # whether it's actually an ISM manifest or some other streaming
  3247. # manifest since there are various streaming URL formats
  3248. # possible (see [1]) as well as some other shenanigans like
  3249. # .smil/manifest URLs that actually serve an ISM (see [2]) and
  3250. # so on.
  3251. # Thus the most reasonable way to solve this is to delegate
  3252. # to generic extractor in order to look into the contents of
  3253. # the manifest itself.
  3254. # 1. https://azure.microsoft.com/en-us/documentation/articles/media-services-deliver-content-overview/#streaming-url-formats
  3255. # 2. https://svs.itworkscdn.net/lbcivod/smil:itwfcdn/lbci/170976.smil/Manifest
  3256. entry_info_dict = self.url_result(
  3257. smuggle_url(video_url, {'to_generic': True}),
  3258. GenericIE.ie_key())
  3259. else:
  3260. entry_info_dict['url'] = video_url
  3261. if entry_info_dict.get('formats'):
  3262. self._sort_formats(entry_info_dict['formats'])
  3263. entries.append(entry_info_dict)
  3264. if len(entries) == 1:
  3265. return entries[0]
  3266. else:
  3267. for num, e in enumerate(entries, start=1):
  3268. # 'url' results don't have a title
  3269. if e.get('title') is not None:
  3270. e['title'] = '%s (%d)' % (e['title'], num)
  3271. return {
  3272. '_type': 'playlist',
  3273. 'entries': entries,
  3274. }