X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0865c28fb29a6481cd837cf8c1ef0cd134c6ef8e..8b4fae8ce16f284d2b7a5bb2ee099e9ecaf0c0d2:/youtube_dl/extractor/generic.py diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 27e2bc3..c6bf8d2 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -4,11 +4,13 @@ from __future__ import unicode_literals import os import re +import sys from .common import InfoExtractor from .youtube import YoutubeIE from ..compat import ( - compat_urllib_parse, + compat_etree_fromstring, + compat_urllib_parse_unquote, compat_urlparse, compat_xml_parse_error, ) @@ -19,19 +21,43 @@ from ..utils import ( HEADRequest, is_html, orderedSet, - parse_xml, + sanitized_Request, smuggle_url, unescapeHTML, unified_strdate, unsmuggle_url, UnsupportedError, url_basename, + xpath_text, ) -from .brightcove import BrightcoveIE +from .brightcove import ( + BrightcoveLegacyIE, + BrightcoveNewIE, +) +from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE +from .tvc import TVCIE +from .sportbox import SportBoxEmbedIE from .smotri import SmotriIE +from .myvi import MyviIE from .condenast import CondeNastIE +from .udn import UDNEmbedIE +from .senateisvp import SenateISVPIE +from .svt import SVTIE +from .pornhub import PornHubIE +from .xhamster import XHamsterEmbedIE +from .vimeo import VimeoIE +from .dailymotion import DailymotionCloudIE +from .onionstudios import OnionStudiosIE +from .snagfilms import SnagFilmsEmbedIE +from .screenwavemedia import ScreenwaveMediaIE +from .mtv import MTVServicesEmbeddedIE +from .pladform import PladformIE +from .videomore import VideomoreIE +from .googledrive import GoogleDriveIE +from .jwplatform import JWPlatformIE +from .digiteka import DigitekaIE class GenericIE(InfoExtractor): @@ -39,6 +65,211 @@ class GenericIE(InfoExtractor): _VALID_URL = r'.*' IE_NAME = 'generic' _TESTS = [ + # Direct link to a video + { + 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', + 'md5': '67d406c2bcb6af27fa886f31aa934bbe', + 'info_dict': { + 'id': 'trailer', + 'ext': 'mp4', + 'title': 'trailer', + 'upload_date': '20100513', + } + }, + # Direct link to media delivered compressed (until Accept-Encoding is *) + { + 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac', + 'md5': '128c42e68b13950268b648275386fc74', + 'info_dict': { + 'id': 'FictionJunction-Parallel_Hearts', + 'ext': 'flac', + 'title': 'FictionJunction-Parallel_Hearts', + 'upload_date': '20140522', + }, + 'expected_warnings': [ + 'URL could be a direct video link, returning it as such.' + ] + }, + # Direct download with broken HEAD + { + 'url': 'http://ai-radio.org:8000/radio.opus', + 'info_dict': { + 'id': 'radio', + 'ext': 'opus', + 'title': 'radio', + }, + 'params': { + 'skip_download': True, # infinite live stream + }, + 'expected_warnings': [ + r'501.*Not Implemented' + ], + }, + # Direct link with incorrect MIME type + { + 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', + 'md5': '4ccbebe5f36706d85221f204d7eb5913', + 'info_dict': { + 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', + 'id': '5_Lennart_Poettering_-_Systemd', + 'ext': 'webm', + 'title': '5_Lennart_Poettering_-_Systemd', + 'upload_date': '20141120', + }, + 'expected_warnings': [ + 'URL could be a direct video link, returning it as such.' + ] + }, + # RSS feed + { + 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'info_dict': { + 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'title': 'Zero Punctuation', + 'description': 're:.*groundbreaking video review series.*' + }, + 'playlist_mincount': 11, + }, + # RSS feed with enclosure + { + 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml', + 'info_dict': { + 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624', + 'ext': 'm4v', + 'upload_date': '20150228', + 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624', + } + }, + # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng + { + 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml', + 'info_dict': { + 'id': 'smil', + 'ext': 'mp4', + 'title': 'Automatics, robotics and biocybernetics', + 'description': 'md5:815fc1deb6b3a2bff99de2d5325be482', + 'upload_date': '20130627', + 'formats': 'mincount:16', + 'subtitles': 'mincount:1', + }, + 'params': { + 'force_generic_extractor': True, + 'skip_download': True, + }, + }, + # SMIL from http://www1.wdr.de/mediathek/video/livestream/index.html + { + 'url': 'http://metafilegenerator.de/WDR/WDR_FS/hds/hds.smil', + 'info_dict': { + 'id': 'hds', + 'ext': 'flv', + 'title': 'hds', + 'formats': 'mincount:1', + }, + 'params': { + 'skip_download': True, + }, + }, + # SMIL from https://www.restudy.dk/video/play/id/1637 + { + 'url': 'https://www.restudy.dk/awsmedia/SmilDirectory/video_1637.xml', + 'info_dict': { + 'id': 'video_1637', + 'ext': 'flv', + 'title': 'video_1637', + 'formats': 'mincount:3', + }, + 'params': { + 'skip_download': True, + }, + }, + # SMIL from http://adventure.howstuffworks.com/5266-cool-jobs-iditarod-musher-video.htm + { + 'url': 'http://services.media.howstuffworks.com/videos/450221/smil-service.smil', + 'info_dict': { + 'id': 'smil-service', + 'ext': 'flv', + 'title': 'smil-service', + 'formats': 'mincount:1', + }, + 'params': { + 'skip_download': True, + }, + }, + # SMIL from http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370 + { + 'url': 'http://api.new.livestream.com/accounts/1570303/events/1585861/videos/4719370.smil', + 'info_dict': { + 'id': '4719370', + 'ext': 'mp4', + 'title': '571de1fd-47bc-48db-abf9-238872a58d1f', + 'formats': 'mincount:3', + }, + 'params': { + 'skip_download': True, + }, + }, + # XSPF playlist from http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html + { + 'url': 'http://www.telegraaf.nl/xml/playlist/2015/8/7/mZlp2ctYIUEB.xspf', + 'info_dict': { + 'id': 'mZlp2ctYIUEB', + 'ext': 'mp4', + 'title': 'Tikibad ontruimd wegens brand', + 'description': 'md5:05ca046ff47b931f9b04855015e163a4', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 33, + }, + 'params': { + 'skip_download': True, + }, + }, + # MPD from http://dash-mse-test.appspot.com/media.html + { + 'url': 'http://yt-dash-mse-test.commondatastorage.googleapis.com/media/car-20120827-manifest.mpd', + 'md5': '4b57baab2e30d6eb3a6a09f0ba57ef53', + 'info_dict': { + 'id': 'car-20120827-manifest', + 'ext': 'mp4', + 'title': 'car-20120827-manifest', + 'formats': 'mincount:9', + }, + 'params': { + 'format': 'bestvideo', + }, + }, + # google redirect + { + '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', + 'info_dict': { + 'id': 'cmQHVoWB5FY', + 'ext': 'mp4', + 'upload_date': '20130224', + 'uploader_id': 'TheVerge', + 'description': 're:^Chris Ziegler takes a look at the\.*', + 'uploader': 'The Verge', + 'title': 'First Firefox OS phones side-by-side', + }, + 'params': { + 'skip_download': False, + } + }, + { + # redirect in Refresh HTTP header + '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', + 'info_dict': { + 'id': 'pO8h3EaFRdo', + 'ext': 'mp4', + 'title': 'Tripeo Boiler Room x Dekmantel Festival DJ Set', + 'description': 'md5:6294cc1af09c4049e0652b51a2df10d5', + 'upload_date': '20150917', + 'uploader_id': 'brtvofficial', + 'uploader': 'Boiler Room', + }, + 'params': { + 'skip_download': False, + }, + }, { 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', 'md5': '85b90ccc9d73b4acd9138d3af4c27f89', @@ -65,7 +296,7 @@ class GenericIE(InfoExtractor): # it also tests brightcove videos that need to set the 'Referer' in the # http requests { - 'add_ie': ['Brightcove'], + 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/', 'info_dict': { 'id': '2765128793001', @@ -89,7 +320,7 @@ class GenericIE(InfoExtractor): 'uploader': 'thestar.com', '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.', }, - 'add_ie': ['Brightcove'], + 'add_ie': ['BrightcoveLegacy'], }, { 'url': 'http://www.championat.com/video/football/v/87/87499.html', @@ -104,7 +335,7 @@ class GenericIE(InfoExtractor): }, { # https://github.com/rg3/youtube-dl/issues/3541 - 'add_ie': ['Brightcove'], + 'add_ie': ['BrightcoveLegacy'], 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', 'info_dict': { 'id': '3866516442001', @@ -118,17 +349,6 @@ class GenericIE(InfoExtractor): 'skip_download': True, # m3u8 download }, }, - # Direct link to a video - { - 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', - 'md5': '67d406c2bcb6af27fa886f31aa934bbe', - 'info_dict': { - 'id': 'trailer', - 'ext': 'mp4', - 'title': 'trailer', - 'upload_date': '20100513', - } - }, # ooyala video { 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', @@ -137,9 +357,24 @@ class GenericIE(InfoExtractor): 'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', 'ext': 'mp4', 'title': '2cc213299525360.mov', # that's what we get + 'duration': 238.231, }, 'add_ie': ['Ooyala'], }, + { + # ooyala video embedded with http://player.ooyala.com/iframe.js + 'url': 'http://www.macrumors.com/2015/07/24/steve-jobs-the-man-in-the-machine-first-trailer/', + 'info_dict': { + 'id': 'p0MGJndjoG5SOKqO_hZJuZFPB-Tr5VgB', + 'ext': 'mp4', + 'title': '"Steve Jobs: Man in the Machine" trailer', + 'description': 'The first trailer for the Alex Gibney documentary "Steve Jobs: Man in the Machine."', + 'duration': 135.427, + }, + 'params': { + 'skip_download': True, + }, + }, # multiple ooyala embeds on SBN network websites { 'url': 'http://www.sbnation.com/college-football-recruiting/2015/2/3/7970291/national-signing-day-rationalizations-itll-be-ok-itll-be-ok', @@ -153,22 +388,6 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Ooyala'], }, - # google redirect - { - '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', - 'info_dict': { - 'id': 'cmQHVoWB5FY', - 'ext': 'mp4', - 'upload_date': '20130224', - 'uploader_id': 'TheVerge', - 'description': 're:^Chris Ziegler takes a look at the\.*', - 'uploader': 'The Verge', - 'title': 'First Firefox OS phones side-by-side', - }, - 'params': { - 'skip_download': False, - } - }, # embed.ly video { 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/', @@ -196,14 +415,6 @@ class GenericIE(InfoExtractor): 'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.', }, }, - # BBC iPlayer embeds - { - 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/posts/BUGGER', - 'info_dict': { - 'title': 'BBC - Blogs - Adam Curtis - BUGGER', - }, - 'playlist_mincount': 18, - }, # RUTV embed { 'url': 'http://www.rg.ru/2014/03/15/reg-dfo/anklav-anons.html', @@ -218,6 +429,66 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, + # TVC embed + { + '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/', + 'info_dict': { + 'id': '55304', + 'ext': 'mp4', + 'title': 'Дошкольное воспитание', + }, + }, + # SportBox embed + { + 'url': 'http://www.vestifinance.ru/articles/25753', + 'info_dict': { + 'id': '25753', + 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"', + }, + 'playlist': [{ + 'info_dict': { + 'id': '370908', + 'title': 'Госзаказ. День 3', + 'ext': 'mp4', + } + }, { + 'info_dict': { + 'id': '370905', + 'title': 'Госзаказ. День 2', + 'ext': 'mp4', + } + }, { + 'info_dict': { + 'id': '370902', + 'title': 'Госзаказ. День 1', + 'ext': 'mp4', + } + }], + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, + # Myvi.ru embed + { + 'url': 'http://www.kinomyvi.tv/news/detail/Pervij-dublirovannij-trejler--Uzhastikov-_nOw1', + 'info_dict': { + 'id': 'f4dafcad-ff21-423d-89b5-146cfd89fa1e', + 'ext': 'mp4', + 'title': 'Ужастики, русский трейлер (2015)', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 153, + } + }, + # XHamster embed + { + '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', + 'info_dict': { + 'id': 'showthread', + 'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )', + }, + 'playlist_mincount': 7, + }, # Embedded TED video { 'url': 'http://en.support.wordpress.com/videos/ted-talks/', @@ -230,7 +501,7 @@ class GenericIE(InfoExtractor): 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9', } }, - # Embeded Ustream video + # Embedded Ustream video { 'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm', 'md5': '27b99cdb639c9b12a79bca876a073417', @@ -267,6 +538,26 @@ class GenericIE(InfoExtractor): 'skip_download': 'Requires rtmpdump' } }, + # francetv embed + { + 'url': 'http://www.tsprod.com/replay-du-concert-alcaline-de-calogero', + 'info_dict': { + 'id': 'EV_30231', + 'ext': 'mp4', + 'title': 'Alcaline, le concert avec Calogero', + 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff', + 'upload_date': '20150226', + 'timestamp': 1424989860, + 'duration': 5400, + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + }, + 'expected_warnings': [ + 'Forbidden' + ] + }, # Condé Nast embed { 'url': 'http://www.wired.com/2014/04/honda-asimo/', @@ -369,16 +660,6 @@ class GenericIE(InfoExtractor): 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com', } }, - # RSS feed - { - 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', - 'info_dict': { - 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', - 'title': 'Zero Punctuation', - 'description': 're:.*groundbreaking video review series.*' - }, - 'playlist_mincount': 11, - }, # Multiple brightcove videos # https://github.com/rg3/youtube-dl/issues/2283 { @@ -432,21 +713,6 @@ class GenericIE(InfoExtractor): 'uploader': 'thoughtworks.wistia.com', }, }, - # Direct download with broken HEAD - { - 'url': 'http://ai-radio.org:8000/radio.opus', - 'info_dict': { - 'id': 'radio', - 'ext': 'opus', - 'title': 'radio', - }, - 'params': { - 'skip_download': True, # infinite live stream - }, - 'expected_warnings': [ - r'501.*Not Implemented' - ], - }, # Soundcloud embed { 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/', @@ -478,21 +744,6 @@ class GenericIE(InfoExtractor): }, 'playlist_mincount': 2, }, - # Direct link with incorrect MIME type - { - 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', - 'md5': '4ccbebe5f36706d85221f204d7eb5913', - 'info_dict': { - 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', - 'id': '5_Lennart_Poettering_-_Systemd', - 'ext': 'webm', - 'title': '5_Lennart_Poettering_-_Systemd', - 'upload_date': '20141120', - }, - 'expected_warnings': [ - 'URL could be a direct video link, returning it as such.' - ] - }, # Cinchcast embed { 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/', @@ -526,6 +777,17 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Viddler'], }, + # Libsyn embed + { + 'url': 'http://thedailyshow.cc.com/podcast/episodetwelve', + 'info_dict': { + 'id': '3377616', + 'ext': 'mp3', + 'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart", + 'description': 'md5:601cb790edd05908957dae8aaa866465', + 'upload_date': '20150220', + }, + }, # jwplayer YouTube { 'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/', @@ -569,6 +831,269 @@ class GenericIE(InfoExtractor): 'title': 'John Carlson Postgame 2/25/15', }, }, + # Kaltura embed (different embed code) + { + 'url': 'http://www.premierchristianradio.com/Shows/Saturday/Unbelievable/Conference-Videos/Os-Guinness-Is-It-Fools-Talk-Unbelievable-Conference-2014', + 'info_dict': { + 'id': '1_a52wc67y', + 'ext': 'flv', + 'upload_date': '20150127', + 'uploader_id': 'PremierMedia', + 'timestamp': int, + 'title': 'Os Guinness // Is It Fools Talk? // Unbelievable? Conference 2014', + }, + }, + # Kaltura embed protected with referrer + { + 'url': 'http://www.disney.nl/disney-channel/filmpjes/achter-de-schermen#/videoId/violetta-achter-de-schermen-ruggero', + 'info_dict': { + 'id': '1_g4fbemnq', + 'ext': 'mp4', + 'title': 'Violetta - Achter De Schermen - Ruggero', + 'description': 'Achter de schermen met Ruggero', + 'timestamp': 1435133761, + 'upload_date': '20150624', + 'uploader_id': 'echojecka', + }, + }, + # Eagle.Platform embed (generic URL) + { + 'url': 'http://lenta.ru/news/2015/03/06/navalny/', + 'info_dict': { + 'id': '227304', + 'ext': 'mp4', + 'title': 'Навальный вышел на свободу', + 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 87, + 'view_count': int, + 'age_limit': 0, + }, + }, + # ClipYou (Eagle.Platform) embed (custom URL) + { + 'url': 'http://muz-tv.ru/play/7129/', + 'info_dict': { + 'id': '12820', + 'ext': 'mp4', + 'title': "'O Sole Mio", + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 216, + 'view_count': int, + }, + }, + # Pladform embed + { + 'url': 'http://muz-tv.ru/kinozal/view/7400/', + 'info_dict': { + 'id': '100183293', + 'ext': 'mp4', + 'title': 'Тайны перевала Дятлова • 1 серия 2 часть', + 'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 694, + 'age_limit': 0, + }, + }, + # Playwire embed + { + 'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html', + 'info_dict': { + 'id': '3519514', + 'ext': 'mp4', + 'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer', + 'thumbnail': 're:^https?://.*\.png$', + 'duration': 45.115, + }, + }, + # 5min embed + { + 'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/', + 'md5': '4c6f127a30736b59b3e2c19234ee2bf7', + 'info_dict': { + 'id': '518726732', + 'ext': 'mp4', + 'title': 'Facebook Creates "On This Day" | Crunch Report', + }, + }, + # SVT embed + { + 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', + 'info_dict': { + 'id': '2900353', + 'ext': 'flv', + 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)', + 'duration': 27, + 'age_limit': 0, + }, + }, + # Crooks and Liars embed + { + 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists', + 'info_dict': { + 'id': '8RUoRhRi', + 'ext': 'mp4', + 'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!", + 'description': 'md5:e1a46ad1650e3a5ec7196d432799127f', + 'timestamp': 1428207000, + 'upload_date': '20150405', + 'uploader': 'Heather', + }, + }, + # Crooks and Liars external embed + { + 'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/', + 'info_dict': { + 'id': 'MTE3MjUtMzQ2MzA', + 'ext': 'mp4', + 'title': 'md5:5e3662a81a4014d24c250d76d41a08d5', + 'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec', + 'timestamp': 1265032391, + 'upload_date': '20100201', + 'uploader': 'Heather', + }, + }, + # NBC Sports vplayer embed + { + 'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a', + 'info_dict': { + 'id': 'ln7x1qSThw4k', + 'ext': 'flv', + 'title': "PFT Live: New leader in the 'new-look' defense", + 'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e', + }, + }, + # UDN embed + { + 'url': 'http://www.udn.com/news/story/7314/822787', + 'md5': 'fd2060e988c326991037b9aff9df21a6', + 'info_dict': { + 'id': '300346', + 'ext': 'mp4', + 'title': '中一中男師變性 全校師生力挺', + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, + # Ooyala embed + { + 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T', + 'info_dict': { + 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs', + 'ext': 'mp4', + 'description': 'VIDEO: INDEX/MATCH versus VLOOKUP.', + 'title': 'This is what separates the Excel masters from the wannabes', + 'duration': 191.933, + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + } + }, + # Contains a SMIL manifest + { + 'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html', + 'info_dict': { + 'id': 'file', + 'ext': 'flv', + 'title': '+ Football: Lottery Champions League Europe', + 'uploader': 'www.telewebion.com', + }, + 'params': { + # rtmpe downloads + 'skip_download': True, + } + }, + # Brightcove URL in single quotes + { + 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/', + 'md5': '4ae374f1f8b91c889c4b9203c8c752af', + 'info_dict': { + 'id': '4255764656001', + 'ext': 'mp4', + 'title': 'SN Presents: Russell Martin, World Citizen', + 'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.', + 'uploader': 'Rogers Sportsnet', + }, + }, + # Dailymotion Cloud video + { + 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910', + 'md5': '49444254273501a64675a7e68c502681', + 'info_dict': { + 'id': '5585de919473990de4bee11b', + 'ext': 'mp4', + 'title': 'Le débat', + 'thumbnail': 're:^https?://.*\.jpe?g$', + } + }, + # OnionStudios embed + { + 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537', + 'info_dict': { + 'id': '2855', + 'ext': 'mp4', + 'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You', + 'thumbnail': 're:^https?://.*\.jpe?g$', + 'uploader': 'ClickHole', + 'uploader_id': 'clickhole', + } + }, + # SnagFilms embed + { + 'url': 'http://whilewewatch.blogspot.ru/2012/06/whilewewatch-whilewewatch-gripping.html', + 'info_dict': { + 'id': '74849a00-85a9-11e1-9660-123139220831', + 'ext': 'mp4', + 'title': '#whilewewatch', + } + }, + # AdobeTVVideo embed + { + 'url': 'https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners', + 'md5': '43662b577c018ad707a63766462b1e87', + 'info_dict': { + 'id': '2456', + 'ext': 'mp4', + 'title': 'New experience with Acrobat DC', + 'description': 'New experience with Acrobat DC', + 'duration': 248.667, + }, + }, + # ScreenwaveMedia embed + { + 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1', + 'md5': '24ace5baba0d35d55c6810b51f34e9e0', + 'info_dict': { + 'id': 'cinemasnob-55d26273809dd', + 'ext': 'mp4', + 'title': 'cinemasnob', + }, + }, + # BrightcoveInPageEmbed embed + { + 'url': 'http://www.geekandsundry.com/tabletop-bonus-wils-final-thoughts-on-dread/', + 'info_dict': { + 'id': '4238694884001', + 'ext': 'flv', + 'title': 'Tabletop: Dread, Last Thoughts', + 'description': 'Tabletop: Dread, Last Thoughts', + 'duration': 51690, + }, + }, + # JWPlayer with M3U8 + { + 'url': 'http://ren.tv/novosti/2015-09-25/sluchaynyy-prohozhiy-poymal-avtougonshchika-v-murmanske-video', + 'info_dict': { + 'id': 'playlist', + 'ext': 'mp4', + 'title': 'Случайный прохожий поймал автоугонщика в Мурманске. ВИДЕО | РЕН ТВ', + 'uploader': 'ren.tv', + }, + 'params': { + # m3u8 downloads + 'skip_download': True, + } + } ] def report_following_redirect(self, new_url): @@ -580,11 +1105,24 @@ class GenericIE(InfoExtractor): playlist_desc_el = doc.find('./channel/description') playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text - entries = [{ - '_type': 'url', - 'url': e.find('link').text, - 'title': e.find('title').text, - } for e in doc.findall('./channel/item')] + entries = [] + for it in doc.findall('./channel/item'): + next_url = xpath_text(it, 'link', fatal=False) + if not next_url: + enclosure_nodes = it.findall('./enclosure') + for e in enclosure_nodes: + next_url = e.attrib.get('url') + if next_url: + break + + if not next_url: + continue + + entries.append({ + '_type': 'url', + 'url': next_url, + 'title': it.find('title').text, + }) return { '_type': 'playlist', @@ -676,7 +1214,7 @@ class GenericIE(InfoExtractor): force_videoid = smuggled_data['force_videoid'] video_id = force_videoid else: - video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] + video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0]) self.to_screen('%s: Requesting header' % video_id) @@ -698,32 +1236,51 @@ class GenericIE(InfoExtractor): full_response = None if head_response is False: - full_response = self._request_webpage(url, video_id) + request = sanitized_Request(url) + request.add_header('Accept-Encoding', '*') + full_response = self._request_webpage(request, video_id) head_response = full_response # Check for direct link to a video content_type = head_response.headers.get('Content-Type', '') - m = re.match(r'^(?Paudio|video|application(?=/ogg$))/(?P.+)$', content_type) + m = re.match(r'^(?Paudio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P.+)$', content_type) if m: upload_date = unified_strdate( head_response.headers.get('Last-Modified')) - return { - 'id': video_id, - 'title': os.path.splitext(url_basename(url))[0], - 'direct': True, - 'formats': [{ + formats = [] + if m.group('format_id').endswith('mpegurl'): + formats = self._extract_m3u8_formats(url, video_id, 'mp4') + else: + formats = [{ 'format_id': m.group('format_id'), 'url': url, 'vcodec': 'none' if m.group('type') == 'audio' else None - }], + }] + return { + 'id': video_id, + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + 'direct': True, + 'formats': formats, 'upload_date': upload_date, } if not self._downloader.params.get('test', False) and not is_intentional: - self._downloader.report_warning('Falling back on generic information extractor.') + force = self._downloader.params.get('force_generic_extractor', False) + self._downloader.report_warning( + '%s on generic information extractor.' % ('Forcing' if force else 'Falling back')) if not full_response: - full_response = self._request_webpage(url, video_id) + request = sanitized_Request(url) + # Some webservers may serve compressed content of rather big size (e.g. gzipped flac) + # making it impossible to download only chunk of the file (yet we need only 512kB to + # test whether it's HTML or not). According to youtube-dl default Accept-Encoding + # that will always result in downloading the whole file that is not desirable. + # Therefore for extraction pass we have to override Accept-Encoding to any in order + # to accept raw bytes and being able to download only a chunk. + # It may probably better to solve this by checking Content-Type for application/octet-stream + # after HEAD request finishes, but not sure if we can rely on this. + request.add_header('Accept-Encoding', '*') + full_response = self._request_webpage(request, video_id) # Maybe it's a direct link to a video? # Be careful not to download the whole thing! @@ -735,7 +1292,7 @@ class GenericIE(InfoExtractor): head_response.headers.get('Last-Modified')) return { 'id': video_id, - 'title': os.path.splitext(url_basename(url))[0], + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), 'direct': True, 'url': url, 'upload_date': upload_date, @@ -746,11 +1303,22 @@ class GenericIE(InfoExtractor): self.report_extraction(video_id) - # Is it an RSS feed? + # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest? try: - doc = parse_xml(webpage) + doc = compat_etree_fromstring(webpage.encode('utf-8')) if doc.tag == 'rss': return self._extract_rss(url, video_id, doc) + elif re.match(r'^(?:{[^}]+})?smil$', doc.tag): + return self._parse_smil(doc, url, video_id) + elif doc.tag == '{http://xspf.org/ns/0/}playlist': + return self.playlist_result(self._parse_xspf(doc, video_id), video_id) + elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): + return { + 'id': video_id, + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + 'formats': self._parse_mpd_formats( + doc, video_id, mpd_base_url=url.rpartition('/')[0]), + } except compat_xml_parse_error: pass @@ -762,7 +1330,7 @@ class GenericIE(InfoExtractor): # Sometimes embedded video player is hidden behind percent encoding # (e.g. https://github.com/rg3/youtube-dl/issues/2448) # Unescaping the whole page allows to handle those cases in a generic way - webpage = compat_urllib_parse.unquote(webpage) + webpage = compat_urllib_parse_unquote(webpage) # it's tempting to parse this further, but you would # have to take into account all the variations like @@ -796,14 +1364,14 @@ class GenericIE(InfoExtractor): return self.playlist_result( urlrs, playlist_id=video_id, playlist_title=video_title) - # Look for BrightCove: - bc_urls = BrightcoveIE._extract_brightcove_urls(webpage) + # Look for Brightcove Legacy Studio embeds + bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage) if bc_urls: self.to_screen('Brightcove video detected.') entries = [{ '_type': 'url', 'url': smuggle_url(bc_url, {'Referer': url}), - 'ie_key': 'Brightcove' + 'ie_key': 'BrightcoveLegacy' } for bc_url in bc_urls] return { @@ -813,25 +1381,27 @@ class GenericIE(InfoExtractor): 'entries': entries, } + # Look for Brightcove New Studio embeds + bc_urls = BrightcoveNewIE._extract_urls(webpage) + if bc_urls: + return _playlist_from_matches(bc_urls, ie='BrightcoveNew') + # Look for embedded rtl.nl player matches = re.findall( - r']+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"', webpage) if matches: return _playlist_from_matches(matches, ie='RtlNl') - # Look for embedded (iframe) Vimeo player - mobj = re.search( - r']+?src=(["\'])(?P(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage) - if mobj: - player_url = unescapeHTML(mobj.group('url')) - surl = smuggle_url(player_url, {'Referer': url}) - return self.url_result(surl) - # Look for embedded (swf embed) Vimeo player - mobj = re.search( - r']+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) - if mobj: - return self.url_result(mobj.group(1)) + vimeo_url = VimeoIE._extract_vimeo_url(url, webpage) + if vimeo_url is not None: + return self.url_result(vimeo_url) + + vid_me_embed_url = self._search_regex( + r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]', + webpage, 'vid.me embed', default=None) + if vid_me_embed_url is not None: + return self.url_result(vid_me_embed_url, 'Vidme') # Look for embedded YouTube player matches = re.findall(r'''(?x) @@ -858,7 +1428,7 @@ class GenericIE(InfoExtractor): # Look for embedded Dailymotion player matches = re.findall( - r']+?src=(["\'])(?P(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage) + r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage) if matches: return _playlist_from_matches( matches, lambda m: unescapeHTML(m[1])) @@ -899,13 +1469,10 @@ class GenericIE(InfoExtractor): 'id': match.group('id') } - # Look for embedded blip.tv player - mobj = re.search(r']*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) - if mobj: - return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV') - mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) - if mobj: - return self.url_result(mobj.group(1), 'BlipTV') + # Look for SVT player + svt_url = SVTIE._extract_url(webpage) + if svt_url: + return self.url_result(svt_url, 'SVT') # Look for embedded condenast player matches = re.findall( @@ -943,12 +1510,26 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url')) + # Look for NYTimes player + mobj = re.search( + r']+src=(["\'])(?P(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url')) + + # Look for Libsyn player + mobj = re.search( + r']+src=(["\'])(?P(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage) + if mobj is not None: + return self.url_result(mobj.group('url')) + # Look for Ooyala videos - mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P[^"&]+)', webpage) or + mobj = (re.search(r'player\.ooyala\.com/[^"?]+[?#][^"]*?(?:embedCode|ec)=(?P[^"&]+)', webpage) or re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P.{32})[\'"]', webpage) or - re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P.{32})[\'"]\)', webpage)) + re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P.{32})[\'"]\)', webpage) or + re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P.{32})[\'"]', webpage)) if mobj is not None: - return OoyalaIE._build_url_result(mobj.group('ec')) + return OoyalaIE._build_url_result(smuggle_url(mobj.group('ec'), {'domain': url})) # Look for multiple Ooyala embeds on SBN network websites mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage) @@ -956,7 +1537,7 @@ class GenericIE(InfoExtractor): embeds = self._parse_json(mobj.group(1), video_id, fatal=False) if embeds: return _playlist_from_matches( - embeds, getter=lambda v: OoyalaIE._url_for_embed_code(v['provider_video_id']), ie='Ooyala') + embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala') # Look for Aparat videos mobj = re.search(r'