mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-01-07 17:16:08 +00:00
45eedbe58c
of the entire page in python 2.
-requires- fixed compat_urllib_parse_unquote
example - the following will save with a mangled playlist title,
instead of the kanji for 'tsunami'. This affects all utf8encoded
urls as well
youtube-dl -f18 -o '%(playlist_title)s-%(title)s.%(ext)s' \
61c14c1e3a/tsunami.html
1723 lines
69 KiB
Python
1723 lines
69 KiB
Python
# encoding: utf-8
|
||
|
||
from __future__ import unicode_literals
|
||
|
||
import os
|
||
import re
|
||
|
||
from .common import InfoExtractor
|
||
from .youtube import YoutubeIE
|
||
from ..compat import (
|
||
compat_urllib_parse,
|
||
compat_urllib_parse_unquote,
|
||
compat_urllib_request,
|
||
compat_urlparse,
|
||
compat_xml_parse_error,
|
||
)
|
||
from ..utils import (
|
||
determine_ext,
|
||
ExtractorError,
|
||
float_or_none,
|
||
HEADRequest,
|
||
is_html,
|
||
orderedSet,
|
||
parse_xml,
|
||
smuggle_url,
|
||
unescapeHTML,
|
||
unified_strdate,
|
||
unsmuggle_url,
|
||
UnsupportedError,
|
||
url_basename,
|
||
xpath_text,
|
||
)
|
||
from .brightcove import BrightcoveIE
|
||
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 .bliptv import BlipTVIE
|
||
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
|
||
|
||
|
||
class GenericIE(InfoExtractor):
|
||
IE_DESC = 'Generic downloader that works on some sites'
|
||
_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',
|
||
}
|
||
},
|
||
# 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,
|
||
}
|
||
},
|
||
{
|
||
'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
|
||
'md5': '85b90ccc9d73b4acd9138d3af4c27f89',
|
||
'info_dict': {
|
||
'id': '13601338388002',
|
||
'ext': 'mp4',
|
||
'uploader': 'www.hodiho.fr',
|
||
'title': 'R\u00e9gis plante sa Jeep',
|
||
}
|
||
},
|
||
# bandcamp page with custom domain
|
||
{
|
||
'add_ie': ['Bandcamp'],
|
||
'url': 'http://bronyrock.com/track/the-pony-mash',
|
||
'info_dict': {
|
||
'id': '3235767654',
|
||
'ext': 'mp3',
|
||
'title': 'The Pony Mash',
|
||
'uploader': 'M_Pallante',
|
||
},
|
||
'skip': 'There is a limit of 200 free downloads / month for the test song',
|
||
},
|
||
# embedded brightcove video
|
||
# it also tests brightcove videos that need to set the 'Referer' in the
|
||
# http requests
|
||
{
|
||
'add_ie': ['Brightcove'],
|
||
'url': 'http://www.bfmtv.com/video/bfmbusiness/cours-bourse/cours-bourse-l-analyse-technique-154522/',
|
||
'info_dict': {
|
||
'id': '2765128793001',
|
||
'ext': 'mp4',
|
||
'title': 'Le cours de bourse : l’analyse technique',
|
||
'description': 'md5:7e9ad046e968cb2d1114004aba466fd9',
|
||
'uploader': 'BFM BUSINESS',
|
||
},
|
||
'params': {
|
||
'skip_download': True,
|
||
},
|
||
},
|
||
{
|
||
# https://github.com/rg3/youtube-dl/issues/2253
|
||
'url': 'http://bcove.me/i6nfkrc3',
|
||
'md5': '0ba9446db037002366bab3b3eb30c88c',
|
||
'info_dict': {
|
||
'id': '3101154703001',
|
||
'ext': 'mp4',
|
||
'title': 'Still no power',
|
||
'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'],
|
||
},
|
||
{
|
||
'url': 'http://www.championat.com/video/football/v/87/87499.html',
|
||
'md5': 'fb973ecf6e4a78a67453647444222983',
|
||
'info_dict': {
|
||
'id': '3414141473001',
|
||
'ext': 'mp4',
|
||
'title': 'Видео. Удаление Дзагоева (ЦСКА)',
|
||
'description': 'Онлайн-трансляция матча ЦСКА - "Волга"',
|
||
'uploader': 'Championat',
|
||
},
|
||
},
|
||
{
|
||
# https://github.com/rg3/youtube-dl/issues/3541
|
||
'add_ie': ['Brightcove'],
|
||
'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1',
|
||
'info_dict': {
|
||
'id': '3866516442001',
|
||
'ext': 'mp4',
|
||
'title': 'Leer mij vrouwen kennen: Aflevering 1',
|
||
'description': 'Leer mij vrouwen kennen: Aflevering 1',
|
||
'uploader': 'SBS Broadcasting',
|
||
},
|
||
'skip': 'Restricted to Netherlands',
|
||
'params': {
|
||
'skip_download': True, # m3u8 download
|
||
},
|
||
},
|
||
# ooyala video
|
||
{
|
||
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
|
||
'md5': '166dd577b433b4d4ebfee10b0824d8ff',
|
||
'info_dict': {
|
||
'id': 'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ',
|
||
'ext': 'mp4',
|
||
'title': '2cc213299525360.mov', # that's what we get
|
||
},
|
||
'add_ie': ['Ooyala'],
|
||
},
|
||
# 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',
|
||
'info_dict': {
|
||
'id': 'national-signing-day-rationalizations-itll-be-ok-itll-be-ok',
|
||
'title': '25 lies you will tell yourself on National Signing Day - SBNation.com',
|
||
},
|
||
'playlist_mincount': 3,
|
||
'params': {
|
||
'skip_download': True,
|
||
},
|
||
'add_ie': ['Ooyala'],
|
||
},
|
||
# embed.ly video
|
||
{
|
||
'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/',
|
||
'info_dict': {
|
||
'id': '9ODmcdjQcHQ',
|
||
'ext': 'mp4',
|
||
'title': 'Tested: Grinding Coffee at 2000 Frames Per Second',
|
||
'upload_date': '20140225',
|
||
'description': 'md5:06a40fbf30b220468f1e0957c0f558ff',
|
||
'uploader': 'Tested',
|
||
'uploader_id': 'testedcom',
|
||
},
|
||
# No need to test YoutubeIE here
|
||
'params': {
|
||
'skip_download': True,
|
||
},
|
||
},
|
||
# funnyordie embed
|
||
{
|
||
'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns',
|
||
'info_dict': {
|
||
'id': '18e820ec3f',
|
||
'ext': 'mp4',
|
||
'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
|
||
'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',
|
||
'info_dict': {
|
||
'id': '776940',
|
||
'ext': 'mp4',
|
||
'title': 'Охотское море стало целиком российским',
|
||
'description': 'md5:5ed62483b14663e2a95ebbe115eb8f43',
|
||
},
|
||
'params': {
|
||
# m3u8 download
|
||
'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/',
|
||
'md5': '65fdff94098e4a607385a60c5177c638',
|
||
'info_dict': {
|
||
'id': '1969',
|
||
'ext': 'mp4',
|
||
'title': 'Hidden miracles of the natural world',
|
||
'uploader': 'Louie Schwartzberg',
|
||
'description': 'md5:8145d19d320ff3e52f28401f4c4283b9',
|
||
}
|
||
},
|
||
# Embeded Ustream video
|
||
{
|
||
'url': 'http://www.american.edu/spa/pti/nsa-privacy-janus-2014.cfm',
|
||
'md5': '27b99cdb639c9b12a79bca876a073417',
|
||
'info_dict': {
|
||
'id': '45734260',
|
||
'ext': 'flv',
|
||
'uploader': 'AU SPA: The NSA and Privacy',
|
||
'title': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman'
|
||
}
|
||
},
|
||
# nowvideo embed hidden behind percent encoding
|
||
{
|
||
'url': 'http://www.waoanime.tv/the-super-dimension-fortress-macross-episode-1/',
|
||
'md5': '2baf4ddd70f697d94b1c18cf796d5107',
|
||
'info_dict': {
|
||
'id': '06e53103ca9aa',
|
||
'ext': 'flv',
|
||
'title': 'Macross Episode 001 Watch Macross Episode 001 onl',
|
||
'description': 'No description',
|
||
},
|
||
},
|
||
# arte embed
|
||
{
|
||
'url': 'http://www.tv-replay.fr/redirection/20-03-14/x-enius-arte-10753389.html',
|
||
'md5': '7653032cbb25bf6c80d80f217055fa43',
|
||
'info_dict': {
|
||
'id': '048195-004_PLUS7-F',
|
||
'ext': 'flv',
|
||
'title': 'X:enius',
|
||
'description': 'md5:d5fdf32ef6613cdbfd516ae658abf168',
|
||
'upload_date': '20140320',
|
||
},
|
||
'params': {
|
||
'skip_download': 'Requires rtmpdump'
|
||
}
|
||
},
|
||
# Condé Nast embed
|
||
{
|
||
'url': 'http://www.wired.com/2014/04/honda-asimo/',
|
||
'md5': 'ba0dfe966fa007657bd1443ee672db0f',
|
||
'info_dict': {
|
||
'id': '53501be369702d3275860000',
|
||
'ext': 'mp4',
|
||
'title': 'Honda’s New Asimo Robot Is More Human Than Ever',
|
||
}
|
||
},
|
||
# Dailymotion embed
|
||
{
|
||
'url': 'http://www.spi0n.com/zap-spi0n-com-n216/',
|
||
'md5': '441aeeb82eb72c422c7f14ec533999cd',
|
||
'info_dict': {
|
||
'id': 'k2mm4bCdJ6CQ2i7c8o2',
|
||
'ext': 'mp4',
|
||
'title': 'Le Zap de Spi0n n°216 - Zapping du Web',
|
||
'uploader': 'Spi0n',
|
||
},
|
||
'add_ie': ['Dailymotion'],
|
||
},
|
||
# YouTube embed
|
||
{
|
||
'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
|
||
'info_dict': {
|
||
'id': 'FXRb4ykk4S0',
|
||
'ext': 'mp4',
|
||
'title': 'The NBL Auction 2014',
|
||
'uploader': 'BADMINTON England',
|
||
'uploader_id': 'BADMINTONEvents',
|
||
'upload_date': '20140603',
|
||
'description': 'md5:9ef128a69f1e262a700ed83edb163a73',
|
||
},
|
||
'add_ie': ['Youtube'],
|
||
'params': {
|
||
'skip_download': True,
|
||
}
|
||
},
|
||
# MTVSercices embed
|
||
{
|
||
'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
|
||
'md5': '35727f82f58c76d996fc188f9755b0d5',
|
||
'info_dict': {
|
||
'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
|
||
'ext': 'mp4',
|
||
'title': 'Review',
|
||
'description': 'Mario\'s life in the fast lane has never looked so good.',
|
||
},
|
||
},
|
||
# YouTube embed via <data-embed-url="">
|
||
{
|
||
'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM',
|
||
'info_dict': {
|
||
'id': '4vAffPZIT44',
|
||
'ext': 'mp4',
|
||
'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!',
|
||
'uploader': 'Gameloft',
|
||
'uploader_id': 'gameloft',
|
||
'upload_date': '20140828',
|
||
'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4',
|
||
},
|
||
'params': {
|
||
'skip_download': True,
|
||
}
|
||
},
|
||
# Camtasia studio
|
||
{
|
||
'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
|
||
'playlist': [{
|
||
'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
|
||
'info_dict': {
|
||
'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
|
||
'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
|
||
'ext': 'flv',
|
||
'duration': 2235.90,
|
||
}
|
||
}, {
|
||
'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
|
||
'info_dict': {
|
||
'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
|
||
'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
|
||
'ext': 'flv',
|
||
'duration': 2235.93,
|
||
}
|
||
}],
|
||
'info_dict': {
|
||
'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
|
||
}
|
||
},
|
||
# Flowplayer
|
||
{
|
||
'url': 'http://www.handjobhub.com/video/busty-blonde-siri-tit-fuck-while-wank-6313.html',
|
||
'md5': '9d65602bf31c6e20014319c7d07fba27',
|
||
'info_dict': {
|
||
'id': '5123ea6d5e5a7',
|
||
'ext': 'mp4',
|
||
'age_limit': 18,
|
||
'uploader': 'www.handjobhub.com',
|
||
'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com',
|
||
}
|
||
},
|
||
# Multiple brightcove videos
|
||
# https://github.com/rg3/youtube-dl/issues/2283
|
||
{
|
||
'url': 'http://www.newyorker.com/online/blogs/newsdesk/2014/01/always-never-nuclear-command-and-control.html',
|
||
'info_dict': {
|
||
'id': 'always-never',
|
||
'title': 'Always / Never - The New Yorker',
|
||
},
|
||
'playlist_count': 3,
|
||
'params': {
|
||
'extract_flat': False,
|
||
'skip_download': True,
|
||
}
|
||
},
|
||
# MLB embed
|
||
{
|
||
'url': 'http://umpire-empire.com/index.php/topic/58125-laz-decides-no-thats-low/',
|
||
'md5': '96f09a37e44da40dd083e12d9a683327',
|
||
'info_dict': {
|
||
'id': '33322633',
|
||
'ext': 'mp4',
|
||
'title': 'Ump changes call to ball',
|
||
'description': 'md5:71c11215384298a172a6dcb4c2e20685',
|
||
'duration': 48,
|
||
'timestamp': 1401537900,
|
||
'upload_date': '20140531',
|
||
'thumbnail': 're:^https?://.*\.jpg$',
|
||
},
|
||
},
|
||
# Wistia embed
|
||
{
|
||
'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
|
||
'md5': '8788b683c777a5cf25621eaf286d0c23',
|
||
'info_dict': {
|
||
'id': '1cfaf6b7ea',
|
||
'ext': 'mov',
|
||
'title': 'md5:51364a8d3d009997ba99656004b5e20d',
|
||
'duration': 643.0,
|
||
'filesize': 182808282,
|
||
'uploader': 'education-portal.com',
|
||
},
|
||
},
|
||
{
|
||
'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz',
|
||
'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4',
|
||
'info_dict': {
|
||
'id': 'uxjb0lwrcz',
|
||
'ext': 'mp4',
|
||
'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks',
|
||
'duration': 1715.0,
|
||
'uploader': 'thoughtworks.wistia.com',
|
||
},
|
||
},
|
||
# Soundcloud embed
|
||
{
|
||
'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/',
|
||
'info_dict': {
|
||
'id': '174391317',
|
||
'ext': 'mp3',
|
||
'description': 'md5:ff867d6b555488ad3c52572bb33d432c',
|
||
'uploader': 'Sophos Security',
|
||
'title': 'Chet Chat 171 - Oct 29, 2014',
|
||
'upload_date': '20141029',
|
||
}
|
||
},
|
||
# Livestream embed
|
||
{
|
||
'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
|
||
'info_dict': {
|
||
'id': '67864563',
|
||
'ext': 'flv',
|
||
'upload_date': '20141112',
|
||
'title': 'Rosetta #CometLanding webcast HL 10',
|
||
}
|
||
},
|
||
# LazyYT
|
||
{
|
||
'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
|
||
'info_dict': {
|
||
'id': '1986',
|
||
'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
|
||
},
|
||
'playlist_mincount': 2,
|
||
},
|
||
# Cinchcast embed
|
||
{
|
||
'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/',
|
||
'info_dict': {
|
||
'id': '7141703',
|
||
'ext': 'mp3',
|
||
'upload_date': '20141126',
|
||
'title': 'Jack Tips: 5 Steps to Permanent Gut Healing',
|
||
}
|
||
},
|
||
# Cinerama player
|
||
{
|
||
'url': 'http://www.abc.net.au/7.30/content/2015/s4164797.htm',
|
||
'info_dict': {
|
||
'id': '730m_DandD_1901_512k',
|
||
'ext': 'mp4',
|
||
'uploader': 'www.abc.net.au',
|
||
'title': 'Game of Thrones with dice - Dungeons and Dragons fantasy role-playing game gets new life - 19/01/2015',
|
||
}
|
||
},
|
||
# embedded viddler video
|
||
{
|
||
'url': 'http://deadspin.com/i-cant-stop-watching-john-wall-chop-the-nuggets-with-th-1681801597',
|
||
'info_dict': {
|
||
'id': '4d03aad9',
|
||
'ext': 'mp4',
|
||
'uploader': 'deadspin',
|
||
'title': 'WALL-TO-GORTAT',
|
||
'timestamp': 1422285291,
|
||
'upload_date': '20150126',
|
||
},
|
||
'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/',
|
||
'info_dict': {
|
||
'id': 'Mrj4DVp2zeA',
|
||
'ext': 'mp4',
|
||
'upload_date': '20150212',
|
||
'uploader': 'The National Archives UK',
|
||
'description': 'md5:a236581cd2449dd2df4f93412f3f01c6',
|
||
'uploader_id': 'NationalArchives08',
|
||
'title': 'Webinar: Using Discovery, The National Archives’ online catalogue',
|
||
},
|
||
},
|
||
# rtl.nl embed
|
||
{
|
||
'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
|
||
'playlist_mincount': 5,
|
||
'info_dict': {
|
||
'id': 'aanslagen-kopenhagen',
|
||
'title': 'Aanslagen Kopenhagen | RTL Nieuws',
|
||
}
|
||
},
|
||
# Zapiks embed
|
||
{
|
||
'url': 'http://www.skipass.com/news/116090-bon-appetit-s5ep3-baqueira-mi-cor.html',
|
||
'info_dict': {
|
||
'id': '118046',
|
||
'ext': 'mp4',
|
||
'title': 'EP3S5 - Bon Appétit - Baqueira Mi Corazon !',
|
||
}
|
||
},
|
||
# Kaltura embed
|
||
{
|
||
'url': 'http://www.monumentalnetwork.com/videos/john-carlson-postgame-2-25-15',
|
||
'info_dict': {
|
||
'id': '1_eergr3h1',
|
||
'ext': 'mp4',
|
||
'upload_date': '20150226',
|
||
'uploader_id': 'MonumentalSports-Kaltura@perfectsensedigital.com',
|
||
'timestamp': int,
|
||
'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',
|
||
},
|
||
},
|
||
# 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$',
|
||
}
|
||
},
|
||
# Ooyala embed
|
||
{
|
||
'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
|
||
'info_dict': {
|
||
'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
|
||
'ext': 'mp4',
|
||
'description': 'VIDEO: Index/Match versus VLOOKUP.',
|
||
'title': 'This is what separates the Excel masters from the wannabes',
|
||
},
|
||
'params': {
|
||
# m3u8 downloads
|
||
'skip_download': True,
|
||
}
|
||
},
|
||
# Contains a SMIL manifest
|
||
{
|
||
'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
|
||
'info_dict': {
|
||
'id': 'file',
|
||
'ext': 'flv',
|
||
'title': '+ Football: Lottery Champions League Europe',
|
||
'uploader': 'www.telewebion.com',
|
||
},
|
||
'params': {
|
||
# rtmpe downloads
|
||
'skip_download': True,
|
||
}
|
||
},
|
||
# Brightcove URL in single quotes
|
||
{
|
||
'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/',
|
||
'md5': '4ae374f1f8b91c889c4b9203c8c752af',
|
||
'info_dict': {
|
||
'id': '4255764656001',
|
||
'ext': 'mp4',
|
||
'title': 'SN Presents: Russell Martin, World Citizen',
|
||
'description': 'To understand why he was the Toronto Blue Jays’ top off-season priority is to appreciate his background and upbringing in Montreal, where he first developed his baseball skills. Written and narrated by Stephen Brunt.',
|
||
'uploader': 'Rogers Sportsnet',
|
||
},
|
||
},
|
||
# Dailymotion Cloud video
|
||
{
|
||
'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910',
|
||
'md5': '49444254273501a64675a7e68c502681',
|
||
'info_dict': {
|
||
'id': '5585de919473990de4bee11b',
|
||
'ext': 'mp4',
|
||
'title': 'Le débat',
|
||
'thumbnail': 're:^https?://.*\.jpe?g$',
|
||
}
|
||
},
|
||
# 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,
|
||
},
|
||
}
|
||
]
|
||
|
||
def report_following_redirect(self, new_url):
|
||
"""Report information extraction."""
|
||
self._downloader.to_screen('[redirect] Following redirect to %s' % new_url)
|
||
|
||
def _extract_rss(self, url, video_id, doc):
|
||
playlist_title = doc.find('./channel/title').text
|
||
playlist_desc_el = doc.find('./channel/description')
|
||
playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
|
||
|
||
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',
|
||
'id': url,
|
||
'title': playlist_title,
|
||
'description': playlist_desc,
|
||
'entries': entries,
|
||
}
|
||
|
||
def _extract_camtasia(self, url, video_id, webpage):
|
||
""" Returns None if no camtasia video can be found. """
|
||
|
||
camtasia_cfg = self._search_regex(
|
||
r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
|
||
webpage, 'camtasia configuration file', default=None)
|
||
if camtasia_cfg is None:
|
||
return None
|
||
|
||
title = self._html_search_meta('DC.title', webpage, fatal=True)
|
||
|
||
camtasia_url = compat_urlparse.urljoin(url, camtasia_cfg)
|
||
camtasia_cfg = self._download_xml(
|
||
camtasia_url, video_id,
|
||
note='Downloading camtasia configuration',
|
||
errnote='Failed to download camtasia configuration')
|
||
fileset_node = camtasia_cfg.find('./playlist/array/fileset')
|
||
|
||
entries = []
|
||
for n in fileset_node.getchildren():
|
||
url_n = n.find('./uri')
|
||
if url_n is None:
|
||
continue
|
||
|
||
entries.append({
|
||
'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
|
||
'title': '%s - %s' % (title, n.tag),
|
||
'url': compat_urlparse.urljoin(url, url_n.text),
|
||
'duration': float_or_none(n.find('./duration').text),
|
||
})
|
||
|
||
return {
|
||
'_type': 'playlist',
|
||
'entries': entries,
|
||
'title': title,
|
||
}
|
||
|
||
def _real_extract(self, url):
|
||
if url.startswith('//'):
|
||
return {
|
||
'_type': 'url',
|
||
'url': self.http_scheme() + url,
|
||
}
|
||
|
||
parsed_url = compat_urlparse.urlparse(url)
|
||
if not parsed_url.scheme:
|
||
default_search = self._downloader.params.get('default_search')
|
||
if default_search is None:
|
||
default_search = 'fixup_error'
|
||
|
||
if default_search in ('auto', 'auto_warning', 'fixup_error'):
|
||
if '/' in url:
|
||
self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
|
||
return self.url_result('http://' + url)
|
||
elif default_search != 'fixup_error':
|
||
if default_search == 'auto_warning':
|
||
if re.match(r'^(?:url|URL)$', url):
|
||
raise ExtractorError(
|
||
'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url,
|
||
expected=True)
|
||
else:
|
||
self._downloader.report_warning(
|
||
'Falling back to youtube search for %s . Set --default-search "auto" to suppress this warning.' % url)
|
||
return self.url_result('ytsearch:' + url)
|
||
|
||
if default_search in ('error', 'fixup_error'):
|
||
raise ExtractorError(
|
||
'%r is not a valid URL. '
|
||
'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube'
|
||
% (url, url), expected=True)
|
||
else:
|
||
if ':' not in default_search:
|
||
default_search += ':'
|
||
return self.url_result(default_search + url)
|
||
|
||
url, smuggled_data = unsmuggle_url(url)
|
||
force_videoid = None
|
||
is_intentional = smuggled_data and smuggled_data.get('to_generic')
|
||
if smuggled_data and 'force_videoid' in smuggled_data:
|
||
force_videoid = smuggled_data['force_videoid']
|
||
video_id = force_videoid
|
||
else:
|
||
video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
|
||
|
||
self.to_screen('%s: Requesting header' % video_id)
|
||
|
||
head_req = HEADRequest(url)
|
||
head_response = self._request_webpage(
|
||
head_req, video_id,
|
||
note=False, errnote='Could not send HEAD request to %s' % url,
|
||
fatal=False)
|
||
|
||
if head_response is not False:
|
||
# Check for redirect
|
||
new_url = head_response.geturl()
|
||
if url != new_url:
|
||
self.report_following_redirect(new_url)
|
||
if force_videoid:
|
||
new_url = smuggle_url(
|
||
new_url, {'force_videoid': force_videoid})
|
||
return self.url_result(new_url)
|
||
|
||
full_response = None
|
||
if head_response is False:
|
||
request = compat_urllib_request.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'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type)
|
||
if m:
|
||
upload_date = unified_strdate(
|
||
head_response.headers.get('Last-Modified'))
|
||
return {
|
||
'id': video_id,
|
||
'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
|
||
'direct': True,
|
||
'formats': [{
|
||
'format_id': m.group('format_id'),
|
||
'url': url,
|
||
'vcodec': 'none' if m.group('type') == 'audio' else None
|
||
}],
|
||
'upload_date': upload_date,
|
||
}
|
||
|
||
if not self._downloader.params.get('test', False) and not is_intentional:
|
||
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:
|
||
request = compat_urllib_request.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!
|
||
first_bytes = full_response.read(512)
|
||
if not is_html(first_bytes):
|
||
self._downloader.report_warning(
|
||
'URL could be a direct video link, returning it as such.')
|
||
upload_date = unified_strdate(
|
||
head_response.headers.get('Last-Modified'))
|
||
return {
|
||
'id': video_id,
|
||
'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]),
|
||
'direct': True,
|
||
'url': url,
|
||
'upload_date': upload_date,
|
||
}
|
||
|
||
webpage = self._webpage_read_content(
|
||
full_response, url, video_id, prefix=first_bytes)
|
||
|
||
self.report_extraction(video_id)
|
||
|
||
# Is it an RSS feed?
|
||
try:
|
||
doc = parse_xml(webpage)
|
||
if doc.tag == 'rss':
|
||
return self._extract_rss(url, video_id, doc)
|
||
except compat_xml_parse_error:
|
||
pass
|
||
|
||
# Is it a Camtasia project?
|
||
camtasia_res = self._extract_camtasia(url, video_id, webpage)
|
||
if camtasia_res is not None:
|
||
return camtasia_res
|
||
|
||
# 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)
|
||
|
||
# it's tempting to parse this further, but you would
|
||
# have to take into account all the variations like
|
||
# Video Title - Site Name
|
||
# Site Name | Video Title
|
||
# Video Title - Tagline | Site Name
|
||
# and so on and so forth; it's just not practical
|
||
video_title = self._html_search_regex(
|
||
r'(?s)<title>(.*?)</title>', webpage, 'video title',
|
||
default='video')
|
||
|
||
# Try to detect age limit automatically
|
||
age_limit = self._rta_search(webpage)
|
||
# And then there are the jokers who advertise that they use RTA,
|
||
# but actually don't.
|
||
AGE_LIMIT_MARKERS = [
|
||
r'Proudly Labeled <a href="http://www.rtalabel.org/" title="Restricted to Adults">RTA</a>',
|
||
]
|
||
if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
|
||
age_limit = 18
|
||
|
||
# video uploader is domain name
|
||
video_uploader = self._search_regex(
|
||
r'^(?:https?://)?([^/]*)/.*', url, 'video uploader')
|
||
|
||
# Helper method
|
||
def _playlist_from_matches(matches, getter=None, ie=None):
|
||
urlrs = orderedSet(
|
||
self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
|
||
for m in matches)
|
||
return self.playlist_result(
|
||
urlrs, playlist_id=video_id, playlist_title=video_title)
|
||
|
||
# Look for BrightCove:
|
||
bc_urls = BrightcoveIE._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'
|
||
} for bc_url in bc_urls]
|
||
|
||
return {
|
||
'_type': 'playlist',
|
||
'title': video_title,
|
||
'id': video_id,
|
||
'entries': entries,
|
||
}
|
||
|
||
# Look for embedded rtl.nl player
|
||
matches = re.findall(
|
||
r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
|
||
webpage)
|
||
if matches:
|
||
return _playlist_from_matches(matches, ie='RtlNl')
|
||
|
||
vimeo_url = VimeoIE._extract_vimeo_url(url, webpage)
|
||
if vimeo_url is not None:
|
||
return self.url_result(vimeo_url)
|
||
|
||
# Look for embedded YouTube player
|
||
matches = re.findall(r'''(?x)
|
||
(?:
|
||
<iframe[^>]+?src=|
|
||
data-video-url=|
|
||
<embed[^>]+?src=|
|
||
embedSWF\(?:\s*|
|
||
new\s+SWFObject\(
|
||
)
|
||
(["\'])
|
||
(?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
|
||
(?:embed|v|p)/.+?)
|
||
\1''', webpage)
|
||
if matches:
|
||
return _playlist_from_matches(
|
||
matches, lambda m: unescapeHTML(m[1]))
|
||
|
||
# Look for lazyYT YouTube embed
|
||
matches = re.findall(
|
||
r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
|
||
if matches:
|
||
return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
|
||
|
||
# Look for embedded Dailymotion player
|
||
matches = re.findall(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/embed/video/.+?)\1', webpage)
|
||
if matches:
|
||
return _playlist_from_matches(
|
||
matches, lambda m: unescapeHTML(m[1]))
|
||
|
||
# Look for embedded Dailymotion playlist player (#3822)
|
||
m = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage)
|
||
if m:
|
||
playlists = re.findall(
|
||
r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
|
||
if playlists:
|
||
return _playlist_from_matches(
|
||
playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
|
||
|
||
# Look for embedded Wistia player
|
||
match = re.search(
|
||
r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
|
||
if match:
|
||
embed_url = self._proto_relative_url(
|
||
unescapeHTML(match.group('url')))
|
||
return {
|
||
'_type': 'url_transparent',
|
||
'url': embed_url,
|
||
'ie_key': 'Wistia',
|
||
'uploader': video_uploader,
|
||
'title': video_title,
|
||
'id': video_id,
|
||
}
|
||
|
||
match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
|
||
if match:
|
||
return {
|
||
'_type': 'url_transparent',
|
||
'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
|
||
'ie_key': 'Wistia',
|
||
'uploader': video_uploader,
|
||
'title': video_title,
|
||
'id': match.group('id')
|
||
}
|
||
|
||
# Look for embedded blip.tv player
|
||
bliptv_url = BlipTVIE._extract_url(webpage)
|
||
if bliptv_url:
|
||
return self.url_result(bliptv_url, '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(
|
||
r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
|
||
webpage)
|
||
if matches:
|
||
return {
|
||
'_type': 'playlist',
|
||
'entries': [{
|
||
'_type': 'url',
|
||
'ie_key': 'CondeNast',
|
||
'url': ma,
|
||
} for ma in matches],
|
||
'title': video_title,
|
||
'id': video_id,
|
||
}
|
||
|
||
# Look for Bandcamp pages with custom domain
|
||
mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
|
||
if mobj is not None:
|
||
burl = unescapeHTML(mobj.group(1))
|
||
# Don't set the extractor because it can be a track url or an album
|
||
return self.url_result(burl)
|
||
|
||
# Look for embedded Vevo player
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:cache\.)?vevo\.com/.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'))
|
||
|
||
# Look for embedded Viddler player
|
||
mobj = re.search(
|
||
r'<(?:iframe[^>]+?src|param[^>]+?value)=(["\'])(?P<url>(?:https?:)?//(?:www\.)?viddler\.com/(?:embed|player)/.+?)\1',
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'))
|
||
|
||
# Look for NYTimes player
|
||
mobj = re.search(
|
||
r'<iframe[^>]+src=(["\'])(?P<url>(?: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'<iframe[^>]+src=(["\'])(?P<url>(?: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<ec>[^"&]+)', webpage) or
|
||
re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
|
||
re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
|
||
re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
|
||
if mobj is not None:
|
||
return OoyalaIE._build_url_result(mobj.group('ec'))
|
||
|
||
# Look for multiple Ooyala embeds on SBN network websites
|
||
mobj = re.search(r'SBN\.VideoLinkset\.entryGroup\((\[.*?\])', webpage)
|
||
if mobj is not None:
|
||
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')
|
||
|
||
# Look for Aparat videos
|
||
mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group(1), 'Aparat')
|
||
|
||
# Look for MPORA videos
|
||
mobj = re.search(r'<iframe .*?src="(http://mpora\.(?:com|de)/videos/[^"]+)"', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group(1), 'Mpora')
|
||
|
||
# Look for embedded NovaMov-based player
|
||
mobj = re.search(
|
||
r'''(?x)<(?:pagespeed_)?iframe[^>]+?src=(["\'])
|
||
(?P<url>http://(?:(?:embed|www)\.)?
|
||
(?:novamov\.com|
|
||
nowvideo\.(?:ch|sx|eu|at|ag|co)|
|
||
videoweed\.(?:es|com)|
|
||
movshare\.(?:net|sx|ag)|
|
||
divxstage\.(?:eu|net|ch|co|at|ag))
|
||
/embed\.php.+?)\1''', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'))
|
||
|
||
# Look for embedded Facebook player
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>https://www\.facebook\.com/video/embed.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Facebook')
|
||
|
||
# Look for embedded VK player
|
||
mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'VK')
|
||
|
||
# Look for embedded ivi player
|
||
mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Ivi')
|
||
|
||
# Look for embedded Huffington Post player
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed\.live\.huffingtonpost\.com/.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'HuffPost')
|
||
|
||
# Look for embed.ly
|
||
mobj = re.search(r'class=["\']embedly-card["\'][^>]href=["\'](?P<url>[^"\']+)', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'))
|
||
mobj = re.search(r'class=["\']embedly-embed["\'][^>]src=["\'][^"\']*url=(?P<url>[^&]+)', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(compat_urllib_parse.unquote(mobj.group('url')))
|
||
|
||
# Look for funnyordie embed
|
||
matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
|
||
if matches:
|
||
return _playlist_from_matches(
|
||
matches, getter=unescapeHTML, ie='FunnyOrDie')
|
||
|
||
# Look for BBC iPlayer embed
|
||
matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
|
||
if matches:
|
||
return _playlist_from_matches(matches, ie='BBCCoUk')
|
||
|
||
# Look for embedded RUTV player
|
||
rutv_url = RUTVIE._extract_url(webpage)
|
||
if rutv_url:
|
||
return self.url_result(rutv_url, 'RUTV')
|
||
|
||
# Look for embedded TVC player
|
||
tvc_url = TVCIE._extract_url(webpage)
|
||
if tvc_url:
|
||
return self.url_result(tvc_url, 'TVC')
|
||
|
||
# Look for embedded SportBox player
|
||
sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
|
||
if sportbox_urls:
|
||
return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
|
||
|
||
# Look for embedded PornHub player
|
||
pornhub_url = PornHubIE._extract_url(webpage)
|
||
if pornhub_url:
|
||
return self.url_result(pornhub_url, 'PornHub')
|
||
|
||
# Look for embedded XHamster player
|
||
xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
|
||
if xhamster_urls:
|
||
return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
|
||
|
||
# Look for embedded Tvigle player
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Tvigle')
|
||
|
||
# Look for embedded TED player
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'TED')
|
||
|
||
# Look for embedded Ustream videos
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>http://www\.ustream\.tv/embed/.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Ustream')
|
||
|
||
# Look for embedded arte.tv player
|
||
mobj = re.search(
|
||
r'<script [^>]*?src="(?P<url>http://www\.arte\.tv/playerv2/embed[^"]+)"',
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'ArteTVEmbed')
|
||
|
||
# Look for embedded smotri.com player
|
||
smotri_url = SmotriIE._extract_url(webpage)
|
||
if smotri_url:
|
||
return self.url_result(smotri_url, 'Smotri')
|
||
|
||
# Look for embedded Myvi.ru player
|
||
myvi_url = MyviIE._extract_url(webpage)
|
||
if myvi_url:
|
||
return self.url_result(myvi_url)
|
||
|
||
# Look for embeded soundcloud player
|
||
mobj = re.search(
|
||
r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
|
||
webpage)
|
||
if mobj is not None:
|
||
url = unescapeHTML(mobj.group('url'))
|
||
return self.url_result(url)
|
||
|
||
# Look for embedded vulture.com player
|
||
mobj = re.search(
|
||
r'<iframe src="(?P<url>https?://video\.vulture\.com/[^"]+)"',
|
||
webpage)
|
||
if mobj is not None:
|
||
url = unescapeHTML(mobj.group('url'))
|
||
return self.url_result(url, ie='Vulture')
|
||
|
||
# Look for embedded mtvservices player
|
||
mobj = re.search(
|
||
r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
|
||
webpage)
|
||
if mobj is not None:
|
||
url = unescapeHTML(mobj.group('url'))
|
||
return self.url_result(url, ie='MTVServicesEmbedded')
|
||
|
||
# Look for embedded yahoo player
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1',
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Yahoo')
|
||
|
||
# Look for embedded sbs.com.au player
|
||
mobj = re.search(
|
||
r'''(?x)
|
||
(?:
|
||
<meta\s+property="og:video"\s+content=|
|
||
<iframe[^>]+?src=
|
||
)
|
||
(["\'])(?P<url>https?://(?:www\.)?sbs\.com\.au/ondemand/video/.+?)\1''',
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'SBS')
|
||
|
||
# Look for embedded Cinchcast player
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1',
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Cinchcast')
|
||
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1',
|
||
webpage)
|
||
if not mobj:
|
||
mobj = re.search(
|
||
r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'MLB')
|
||
|
||
mobj = re.search(
|
||
r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL,
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast')
|
||
|
||
mobj = re.search(
|
||
r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"',
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Livestream')
|
||
|
||
# Look for Zapiks embed
|
||
mobj = re.search(
|
||
r'<iframe[^>]+src="(?P<url>https?://(?:www\.)?zapiks\.fr/index\.php\?.+?)"', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Zapiks')
|
||
|
||
# Look for Kaltura embeds
|
||
mobj = (re.search(r"(?s)kWidget\.(?:thumb)?[Ee]mbed\(\{.*?'wid'\s*:\s*'_?(?P<partner_id>[^']+)',.*?'entry_id'\s*:\s*'(?P<id>[^']+)',", webpage) or
|
||
re.search(r'(?s)(["\'])(?:https?:)?//cdnapisec\.kaltura\.com/.*?(?:p|partner_id)/(?P<partner_id>\d+).*?\1.*?entry_id\s*:\s*(["\'])(?P<id>[^\2]+?)\2', webpage))
|
||
if mobj is not None:
|
||
return self.url_result('kaltura:%(partner_id)s:%(id)s' % mobj.groupdict(), 'Kaltura')
|
||
|
||
# Look for Eagle.Platform embeds
|
||
mobj = re.search(
|
||
r'<iframe[^>]+src="(?P<url>https?://.+?\.media\.eagleplatform\.com/index/player\?.+?)"', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'EaglePlatform')
|
||
|
||
# Look for ClipYou (uses Eagle.Platform) embeds
|
||
mobj = re.search(
|
||
r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
|
||
if mobj is not None:
|
||
return self.url_result('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), 'EaglePlatform')
|
||
|
||
# Look for Pladform embeds
|
||
mobj = re.search(
|
||
r'<iframe[^>]+src="(?P<url>https?://out\.pladform\.ru/player\?.+?)"', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'), 'Pladform')
|
||
|
||
# Look for Playwire embeds
|
||
mobj = re.search(
|
||
r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'))
|
||
|
||
# Look for 5min embeds
|
||
mobj = re.search(
|
||
r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
|
||
if mobj is not None:
|
||
return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
|
||
|
||
# Look for Crooks and Liars embeds
|
||
mobj = re.search(
|
||
r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
|
||
if mobj is not None:
|
||
return self.url_result(mobj.group('url'))
|
||
|
||
# Look for NBC Sports VPlayer embeds
|
||
nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
|
||
if nbc_sports_url:
|
||
return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
|
||
|
||
# Look for UDN embeds
|
||
mobj = re.search(
|
||
r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
|
||
if mobj is not None:
|
||
return self.url_result(
|
||
compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
|
||
|
||
# Look for Senate ISVP iframe
|
||
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
|
||
if senate_isvp_url:
|
||
return self.url_result(senate_isvp_url, 'SenateISVP')
|
||
|
||
# Look for Dailymotion Cloud videos
|
||
dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
|
||
if dmcloud_url:
|
||
return self.url_result(dmcloud_url, 'DailymotionCloud')
|
||
|
||
# Look for OnionStudios embeds
|
||
onionstudios_url = OnionStudiosIE._extract_url(webpage)
|
||
if onionstudios_url:
|
||
return self.url_result(onionstudios_url)
|
||
|
||
# Look for SnagFilms embeds
|
||
snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
|
||
if snagfilms_url:
|
||
return self.url_result(snagfilms_url)
|
||
|
||
# Look for AdobeTVVideo embeds
|
||
mobj = re.search(
|
||
r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]',
|
||
webpage)
|
||
if mobj is not None:
|
||
return self.url_result(
|
||
self._proto_relative_url(unescapeHTML(mobj.group(1))),
|
||
'AdobeTVVideo')
|
||
|
||
def check_video(vurl):
|
||
if YoutubeIE.suitable(vurl):
|
||
return True
|
||
vpath = compat_urlparse.urlparse(vurl).path
|
||
vext = determine_ext(vpath)
|
||
return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml')
|
||
|
||
def filter_video(urls):
|
||
return list(filter(check_video, urls))
|
||
|
||
# Start with something easy: JW Player in SWFObject
|
||
found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage))
|
||
if not found:
|
||
# Look for gorilla-vid style embedding
|
||
found = filter_video(re.findall(r'''(?sx)
|
||
(?:
|
||
jw_plugins|
|
||
JWPlayerOptions|
|
||
jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup
|
||
)
|
||
.*?
|
||
['"]?file['"]?\s*:\s*["\'](.*?)["\']''', webpage))
|
||
if not found:
|
||
# Broaden the search a little bit
|
||
found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage))
|
||
if not found:
|
||
# Broaden the findall a little bit: JWPlayer JS loader
|
||
found = filter_video(re.findall(
|
||
r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage))
|
||
if not found:
|
||
# Flow player
|
||
found = filter_video(re.findall(r'''(?xs)
|
||
flowplayer\("[^"]+",\s*
|
||
\{[^}]+?\}\s*,
|
||
\s*\{[^}]+? ["']?clip["']?\s*:\s*\{\s*
|
||
["']?url["']?\s*:\s*["']([^"']+)["']
|
||
''', webpage))
|
||
if not found:
|
||
# Cinerama player
|
||
found = re.findall(
|
||
r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
|
||
if not found:
|
||
# Try to find twitter cards info
|
||
found = filter_video(re.findall(
|
||
r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
|
||
if not found:
|
||
# We look for Open Graph info:
|
||
# We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am)
|
||
m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage)
|
||
# We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
|
||
if m_video_type is not None:
|
||
found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))
|
||
if not found:
|
||
# HTML5 video
|
||
found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
|
||
if not found:
|
||
REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
|
||
found = re.search(
|
||
r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
|
||
r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
|
||
webpage)
|
||
if not found:
|
||
# Look also in Refresh HTTP header
|
||
refresh_header = head_response.headers.get('Refresh')
|
||
if refresh_header:
|
||
found = re.search(REDIRECT_REGEX, refresh_header)
|
||
if found:
|
||
new_url = compat_urlparse.urljoin(url, found.group(1))
|
||
self.report_following_redirect(new_url)
|
||
return {
|
||
'_type': 'url',
|
||
'url': new_url,
|
||
}
|
||
if not found:
|
||
raise UnsupportedError(url)
|
||
|
||
entries = []
|
||
for video_url in found:
|
||
video_url = compat_urlparse.urljoin(url, video_url)
|
||
video_id = compat_urllib_parse.unquote(os.path.basename(video_url))
|
||
|
||
# Sometimes, jwplayer extraction will result in a YouTube URL
|
||
if YoutubeIE.suitable(video_url):
|
||
entries.append(self.url_result(video_url, 'Youtube'))
|
||
continue
|
||
|
||
# here's a fun little line of code for you:
|
||
video_id = os.path.splitext(video_id)[0]
|
||
|
||
if determine_ext(video_url) == 'smil':
|
||
entries.append({
|
||
'id': video_id,
|
||
'formats': self._extract_smil_formats(video_url, video_id),
|
||
'uploader': video_uploader,
|
||
'title': video_title,
|
||
'age_limit': age_limit,
|
||
})
|
||
else:
|
||
entries.append({
|
||
'id': video_id,
|
||
'url': video_url,
|
||
'uploader': video_uploader,
|
||
'title': video_title,
|
||
'age_limit': age_limit,
|
||
})
|
||
|
||
if len(entries) == 1:
|
||
return entries[0]
|
||
else:
|
||
for num, e in enumerate(entries, start=1):
|
||
# 'url' results don't have a title
|
||
if e.get('title') is not None:
|
||
e['title'] = '%s (%d)' % (e['title'], num)
|
||
return {
|
||
'_type': 'playlist',
|
||
'entries': entries,
|
||
}
|