Aidan Rowe
mutantmonkey
Ben Congdon
+Kacper Michajłow
+José Joaquín Atria
+Viťas Strádal
PYTHON ?= /usr/bin/env python
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
-ifeq ($(PREFIX),/usr)
- SYSCONFDIR=/etc
-else
- ifeq ($(PREFIX),/usr/local)
- SYSCONFDIR=/etc
- else
- SYSCONFDIR=$(PREFIX)/etc
- endif
-endif
+SYSCONFDIR != if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
install -d $(DESTDIR)$(BINDIR)
If you want to create a build of youtube-dl yourself, you'll need
* python
-* make
+* make (both GNU make and BSD make are supported)
* pandoc
* zip
* nosetests
#!/usr/bin/env python
+# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
response = ydl.urlopen(req).read().decode('utf-8')
self.assertEqual(response, 'cn: {0}'.format(url))
+ def test_proxy_with_idn(self):
+ ydl = YoutubeDL({
+ 'proxy': 'localhost:{0}'.format(self.port),
+ })
+ url = 'http://中文.tw/'
+ response = ydl.urlopen(url).read().decode('utf-8')
+ # b'xn--fiq228c' is '中文'.encode('idna')
+ self.assertEqual(response, 'normal: http://xn--fiq228c.tw/')
+
if __name__ == '__main__':
unittest.main()
passenv = HOME
defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
--exclude test_subtitles.py --exclude test_write_annotations.py
- --exclude test_youtube_lists.py
+ --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py
commands = nosetests --verbose {posargs:{[testenv]defaultargs}} # --with-coverage --cover-package=youtube_dl --cover-html
# test.test_download:TestDownload.test_NowVideo
if fdict.get('language'):
if res:
res += ' '
- res += '[%s]' % fdict['language']
+ res += '[%s] ' % fdict['language']
if fdict.get('format_note') is not None:
res += fdict['format_note'] + ' '
if fdict.get('tbr') is not None:
from .bigflix import BigflixIE
from .bild import BildIE
from .bilibili import BiliBiliIE
+from .biobiochiletv import BioBioChileTVIE
from .bleacherreport import (
BleacherReportIE,
BleacherReportCMSIE,
)
from .cbssports import CBSSportsIE
from .ccc import CCCIE
+from .cda import CDAIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .chaturbate import ChaturbateIE
OoyalaIE,
OoyalaExternalIE,
)
+from .openload import OpenloadIE
from .ora import OraTVIE
from .orf import (
ORFTVthekIE,
from .sandia import SandiaIE
from .safari import (
SafariIE,
+ SafariApiIE,
SafariCourseIE,
)
from .sapo import SapoIE
ThePlatformIE,
ThePlatformFeedIE,
)
+from .thescene import TheSceneIE
from .thesixtyone import TheSixtyOneIE
from .thestar import TheStarIE
from .thisamericanlife import ThisAmericanLifeIE
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
- _VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
+ _VALID_URL = r'https?://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
class AddAnimeIE(InfoExtractor):
- _VALID_URL = r'http://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
+ _VALID_URL = r'https?://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
_TESTS = [{
'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
'md5': '72954ea10bc979ab5e2eb288b21425a0',
class AftonbladetIE(InfoExtractor):
- _VALID_URL = r'http://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
'info_dict': {
class AlJazeeraIE(InfoExtractor):
- _VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
+ _VALID_URL = r'https?://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
_TEST = {
'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
import re
from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+ compat_urlparse,
+ compat_str,
+)
from ..utils import (
determine_ext,
encode_dict,
+ extract_attributes,
ExtractorError,
sanitized_Request,
urlencode_postdata,
# Episodes without titles
'url': 'https://www.anime-on-demand.de/anime/162',
'only_matching': True,
+ }, {
+ # ger/jap, Dub/OmU, account required
+ 'url': 'https://www.anime-on-demand.de/anime/169',
+ 'only_matching': True,
}]
def _login(self):
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
+ if '>Our licensing terms allow the distribution of animes only to German-speaking countries of Europe' in login_page:
+ self.raise_geo_restricted(
+ '%s is only available in German-speaking countries of Europe' % self.IE_NAME)
+
login_form = self._form_hidden_inputs('new_user', login_page)
login_form.update({
formats = []
- playlist_url = self._search_regex(
- r'data-playlist=(["\'])(?P<url>.+?)\1',
- episode_html, 'data playlist', default=None, group='url')
- if playlist_url:
- request = sanitized_Request(
- compat_urlparse.urljoin(url, playlist_url),
- headers={
- 'X-Requested-With': 'XMLHttpRequest',
- 'X-CSRF-Token': csrf_token,
- 'Referer': url,
- 'Accept': 'application/json, text/javascript, */*; q=0.01',
- })
-
- playlist = self._download_json(
- request, video_id, 'Downloading playlist JSON', fatal=False)
- if playlist:
- playlist = playlist['playlist'][0]
- title = playlist['title']
+ for input_ in re.findall(
+ r'<input[^>]+class=["\'].*?streamstarter_html5[^>]+>', episode_html):
+ attributes = extract_attributes(input_)
+ playlist_urls = []
+ for playlist_key in ('data-playlist', 'data-otherplaylist'):
+ playlist_url = attributes.get(playlist_key)
+ if isinstance(playlist_url, compat_str) and re.match(
+ r'/?[\da-zA-Z]+', playlist_url):
+ playlist_urls.append(attributes[playlist_key])
+ if not playlist_urls:
+ continue
+
+ lang = attributes.get('data-lang')
+ lang_note = attributes.get('value')
+
+ for playlist_url in playlist_urls:
+ kind = self._search_regex(
+ r'videomaterialurl/\d+/([^/]+)/',
+ playlist_url, 'media kind', default=None)
+ format_id_list = []
+ if lang:
+ format_id_list.append(lang)
+ if kind:
+ format_id_list.append(kind)
+ if not format_id_list:
+ format_id_list.append(compat_str(num))
+ format_id = '-'.join(format_id_list)
+ format_note = ', '.join(filter(None, (kind, lang_note)))
+ request = sanitized_Request(
+ compat_urlparse.urljoin(url, playlist_url),
+ headers={
+ 'X-Requested-With': 'XMLHttpRequest',
+ 'X-CSRF-Token': csrf_token,
+ 'Referer': url,
+ 'Accept': 'application/json, text/javascript, */*; q=0.01',
+ })
+ playlist = self._download_json(
+ request, video_id, 'Downloading %s playlist JSON' % format_id,
+ fatal=False)
+ if not playlist:
+ continue
+ start_video = playlist.get('startvideo', 0)
+ playlist = playlist.get('playlist')
+ if not playlist or not isinstance(playlist, list):
+ continue
+ playlist = playlist[start_video]
+ title = playlist.get('title')
+ if not title:
+ continue
description = playlist.get('description')
for source in playlist.get('sources', []):
file_ = source.get('file')
- if file_ and determine_ext(file_) == 'm3u8':
- formats = self._extract_m3u8_formats(
+ if not file_:
+ continue
+ ext = determine_ext(file_)
+ format_id_list = [lang, kind]
+ if ext == 'm3u8':
+ format_id_list.append('hls')
+ elif source.get('type') == 'video/dash' or ext == 'mpd':
+ format_id_list.append('dash')
+ format_id = '-'.join(filter(None, format_id_list))
+ if ext == 'm3u8':
+ file_formats = self._extract_m3u8_formats(
file_, video_id, 'mp4',
- entry_protocol='m3u8_native', m3u8_id='hls')
+ entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False)
+ elif source.get('type') == 'video/dash' or ext == 'mpd':
+ continue
+ file_formats = self._extract_mpd_formats(
+ file_, video_id, mpd_id=format_id, fatal=False)
+ else:
+ continue
+ for f in file_formats:
+ f.update({
+ 'language': lang,
+ 'format_note': format_note,
+ })
+ formats.extend(file_formats)
if formats:
+ self._sort_formats(formats)
f = common_info.copy()
f.update({
'title': title,
})
entries.append(f)
- m = re.search(
- r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
- episode_html)
- if m:
- f = common_info.copy()
- f.update({
- 'id': '%s-teaser' % f['id'],
- 'title': m.group('title'),
- 'url': compat_urlparse.urljoin(url, m.group('href')),
- })
- entries.append(f)
+ # Extract teaser only when full episode is not available
+ if not formats:
+ m = re.search(
+ r'data-dialog-header=(["\'])(?P<title>.+?)\1[^>]+href=(["\'])(?P<href>.+?)\3[^>]*>Teaser<',
+ episode_html)
+ if m:
+ f = common_info.copy()
+ f.update({
+ 'id': '%s-teaser' % f['id'],
+ 'title': m.group('title'),
+ 'url': compat_urlparse.urljoin(url, m.group('href')),
+ })
+ entries.append(f)
return self.playlist_result(entries, anime_id, anime_title, anime_description)
class AolIE(InfoExtractor):
IE_NAME = 'on.aol.com'
- _VALID_URL = r'(?:aol-video:|http://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)'
+ _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/video/.*-)(?P<id>[0-9]+)(?:$|\?)'
_TESTS = [{
'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
class AolFeaturesIE(InfoExtractor):
IE_NAME = 'features.aol.com'
- _VALID_URL = r'http://features\.aol\.com/video/(?P<id>[^/?#]+)'
+ _VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
class ArteTvIE(InfoExtractor):
- _VALID_URL = r'http://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
+ _VALID_URL = r'https?://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
IE_NAME = 'arte.tv'
def _real_extract(self, url):
class AzubuLiveIE(InfoExtractor):
- _VALID_URL = r'http://www.azubu.tv/(?P<id>[^/]+)$'
+ _VALID_URL = r'https?://www.azubu.tv/(?P<id>[^/]+)$'
_TEST = {
'url': 'http://www.azubu.tv/MarsTVMDLen',
class BaiduVideoIE(InfoExtractor):
IE_DESC = '百度视频'
- _VALID_URL = r'http://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
+ _VALID_URL = r'https?://v\.baidu\.com/(?P<type>[a-z]+)/(?P<id>\d+)\.htm'
_TESTS = [{
'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6',
'info_dict': {
class BBCCoUkArticleIE(InfoExtractor):
- _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+ _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
IE_NAME = 'bbc.co.uk:article'
IE_DESC = 'BBC articles'
class BehindKinkIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
+ _VALID_URL = r'https?://(?:www\.)?behindkink\.com/(?P<year>[0-9]{4})/(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<id>[^/#?_]+)'
_TEST = {
'url': 'http://www.behindkink.com/2014/12/05/what-are-you-passionate-about-marley-blaze/',
'md5': '507b57d8fdcd75a41a9a7bdb7989c762',
class BiliBiliIE(InfoExtractor):
- _VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
+ _VALID_URL = r'http
s?://www\.bilibili\.(?:tv|com)/video/av(?P<id>\d+)(?:/index_(?P<page_num>\d+).html)?'
_TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import remove_end
+
+
+class BioBioChileTVIE(InfoExtractor):
+ _VALID_URL = r'https?://tv\.biobiochile\.cl/notas/(?:[^/]+/)+(?P<id>[^/]+)\.shtml'
+
+ _TESTS = [{
+ 'url': 'http://tv.biobiochile.cl/notas/2015/10/21/sobre-camaras-y-camarillas-parlamentarias.shtml',
+ 'md5': '26f51f03cf580265defefb4518faec09',
+ 'info_dict': {
+ 'id': 'sobre-camaras-y-camarillas-parlamentarias',
+ 'ext': 'mp4',
+ 'title': 'Sobre Cámaras y camarillas parlamentarias',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'uploader': 'Fernando Atria',
+ },
+ }, {
+ # different uploader layout
+ 'url': 'http://tv.biobiochile.cl/notas/2016/03/18/natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades.shtml',
+ 'md5': 'edc2e6b58974c46d5b047dea3c539ff3',
+ 'info_dict': {
+ 'id': 'natalia-valdebenito-repasa-a-diputado-hasbun-paso-a-la-categoria-de-hablar-brutalidades',
+ 'ext': 'mp4',
+ 'title': 'Natalia Valdebenito repasa a diputado Hasbún: Pasó a la categoría de hablar brutalidades',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'uploader': 'Piangella Obrador',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://tv.biobiochile.cl/notas/2015/10/21/exclusivo-hector-pinto-formador-de-chupete-revela-version-del-ex-delantero-albo.shtml',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = remove_end(self._og_search_title(webpage), ' - BioBioChile TV')
+
+ file_url = self._search_regex(
+ r'loadFWPlayerVideo\([^,]+,\s*(["\'])(?P<url>.+?)\1',
+ webpage, 'file url', group='url')
+
+ base_url = self._search_regex(
+ r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*fileURL', webpage,
+ 'base url', default='http://unlimited2-cl.digitalproserver.com/bbtv/',
+ group='url')
+
+ formats = self._extract_m3u8_formats(
+ '%s%s/playlist.m3u8' % (base_url, file_url), video_id, 'mp4',
+ entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+ f = {
+ 'url': '%s%s' % (base_url, file_url),
+ 'format_id': 'http',
+ 'protocol': 'http',
+ 'preference': 1,
+ }
+ if formats:
+ f_copy = formats[-1].copy()
+ f_copy.update(f)
+ f = f_copy
+ formats.append(f)
+ self._sort_formats(formats)
+
+ thumbnail = self._og_search_thumbnail(webpage)
+ uploader = self._html_search_regex(
+ r'<a[^>]+href=["\']https?://busca\.biobiochile\.cl/author[^>]+>(.+?)</a>',
+ webpage, 'uploader', fatal=False)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': thumbnail,
+ 'uploader': uploader,
+ 'formats': formats,
+ }
class BokeCCIE(BokeCCBaseIE):
_IE_DESC = 'CC视频'
- _VALID_URL = r'http://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
+ _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{
'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B',
class BpbIE(InfoExtractor):
IE_DESC = 'Bundeszentrale für politische Bildung'
- _VALID_URL = r'http://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
+ _VALID_URL = r'https?://www\.bpb\.de/mediathek/(?P<id>[0-9]+)/'
_TEST = {
'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
class BreakIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
'info_dict': {
class CamdemyIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?camdemy\.com/media/(?P<id>\d+)'
_TESTS = [{
# single file
'url': 'http://www.camdemy.com/media/5181/',
class CamdemyFolderIE(InfoExtractor):
- _VALID_URL = r'http://www.camdemy.com/folder/(?P<id>\d+)'
+ _VALID_URL = r'https?://www.camdemy.com/folder/(?P<id>\d+)'
_TESTS = [{
# links with trailing slash
'url': 'http://www.camdemy.com/folder/450',
class CBSNewsIE(ThePlatformIE):
IE_DESC = 'CBS News'
- _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
+ _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
_TESTS = [
{
class CBSNewsLiveVideoIE(InfoExtractor):
IE_DESC = 'CBS News Live Videos'
- _VALID_URL = r'http://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
+ _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
_TEST = {
'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
class CBSSportsIE(InfoExtractor):
- _VALID_URL = r'http://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
+ _VALID_URL = r'https?://www\.cbssports\.com/video/player/(?P<section>[^/]+)/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.cbssports.com/video/player/tennis/318462531970/0/us-open-flashbacks-1990s',
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ decode_packed_codes,
+ ExtractorError,
+ parse_duration
+)
+
+
+class CDAIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:(?:www\.)?cda\.pl/video|ebd\.cda\.pl/[0-9]+x[0-9]+)/(?P<id>[0-9a-z]+)'
+ _TESTS = [{
+ 'url': 'http://www.cda.pl/video/5749950c',
+ 'md5': '6f844bf51b15f31fae165365707ae970',
+ 'info_dict': {
+ 'id': '5749950c',
+ 'ext': 'mp4',
+ 'height': 720,
+ 'title': 'Oto dlaczego przed zakrętem należy zwolnić.',
+ 'duration': 39
+ }
+ }, {
+ 'url': 'http://www.cda.pl/video/57413289',
+ 'md5': 'a88828770a8310fc00be6c95faf7f4d5',
+ 'info_dict': {
+ 'id': '57413289',
+ 'ext': 'mp4',
+ 'title': 'Lądowanie na lotnisku na Maderze',
+ 'duration': 137
+ }
+ }, {
+ 'url': 'http://ebd.cda.pl/0x0/5749950c',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage('http://ebd.cda.pl/0x0/' + video_id, video_id)
+
+ if 'Ten film jest dostępny dla użytkowników premium' in webpage:
+ raise ExtractorError('This video is only available for premium users.', expected=True)
+
+ title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
+
+ formats = []
+
+ info_dict = {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'duration': None,
+ }
+
+ def extract_format(page, version):
+ unpacked = decode_packed_codes(page)
+ format_url = self._search_regex(
+ r"url:\\'(.+?)\\'", unpacked, '%s url' % version, fatal=False)
+ if not format_url:
+ return
+ f = {
+ 'url': format_url,
+ }
+ m = re.search(
+ r'<a[^>]+data-quality="(?P<format_id>[^"]+)"[^>]+href="[^"]+"[^>]+class="[^"]*quality-btn-active[^"]*">(?P<height>[0-9]+)p',
+ page)
+ if m:
+ f.update({
+ 'format_id': m.group('format_id'),
+ 'height': int(m.group('height')),
+ })
+ info_dict['formats'].append(f)
+ if not info_dict['duration']:
+ info_dict['duration'] = parse_duration(self._search_regex(
+ r"duration:\\'(.+?)\\'", unpacked, 'duration', fatal=False))
+
+ extract_format(webpage, 'default')
+
+ for href, resolution in re.findall(
+ r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
+ webpage):
+ webpage = self._download_webpage(
+ href, video_id, 'Downloading %s version information' % resolution, fatal=False)
+ if not webpage:
+ # Manually report warning because empty page is returned when
+ # invalid version is requested.
+ self.report_warning('Unable to download %s version information' % resolution)
+ continue
+ extract_format(webpage, resolution)
+
+ self._sort_formats(formats)
+
+ return info_dict
formats = []
for format_id, stream_url in item['streamUrls'].items():
formats.extend(self._extract_m3u8_formats(
- stream_url, playlist_id, 'mp4', entry_protocol='m3u8_native'))
+ stream_url, playlist_id, 'mp4',
+ entry_protocol='m3u8_native', fatal=False))
self._sort_formats(formats)
item_id = item.get('id') or item['assetId']
class CliphunterIE(InfoExtractor):
IE_NAME = 'cliphunter'
- _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
+ _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
(?P<id>[0-9]+)/
(?P<seo>.+?)(?:$|[#\?])
'''
class ClipsyndicateIE(InfoExtractor):
- _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
class ClubicIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
+ _VALID_URL = r'https?://(?:www\.)?clubic\.com/video/(?:[^/]+/)*video.*-(?P<id>[0-9]+)\.html'
_TESTS = [{
'url': 'http://www.clubic.com/video/clubic-week/video-clubic-week-2-0-le-fbi-se-lance-dans-la-photo-d-identite-448474.html',
class ComCarCoffIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
+ _VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
_TESTS = [{
'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
'info_dict': {
'wmagazine': 'W Magazine',
}
- _VALID_URL = r'http://(?:video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed(?:js)?)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
+ _VALID_URL = r'https?://(?:video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed(?:js)?)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
EMBED_URL = r'(?:https?:)?//player\.(?P<site>%s)\.com/(?P<type>embed(?:js)?)/.+?' % '|'.join(_SITES.keys())
class CSpanIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
+ _VALID_URL = r'https?://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
IE_DESC = 'C-SPAN'
_TESTS = [{
'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
class CtsNewsIE(InfoExtractor):
IE_DESC = '華視新聞'
# https connection failed (Connection reset)
- _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
+ _VALID_URL = r'https?://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
_TESTS = [{
'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
'md5': 'a9875cb790252b08431186d741beaabe',
class DctpTvIE(InfoExtractor):
- _VALID_URL = r'http://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
+ _VALID_URL = r'https?://www.dctp.tv/(#/)?filme/(?P<id>.+?)/$'
_TEST = {
'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
'info_dict': {
class DefenseGouvFrIE(InfoExtractor):
IE_NAME = 'defense.gouv.fr'
- _VALID_URL = r'http://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
+ _VALID_URL = r'https?://.*?\.defense\.gouv\.fr/layout/set/ligthboxvideo/base-de-medias/webtv/(?P<id>[^/?#]*)'
_TEST = {
'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1',
class DiscoveryIE(InfoExtractor):
- _VALID_URL = r'''(?x)http://(?:www\.)?(?:
+ _VALID_URL = r'''(?x)https?://(?:www\.)?(?:
discovery|
investigationdiscovery|
discoverylife|
class DouyuTVIE(InfoExtractor):
IE_DESC = '斗鱼'
- _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'http://www.douyutv.com/iseven',
'info_dict': {
class DPlayIE(InfoExtractor):
- _VALID_URL = r'http://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)'
+ _VALID_URL = r'https?://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/',
class DreiSatIE(ZDFIE):
IE_NAME = '3sat'
- _VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
+ _VALID_URL = r'(?:https?://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php|mediathek\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
_TESTS = [
{
'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
IE_NAME = 'dvtv'
IE_DESC = 'http://video.aktualne.cz/'
- _VALID_URL = r'http://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
+ _VALID_URL = r'https?://video\.aktualne\.cz/(?:[^/]+/)+r~(?P<id>[0-9a-f]{32})'
_TESTS = [{
'url': 'http://video.aktualne.cz/dvtv/vondra-o-ceskem-stoleti-pri-pohledu-na-havla-mi-bylo-trapne/r~e5efe9ca855511e4833a0025900fea04/',
class EchoMskIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?echo\.msk\.ru/sounds/(?P<id>\d+)'
_TEST = {
'url': 'http://www.echo.msk.ru/sounds/1464134.html',
'md5': '2e44b3b78daff5b458e4dbc37f191f7c',
class ExfmIE(InfoExtractor):
IE_NAME = 'exfm'
IE_DESC = 'ex.fm'
- _VALID_URL = r'http://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
_SOUNDCLOUD_URL = r'http://(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
_TESTS = [
{
class FC2IE(InfoExtractor):
- _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
+ _VALID_URL = r'^https?://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
IE_NAME = 'fc2'
_NETRC_MACHINE = 'fc2'
_TESTS = [{
class FirstpostIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
+ _VALID_URL = r'https?://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
_TEST = {
'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
class FirstTVIE(InfoExtractor):
IE_NAME = '1tv'
IE_DESC = 'Первый канал'
- _VALID_URL = r'http://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>.+)'
+ _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>.+)'
_TESTS = [{
'url': 'http://www.1tv.ru/videoarchive/73390',
class FKTVIE(InfoExtractor):
IE_NAME = 'fernsehkritik.tv'
- _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
+ _VALID_URL = r'https?://(?:www\.)?fernsehkritik\.tv/folge-(?P<id>[0-9]+)(?:/.*)?'
_TEST = {
'url': 'http://fernsehkritik.tv/folge-1',
class FootyRoomIE(InfoExtractor):
- _VALID_URL = r'http://footyroom\.com/(?P<id>[^/]+)'
+ _VALID_URL = r'https?://footyroom\.com/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://footyroom.com/schalke-04-0-2-real-madrid-2015-02/',
'info_dict': {
class FoxgayIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
+ _VALID_URL = r'https?://(?:www\.)?foxgay\.com/videos/(?:\S+-)?(?P<id>\d+)\.shtml'
_TEST = {
'url': 'http://foxgay.com/videos/fuck-turkish-style-2582.shtml',
'md5': '80d72beab5d04e1655a56ad37afe6841',
class FranceInterIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
'md5': '4764932e466e6f6c79c317d2e74f6884',
video_id, 'Downloading f4m manifest token', fatal=False)
if f4m_url:
formats.extend(self._extract_f4m_formats(
- f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, 1, format_id))
+ f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44',
+ video_id, f4m_id=format_id, fatal=False))
elif ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
+ formats.extend(self._extract_m3u8_formats(
+ video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id=format_id, fatal=False))
elif video_url.startswith('rtmp'):
formats.append({
'url': video_url,
'format_id': 'rtmp-%s' % format_id,
'ext': 'flv',
- 'preference': 1,
})
else:
- formats.append({
- 'url': video_url,
- 'format_id': format_id,
- 'preference': -1,
- })
+ if self._is_valid_url(video_url, video_id, format_id):
+ formats.append({
+ 'url': video_url,
+ 'format_id': format_id,
+ })
self._sort_formats(formats)
title = info['titre']
subtitle = info.get('sous_titre')
if subtitle:
title += ' - %s' % subtitle
+ title = title.strip()
subtitles = {}
subtitles_list = [{
class FranceTvInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = 'francetvinfo.fr'
- _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
+ _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
_TESTS = [{
'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
'info_dict': {
'id': '84981923',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Soir 3',
'upload_date': '20130826',
'timestamp': 1377548400,
'fr': 'mincount:2',
},
},
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
'info_dict': {
'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
'md5': 'f485bda6e185e7d15dbc69b72bae993e',
'info_dict': {
- 'id': '556e03339473995ee145930c',
+ 'id': 'NI_173343',
'ext': 'mp4',
'title': 'Les entreprises familiales : le secret de la réussite',
'thumbnail': 're:^https?://.*\.jpe?g$',
- }
+ 'timestamp': 1433273139,
+ 'upload_date': '20150602',
+ },
+ 'params': {
+ # m3u8 downloads
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'http://france3-regions.francetvinfo.fr/bretagne/cotes-d-armor/thalassa-echappee-breizh-ce-venredi-dans-les-cotes-d-armor-954961.html',
+ 'md5': 'f485bda6e185e7d15dbc69b72bae993e',
+ 'info_dict': {
+ 'id': 'NI_657393',
+ 'ext': 'mp4',
+ 'title': 'Olivier Monthus, réalisateur de "Bretagne, le choix de l’Armor"',
+ 'description': 'md5:a3264114c9d29aeca11ced113c37b16c',
+ 'thumbnail': 're:^https?://.*\.jpe?g$',
+ 'timestamp': 1458300695,
+ 'upload_date': '20160318',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}]
def _real_extract(self, url):
return self.url_result(dmcloud_url, 'DailymotionCloud')
video_id, catalogue = self._search_regex(
- r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
+ (r'id-video=([^@]+@[^"]+)',
+ r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
+ webpage, 'video id').split('@')
return self._extract_video(video_id, catalogue)
class FreeVideoIE(InfoExtractor):
- _VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
+ _VALID_URL = r'^https?://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])'
_TEST = {
'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html',
class GamekingsIE(InfoExtractor):
- _VALID_URL = r'http://www\.gamekings\.nl/(?:videos|nieuws)/(?P<id>[^/]+)'
+ _VALID_URL = r'https?://www\.gamekings\.nl/(?:videos|nieuws)/(?P<id>[^/]+)'
_TESTS = [{
# YouTube embed video
'url': 'http://www.gamekings.nl/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
class GameSpotIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
+ _VALID_URL = r'https?://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
_TESTS = [{
'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
class GameStarIE(InfoExtractor):
- _VALID_URL = r'http://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
+ _VALID_URL = r'https?://www\.gamestar\.de/videos/.*,(?P<id>[0-9]+)\.html'
_TEST = {
'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html',
'md5': '96974ecbb7fd8d0d20fca5a00810cea7',
class GametrailersIE(InfoExtractor):
- _VALID_URL = r'http://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
+ _VALID_URL = r'https?://www\.gametrailers\.com/videos/view/[^/]+/(?P<id>.+)'
_TEST = {
'url': 'http://www.gametrailers.com/videos/view/gametrailers-com/116437-Just-Cause-3-Review',
class HotNewHipHopIE(InfoExtractor):
- _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
+ _VALID_URL = r'https?://www\.hotnewhiphop\.com/.*\.(?P<id>.*)\.html'
_TEST = {
'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html',
'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96',
class HypemIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/'
+ _VALID_URL = r'https?://(?:www\.)?hypem\.com/track/(?P<id>[^/]+)/'
_TEST = {
'url': 'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
'md5': 'b9cc91b5af8995e9f0c1cee04c575828',
class ImdbIE(InfoExtractor):
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
- _VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
_TEST = {
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
class ImdbListIE(InfoExtractor):
IE_NAME = 'imdb:list'
IE_DESC = 'Internet Movie Database lists'
- _VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
+ _VALID_URL = r'https?://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
_TEST = {
'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
'info_dict': {
IE_NAME = 'iqiyi'
IE_DESC = '爱奇艺'
- _VALID_URL = r'http://(?:[^.]+\.)?iqiyi\.com/.+\.html'
+ _VALID_URL = r'https?://(?:[^.]+\.)?iqiyi\.com/.+\.html'
_NETRC_MACHINE = 'iqiyi'
class JadoreCettePubIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?jadorecettepub\.com/[0-9]{4}/[0-9]{2}/(?P<id>.*?)\.html'
+ _VALID_URL = r'https?://(?:www\.)?jadorecettepub\.com/[0-9]{4}/[0-9]{2}/(?P<id>.*?)\.html'
_TEST = {
'url': 'http://www.jadorecettepub.com/2010/12/star-wars-massacre-par-les-japonais.html',
class JeuxVideoIE(InfoExtractor):
- _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
+ _VALID_URL = r'https?://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
_TESTS = [{
'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
class KaraoketvIE(InfoExtractor):
- _VALID_URL = r'http://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://karaoketv\.co\.il/\?container=songs&id=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://karaoketv.co.il/?container=songs&id=171568',
'info_dict': {
class KarriereVideosIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?karrierevideos\.at(?:/[^/]+)+/(?P<id>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?karrierevideos\.at(?:/[^/]+)+/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.karrierevideos.at/berufsvideos/mittlere-hoehere-schulen/altenpflegerin',
'info_dict': {
class KontrTubeIE(InfoExtractor):
IE_NAME = 'kontrtube'
IE_DESC = 'KontrTube.ru - Труба зовёт'
- _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
+ _VALID_URL = r'https?://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
_TEST = {
'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
class Ku6IE(InfoExtractor):
- _VALID_URL = r'http://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
+ _VALID_URL = r'https?://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
_TEST = {
'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
'md5': '01203549b9efbb45f4b87d55bdea1ed1',
class KUSIIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
+ _VALID_URL = r'http
s?://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
_TESTS = [{
'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold',
'md5': 'f926e7684294cf8cb7bdf8858e1b3988',
from __future__ import unicode_literals
import re
-import itertools
from .common import InfoExtractor
from ..utils import (
get_element_by_id,
clean_html,
ExtractorError,
+ InAdvancePagedList,
remove_start,
)
class KuwoIE(KuwoBaseIE):
IE_NAME = 'kuwo:song'
IE_DESC = '酷我音乐'
- _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/'
+ _VALID_URL = r'https?://www\.kuwo\.cn/yinyue/(?P<id>\d+?)'
_TESTS = [{
'url': 'http://www.kuwo.cn/yinyue/635632/',
'info_dict': {
'params': {
'format': 'mp3-320'
},
+ }, {
+ 'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
+ 'only_matching': True,
}]
def _real_extract(self, url):
class KuwoAlbumIE(InfoExtractor):
IE_NAME = 'kuwo:album'
IE_DESC = '酷我音乐 - 专辑'
- _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>\d+?)/'
+ _VALID_URL = r'https?://www\.kuwo\.cn/album/(?P<id>\d+?)/'
_TEST = {
'url': 'http://www.kuwo.cn/album/502294/',
'info_dict': {
class KuwoChartIE(InfoExtractor):
IE_NAME = 'kuwo:chart'
IE_DESC = '酷我音乐 - 排行榜'
- _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
+ _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
_TEST = {
'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
'info_dict': {
'id': '香港中文龙虎榜',
- 'title': '香港中文龙虎榜',
- 'description': 're:\d{4}第\d{2}期',
},
'playlist_mincount': 10,
}
url, chart_id, note='Download chart info',
errnote='Unable to get chart info')
- chart_name = self._html_search_regex(
- r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name')
-
- chart_desc = self._html_search_regex(
- r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc')
-
entries = [
self.url_result(song_url, 'Kuwo') for song_url in re.findall(
- r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage)
+ r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
]
- return self.playlist_result(entries, chart_id, chart_name, chart_desc)
+ return self.playlist_result(entries, chart_id)
class KuwoSingerIE(InfoExtractor):
IE_NAME = 'kuwo:singer'
IE_DESC = '酷我音乐 - 歌手'
- _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
+ _VALID_URL = r'https?://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
'info_dict': {
'id': 'bruno+mars',
'title': 'Bruno Mars',
},
- 'playlist_count': 10,
+ 'playlist_mincount': 329,
}, {
'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
'info_dict': {
'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
}]
+ PAGE_SIZE = 15
+
def _real_extract(self, url):
singer_id = self._match_id(url)
webpage = self._download_webpage(
errnote='Unable to get singer info')
singer_name = self._html_search_regex(
- r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name'
- )
+ r'<h1>([^<]+)</h1>', webpage, 'singer name')
+
+ artist_id = self._html_search_regex(
+ r'data-artistid="(\d+)"', webpage, 'artist id')
+
+ page_count = int(self._html_search_regex(
+ r'data-page="(\d+)"', webpage, 'page count'))
- entries = []
- first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True
- for page_num in itertools.count(1):
+ def page_func(page_num):
webpage = self._download_webpage(
- 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
- singer_id, note='Download song list page #%d' % page_num,
- errnote='Unable to get song list page #%d' % page_num)
+ 'http://www.kuwo.cn/artist/contentMusicsAjax',
+ singer_id, note='Download song list page #%d' % (page_num + 1),
+ errnote='Unable to get song list page #%d' % (page_num + 1),
+ query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
- entries.extend([
+ return [
self.url_result(song_url, 'Kuwo') for song_url in re.findall(
- r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/',
+ r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
webpage)
- ][:10 if first_page_only else None])
+ ]
- if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage):
- break
+ entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)
return self.playlist_result(entries, singer_id, singer_name)
class KuwoCategoryIE(InfoExtractor):
IE_NAME = 'kuwo:category'
IE_DESC = '酷我音乐 - 分类'
- _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
+ _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
_TEST = {
'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
'info_dict': {
class KuwoMvIE(KuwoBaseIE):
IE_NAME = 'kuwo:mv'
IE_DESC = '酷我音乐 - MV'
- _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
+ _VALID_URL = r'https?://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
_TEST = {
'url': 'http://www.kuwo.cn/mv/6480076/',
'info_dict': {
class Laola1TvIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/[^/]+/(?P<slug>[^/?#&]+)'
+ _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P<lang>[a-z]+)-(?P<portal>[a-z]+)/(?P<kind>[^/]+)/(?P<slug>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie/227883.html',
'info_dict': {
},
'params': {
'skip_download': True,
- }
+ },
}, {
'url': 'http://www.laola1.tv/de-de/video/straubing-tigers-koelner-haie',
'info_dict': {
},
'params': {
'skip_download': True,
- }
+ },
+ }, {
+ 'url': 'http://www.laola1.tv/de-de/livestream/2016-03-22-belogorie-belgorod-trentino-diatec-lde',
+ 'info_dict': {
+ 'id': '487850',
+ 'display_id': '2016-03-22-belogorie-belgorod-trentino-diatec-lde',
+ 'ext': 'flv',
+ 'title': 'Belogorie BELGOROD - TRENTINO Diatec',
+ 'upload_date': '20160322',
+ 'uploader': 'CEV - Europäischer Volleyball Verband',
+ 'is_live': True,
+ 'categories': ['Volleyball'],
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('slug')
+ kind = mobj.group('kind')
lang = mobj.group('lang')
portal = mobj.group('portal')
_v = lambda x, **k: xpath_text(hd_doc, './/video/' + x, **k)
title = _v('title', fatal=True)
+ VS_TARGETS = {
+ 'video': '2',
+ 'livestream': '17',
+ }
+
req = sanitized_Request(
'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access?%s' %
compat_urllib_parse.urlencode({
'videoId': video_id,
- 'target': '2',
- 'label': 'laola1tv',
+ 'target': VS_TARGETS.get(kind, '2'),
+ 'label': _v('label'),
'area': _v('area'),
}),
urlencode_postdata(
class LeIE(InfoExtractor):
IE_DESC = '乐视网'
- _VALID_URL = r'http://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html'
+ _VALID_URL = r'https?://www\.le\.com/ptv/vplay/(?P<id>\d+)\.html'
_URL_TEMPLATE = 'http://www.le.com/ptv/vplay/%s.html'
class LePlaylistIE(InfoExtractor):
- _VALID_URL = r'http://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)'
+ _VALID_URL = r'https?://[a-z]+\.le\.com/[a-z]+/(?P<id>[a-z0-9_]+)'
_TESTS = [{
'url': 'http://www.le.com/tv/46177.html',
class LifeNewsIE(InfoExtractor):
IE_NAME = 'lifenews'
IE_DESC = 'LIFE | NEWS'
- _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?(?P<section>news|video)/(?P<id>\d+)'
+ _VALID_URL = r'https?://lifenews\.ru/(?:mobile/)?(?P<section>news|video)/(?P<id>\d+)'
_TESTS = [{
# single video embedded via video/source
class LifeEmbedIE(InfoExtractor):
IE_NAME = 'life:embed'
- _VALID_URL = r'http://embed\.life\.ru/embed/(?P<id>[\da-f]{32})'
+ _VALID_URL = r'https?://embed\.life\.ru/embed/(?P<id>[\da-f]{32})'
_TEST = {
'url': 'http://embed.life.ru/embed/e50c2dec2867350528e2574c899b8291',
class LimelightMediaIE(LimelightBaseIE):
IE_NAME = 'limelight'
- _VALID_URL = r'(?:limelight:media:|http://link\.videoplatform\.limelight\.com/media/\??\bmediaId=)(?P<id>[a-z0-9]{32})'
+ _VALID_URL = r'(?:limelight:media:|https?://link\.videoplatform\.limelight\.com/media/\??\bmediaId=)(?P<id>[a-z0-9]{32})'
_TESTS = [{
'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
'info_dict': {
class LimelightChannelIE(LimelightBaseIE):
IE_NAME = 'limelight:channel'
- _VALID_URL = r'(?:limelight:channel:|http://link\.videoplatform\.limelight\.com/media/\??\bchannelId=)(?P<id>[a-z0-9]{32})'
+ _VALID_URL = r'(?:limelight:channel:|https?://link\.videoplatform\.limelight\.com/media/\??\bchannelId=)(?P<id>[a-z0-9]{32})'
_TEST = {
'url': 'http://link.videoplatform.limelight.com/media/?channelId=ab6a524c379342f9b23642917020c082',
'info_dict': {
class LimelightChannelListIE(LimelightBaseIE):
IE_NAME = 'limelight:channel_list'
- _VALID_URL = r'(?:limelight:channel_list:|http://link\.videoplatform\.limelight\.com/media/\?.*?\bchannelListId=)(?P<id>[a-z0-9]{32})'
+ _VALID_URL = r'(?:limelight:channel_list:|https?://link\.videoplatform\.limelight\.com/media/\?.*?\bchannelListId=)(?P<id>[a-z0-9]{32})'
_TEST = {
'url': 'http://link.videoplatform.limelight.com/media/?channelListId=301b117890c4465c8179ede21fd92e2b',
'info_dict': {
class M6IE(InfoExtractor):
IE_NAME = 'm6'
- _VALID_URL = r'http://(?:www\.)?m6\.fr/[^/]+/videos/(?P<id>\d+)-[^\.]+\.html'
+ _VALID_URL = r'https?://(?:www\.)?m6\.fr/[^/]+/videos/(?P<id>\d+)-[^\.]+\.html'
_TEST = {
'url': 'http://www.m6.fr/emission-les_reines_du_shopping/videos/11323908-emeline_est_la_reine_du_shopping_sur_le_theme_ma_fete_d_8217_anniversaire.html',
class MailRuIE(InfoExtractor):
IE_NAME = 'mailru'
IE_DESC = 'Видео@Mail.Ru'
- _VALID_URL = r'http://(?:www\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)'
+ _VALID_URL = r'https?://(?:www\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)'
_TESTS = [
{
class MetacafeIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+ _VALID_URL = r'https?://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
IE_NAME = 'metacafe'
class OCWMITIE(InfoExtractor):
IE_NAME = 'ocw.mit.edu'
- _VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
+ _VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
_BASE_URL = 'http://ocw.mit.edu/'
_TESTS = [
class MiTeleIE(InfoExtractor):
IE_DESC = 'mitele.es'
- _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
+ _VALID_URL = r'https?://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
_TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
class MooshareIE(InfoExtractor):
IE_NAME = 'mooshare'
IE_DESC = 'Mooshare.biz'
- _VALID_URL = r'http://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})'
+ _VALID_URL = r'https?://(?:www\.)?mooshare\.biz/(?P<id>[\da-z]{12})'
_TESTS = [
{
class MotherlessIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
_TESTS = [{
'url': 'http://motherless.com/AC3FFE1',
'md5': '310f62e325a9fafe64f68c0bccb6e75f',
">The page you're looking for cannot be found.<")):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+ if '>The content you are trying to view is for friends only.' in webpage:
+ raise ExtractorError('Video %s is for friends only' % video_id, expected=True)
+
title = self._html_search_regex(
r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
video_url = self._html_search_regex(
class MotorsportIE(InfoExtractor):
IE_DESC = 'motorsport.com'
- _VALID_URL = r'http://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
+ _VALID_URL = r'https?://www\.motorsport\.com/[^/?#]+/video/(?:[^/?#]+/)(?P<id>[^/]+)/?(?:$|[?#])'
_TEST = {
'url': 'http://www.motorsport.com/f1/video/main-gallery/red-bull-racing-2014-rules-explained/',
'info_dict': {
class MySpassIE(InfoExtractor):
- _VALID_URL = r'http://www\.myspass\.de/.*'
+ _VALID_URL = r'https?://www\.myspass\.de/.*'
_TEST = {
'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
'md5': '0b49f4844a068f8b33f4b7c88405862b',
class MyVideoIE(InfoExtractor):
_WORKING = False
- _VALID_URL = r'http://(?:www\.)?myvideo\.de/(?:[^/]+/)?watch/(?P<id>[0-9]+)/[^?/]+.*'
+ _VALID_URL = r'https?://(?:www\.)?myvideo\.de/(?:[^/]+/)?watch/(?P<id>[0-9]+)/[^?/]+.*'
IE_NAME = 'myvideo'
_TEST = {
'url': 'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
class MyVidsterIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?myvidster\.com/video/(?P<id>\d+)/'
+ _VALID_URL = r'https?://(?:www\.)?myvidster\.com/video/(?P<id>\d+)/'
_TEST = {
'url': 'http://www.myvidster.com/video/32059805/Hot_chemistry_with_raw_love_making',
class NationalGeographicIE(InfoExtractor):
- _VALID_URL = r'http://video\.nationalgeographic\.com/.*?'
+ _VALID_URL = r'https?://video\.nationalgeographic\.com/.*?'
_TESTS = [
{
class NBCSportsIE(InfoExtractor):
# Does not include https because its certificate is invalid
- _VALID_URL = r'http://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
+ _VALID_URL = r'https?://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
_TEST = {
'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
class MSNBCIE(InfoExtractor):
# https URLs redirect to corresponding http ones
- _VALID_URL = r'http://www\.msnbc\.com/[^/]+/watch/(?P<id>[^/]+)'
+ _VALID_URL = r'https?://www\.msnbc\.com/[^/]+/watch/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
class NextMediaIE(InfoExtractor):
IE_DESC = '蘋果日報'
- _VALID_URL = r'http://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
+ _VALID_URL = r'https?://hk.apple.nextmedia.com/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://hk.apple.nextmedia.com/realtime/news/20141108/53109199',
'md5': 'dff9fad7009311c421176d1ac90bfe4f',
class NextMediaActionNewsIE(NextMediaIE):
IE_DESC = '蘋果日報 - 動新聞'
- _VALID_URL = r'http://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
+ _VALID_URL = r'https?://hk.dv.nextmedia.com/actionnews/[^/]+/(?P<date>\d+)/(?P<id>\d+)/\d+'
_TESTS = [{
'url': 'http://hk.dv.nextmedia.com/actionnews/hit/20150121/19009428/20061460',
'md5': '05fce8ffeed7a5e00665d4b7cf0f9201',
class AppleDailyIE(NextMediaIE):
IE_DESC = '臺灣蘋果日報'
- _VALID_URL = r'http://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
+ _VALID_URL = r'https?://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?'
_TESTS = [{
'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694',
'md5': 'a843ab23d150977cc55ef94f1e2c1e4d',
class NocoIE(InfoExtractor):
- _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
_LOGIN_URL = 'http://noco.tv/do.php'
_API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
_SUB_LANG_TEMPLATE = '&sub_lang=%s'
class NormalbootsIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$'
+ _VALID_URL = r'https?://(?:www\.)?normalboots\.com/video/(?P<id>[0-9a-z-]*)/?$'
_TEST = {
'url': 'http://normalboots.com/video/home-alone-games-jontron/',
'md5': '8bf6de238915dd501105b44ef5f1e0f6',
class NovaIE(InfoExtractor):
IE_DESC = 'TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz'
- _VALID_URL = 'http://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
+ _VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
_TESTS = [{
'url': 'http://tvnoviny.nova.cz/clanek/novinky/co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou.html?utm_source=tvnoviny&utm_medium=cpfooter&utm_campaign=novaplus',
'info_dict': {
class NprIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?npr\.org/player/v2/mediaPlayer\.html\?.*\bid=(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?npr\.org/player/v2/mediaPlayer\.html\?.*\bid=(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.npr.org/player/v2/mediaPlayer.html?id=449974205',
'info_dict': {
class NTVRuIE(InfoExtractor):
IE_NAME = 'ntv.ru'
- _VALID_URL = r'http://(?:www\.)?ntv\.ru/(?P<id>.+)'
+ _VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?P<id>.+)'
_TESTS = [
{
media_item_id, 'mp4', m3u8_id='hls', fatal=False)
progressive_formats = []
for adaptive_format in formats:
+ # Prevent advertisement from embedding into m3u8 playlist (see
+ # https://github.com/rg3/youtube-dl/issues/8893#issuecomment-199912684)
+ adaptive_format['url'] = re.sub(
+ r'\badsegmentlength=\d+', r'adsegmentlength=0', adaptive_format['url'])
rendition_id = self._search_regex(
r'/now/media/playlist/[^/]+/[^/]+/([^/]+)',
adaptive_format['url'], 'redition id', default=None)
--- /dev/null
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_chr
+from ..utils import (
+ encode_base_n,
+ ExtractorError,
+)
+
+
+class OpenloadIE(InfoExtractor):
+ _VALID_URL = r'https://openload.(?:co|io)/(?:f|embed)/(?P<id>[a-zA-Z0-9-]+)'
+
+ _TESTS = [{
+ 'url': 'https://openload.co/f/kUEfGclsU9o',
+ 'md5': 'bf1c059b004ebc7a256f89408e65c36e',
+ 'info_dict': {
+ 'id': 'kUEfGclsU9o',
+ 'ext': 'mp4',
+ 'title': 'skyrim_no-audio_1080.mp4',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ }, {
+ 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://openload.io/f/ZAn6oz-VZGE/',
+ 'only_matching': True,
+ }]
+
+ @staticmethod
+ def openload_level2_debase(m):
+ radix, num = int(m.group(1)) + 27, int(m.group(2))
+ return '"' + encode_base_n(num, radix) + '"'
+
+ @classmethod
+ def openload_level2(cls, txt):
+ # The function name is ǃ \u01c3
+ # Using escaped unicode literals does not work in Python 3.2
+ return re.sub(r'ǃ\((\d+),(\d+)\)', cls.openload_level2_debase, txt, re.UNICODE).replace('"+"', '')
+
+ # Openload uses a variant of aadecode
+ # openload_decode and related functions are originally written by
+ # vitas@matfyz.cz and released with public domain
+ # See https://github.com/rg3/youtube-dl/issues/8489
+ @classmethod
+ def openload_decode(cls, txt):
+ symbol_table = [
+ ('_', '(ﾟДﾟ) [ﾟΘﾟ]'),
+ ('a', '(ﾟДﾟ) [ﾟωﾟﾉ]'),
+ ('b', '(ﾟДﾟ) [ﾟΘﾟﾉ]'),
+ ('c', '(ﾟДﾟ) [\'c\']'),
+ ('d', '(ﾟДﾟ) [ﾟｰﾟﾉ]'),
+ ('e', '(ﾟДﾟ) [ﾟДﾟﾉ]'),
+ ('f', '(ﾟДﾟ) [1]'),
+
+ ('o', '(ﾟДﾟ) [\'o\']'),
+ ('u', '(oﾟｰﾟo)'),
+ ('c', '(ﾟДﾟ) [\'c\']'),
+
+ ('7', '((ﾟｰﾟ) + (o^_^o))'),
+ ('6', '((o^_^o) +(o^_^o) +(c^_^o))'),
+ ('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'),
+ ('4', '(-~3)'),
+ ('3', '(-~-~1)'),
+ ('2', '(-~1)'),
+ ('1', '(-~0)'),
+ ('0', '((c^_^o)-(c^_^o))'),
+ ]
+ delim = '(ﾟДﾟ)[ﾟεﾟ]+'
+ ret = ''
+ for aachar in txt.split(delim):
+ for val, pat in symbol_table:
+ aachar = aachar.replace(pat, val)
+ aachar = aachar.replace('+ ', '')
+ m = re.match(r'^\d+', aachar)
+ if m:
+ ret += compat_chr(int(m.group(0), 8))
+ else:
+ m = re.match(r'^u([\da-f]+)', aachar)
+ if m:
+ ret += compat_chr(int(m.group(1), 16))
+ return cls.openload_level2(ret)
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ if 'File not found' in webpage:
+ raise ExtractorError('File not found', expected=True)
+
+ code = self._search_regex(
+ r'<video[^>]+>\s*<script[^>]+>([^<]+)</script>',
+ webpage, 'JS code')
+
+ video_url = self._search_regex(
+ r'return\s+"(https?://[^"]+)"', self.openload_decode(code), 'video URL')
+
+ return {
+ 'id': video_id,
+ 'title': self._og_search_title(webpage),
+ 'thumbnail': self._og_search_thumbnail(webpage),
+ 'url': video_url,
+ }
class ORFOE1IE(InfoExtractor):
IE_NAME = 'orf:oe1'
IE_DESC = 'Radio Österreich 1'
- _VALID_URL = r'http://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)'
# Audios on ORF radio are only available for 7 days, so we can't add tests.
_TEST = {
class ORFFM4IE(InfoExtractor):
IE_NAME = 'orf:fm4'
IE_DESC = 'radio FM4'
- _VALID_URL = r'http://fm4\.orf\.at/(?:7tage/?#|player/)(?P<date>[0-9]+)/(?P<show>\w+)'
+ _VALID_URL = r'https?://fm4\.orf\.at/(?:7tage/?#|player/)(?P<date>[0-9]+)/(?P<show>\w+)'
_TEST = {
'url': 'http://fm4.orf.at/player/20160110/IS/',
class ORFIPTVIE(InfoExtractor):
IE_NAME = 'orf:iptv'
IE_DESC = 'iptv.ORF.at'
- _VALID_URL = r'http://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
+ _VALID_URL = r'https?://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
_TEST = {
'url': 'http://iptv.orf.at/stories/2275236/',
class PhilharmonieDeParisIE(InfoExtractor):
IE_DESC = 'Philharmonie de Paris'
- _VALID_URL = r'http://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
+ _VALID_URL = r'https?://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
'info_dict': {
class PhotobucketIE(InfoExtractor):
- _VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
+ _VALID_URL = r'https?://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
_TEST = {
'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
# encoding: utf-8
from __future__ import unicode_literals
-from ..compat import compat_urllib_parse
+from ..compat import (
+ compat_urllib_parse,
+ compat_urllib_parse_unquote,
+)
from .common import InfoExtractor
from ..utils import (
parse_duration,
def _real_extract(self, url):
video_id = self._match_id(url)
- url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
self._set_cookie('91porn.com', 'language', 'cn_CN')
- webpage = self._download_webpage(url, video_id, 'get HTML content')
+
+ webpage = self._download_webpage(
+ 'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
if '作为游客，你每天只可观看10个视频' in webpage:
raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True)
})
info_cn = self._download_webpage(
'http://91porn.com/getfile.php?' + url_params, video_id,
- 'get real video url')
- video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url')
+ 'Downloading real video url')
+ video_url = compat_urllib_parse_unquote(self._search_regex(
+ r'file=([^&]+)&', info_cn, 'url'))
duration = parse_duration(self._search_regex(
r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
class PornHdIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
+ _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
_TEST = {
'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
'md5': '956b8ca569f7f4d8ec563e2c41598441',
class PornoVoisinesIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
_VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
'/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
class PyvideoIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
+ _VALID_URL = r'https?://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
_TESTS = [
{
class QQMusicIE(InfoExtractor):
IE_NAME = 'qqmusic'
IE_DESC = 'QQ音乐'
- _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
+ _VALID_URL = r'https?://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
'md5': '9ce1c1c8445f561506d2e3cfb0255705',
class QQMusicSingerIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:singer'
IE_DESC = 'QQ音乐 - 歌手'
- _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
+ _VALID_URL = r'https?://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
_TEST = {
'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
'info_dict': {
class QQMusicAlbumIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:album'
IE_DESC = 'QQ音乐 - 专辑'
- _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
+ _VALID_URL = r'https?://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
class QQMusicToplistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:toplist'
IE_DESC = 'QQ音乐 - 排行榜'
- _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
+ _VALID_URL = r'https?://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=toplist&p=global_123',
class QQMusicPlaylistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:playlist'
IE_DESC = 'QQ音乐 - 歌单'
- _VALID_URL = r'http://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=taoge&id=3462654915',
class RaiTVIE(InfoExtractor):
- _VALID_URL = r'http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+media/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
+ _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+media/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
_TESTS = [
{
'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
class RaiIE(InfoExtractor):
- _VALID_URL = r'http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
+ _VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
_TESTS = [
{
'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
class RedTubeIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.redtube.com/66418',
'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
class RingTVIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?ringtv\.craveonline\.com/(?P<type>news|videos/video)/(?P<id>[^/?#]+)'
+ _VALID_URL = r'https?://(?:www\.)?ringtv\.craveonline\.com/(?P<type>news|videos/video)/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://ringtv.craveonline.com/news/310833-luis-collazo-says-victor-ortiz-better-not-quit-on-jan-30',
'md5': 'd25945f5df41cdca2d2587165ac28720',
class RTVEALaCartaIE(InfoExtractor):
IE_NAME = 'rtve.es:alacarta'
IE_DESC = 'RTVE a la carta'
- _VALID_URL = r'http://www\.rtve\.es/(m/)?alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
+ _VALID_URL = r'https?://www\.rtve\.es/(m/)?alacarta/videos/[^/]+/[^/]+/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
class RTVELiveIE(InfoExtractor):
IE_NAME = 'rtve.es:live'
IE_DESC = 'RTVE.es live streams'
- _VALID_URL = r'http://www\.rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
+ _VALID_URL = r'https?://www\.rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
_TESTS = [{
'url': 'http://www.rtve.es/directo/la-1/',
class RUHDIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?ruhd\.ru/play\.php\?vid=(?P<id>\d+)'
_TEST = {
'url': 'http://www.ruhd.ru/play.php?vid=207',
'md5': 'd1a9ec4edf8598e3fbd92bb16072ba83',
class RutubeChannelIE(InfoExtractor):
IE_NAME = 'rutube:channel'
IE_DESC = 'Rutube channels'
- _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
+ _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'
_TESTS = [{
'url': 'http://rutube.ru/tags/video/1800/',
'info_dict': {
class RutubeMovieIE(RutubeChannelIE):
IE_NAME = 'rutube:movie'
IE_DESC = 'Rutube movies'
- _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
+ _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'
_TESTS = []
_MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
class RutubePersonIE(RutubeChannelIE):
IE_NAME = 'rutube:person'
IE_DESC = 'Rutube person videos'
- _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
+ _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'
_TESTS = [{
'url': 'http://rutube.ru/video/person/313878/',
'info_dict': {
IE_DESC = 'RUTV.RU'
_VALID_URL = r'''(?x)
https?://player\.(?:rutv\.ru|vgtrk\.com)/
- (?P<path>flash2v/container\.swf\?id=
+ (?P<path>flash\d+v/container\.swf\?id=
|iframe/(?P<type>swf|video|live)/id/
|index/iframe/cast_id/)
(?P<id>\d+)'''
return mobj.group('url')
mobj = re.search(
- r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)',
+ r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/flash\d+v/container\.swf\?id=.+?\2)',
webpage)
if mobj:
return mobj.group('url')
video_id = mobj.group('id')
video_path = mobj.group('path')
- if video_path.startswith('flash2v'):
+ if re.match(r'flash\d+v', video_path):
video_type = 'video'
elif video_path.startswith('iframe'):
video_type = mobj.group('type')
'play_path': mobj.group('playpath'),
'app': mobj.group('app'),
'page_url': 'http://player.rutv.ru',
- 'player_url': 'http://player.rutv.ru/flash2v/osmf.swf?i=22',
+ 'player_url': 'http://player.rutv.ru/flash3v/osmf.swf?i=22',
'rtmp_live': True,
'ext': 'flv',
'vbr': int(quality),
class SafariIE(SafariBaseIE):
IE_NAME = 'safari'
IE_DESC = 'safaribooksonline.com online video'
- _VALID_URL = r'''(?x)https?://
- (?:www\.)?safaribooksonline\.com/
- (?:
- library/view/[^/]+|
- api/v1/book
- )/
- (?P<course_id>[^/]+)/
- (?:chapter(?:-content)?/)?
- (?P<part>part\d+)\.html
- '''
+ _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>part\d+)\.html'
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
'upload_date': '20150724',
'uploader_id': 'stork',
},
- }, {
- 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
- 'only_matching': True,
}, {
# non-digits in course id
'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- course_id = mobj.group('course_id')
- part = mobj.group('part')
-
- webpage = self._download_webpage(url, '%s/%s' % (course_id, part))
- reference_id = self._search_regex(r'data-reference-id="([^"]+)"', webpage, 'kaltura reference id')
- partner_id = self._search_regex(r'data-partner-id="([^"]+)"', webpage, 'kaltura widget id')
- ui_id = self._search_regex(r'data-ui-id="([^"]+)"', webpage, 'kaltura uiconf id')
+ video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part'))
+
+ webpage = self._download_webpage(url, video_id)
+ reference_id = self._search_regex(
+ r'data-reference-id=(["\'])(?P<id>.+?)\1',
+ webpage, 'kaltura reference id', group='id')
+ partner_id = self._search_regex(
+ r'data-partner-id=(["\'])(?P<id>.+?)\1',
+ webpage, 'kaltura widget id', group='id')
+ ui_id = self._search_regex(
+ r'data-ui-id=(["\'])(?P<id>.+?)\1',
+ webpage, 'kaltura uiconf id', group='id')
query = {
'wid': '_%s' % partner_id,
if self.LOGGED_IN:
kaltura_session = self._download_json(
'%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
- course_id, 'Downloading kaltura session JSON',
+ video_id, 'Downloading kaltura session JSON',
'Unable to download kaltura session JSON', fatal=False)
if kaltura_session:
session = kaltura_session.get('session')
'Kaltura')
+class SafariApiIE(SafariBaseIE):
+ IE_NAME = 'safari:api'
+ _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>part\d+)\.html'
+
+ _TEST = {
+ 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
+ 'only_matching': True,
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ part = self._download_json(
+ url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
+ 'Downloading part JSON')
+ return self.url_result(part['web_url'], SafariIE.ie_key())
+
+
class SafariCourseIE(SafariBaseIE):
IE_NAME = 'safari:course'
IE_DESC = 'safaribooksonline.com online courses'
'No chapters found for course %s' % course_id, expected=True)
entries = [
- self.url_result(chapter, 'Safari')
+ self.url_result(chapter, SafariApiIE.ie_key())
for chapter in course_json['chapters']]
course_title = course_json['title']
class ScreenJunkiesIE(InfoExtractor):
- _VALID_URL = r'http://www.screenjunkies.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
+ _VALID_URL = r'https?://www.screenjunkies.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
_TESTS = [{
'url': 'http://www.screenjunkies.com/video/best-quentin-tarantino-movie-2841915',
'md5': '5c2b686bec3d43de42bde9ec047536b0',
['arch', '', 'http://ussenate-f.akamaihd.net/']
]
_IE_NAME = 'senate.gov'
- _VALID_URL = r'http://www\.senate\.gov/isvp/?\?(?P<qs>.+)'
+ _VALID_URL = r'https?://www\.senate\.gov/isvp/?\?(?P<qs>.+)'
_TESTS = [{
'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
'info_dict': {
class SharedIE(InfoExtractor):
IE_DESC = 'shared.sx and vivo.sx'
- _VALID_URL = r'http://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})'
+ _VALID_URL = r'https?://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})'
_TESTS = [{
'url': 'http://shared.sx/0060718775',
class Sport5IE(InfoExtractor):
- _VALID_URL = r'http://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)'
_TESTS = [
{
'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1',
class SSAIE(InfoExtractor):
- _VALID_URL = r'http://ssa\.nls\.uk/film/(?P<id>\d+)'
+ _VALID_URL = r'https?://ssa\.nls\.uk/film/(?P<id>\d+)'
_TEST = {
'url': 'http://ssa.nls.uk/film/3561',
'info_dict': {
class SztvHuIE(InfoExtractor):
- _VALID_URL = r'http://(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)'
_TEST = {
'url': 'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909',
'md5': 'a6df607b11fb07d0e9f2ad94613375cb',
class TeamcocoIE(InfoExtractor):
- _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
+ _VALID_URL = r'https?://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)'
_TESTS = [
{
'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant',
class Tele13IE(InfoExtractor):
- _VALID_URL = r'^http://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)'
+ _VALID_URL = r'^https?://(?:www\.)?t13\.cl/videos(?:/[^/]+)+/(?P<id>[\w-]+)'
_TESTS = [
{
'url': 'http://www.t13.cl/videos/actualidad/el-circulo-de-hierro-de-michelle-bachelet-en-su-regreso-a-la-moneda',
class TF1IE(InfoExtractor):
"""TF1 uses the wat.tv player."""
- _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/(?:[^/]+/)*(?P<id>.+?)\.html'
+ _VALID_URL = r'https?://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/(?:[^/]+/)*(?P<id>.+?)\.html'
_TESTS = [{
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
'info_dict': {
--- /dev/null
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+from ..compat import compat_urllib_parse
+from ..utils import qualities
+
+
+class TheSceneIE(InfoExtractor):
+ _VALID_URL = r'https://thescene\.com/watch/[^/]+/(?P<id>[^/#?]+)'
+
+ _TEST = {
+ 'url': 'https://thescene.com/watch/vogue/narciso-rodriguez-spring-2013-ready-to-wear',
+ 'info_dict': {
+ 'id': '520e8faac2b4c00e3c6e5f43',
+ 'ext': 'mp4',
+ 'title': 'Narciso Rodriguez: Spring 2013 Ready-to-Wear',
+ 'display_id': 'narciso-rodriguez-spring-2013-ready-to-wear',
+ },
+ }
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+ player_url = compat_urllib_parse.urljoin(
+ url,
+ self._html_search_regex(
+ r'id=\'js-player-script\'[^>]+src=\'(.+?)\'', webpage, 'player url'))
+
+ self.to_screen(player_url)
+ player = self._download_webpage(player_url, player_url)
+ info = self._parse_json(self._search_regex(r'(?m)var\s+video\s+=\s+({.+?});$', player, 'info json'), display_id)
+
+ qualities_order = qualities(['low', 'high'])
+ formats = [{
+ 'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']),
+ 'url': f['src'],
+ 'quality': qualities_order(f['quality']),
+ } for f in info['sources'][0]]
+ self._sort_formats(formats)
+
+ return {
+ 'id': info['id'],
+ 'title': info['title'],
+ 'formats': formats,
+ 'thumbnail': info.get('poster_frame'),
+ 'display_id': display_id,
+ }
class THVideoIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)'
_TEST = {
'url': 'http://thvideo.tv/v/th1987/',
'md5': 'fa107b1f73817e325e9433505a70db50',
class TinyPicIE(InfoExtractor):
IE_NAME = 'tinypic'
IE_DESC = 'tinypic.com videos'
- _VALID_URL = r'http://(?:.+?\.)?tinypic\.com/player\.php\?v=(?P<id>[^&]+)&s=\d+'
+ _VALID_URL = r'https?://(?:.+?\.)?tinypic\.com/player\.php\?v=(?P<id>[^&]+)&s=\d+'
_TESTS = [
{
class TlcDeIE(InfoExtractor):
IE_NAME = 'tlc.de'
- _VALID_URL = r'http://www\.tlc\.de/(?:[^/]+/)*videos/(?P<title>[^/?#]+)?(?:.*#(?P<id>\d+))?'
+ _VALID_URL = r'https?://www\.tlc\.de/(?:[^/]+/)*videos/(?P<title>[^/?#]+)?(?:.*#(?P<id>\d+))?'
_TEST = {
'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
class ToypicsUserIE(InfoExtractor):
IE_DESC = 'Toypics user profile'
- _VALID_URL = r'http://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])'
+ _VALID_URL = r'https?://videos\.toypics\.net/(?P<username>[^/?]+)(?:$|[?#])'
_TEST = {
'url': 'http://videos.toypics.net/Mikey',
'info_dict': {
class TrailerAddictIE(InfoExtractor):
_WORKING = False
- _VALID_URL = r'(?:http://)?(?:www\.)?traileraddict\.com/(?:trailer|clip)/(?P<movie>.+?)/(?P<trailer_name>.+)'
+ _VALID_URL = r'(?:https?://)?(?:www\.)?traileraddict\.com/(?:trailer|clip)/(?P<movie>.+?)/(?P<trailer_name>.+)'
_TEST = {
'url': 'http://www.traileraddict.com/trailer/prince-avalanche/trailer',
'md5': '41365557f3c8c397d091da510e73ceb4',
class TrollvidsIE(NuevoBaseIE):
- _VALID_URL = r'http://(?:www\.)?trollvids\.com/video/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
+ _VALID_URL = r'https?://(?:www\.)?trollvids\.com/video/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
IE_NAME = 'trollvids'
_TEST = {
'url': 'http://trollvids.com/video/2349002/%E3%80%90MMD-R-18%E3%80%91%E3%82%AC%E3%83%BC%E3%83%AB%E3%83%95%E3%83%AC%E3%83%B3%E3%83%89-carrymeoff',
from ..compat import compat_str
from ..utils import (
int_or_none,
+ InAdvancePagedList,
float_or_none,
unescapeHTML,
)
quality = sorted(filter(lambda k: k.isdigit(), segments.keys()),
key=lambda k: int(k))[-1]
parts = segments[quality]
- result = []
len_parts = len(parts)
if len_parts > 1:
self.to_screen('%s: found %s parts' % (video_id, len_parts))
- for part in parts:
+
+ def part_func(partnum):
+ part = parts[partnum]
part_id = part['k']
final_url = self._url_for_id(part_id, quality)
ext = (final_url.split('?')[0]).split('.')[-1]
- part_info = {
+ return [{
'id': '%s' % part_id,
'url': final_url,
'ext': ext,
'http_headers': {
'Referer': self._PLAYER_URL,
},
- }
- result.append(part_info)
+ }]
+
+ entries = InAdvancePagedList(part_func, len_parts, 1)
return {
'_type': 'multi_video',
- 'entries': result,
+ 'entries': entries,
'id': video_id,
'title': title,
}
class TumblrIE(InfoExtractor):
- _VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
+ _VALID_URL = r'https?://(?P<blog_name>.*?)\.tumblr\.com/(?:post|video)/(?P<id>[0-9]+)(?:$|[/?#])'
_TESTS = [{
'url': 'http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes',
'md5': '479bb068e5b16462f5176a6828829767',
# coding: utf-8
from __future__ import unicode_literals
-import json
+import re
from .common import InfoExtractor
from ..utils import ExtractorError
if not streams_url.startswith('http://'):
streams_url = compat_urlparse.urljoin(url, streams_url)
- stream_data = self._download_webpage(
- streams_url, content_id, note='Downloading stream data')
- streams = json.loads(self._search_regex(
- r'\((.*)\);', stream_data, 'stream info'))['Streams']
+ streams = self._download_json(
+ streams_url, content_id, note='Downloading stream data',
+ transform_source=lambda s: re.sub(r'^\s*\((.*)\);\s*$', r'\1', s))['Streams']
is_live = None
formats = []
class TV2IE(InfoExtractor):
- _VALID_URL = 'http://(?:www\.)?tv2\.no/v/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?tv2\.no/v/(?P<id>\d+)'
_TEST = {
'url': 'http://www.tv2.no/v/916509/',
'info_dict': {
class TV2ArticleIE(InfoExtractor):
- _VALID_URL = 'http://(?:www\.)?tv2\.no/(?:a|\d{4}/\d{2}/\d{2}(/[^/]+)+)/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?tv2\.no/(?:a|\d{4}/\d{2}/\d{2}(/[^/]+)+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.tv2.no/2015/05/16/nyheter/alesund/krim/pingvin/6930542',
'info_dict': {
class TVCIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?tvc\.ru/video/iframe/id/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?tvc\.ru/video/iframe/id/(?P<id>\d+)'
_TEST = {
'url': 'http://www.tvc.ru/video/iframe/id/74622/isPlay/false/id_stat/channel/?acc_video_id=/channel/brand/id/17/show/episodes/episode_id/39702',
'md5': 'bbc5ff531d1e90e856f60fc4b3afd708',
class TVCArticleIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?tvc\.ru/(?!video/iframe/id/)(?P<id>[^?#]+)'
+ _VALID_URL = r'https?://(?:www\.)?tvc\.ru/(?!video/iframe/id/)(?P<id>[^?#]+)'
_TESTS = [{
'url': 'http://www.tvc.ru/channel/brand/id/29/show/episodes/episode_id/39702/',
'info_dict': {
class TVPlayIE(InfoExtractor):
IE_DESC = 'TV3Play and related services'
- _VALID_URL = r'''(?x)http://(?:www\.)?
+ _VALID_URL = r'''(?x)https?://(?:www\.)?
(?:tvplay\.lv/parraides|
tv3play\.lt/programos|
play\.tv3\.lt/programos|
class UbuIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
+ _VALID_URL = r'https?://(?:www\.)?ubu\.com/film/(?P<id>[\da-z_-]+)\.html'
_TEST = {
'url': 'http://ubu.com/film/her_noise.html',
'md5': '138d5652618bf0f03878978db9bef1ee',
class UnistraIE(InfoExtractor):
- _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)'
+ _VALID_URL = r'https?://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)'
_TESTS = [
{
class Vbox7IE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
_TEST = {
'url': 'http://vbox7.com/play:249bb972c2',
'md5': '99f65c0c9ef9b682b97313e052734c3f',
class VeohIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/(?P<id>(?:v|yapi-)[\da-zA-Z]+)'
+ _VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/(?P<id>(?:v|yapi-)[\da-zA-Z]+)'
_TESTS = [
{
class VestiIE(InfoExtractor):
IE_DESC = 'Вести.Ru'
- _VALID_URL = r'http://(?:.+?\.)?vesti\.ru/(?P<id>.+)'
+ _VALID_URL = r'https?://(?:.+?\.)?vesti\.ru/(?P<id>.+)'
_TESTS = [
{
class BTArticleIE(InfoExtractor):
IE_NAME = 'bt:article'
IE_DESC = 'Bergens Tidende Articles'
- _VALID_URL = 'http://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
+ _VALID_URL = r'https?://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
_TEST = {
'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
'md5': '2acbe8ad129b3469d5ae51b1158878df',
class BTVestlendingenIE(InfoExtractor):
IE_NAME = 'bt:vestlendingen'
IE_DESC = 'Bergens Tidende - Vestlendingen'
- _VALID_URL = 'http://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
_WORKING = False
ID_NAME = 'video.tt'
IE_DESC = 'video.tt - Your True Tube'
- _VALID_URL = r'http://(?:www\.)?video\.tt/(?:(?:video|embed)/|watch_video\.php\?v=)(?P<id>[\da-zA-Z]{9})'
+ _VALID_URL = r'https?://(?:www\.)?video\.tt/(?:(?:video|embed)/|watch_video\.php\?v=)(?P<id>[\da-zA-Z]{9})'
_TESTS = [{
'url': 'http://www.video.tt/watch_video.php?v=amd5YujV8',
class ViideaIE(InfoExtractor):
- _VALID_URL = r'''(?x)http://(?:www\.)?(?:
+ _VALID_URL = r'''(?x)https?://(?:www\.)?(?:
videolectures\.net|
flexilearn\.viidea\.net|
presentations\.ocwconsortium\.org|
thumbnail = self._og_search_thumbnail(webpage)
creator = self._html_search_regex(
- r'<div[^>]+class="info_area"[^>]*>\s*<strong[^>]+class="name"[^>]*>([^<]+)</strong>',
+ r'<div[^>]+class="info_area"[^>]*>\s*<a\s+[^>]*>([^<]+)',
webpage, 'creator', fatal=False)
view_count = int_or_none(playinfo.get('meta', {}).get('count'))
class VubeIE(InfoExtractor):
IE_NAME = 'vube'
IE_DESC = 'Vube.com'
- _VALID_URL = r'http://vube\.com/(?:[^/]+/)+(?P<id>[\da-zA-Z]{10})\b'
+ _VALID_URL = r'https?://vube\.com/(?:[^/]+/)+(?P<id>[\da-zA-Z]{10})\b'
_TESTS = [
{
class VuClipIE(InfoExtractor):
- _VALID_URL = r'http://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://m.vuclip.com/w?cid=922692425&fid=70295&z=1010&nvar&frm=index.html',
class WallaIE(InfoExtractor):
- _VALID_URL = r'http://vod\.walla\.co\.il/[^/]+/(?P<id>\d+)/(?P<display_id>.+)'
+ _VALID_URL = r'https?://vod\.walla\.co\.il/[^/]+/(?P<id>\d+)/(?P<display_id>.+)'
_TEST = {
'url': 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one',
'info_dict': {
class WatIE(InfoExtractor):
- _VALID_URL = r'(?:wat:(?P<real_id>\d{8})|http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html)'
+ _VALID_URL = r'(?:wat:(?P<real_id>\d{8})|https?://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html)'
IE_NAME = 'wat.tv'
_TESTS = [
{
class WDRMausIE(InfoExtractor):
- _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
+ _VALID_URL = r'https?://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
IE_DESC = 'Sendung mit der Maus'
_TESTS = [{
'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
class WeiqiTVIE(InfoExtractor):
IE_DESC = 'WQTV'
- _VALID_URL = r'http://www\.weiqitv\.com/index/video_play\?videoId=(?P<id>[A-Za-z0-9]+)'
+ _VALID_URL = r'https?://www\.weiqitv\.com/index/video_play\?videoId=(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'http://www.weiqitv.com/index/video_play?videoId=53c744f09874f0e76a8b46f3',
class WimpIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
+ _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.wimp.com/maruexhausted/',
'md5': 'ee21217ffd66d058e8b16be340b74883',
class XBefIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?xbef\.com/video/(?P<id>[0-9]+)'
+ _VALID_URL = r'https?://(?:www\.)?xbef\.com/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://xbef.com/video/5119-glamourous-lesbians-smoking-drinking-and-fucking',
'md5': 'a478b565baff61634a98f5e5338be995',
from .common import InfoExtractor
from ..utils import (
+ dict_get,
float_or_none,
int_or_none,
unified_strdate,
video_url = self._search_regex(
r'href="(https?://xhamster\.com/movies/%s/[^"]+\.html[^"]*)"' % video_id,
- webpage, 'xhamster url')
+ webpage, 'xhamster url', default=None)
+
+ if not video_url:
+ vars = self._parse_json(
+ self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
+ video_id)
+ video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
return self.url_result(video_url, 'XHamster')
class YamIE(InfoExtractor):
IE_DESC = '蕃薯藤yam天空部落'
- _VALID_URL = r'http://mymedia.yam.com/m/(?P<id>\d+)'
+ _VALID_URL = r'https?://mymedia.yam.com/m/(?P<id>\d+)'
_TESTS = [{
# An audio hosted on Yam
class YnetIE(InfoExtractor):
- _VALID_URL = r'http://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
+ _VALID_URL = r'https?://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?P<id>L(?:-[0-9]+)+),00\.html'
_TESTS = [
{
'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html',
postproc.add_option(
'--embed-subs',
action='store_true', dest='embedsubtitles', default=False,
- help='Embed subtitles in the video (only for mkv and mp4 videos)')
+ help='Embed subtitles in the video (only for mp4, webm and mkv videos)')
postproc.add_option(
'--embed-thumbnail',
action='store_true', dest='embedthumbnail', default=False,
class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
def run(self, information):
- if information['ext'] not in ['mp4', 'mkv']:
- self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4 or mkv files')
+ if information['ext'] not in ('mp4', 'webm', 'mkv'):
+ self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4, webm or mkv files')
return [], information
subtitles = information.get('requested_subtitles')
if not subtitles:
self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to embed')
return [], information
- sub_langs = list(subtitles.keys())
filename = information['filepath']
- sub_filenames = [subtitles_filename(filename, lang, sub_info['ext']) for lang, sub_info in subtitles.items()]
+
+ ext = information['ext']
+ sub_langs = []
+ sub_filenames = []
+ webm_vtt_warn = False
+
+ for lang, sub_info in subtitles.items():
+ sub_ext = sub_info['ext']
+ if ext != 'webm' or ext == 'webm' and sub_ext == 'vtt':
+ sub_langs.append(lang)
+ sub_filenames.append(subtitles_filename(filename, lang, sub_ext))
+ else:
+ if not webm_vtt_warn and ext == 'webm' and sub_ext != 'vtt':
+ webm_vtt_warn = True
+ self._downloader.to_screen('[ffmpeg] Only WebVTT subtitles can be embedded in webm files')
+
+ if not sub_langs:
+ return [], information
+
input_files = [filename] + sub_filenames
opts = [
"""Escape URL as suggested by RFC 3986"""
url_parsed = compat_urllib_parse_urlparse(url)
return url_parsed._replace(
+ netloc=url_parsed.netloc.encode('idna').decode('ascii'),
path=escape_rfc3986(url_parsed.path),
params=escape_rfc3986(url_parsed.params),
query=escape_rfc3986(url_parsed.query),
projects / youtube-dl / commitdiff