R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #23 from aviperes/master

Browse Source 
merging recent changes fron youtube-dl:master
This commit is contained in:
aviperes 2019-07-07 11:24:59 +03:00 committed by GitHub
commit 36df1e884a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
12 changed files with 140 additions and 379 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/extractor/adobepass.py
View File

@ -25,6 +25,11 @@ MSO_INFO = {
'username_field': 'username',
'password_field': 'password',
},
'ATT': {
'name': 'AT&T U-verse',
'username_field': 'userid',
'password_field': 'password',
},
'ATTOTT': {
'name': 'DIRECTV NOW',
'username_field': 'email',

330
youtube_dl/extractor/arte.py
View File

@ -4,17 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlparse,
)
from ..compat import compat_str
from ..utils import (
ExtractorError,
find_xpath_attr,
get_element_by_attribute,
int_or_none,
NO_DEFAULT,
qualities,
try_get,
unified_strdate,
@ -25,59 +18,7 @@ from ..utils import (
# add tests.
class ArteTvIE(InfoExtractor):
_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):
mobj = re.match(self._VALID_URL, url)
lang = mobj.group('lang')
video_id = mobj.group('id')
ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
ref_xml_doc = self._download_xml(
ref_xml_url, video_id, note='Downloading metadata')
config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
config_xml_url = config_node.attrib['ref']
config = self._download_xml(
config_xml_url, video_id, note='Downloading configuration')
formats = [{
'format_id': q.attrib['quality'],
# The playpath starts at 'mp4:', if we don't manually
# split the url, rtmpdump will incorrectly parse them
'url': q.text.split('mp4:', 1)[0],
'play_path': 'mp4:' + q.text.split('mp4:', 1)[1],
'ext': 'flv',
'quality': 2 if q.attrib['quality'] == 'hd' else 1,
} for q in config.findall('./urls/url')]
self._sort_formats(formats)
title = config.find('.//name').text
thumbnail = config.find('.//firstThumbnailUrl').text
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}
class ArteTVBaseIE(InfoExtractor):
@classmethod
def _extract_url_info(cls, url):
mobj = re.match(cls._VALID_URL, url)
lang = mobj.group('lang')
query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
if 'vid' in query:
video_id = query['vid'][0]
else:
# This is not a real id, it can be for example AJT for the news
# http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
video_id = mobj.group('id')
return video_id, lang
def _extract_from_json_url(self, json_url, video_id, lang, title=None):
info = self._download_json(json_url, video_id)
player_info = info['videoJsonPlayer']
@ -108,13 +49,15 @@ class ArteTVBaseIE(InfoExtractor):
'upload_date': unified_strdate(upload_date_str),
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
}
qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
qfunc = qualities(['MQ', 'HQ', 'EQ', 'SQ'])
LANGS = {
'fr': 'F',
'de': 'A',
'en': 'E[ANG]',
'es': 'E[ESP]',
'it': 'E[ITA]',
'pl': 'E[POL]',
}
langcode = LANGS.get(lang, lang)
@ -126,8 +69,8 @@ class ArteTVBaseIE(InfoExtractor):
l = re.escape(langcode)
# Language preference from most to least priority
# Reference: section 5.6.3 of
# http://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-05.pdf
# Reference: section 6.8 of
# https://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-07-1.pdf
PREFERENCES = (
# original version in requested language, without subtitles
r'VO{0}$'.format(l),
@ -193,274 +136,59 @@ class ArteTVBaseIE(InfoExtractor):
class ArteTVPlus7IE(ArteTVBaseIE):
IE_NAME = 'arte.tv:+7'
_VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>\d{6}-\d{3}-[AF])'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
'only_matching': True,
}, {
'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
'only_matching': True,
}, {
'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn',
'only_matching': True,
'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
'info_dict': {
'id': '088501-000-A',
'ext': 'mp4',
'title': 'Mexico: Stealing Petrol to Survive',
'upload_date': '20190628',
},
}]
@classmethod
def suitable(cls, url):
return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url)
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, video_id)
return self._extract_from_webpage(webpage, video_id, lang)
def _extract_from_webpage(self, webpage, video_id, lang):
patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
ids = (video_id, '')
# some pages contain multiple videos (like
# http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
# so we first try to look for json URLs that contain the video id from
# the 'vid' parameter.
patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
json_url = self._html_search_regex(
patterns, webpage, 'json vp url', default=None)
if not json_url:
def find_iframe_url(webpage, default=NO_DEFAULT):
return self._html_search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
webpage, 'iframe url', group='url', default=default)
iframe_url = find_iframe_url(webpage, None)
if not iframe_url:
embed_url = self._html_search_regex(
r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
if embed_url:
player = self._download_json(
embed_url, video_id, 'Downloading player page')
iframe_url = find_iframe_url(player['html'])
# en and es URLs produce react-based pages with different layout (e.g.
# http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
if not iframe_url:
program = self._search_regex(
r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
webpage, 'program', default=None)
if program:
embed_html = self._parse_json(program, video_id)
if embed_html:
iframe_url = find_iframe_url(embed_html['embed_html'])
if iframe_url:
json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
if json_url:
title = self._search_regex(
r'<h3[^>]+title=(["\'])(?P<title>.+?)\1',
webpage, 'title', default=None, group='title')
return self._extract_from_json_url(json_url, video_id, lang, title=title)
# Different kind of embed URL (e.g.
# http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
entries = [
self.url_result(url)
for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)]
return self.playlist_result(entries)
# It also uses the arte_vp_url url from the webpage to extract the information
class ArteTVCreativeIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:creative'
_VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1',
'info_dict': {
'id': '057405-001-A',
'ext': 'mp4',
'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)',
'upload_date': '20150716',
},
}, {
'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
'playlist_count': 11,
'add_ie': ['Youtube'],
}, {
'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde',
'only_matching': True,
}]
class ArteTVInfoIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:info'
_VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere',
'info_dict': {
'id': '067528-000-A',
'ext': 'mp4',
'title': 'Service civique, un cache misère ?',
'upload_date': '20160403',
},
}]
class ArteTVFutureIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:future'
_VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses',
'info_dict': {
'id': '050940-028-A',
'ext': 'mp4',
'title': 'Les écrevisses aussi peuvent être anxieuses',
'upload_date': '20140902',
},
}, {
'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable',
'only_matching': True,
}]
class ArteTVDDCIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:ddc'
_VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
_TESTS = []
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
if lang == 'folge':
lang = 'de'
elif lang == 'emission':
lang = 'fr'
webpage = self._download_webpage(url, video_id)
scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
return self._extract_from_json_url(json_url, video_id, lang)
class ArteTVConcertIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:concert'
_VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
'md5': '9ea035b7bd69696b67aa2ccaaa218161',
'info_dict': {
'id': '186',
'ext': 'mp4',
'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
'upload_date': '20140128',
'description': 'md5:486eb08f991552ade77439fe6d82c305',
},
}]
class ArteTVCinemaIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:cinema'
_VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
_TESTS = [{
'url': 'http://cinema.arte.tv/fr/article/les-ailes-du-desir-de-julia-reck',
'md5': 'a5b9dd5575a11d93daf0e3f404f45438',
'info_dict': {
'id': '062494-000-A',
'ext': 'mp4',
'title': 'Film lauréat du concours web - "Les ailes du désir" de Julia Reck',
'upload_date': '20150807',
},
}]
class ArteTVMagazineIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:magazine'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/magazine/[^/]+/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
# Embedded via <iframe src="http://www.arte.tv/arte_vp/index.php?json_url=..."
'url': 'http://www.arte.tv/magazine/trepalium/fr/entretien-avec-le-realisateur-vincent-lannoo-trepalium',
'md5': '2a9369bcccf847d1c741e51416299f25',
'info_dict': {
'id': '065965-000-A',
'ext': 'mp4',
'title': 'Trepalium - Extrait Ep.01',
'upload_date': '20160121',
},
}, {
# Embedded via <iframe src="http://www.arte.tv/guide/fr/embed/054813-004-A/medium"
'url': 'http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium',
'md5': 'fedc64fc7a946110fe311634e79782ca',
'info_dict': {
'id': '054813-004_PLUS7-F',
'ext': 'mp4',
'title': 'Trepalium (4/6)',
'description': 'md5:10057003c34d54e95350be4f9b05cb40',
'upload_date': '20160218',
},
}, {
'url': 'http://www.arte.tv/magazine/metropolis/de/frank-woeste-german-paris-metropolis',
'only_matching': True,
}]
lang, video_id = re.match(self._VALID_URL, url).groups()
return self._extract_from_json_url(
'https://api.arte.tv/api/player/v1/config/%s/%s' % (lang, video_id),
video_id, lang)
class ArteTVEmbedIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:embed'
_VALID_URL = r'''(?x)
http://www\.arte\.tv
/(?:playerv2/embed|arte_vp/index)\.php\?json_url=
https://www\.arte\.tv
/player/v3/index\.php\?json_url=
(?P<json_url>
http://arte\.tv/papi/tvguide/videos/stream/player/
(?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*
https?://api\.arte\.tv/api/player/v1/config/
(?P<lang>[^/]+)/(?P<id>\d{6}-\d{3}-[AF])
)
'''
_TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
lang = mobj.group('lang')
json_url = mobj.group('json_url')
json_url, lang, video_id = re.match(self._VALID_URL, url).groups()
return self._extract_from_json_url(json_url, video_id, lang)
class TheOperaPlatformIE(ArteTVPlus7IE):
IE_NAME = 'theoperaplatform'
_VALID_URL = r'https?://(?:www\.)?theoperaplatform\.eu/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.theoperaplatform.eu/de/opera/verdi-otello',
'md5': '970655901fa2e82e04c00b955e9afe7b',
'info_dict': {
'id': '060338-009-A',
'ext': 'mp4',
'title': 'Verdi - OTELLO',
'upload_date': '20160927',
},
}]
class ArteTVPlaylistIE(ArteTVBaseIE):
IE_NAME = 'arte.tv:playlist'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>RC-\d{6})'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/plus7/?country=DE#collection/PL-013263/ARTETV',
'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
'info_dict': {
'id': 'PL-013263',
'title': 'Areva & Uramin',
'description': 'md5:a1dc0312ce357c262259139cfd48c9bf',
'id': 'RC-016954',
'title': 'Earn a Living',
'description': 'md5:d322c55011514b3a7241f7fb80d494c2',
},
'playlist_mincount': 6,
}, {
'url': 'http://www.arte.tv/guide/de/playlists?country=DE#collection/PL-013190/ARTETV',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id, lang = self._extract_url_info(url)
lang, playlist_id = re.match(self._VALID_URL, url).groups()
collection = self._download_json(
'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos'
% (lang, playlist_id), playlist_id)

5
youtube_dl/extractor/beampro.py
View File

@ -99,7 +99,7 @@ class BeamProLiveIE(BeamProBaseIE):
class BeamProVodIE(BeamProBaseIE):
IE_NAME = 'Mixer:vod'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>\w+)'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>[^?#&]+)'
_TESTS = [{
'url': 'https://mixer.com/willow8714?vod=2259830',
'md5': 'b2431e6e8347dc92ebafb565d368b76b',
@ -122,6 +122,9 @@ class BeamProVodIE(BeamProBaseIE):
}, {
'url': 'https://mixer.com/streamer?vod=IxFno1rqC0S_XJ1a2yGgNw',
'only_matching': True,
}, {
'url': 'https://mixer.com/streamer?vod=Rh3LY0VAqkGpEQUe2pN-ig',
'only_matching': True,
}]
@staticmethod

9
youtube_dl/extractor/extractors.py
View File

@ -58,17 +58,8 @@ from .ard import (
ARDMediathekIE,
)
from .arte import (
ArteTvIE,
ArteTVPlus7IE,
ArteTVCreativeIE,
ArteTVConcertIE,
ArteTVInfoIE,
ArteTVFutureIE,
ArteTVCinemaIE,
ArteTVDDCIE,
ArteTVMagazineIE,
ArteTVEmbedIE,
TheOperaPlatformIE,
ArteTVPlaylistIE,
)
from .asiancrush import (

10
youtube_dl/extractor/go.py
View File

@ -34,9 +34,13 @@ class GoIE(AdobePassIE):
'watchdisneyxd': {
'brand': '009',
'resource_id': 'DisneyXD',
},
'disneynow': {
'brand': '011',
'resource_id': 'Disney',
}
}
_VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|disneynow)\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
_VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|(?P<sub_domain_2>disneynow))\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
% '|'.join(list(_SITE_INFO.keys()) + ['disneynow'])
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
@ -83,7 +87,9 @@ class GoIE(AdobePassIE):
display_id)['video']
def _real_extract(self, url):
sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
mobj = re.match(self._VALID_URL, url)
sub_domain = mobj.group('sub_domain') or mobj.group('sub_domain_2')
video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand')
if not video_id or not site_info:

113
youtube_dl/extractor/lecturio.py
View File

@ -6,8 +6,8 @@ import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
determine_ext,
extract_attributes,
ExtractorError,
float_or_none,
int_or_none,
@ -19,6 +19,7 @@ from ..utils import (
class LecturioBaseIE(InfoExtractor):
_API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
_LOGIN_URL = 'https://app.lecturio.com/en/login'
_NETRC_MACHINE = 'lecturio'
@ -67,51 +68,56 @@ class LecturioIE(LecturioBaseIE):
_VALID_URL = r'''(?x)
https://
(?:
app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture|
(?:www\.)?lecturio\.de/[^/]+/(?P<id_de>[^/?#&]+)\.vortrag
app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
(?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
)
'''
_TESTS = [{
'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
'md5': '9a42cf1d8282a6311bf7211bbde26fde',
'info_dict': {
'id': '39634',
'ext': 'mp4',
'title': 'Important Concepts and Terms – Introduction to Microbiology',
'title': 'Important Concepts and Terms — Introduction to Microbiology',
},
'skip': 'Requires lecturio account credentials',
}, {
'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
'only_matching': True,
}, {
'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
'only_matching': True,
}]
_CC_LANGS = {
'Arabic': 'ar',
'Bulgarian': 'bg',
'German': 'de',
'English': 'en',
'Spanish': 'es',
'Persian': 'fa',
'French': 'fr',
'Japanese': 'ja',
'Polish': 'pl',
'Pashto': 'ps',
'Russian': 'ru',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id') or mobj.group('id_de')
webpage = self._download_webpage(
'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
display_id)
lecture_id = self._search_regex(
r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id')
api_url = self._search_regex(
r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'api url', group='url')
video = self._download_json(api_url, display_id)
nt = mobj.group('nt') or mobj.group('nt_de')
lecture_id = mobj.group('id')
display_id = nt or lecture_id
api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
video = self._download_json(
self._API_BASE_URL + api_path, display_id)
title = video['title'].strip()
if not lecture_id:
pid = video.get('productId') or video.get('uid')
if pid:
spid = pid.split('_')
if spid and len(spid) == 2:
lecture_id = spid[1]
formats = []
for format_ in video['content']['media']:
@ -129,24 +135,30 @@ class LecturioIE(LecturioBaseIE):
continue
label = str_or_none(format_.get('label'))
filesize = int_or_none(format_.get('fileSize'))
formats.append({
f = {
'url': file_url,
'format_id': label,
'filesize': float_or_none(filesize, invscale=1000)
})
}
if label:
mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
if mobj:
f.update({
'format_id': mobj.group(2),
'height': int(mobj.group(1)),
})
formats.append(f)
self._sort_formats(formats)
subtitles = {}
automatic_captions = {}
cc = self._parse_json(
self._search_regex(
r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles',
default='{}'), display_id, fatal=False)
for cc_label, cc_url in cc.items():
cc_url = url_or_none(cc_url)
captions = video.get('captions') or []
for cc in captions:
cc_url = cc.get('url')
if not cc_url:
continue
lang = self._search_regex(
cc_label = cc.get('translatedCode')
lang = cc.get('languageCode') or self._search_regex(
r'/([a-z]{2})_', cc_url, 'lang',
default=cc_label.split()[0] if cc_label else 'en')
original_lang = self._search_regex(
@ -160,7 +172,7 @@ class LecturioIE(LecturioBaseIE):
})
return {
'id': lecture_id,
'id': lecture_id or nt,
'title': title,
'formats': formats,
'subtitles': subtitles,
@ -169,37 +181,40 @@ class LecturioIE(LecturioBaseIE):
class LecturioCourseIE(LecturioBaseIE):
_VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course'
_TEST = {
_VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
_TESTS = [{
'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
'info_dict': {
'id': 'microbiology-introduction',
'title': 'Microbiology: Introduction',
'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
},
'playlist_count': 45,
'skip': 'Requires lecturio account credentials',
}
}, {
'url': 'https://app.lecturio.com/#/course/c/6434',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nt, course_id = re.match(self._VALID_URL, url).groups()
display_id = nt or course_id
api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
course = self._download_json(
self._API_BASE_URL + api_path, display_id)
entries = []
for mobj in re.finditer(
r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>',
webpage):
params = extract_attributes(mobj.group(0))
lecture_url = urljoin(url, params.get('data-url'))
lecture_id = params.get('data-id')
for lecture in course.get('lectures', []):
lecture_id = str_or_none(lecture.get('id'))
lecture_url = lecture.get('url')
if lecture_url:
lecture_url = urljoin(url, lecture_url)
else:
lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
entries.append(self.url_result(
lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
title = self._search_regex(
r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage,
'title', default=None)
return self.playlist_result(entries, display_id, title)
return self.playlist_result(
entries, display_id, course.get('title'),
clean_html(course.get('description')))
class LecturioDeCourseIE(LecturioBaseIE):

2
youtube_dl/extractor/peertube.py
View File

@ -168,7 +168,7 @@ class PeerTubeIE(InfoExtractor):
@staticmethod
def _extract_peertube_url(webpage, source_url):
mobj = re.match(
r'https?://(?P<host>[^/]+)/videos/watch/(?P<id>%s)'
r'https?://(?P<host>[^/]+)/videos/(?:watch|embed)/(?P<id>%s)'
% PeerTubeIE._UUID_RE, source_url)
if mobj and any(p in webpage for p in (
'<title>PeerTube<',

8
youtube_dl/extractor/philharmoniedeparis.py
View File

@ -14,7 +14,7 @@ class PhilharmonieDeParisIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)|
live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|embed(?:app)?/|misc/Playlist\.ashx\?id=)|
pad\.philharmoniedeparis\.fr/doc/CIMU/
)
(?P<id>\d+)
@ -40,6 +40,12 @@ class PhilharmonieDeParisIE(InfoExtractor):
}, {
'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
'only_matching': True,
}, {
'url': 'https://live.philharmoniedeparis.fr/embedapp/1098406/berlioz-fantastique-lelio-les-siecles-national-youth-choir-of.html?lang=fr-FR',
'only_matching': True,
}, {
'url': 'https://live.philharmoniedeparis.fr/embed/1098406/berlioz-fantastique-lelio-les-siecles-national-youth-choir-of.html?lang=fr-FR',
'only_matching': True,
}]
_LIVE_URL = 'https://live.philharmoniedeparis.fr'

2
youtube_dl/extractor/ted.py
View File

@ -133,7 +133,7 @@ class TEDIE(InfoExtractor):
def _extract_info(self, webpage):
info_json = self._search_regex(
r'(?s)q\(\s*"\w+.init"\s*,\s*({.+})\)\s*</script>',
r'(?s)q\(\s*"\w+.init"\s*,\s*({.+?})\)\s*</script>',
webpage, 'info json')
return json.loads(info_json)

27
youtube_dl/extractor/tvland.py
View File

@ -1,32 +1,35 @@
# coding: utf-8
from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
from .spike import ParamountNetworkIE
class TVLandIE(MTVServicesInfoExtractor):
class TVLandIE(ParamountNetworkIE):
IE_NAME = 'tvland.com'
_VALID_URL = r'https?://(?:www\.)?tvland\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
_FEED_URL = 'http://www.tvland.com/feeds/mrss/'
_TESTS = [{
# Geo-restricted. Without a proxy metadata are still there. With a
# proxy it redirects to http://m.tvland.com/app/
'url': 'http://www.tvland.com/episodes/hqhps2/everybody-loves-raymond-the-invasion-ep-048',
'url': 'https://www.tvland.com/episodes/s04pzf/everybody-loves-raymond-the-dog-season-1-ep-19',
'info_dict': {
'description': 'md5:80973e81b916a324e05c14a3fb506d29',
'title': 'The Invasion',
'description': 'md5:84928e7a8ad6649371fbf5da5e1ad75a',
'title': 'The Dog',
},
'playlist': [],
'playlist_mincount': 5,
}, {
'url': 'http://www.tvland.com/video-clips/zea2ev/younger-younger--hilary-duff---little-lies',
'url': 'https://www.tvland.com/video-clips/4n87f2/younger-a-first-look-at-younger-season-6',
'md5': 'e2c6389401cf485df26c79c247b08713',
'info_dict': {
'id': 'b8697515-4bbe-4e01-83d5-fa705ce5fa88',
'id': '891f7d3c-5b5b-4753-b879-b7ba1a601757',
'ext': 'mp4',
'title': 'Younger|December 28, 2015|2|NO-EPISODE#|Younger: Hilary Duff - Little Lies',
'description': 'md5:7d192f56ca8d958645c83f0de8ef0269',
'upload_date': '20151228',
'timestamp': 1451289600,
'title': 'Younger|April 30, 2019|6|NO-EPISODE#|A First Look at Younger Season 6',
'description': 'md5:595ea74578d3a888ae878dfd1c7d4ab2',
'upload_date': '20190430',
'timestamp': 1556658000,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.tvland.com/full-episodes/iu0hz6/younger-a-kiss-is-just-a-kiss-season-3-ep-301',

2
youtube_dl/extractor/twitch.py
View File

@ -317,7 +317,7 @@ class TwitchVodIE(TwitchItemBaseIE):
'Downloading %s access token' % self._ITEM_TYPE)
formats = self._extract_m3u8_formats(
'%s/vod/%s?%s' % (
'%s/vod/%s.m3u8?%s' % (
self._USHER_BASE, item_id,
compat_urllib_parse_urlencode({
'allow_source': 'true',

6
youtube_dl/extractor/vzaar.py
View File

@ -32,6 +32,10 @@ class VzaarIE(InfoExtractor):
'ext': 'mp3',
'title': 'MP3',
},
}, {
# with null videoTitle
'url': 'https://view.vzaar.com/20313539/download',
'only_matching': True,
}]
@staticmethod
@ -45,7 +49,7 @@ class VzaarIE(InfoExtractor):
video_data = self._download_json(
'http://view.vzaar.com/v2/%s/video' % video_id, video_id)
title = video_data['videoTitle']
title = video_data.get('videoTitle') or video_id
formats = []