Script 'mail_helper' called by obssrc
Hello community,
here is the log from the commit of package youtube-dl for openSUSE:Factory
checked in at 2021-04-01 14:17:59
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/youtube-dl (Old)
and /work/SRC/openSUSE:Factory/.youtube-dl.new.2401 (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "youtube-dl"
Thu Apr 1 14:17:59 2021 rev:163 rq:882458 version:2021.04.01
Changes:
--------
--- /work/SRC/openSUSE:Factory/youtube-dl/python-youtube-dl.changes
2021-03-28 11:56:27.952229457 +0200
+++ /work/SRC/openSUSE:Factory/.youtube-dl.new.2401/python-youtube-dl.changes
2021-04-01 14:19:27.236167290 +0200
@@ -1,0 +2,10 @@
+Wed Mar 31 22:09:07 UTC 2021 - Jan Engelhardt <jeng...@inai.de>
+
+- Update to release 2021.04.01
+ * youtube: fix playlist/comunity continuation items extraction
+ * vimeo: fix unlisted video extraction
+ * youtube: fix video's channel extraction
+ * youtube: imporve age-restricted video extraction
+ * youtube: setup CONSENT cookie when needed
+
+-------------------------------------------------------------------
youtube-dl.changes: same change
Old:
----
youtube-dl-2021.03.25.tar.gz
youtube-dl-2021.03.25.tar.gz.sig
New:
----
youtube-dl-2021.04.01.tar.gz
youtube-dl-2021.04.01.tar.gz.sig
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Other differences:
------------------
++++++ python-youtube-dl.spec ++++++
--- /var/tmp/diff_new_pack.aM0J0c/_old 2021-04-01 14:19:27.952168245 +0200
+++ /var/tmp/diff_new_pack.aM0J0c/_new 2021-04-01 14:19:27.956168251 +0200
@@ -19,7 +19,7 @@
%define modname youtube-dl
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
Name: python-youtube-dl
-Version: 2021.03.25
+Version: 2021.04.01
Release: 0
Summary: A Python module for downloading from video sites for offline
watching
License: CC-BY-SA-3.0 AND SUSE-Public-Domain
++++++ youtube-dl.spec ++++++
--- /var/tmp/diff_new_pack.aM0J0c/_old 2021-04-01 14:19:27.972168272 +0200
+++ /var/tmp/diff_new_pack.aM0J0c/_new 2021-04-01 14:19:27.976168277 +0200
@@ -17,7 +17,7 @@
Name: youtube-dl
-Version: 2021.03.25
+Version: 2021.04.01
Release: 0
Summary: A tool for downloading from video sites for offline watching
License: CC-BY-SA-3.0 AND SUSE-Public-Domain
++++++ youtube-dl-2021.03.25.tar.gz -> youtube-dl-2021.04.01.tar.gz ++++++
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/ChangeLog new/youtube-dl/ChangeLog
--- old/youtube-dl/ChangeLog 2021-03-24 18:04:07.000000000 +0100
+++ new/youtube-dl/ChangeLog 2021-03-31 23:47:08.000000000 +0200
@@ -1,3 +1,26 @@
+version 2021.04.01
+
+Extractors
+* [youtube] Setup CONSENT cookie when needed (#28604)
+* [vimeo] Fix password protected review extraction (#27591)
+* [youtube] Improve age-restricted video extraction (#28578)
+
+
+version 2021.03.31
+
+Extractors
+* [vlive] Fix inkey request (#28589)
+* [francetvinfo] Improve video id extraction (#28584)
++ [instagram] Extract duration (#28469)
+* [instagram] Improve title extraction (#28469)
++ [sbs] Add support for ondemand watch URLs (#28566)
+* [youtube] Fix video's channel extraction (#28562)
+* [picarto] Fix live stream extraction (#28532)
+* [vimeo] Fix unlisted video extraction (#28414)
+* [youtube:tab] Fix playlist/community continuation items extraction (#28266)
+* [ard] Improve clip id extraction (#22724, #28528)
+
+
version 2021.03.25
Extractors
Binary files old/youtube-dl/youtube-dl and new/youtube-dl/youtube-dl differ
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/ard.py
new/youtube-dl/youtube_dl/extractor/ard.py
--- old/youtube-dl/youtube_dl/extractor/ard.py 2021-03-24 18:03:49.000000000
+0100
+++ new/youtube-dl/youtube_dl/extractor/ard.py 2021-03-30 22:01:34.000000000
+0200
@@ -335,7 +335,7 @@
class ARDBetaMediathekIE(ARDMediathekBaseIE):
- _VALID_URL =
r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?P<client>[^/]+)/(?:player|live|video)/(?P<display_id>(?:[^/]+/)*)(?P<video_id>[a-zA-Z0-9]+)'
+ _VALID_URL =
r'https://(?:(?:beta|www)\.)?ardmediathek\.de/(?:[^/]+/)?(?:player|live|video)/(?:[^/]+/)*(?P<id>Y3JpZDovL[a-zA-Z0-9]+)'
_TESTS = [{
'url':
'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
'md5': 'a1dc75a39c61601b980648f7c9f9f71d',
@@ -365,22 +365,22 @@
}, {
'url':
'https://www.ardmediathek.de/swr/live/Y3JpZDovL3N3ci5kZS8xMzQ4MTA0Mg',
'only_matching': True,
+ }, {
+ 'url':
'https://www.ardmediathek.de/video/coronavirus-update-ndr-info/astrazeneca-kurz-lockdown-und-pims-syndrom-81/ndr/Y3JpZDovL25kci5kZS84NzE0M2FjNi0wMWEwLTQ5ODEtOTE5NS1mOGZhNzdhOTFmOTI/',
+ 'only_matching': True,
+ }, {
+ 'url':
'https://www.ardmediathek.de/ard/player/Y3JpZDovL3dkci5kZS9CZWl0cmFnLWQ2NDJjYWEzLTMwZWYtNGI4NS1iMTI2LTU1N2UxYTcxOGIzOQ/tatort-duo-koeln-leipzig-ihr-kinderlein-kommet',
+ 'only_matching': True,
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('video_id')
- display_id = mobj.group('display_id')
- if display_id:
- display_id = display_id.rstrip('/')
- if not display_id:
- display_id = video_id
+ video_id = self._match_id(url)
player_page = self._download_json(
'https://api.ardmediathek.de/public-gateway',
- display_id, data=json.dumps({
+ video_id, data=json.dumps({
'query': '''{
- playerPage(client:"%s", clipId: "%s") {
+ playerPage(client: "ard", clipId: "%s") {
blockedByFsk
broadcastedOn
maturityContentRating
@@ -410,7 +410,7 @@
}
}
}
-}''' % (mobj.group('client'), video_id),
+}''' % video_id,
}).encode(), headers={
'Content-Type': 'application/json'
})['data']['playerPage']
@@ -435,7 +435,6 @@
r'\(FSK\s*(\d+)\)\s*$', description, 'age limit',
default=None))
info.update({
'age_limit': age_limit,
- 'display_id': display_id,
'title': title,
'description': description,
'timestamp': unified_timestamp(player_page.get('broadcastedOn')),
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/francetv.py
new/youtube-dl/youtube_dl/extractor/francetv.py
--- old/youtube-dl/youtube_dl/extractor/francetv.py 2021-03-24
18:03:49.000000000 +0100
+++ new/youtube-dl/youtube_dl/extractor/francetv.py 2021-03-30
22:01:34.000000000 +0200
@@ -399,7 +399,8 @@
video_id = self._search_regex(
(r'player\.load[^;]+src:\s*["\']([^"\']+)',
r'id-video=([^@]+@[^"]+)',
-
r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"'),
+
r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"',
+
r'data-id=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'),
webpage, 'video id')
return self._make_url_result(video_id)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/instagram.py
new/youtube-dl/youtube_dl/extractor/instagram.py
--- old/youtube-dl/youtube_dl/extractor/instagram.py 2021-03-24
18:03:49.000000000 +0100
+++ new/youtube-dl/youtube_dl/extractor/instagram.py 2021-03-30
22:01:34.000000000 +0200
@@ -12,6 +12,7 @@
)
from ..utils import (
ExtractorError,
+ float_or_none,
get_element_by_attribute,
int_or_none,
lowercase_escape,
@@ -32,6 +33,7 @@
'title': 'Video by naomipq',
'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
'thumbnail': r're:^https?://.*\.jpg',
+ 'duration': 0,
'timestamp': 1371748545,
'upload_date': '20130620',
'uploader_id': 'naomipq',
@@ -48,6 +50,7 @@
'ext': 'mp4',
'title': 'Video by britneyspears',
'thumbnail': r're:^https?://.*\.jpg',
+ 'duration': 0,
'timestamp': 1453760977,
'upload_date': '20160125',
'uploader_id': 'britneyspears',
@@ -87,6 +90,24 @@
'description': 'md5:0f9203fc6a2ce4d228da5754bcf54957',
},
}, {
+ # IGTV
+ 'url': 'https://www.instagram.com/tv/BkfuX9UB-eK/',
+ 'info_dict': {
+ 'id': 'BkfuX9UB-eK',
+ 'ext': 'mp4',
+ 'title': 'Fingerboarding Tricks with @cass.fb',
+ 'thumbnail': r're:^https?://.*\.jpg',
+ 'duration': 53.83,
+ 'timestamp': 1530032919,
+ 'upload_date': '20180626',
+ 'uploader_id': 'instagram',
+ 'uploader': 'Instagram',
+ 'like_count': int,
+ 'comment_count': int,
+ 'comments': list,
+ 'description': 'Meet Cass Hirst (@cass.fb), a fingerboarding pro
who can perform tiny ollies and kickflips while blindfolded.',
+ }
+ }, {
'url': 'https://instagram.com/p/-Cmh1cukG2/',
'only_matching': True,
}, {
@@ -159,7 +180,9 @@
description = try_get(
media, lambda x:
x['edge_media_to_caption']['edges'][0]['node']['text'],
compat_str) or media.get('caption')
+ title = media.get('title')
thumbnail = media.get('display_src') or media.get('display_url')
+ duration = float_or_none(media.get('video_duration'))
timestamp = int_or_none(media.get('taken_at_timestamp') or
media.get('date'))
uploader = media.get('owner', {}).get('full_name')
uploader_id = media.get('owner', {}).get('username')
@@ -200,9 +223,10 @@
continue
entries.append({
'id': node.get('shortcode') or node['id'],
- 'title': 'Video %d' % edge_num,
+ 'title': node.get('title') or 'Video %d' %
edge_num,
'url': node_video_url,
'thumbnail': node.get('display_url'),
+ 'duration':
float_or_none(node.get('video_duration')),
'width': int_or_none(try_get(node, lambda x:
x['dimensions']['width'])),
'height': int_or_none(try_get(node, lambda x:
x['dimensions']['height'])),
'view_count':
int_or_none(node.get('video_view_count')),
@@ -239,8 +263,9 @@
'id': video_id,
'formats': formats,
'ext': 'mp4',
- 'title': 'Video by %s' % uploader_id,
+ 'title': title or 'Video by %s' % uploader_id,
'description': description,
+ 'duration': duration,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader_id': uploader_id,
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/picarto.py
new/youtube-dl/youtube_dl/extractor/picarto.py
--- old/youtube-dl/youtube_dl/extractor/picarto.py 2021-03-24
18:03:49.000000000 +0100
+++ new/youtube-dl/youtube_dl/extractor/picarto.py 2021-03-30
22:01:34.000000000 +0200
@@ -1,22 +1,15 @@
# coding: utf-8
from __future__ import unicode_literals
-import re
-import time
-
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
ExtractorError,
js_to_json,
- try_get,
- update_url_query,
- urlencode_postdata,
)
class PicartoIE(InfoExtractor):
- _VALID_URL =
r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)(?:/(?P<token>[a-zA-Z0-9]+))?'
+ _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
_TEST = {
'url': 'https://picarto.tv/Setz',
'info_dict': {
@@ -34,65 +27,46 @@
return False if PicartoVodIE.suitable(url) else super(PicartoIE,
cls).suitable(url)
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- channel_id = mobj.group('id')
+ channel_id = self._match_id(url)
- metadata = self._download_json(
- 'https://api.picarto.tv/v1/channel/name/' + channel_id,
- channel_id)
+ data = self._download_json(
+ 'https://ptvintern.picarto.tv/ptvapi', channel_id, query={
+ 'query': '''{
+ channel(name: "%s") {
+ adult
+ id
+ online
+ stream_name
+ title
+ }
+ getLoadBalancerUrl(channel_name: "%s") {
+ url
+ }
+}''' % (channel_id, channel_id),
+ })['data']
+ metadata = data['channel']
- if metadata.get('online') is False:
+ if metadata.get('online') == 0:
raise ExtractorError('Stream is offline', expected=True)
+ title = metadata['title']
cdn_data = self._download_json(
- 'https://picarto.tv/process/channel', channel_id,
- data=urlencode_postdata({'loadbalancinginfo': channel_id}),
- note='Downloading load balancing info')
-
- token = mobj.group('token') or 'public'
- params = {
- 'con': int(time.time() * 1000),
- 'token': token,
- }
+ data['getLoadBalancerUrl']['url'] + '/stream/json_' +
metadata['stream_name'] + '.js',
+ channel_id, 'Downloading load balancing info')
- prefered_edge = cdn_data.get('preferedEdge')
formats = []
-
- for edge in cdn_data['edges']:
- edge_ep = edge.get('ep')
- if not edge_ep or not isinstance(edge_ep, compat_str):
+ for source in (cdn_data.get('source') or []):
+ source_url = source.get('url')
+ if not source_url:
continue
- edge_id = edge.get('id')
- for tech in cdn_data['techs']:
- tech_label = tech.get('label')
- tech_type = tech.get('type')
- preference = 0
- if edge_id == prefered_edge:
- preference += 1
- format_id = []
- if edge_id:
- format_id.append(edge_id)
- if tech_type == 'application/x-mpegurl' or tech_label == 'HLS':
- format_id.append('hls')
- formats.extend(self._extract_m3u8_formats(
- update_url_query(
- 'https://%s/hls/%s/index.m3u8'
- % (edge_ep, channel_id), params),
- channel_id, 'mp4', preference=preference,
- m3u8_id='-'.join(format_id), fatal=False))
- continue
- elif tech_type == 'video/mp4' or tech_label == 'MP4':
- format_id.append('mp4')
- formats.append({
- 'url': update_url_query(
- 'https://%s/mp4/%s.mp4' % (edge_ep, channel_id),
- params),
- 'format_id': '-'.join(format_id),
- 'preference': preference,
- })
- else:
- # rtmp format does not seem to work
- continue
+ source_type = source.get('type')
+ if source_type == 'html5/application/vnd.apple.mpegurl':
+ formats.extend(self._extract_m3u8_formats(
+ source_url, channel_id, 'mp4', m3u8_id='hls', fatal=False))
+ elif source_type == 'html5/video/mp4':
+ formats.append({
+ 'url': source_url,
+ })
self._sort_formats(formats)
mature = metadata.get('adult')
@@ -103,10 +77,10 @@
return {
'id': channel_id,
- 'title': self._live_title(metadata.get('title') or channel_id),
+ 'title': self._live_title(title.strip()),
'is_live': True,
- 'thumbnail': try_get(metadata, lambda x: x['thumbnails']['web']),
'channel': channel_id,
+ 'channel_id': metadata.get('id'),
'channel_url': 'https://picarto.tv/%s' % channel_id,
'age_limit': age_limit,
'formats': formats,
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/sbs.py
new/youtube-dl/youtube_dl/extractor/sbs.py
--- old/youtube-dl/youtube_dl/extractor/sbs.py 2021-03-24 18:03:49.000000000
+0100
+++ new/youtube-dl/youtube_dl/extractor/sbs.py 2021-03-30 22:01:34.000000000
+0200
@@ -10,7 +10,7 @@
class SBSIE(InfoExtractor):
IE_DESC = 'sbs.com.au'
- _VALID_URL =
r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=)|news/(?:embeds/)?video/)(?P<id>[0-9]+)'
+ _VALID_URL =
r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=|/watch/)|news/(?:embeds/)?video/)(?P<id>[0-9]+)'
_TESTS = [{
# Original URL is handled by the generic IE which finds the iframe:
@@ -43,6 +43,9 @@
}, {
'url': 'https://www.sbs.com.au/news/embeds/video/1840778819866',
'only_matching': True,
+ }, {
+ 'url': 'https://www.sbs.com.au/ondemand/watch/1698704451971',
+ 'only_matching': True,
}]
def _real_extract(self, url):
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/vimeo.py
new/youtube-dl/youtube_dl/extractor/vimeo.py
--- old/youtube-dl/youtube_dl/extractor/vimeo.py 2021-03-24
18:03:54.000000000 +0100
+++ new/youtube-dl/youtube_dl/extractor/vimeo.py 2021-03-30
22:01:39.000000000 +0200
@@ -24,6 +24,7 @@
merge_dicts,
OnDemandPagedList,
parse_filesize,
+ parse_iso8601,
RegexNotFoundError,
sanitized_Request,
smuggle_url,
@@ -74,25 +75,28 @@
expected=True)
raise ExtractorError('Unable to log in')
- def _verify_video_password(self, url, video_id, webpage):
+ def _get_video_password(self):
password = self._downloader.params.get('videopassword')
if password is None:
- raise ExtractorError('This video is protected by a password, use
the --video-password option', expected=True)
- token, vuid = self._extract_xsrft_and_vuid(webpage)
- data = urlencode_postdata({
- 'password': password,
- 'token': token,
- })
+ raise ExtractorError(
+ 'This video is protected by a password, use the
--video-password option',
+ expected=True)
+ return password
+
+ def _verify_video_password(self, url, video_id, password, token, vuid):
if url.startswith('http://'):
# vimeo only supports https now, but the user can give an http url
url = url.replace('http://', 'https://')
- password_request = sanitized_Request(url + '/password', data)
- password_request.add_header('Content-Type',
'application/x-www-form-urlencoded')
- password_request.add_header('Referer', url)
self._set_vimeo_cookie('vuid', vuid)
return self._download_webpage(
- password_request, video_id,
- 'Verifying the password', 'Wrong password')
+ url + '/password', video_id, 'Verifying the password',
+ 'Wrong password', data=urlencode_postdata({
+ 'password': password,
+ 'token': token,
+ }), headers={
+ 'Content-Type': 'application/x-www-form-urlencoded',
+ 'Referer': url,
+ })
def _extract_xsrft_and_vuid(self, webpage):
xsrft = self._search_regex(
@@ -278,7 +282,7 @@
)?
(?:videos?/)?
(?P<id>[0-9]+)
- (?:/[\da-f]+)?
+ (?:/(?P<unlisted_hash>[\da-f]{10}))?
/?(?:[?&].*)?(?:[#].*)?$
'''
IE_NAME = 'vimeo'
@@ -331,9 +335,9 @@
'id': '54469442',
'ext': 'mp4',
'title': 'Kathy Sierra: Building the minimum Badass User,
Business of Software 2012',
- 'uploader': 'The BLN & Business of Software',
- 'uploader_url':
r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
- 'uploader_id': 'theblnbusinessofsoftware',
+ 'uploader': 'Business of Software',
+ 'uploader_url':
r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
+ 'uploader_id': 'businessofsoftware',
'duration': 3610,
'description': None,
},
@@ -468,6 +472,7 @@
'skip_download': True,
},
'expected_warnings': ['Unable to download JSON metadata'],
+ 'skip': 'this page is no longer available.',
},
{
'url': 'http://player.vimeo.com/video/68375962',
@@ -550,9 +555,7 @@
return urls[0] if urls else None
def _verify_player_video_password(self, url, video_id, headers):
- password = self._downloader.params.get('videopassword')
- if password is None:
- raise ExtractorError('This video is protected by a password, use
the --video-password option', expected=True)
+ password = self._get_video_password()
data = urlencode_postdata({
'password': base64.b64encode(password.encode()),
})
@@ -577,11 +580,37 @@
if 'Referer' not in headers:
headers['Referer'] = url
- channel_id = self._search_regex(
- r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
-
# Extract ID from URL
- video_id = self._match_id(url)
+ video_id, unlisted_hash = re.match(self._VALID_URL, url).groups()
+ if unlisted_hash:
+ token = self._download_json(
+ 'https://vimeo.com/_rv/jwt', video_id, headers={
+ 'X-Requested-With': 'XMLHttpRequest'
+ })['token']
+ video = self._download_json(
+ 'https://api.vimeo.com/videos/%s:%s' % (video_id,
unlisted_hash),
+ video_id, headers={
+ 'Authorization': 'jwt ' + token,
+ }, query={
+ 'fields':
'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
+ })
+ info = self._parse_config(self._download_json(
+ video['config_url'], video_id), video_id)
+ self._vimeo_sort_formats(info['formats'])
+ get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
+ info.update({
+ 'description': video.get('description'),
+ 'license': video.get('license'),
+ 'release_timestamp': get_timestamp('release'),
+ 'timestamp': get_timestamp('created'),
+ 'view_count': int_or_none(try_get(video, lambda x:
x['stats']['plays'])),
+ })
+ connections = try_get(
+ video, lambda x: x['metadata']['connections'], dict) or {}
+ for k in ('comment', 'like'):
+ info[k + '_count'] = int_or_none(try_get(connections, lambda
x: x[k + 's']['total']))
+ return info
+
orig_url = url
is_pro = 'vimeopro.com/' in url
is_player = '://player.vimeo.com/video/' in url
@@ -670,7 +699,10 @@
if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
if '_video_password_verified' in data:
raise ExtractorError('video password verification failed!')
- self._verify_video_password(redirect_url, video_id, webpage)
+ video_password = self._get_video_password()
+ token, vuid = self._extract_xsrft_and_vuid(webpage)
+ self._verify_video_password(
+ redirect_url, video_id, video_password, token, vuid)
return self._real_extract(
smuggle_url(redirect_url, {'_video_password_verified':
'verified'}))
else:
@@ -756,6 +788,8 @@
r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
webpage, 'license', default=None, group='license')
+ channel_id = self._search_regex(
+ r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
channel_url = 'https://vimeo.com/channels/%s' % channel_id if
channel_id else None
info_dict = {
@@ -1062,10 +1096,23 @@
def _real_extract(self, url):
page_url, video_id = re.match(self._VALID_URL, url).groups()
- clip_data = self._download_json(
- page_url.replace('/review/', '/review/data/'),
- video_id)['clipData']
- config_url = clip_data['configUrl']
+ data = self._download_json(
+ page_url.replace('/review/', '/review/data/'), video_id)
+ if data.get('isLocked') is True:
+ video_password = self._get_video_password()
+ viewer = self._download_json(
+ 'https://vimeo.com/_rv/viewer', video_id)
+ webpage = self._verify_video_password(
+ 'https://vimeo.com/' + video_id, video_id,
+ video_password, viewer['xsrft'], viewer['vuid'])
+ clip_page_config = self._parse_json(self._search_regex(
+ r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
+ webpage, 'clip page config'), video_id)
+ config_url = clip_page_config['player']['config_url']
+ clip_data = clip_page_config.get('clip') or {}
+ else:
+ clip_data = data['clipData']
+ config_url = clip_data['configUrl']
config = self._download_json(config_url, video_id)
info_dict = self._parse_config(config, video_id)
source_format = self._extract_original_format(
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/vlive.py
new/youtube-dl/youtube_dl/extractor/vlive.py
--- old/youtube-dl/youtube_dl/extractor/vlive.py 2021-03-24
18:03:49.000000000 +0100
+++ new/youtube-dl/youtube_dl/extractor/vlive.py 2021-03-30
22:01:34.000000000 +0200
@@ -106,7 +106,7 @@
raise ExtractorError('Unable to log in', expected=True)
def _call_api(self, path_template, video_id, fields=None):
- query = {'appId': self._APP_ID, 'gcc': 'KR'}
+ query = {'appId': self._APP_ID, 'gcc': 'KR', 'platformType': 'PC'}
if fields:
query['fields'] = fields
try:
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/youtube.py
new/youtube-dl/youtube_dl/extractor/youtube.py
--- old/youtube-dl/youtube_dl/extractor/youtube.py 2021-03-24
18:03:54.000000000 +0100
+++ new/youtube-dl/youtube_dl/extractor/youtube.py 2021-03-30
22:01:39.000000000 +0200
@@ -24,6 +24,7 @@
from ..utils import (
ExtractorError,
clean_html,
+ dict_get,
float_or_none,
int_or_none,
mimetype2ext,
@@ -248,7 +249,23 @@
return True
+ def _initialize_consent(self):
+ cookies = self._get_cookies('https://www.youtube.com/')
+ if cookies.get('__Secure-3PSID'):
+ return
+ consent_id = None
+ consent = cookies.get('CONSENT')
+ if consent:
+ if 'YES' in consent.value:
+ return
+ consent_id = self._search_regex(
+ r'PENDING\+(\d+)', consent.value, 'consent', default=None)
+ if not consent_id:
+ consent_id = random.randint(100, 999)
+ self._set_cookie('.youtube.com', 'CONSENT',
'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
+
def _real_initialize(self):
+ self._initialize_consent()
if self._downloader is None:
return
if not self._login():
@@ -1431,7 +1448,7 @@
base_url = self.http_scheme() + '//www.youtube.com/'
webpage_url = base_url + 'watch?v=' + video_id
webpage = self._download_webpage(
- webpage_url + '&bpctr=9999999999', video_id, fatal=False)
+ webpage_url + '&bpctr=9999999999&has_verified=1', video_id,
fatal=False)
player_response = None
if webpage:
@@ -1895,7 +1912,7 @@
info['channel'] = get_text(try_get(
vsir,
lambda x: x['owner']['videoOwnerRenderer']['title'],
- compat_str))
+ dict))
rows = try_get(
vsir,
lambda x:
x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
@@ -2541,13 +2558,14 @@
continuation =
self._extract_continuation(continuation_renderer)
continue
+ on_response_received = dict_get(response,
('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
continuation_items = try_get(
- response, lambda x:
x['onResponseReceivedActions'][0]['appendContinuationItemsAction']['continuationItems'],
list)
+ on_response_received, lambda x:
x[0]['appendContinuationItemsAction']['continuationItems'], list)
if continuation_items:
continuation_item = continuation_items[0]
if not isinstance(continuation_item, dict):
continue
- renderer = continuation_item.get('gridVideoRenderer')
+ renderer = self._extract_grid_item_renderer(continuation_item)
if renderer:
grid_renderer = {'items': continuation_items}
for entry in self._grid_entries(grid_renderer):
@@ -2561,6 +2579,13 @@
yield entry
continuation =
self._extract_continuation(video_list_renderer)
continue
+ renderer = continuation_item.get('backstagePostThreadRenderer')
+ if renderer:
+ continuation_renderer = {'contents': continuation_items}
+ for entry in
self._post_thread_continuation_entries(continuation_renderer):
+ yield entry
+ continuation =
self._extract_continuation(continuation_renderer)
+ continue
break
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn'
'--exclude=.svnignore' old/youtube-dl/youtube_dl/version.py
new/youtube-dl/youtube_dl/version.py
--- old/youtube-dl/youtube_dl/version.py 2021-03-24 18:04:07.000000000
+0100
+++ new/youtube-dl/youtube_dl/version.py 2021-03-31 23:47:08.000000000
+0200
@@ -1,3 +1,3 @@
from __future__ import unicode_literals
-__version__ = '2021.03.25'
+__version__ = '2021.04.01'
