1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-20 20:25:37 +08:00

[prosiebensat1] Improve extraction and remove 7tv.de support (#24948)

This commit is contained in:
Philipp Stehle 2020-04-23 21:44:13 +02:00 committed by GitHub
parent 46d0baf941
commit 2cdfe977d7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -175,7 +175,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
(?: (?:
(?:beta\.)? (?:beta\.)?
(?: (?:
prosieben(?:maxx)?|sixx|sat1(?:gold)?|kabeleins(?:doku)?|the-voice-of-germany|7tv|advopedia prosieben(?:maxx)?|sixx|sat1(?:gold)?|kabeleins(?:doku)?|the-voice-of-germany|advopedia
)\.(?:de|at|ch)| )\.(?:de|at|ch)|
ran\.de|fem\.com|advopedia\.de|galileo\.tv/video ran\.de|fem\.com|advopedia\.de|galileo\.tv/video
) )
@ -193,7 +193,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'info_dict': { 'info_dict': {
'id': '2104602', 'id': '2104602',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Episode 18 - Staffel 2', 'title': 'CIRCUS HALLIGALLI - Episode 18 - Staffel 2',
'description': 'md5:8733c81b702ea472e069bc48bb658fc1', 'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
'upload_date': '20131231', 'upload_date': '20131231',
'duration': 5845.04, 'duration': 5845.04,
@ -300,7 +300,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'info_dict': { 'info_dict': {
'id': '2572814', 'id': '2572814',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Andreas Kümmert: Rocket Man', 'title': 'The Voice of Germany - Andreas Kümmert: Rocket Man',
'description': 'md5:6ddb02b0781c6adf778afea606652e38', 'description': 'md5:6ddb02b0781c6adf778afea606652e38',
'upload_date': '20131017', 'upload_date': '20131017',
'duration': 469.88, 'duration': 469.88,
@ -310,7 +310,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
}, },
}, },
{ {
'url': 'http://www.fem.com/wellness/videos/wellness-video-clip-kurztripps-zum-valentinstag.html', 'url': 'http://www.fem.com/videos/beauty-lifestyle/kurztrips-zum-valentinstag',
'info_dict': { 'info_dict': {
'id': '2156342', 'id': '2156342',
'ext': 'mp4', 'ext': 'mp4',
@ -332,19 +332,6 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'playlist_count': 2, 'playlist_count': 2,
'skip': 'This video is unavailable', 'skip': 'This video is unavailable',
}, },
{
'url': 'http://www.7tv.de/circus-halligalli/615-best-of-circus-halligalli-ganze-folge',
'info_dict': {
'id': '4187506',
'ext': 'mp4',
'title': 'Best of Circus HalliGalli',
'description': 'md5:8849752efd90b9772c9db6fdf87fb9e9',
'upload_date': '20151229',
},
'params': {
'skip_download': True,
},
},
{ {
# title in <h2 class="subtitle"> # title in <h2 class="subtitle">
'url': 'http://www.prosieben.de/stars/oscar-award/videos/jetzt-erst-enthuellt-das-geheimnis-von-emma-stones-oscar-robe-clip', 'url': 'http://www.prosieben.de/stars/oscar-award/videos/jetzt-erst-enthuellt-das-geheimnis-von-emma-stones-oscar-robe-clip',
@ -421,7 +408,6 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
r'<div[^>]+id="veeseoDescription"[^>]*>(.+?)</div>', r'<div[^>]+id="veeseoDescription"[^>]*>(.+?)</div>',
] ]
_UPLOAD_DATE_REGEXES = [ _UPLOAD_DATE_REGEXES = [
r'<meta property="og:published_time" content="(.+?)">',
r'<span>\s*(\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}) \|\s*<span itemprop="duration"', r'<span>\s*(\d{2}\.\d{2}\.\d{4} \d{2}:\d{2}) \|\s*<span itemprop="duration"',
r'<footer>\s*(\d{2}\.\d{2}\.\d{4}) \d{2}:\d{2} Uhr', r'<footer>\s*(\d{2}\.\d{2}\.\d{4}) \d{2}:\d{2} Uhr',
r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>', r'<span style="padding-left: 4px;line-height:20px; color:#404040">(\d{2}\.\d{2}\.\d{4})</span>',
@ -451,8 +437,11 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
if description is None: if description is None:
description = self._og_search_description(webpage) description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._html_search_regex( upload_date = unified_strdate(
self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None)) self._html_search_meta('og:published_time', webpage,
'upload date', default=None)
or self._html_search_regex(self._UPLOAD_DATE_REGEXES,
webpage, 'upload date', default=None))
info.update({ info.update({
'id': clip_id, 'id': clip_id,