mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 00:52:01 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[ie/altcensored:channel] Fix playlist extraction (#9297)

Browse Source 
Authored by: marcdumais
This commit is contained in:
marcdumais 2024-02-25 18:21:08 -05:00 committed by GitHub
parent f1570ab84d
commit e28e135d6f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
yt_dlp/extractor/altcensored.py
View File

@ -22,7 +22,7 @@ class AltCensoredIE(InfoExtractor):
'title': "QUELLES SONT LES CONSÉQUENCES DE L'HYPERSEXUALISATION DE LA SOCIÉTÉ ?", 'title': "QUELLES SONT LES CONSÉQUENCES DE L'HYPERSEXUALISATION DE LA SOCIÉTÉ ?",
'display_id': 'k0srjLSkga8.webm', 'display_id': 'k0srjLSkga8.webm',
'release_date': '20180403', 'release_date': '20180403',
'creator': 'Virginie Vota', 'creators': ['Virginie Vota'],
'release_year': 2018, 'release_year': 2018,
'upload_date': '20230318', 'upload_date': '20230318',
'uploader': 'admin@altcensored.com', 'uploader': 'admin@altcensored.com',
@ -32,7 +32,7 @@ class AltCensoredIE(InfoExtractor):
'duration': 926.09, 'duration': 926.09,
'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg', 'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg',
'view_count': int, 'view_count': int,
'categories': ['News & Politics'], 'categories': ['News & Politics'], # FIXME
} }
}] }]
@ -62,14 +62,21 @@ class AltCensoredChannelIE(InfoExtractor):
'title': 'Virginie Vota', 'title': 'Virginie Vota',
'id': 'UCFPTO55xxHqFqkzRZHu4kcw', 'id': 'UCFPTO55xxHqFqkzRZHu4kcw',
}, },
'playlist_count': 91 'playlist_count': 85,
}, { }, {
'url': 'https://altcensored.com/channel/UC9CcJ96HKMWn0LZlcxlpFTw', 'url': 'https://altcensored.com/channel/UC9CcJ96HKMWn0LZlcxlpFTw',
'info_dict': { 'info_dict': {
'title': 'yukikaze775', 'title': 'yukikaze775',
'id': 'UC9CcJ96HKMWn0LZlcxlpFTw', 'id': 'UC9CcJ96HKMWn0LZlcxlpFTw',
}, },
'playlist_count': 4 'playlist_count': 4,
}, {
'url': 'https://altcensored.com/channel/UCfYbb7nga6-icsFWWgS-kWw',
'info_dict': {
'title': 'Mister Metokur',
'id': 'UCfYbb7nga6-icsFWWgS-kWw',
},
'playlist_count': 121,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -78,7 +85,7 @@ def _real_extract(self, url):
url, channel_id, 'Download channel webpage', 'Unable to get channel webpage') url, channel_id, 'Download channel webpage', 'Unable to get channel webpage')
title = self._html_search_meta('altcen_title', webpage, 'title', fatal=False) title = self._html_search_meta('altcen_title', webpage, 'title', fatal=False)
page_count = int_or_none(self._html_search_regex( page_count = int_or_none(self._html_search_regex(
r'<a[^>]+href="/channel/\w+/page/(\d+)">(?:\1)</a>', r'<a[^>]+href="/channel/[\w-]+/page/(\d+)">(?:\1)</a>',
webpage, 'page count', default='1')) webpage, 'page count', default='1'))
def page_func(page_num): def page_func(page_num):