Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-12 14:26:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

[Motherless] Fix extractor (#809)

Browse Source 
Authored-by: coletdjnz
Fixes #806, https://github.com/ytdl-org/youtube-dl/issues/29626
This commit is contained in:
coletdjnz 2021-08-30 10:22:57 +12:00 committed by GitHub
parent 54153fb71b
commit 419508eabb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 24 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
yt_dlp/extractor/motherless.py
View File

@ -127,9 +127,9 @@ def _real_extract(self, url):
comment_count = webpage.count('class="media-comment-contents"') comment_count = webpage.count('class="media-comment-contents"')
uploader_id = self._html_search_regex( uploader_id = self._html_search_regex(
r'"thumb-member-username">\s+<a href="/m/([^"]+)"', (r'"media-meta-member">\s+<a href="/m/([^"]+)"',
webpage, 'uploader_id') r'<span\b[^>]+\bclass="username">([^<]+)</span>'),
webpage, 'uploader_id', fatal=False)
categories = self._html_search_meta('keywords', webpage, default=None) categories = self._html_search_meta('keywords', webpage, default=None)
if categories: if categories:
categories = [cat.strip() for cat in categories.split(',')] categories = [cat.strip() for cat in categories.split(',')]
@ -169,7 +169,18 @@ class MotherlessGroupIE(InfoExtractor):
'description': 'Sex can be funny. Wide smiles,laugh, games, fun of ' 'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
'any kind!' 'any kind!'
}, },
'playlist_mincount': 9, 'playlist_mincount': 0,
'expected_warnings': [
'This group has no videos.',
]
}, {
'url': 'https://motherless.com/g/beautiful_cock',
'info_dict': {
'id': 'beautiful_cock',
'title': 'Beautiful Cock',
'description': 'Group for lovely cocks yours, mine, a friends anything human',
},
'playlist_mincount': 2500,
}] }]
@classmethod @classmethod
@ -209,11 +220,18 @@ def _real_extract(self, url):
description = self._html_search_meta( description = self._html_search_meta(
'description', webpage, fatal=False) 'description', webpage, fatal=False)
page_count = self._int(self._search_regex( page_count = self._int(self._search_regex(
r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT', r'(\d+)</(?:a|span)><(?:a|span)[^>]+rel="next">',
webpage, 'page_count'), 'page_count') webpage, 'page_count', default=0), 'page_count')
if not page_count:
message = self._search_regex(
r'class="error-page"[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*',
webpage, 'error_msg', default=None) or 'This group has no videos.'
self.report_warning(message, group_id)
PAGE_SIZE = 80 PAGE_SIZE = 80
def _get_page(idx): def _get_page(idx):
if not page_count:
return
webpage = self._download_webpage( webpage = self._download_webpage(
page_url, group_id, query={'page': idx + 1}, page_url, group_id, query={'page': idx + 1},
note='Downloading page %d/%d' % (idx + 1, page_count) note='Downloading page %d/%d' % (idx + 1, page_count)