midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[spangbang:playlist] Fix extraction (closes #24087)

Browse source
This commit is contained in:
Sergey M․ 2020-12-26 21:58:26 +07:00
parent cfa4ffa23b
commit 8bc4c6350e
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 12 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
youtube_dl/extractor/spankbang.py
View file

@ -13,6 +13,7 @@ from ..utils import (
str_to_int, str_to_int,
url_or_none, url_or_none,
urlencode_postdata, urlencode_postdata,
urljoin,
) )
@ -166,30 +167,33 @@ class SpankBangIE(InfoExtractor):
class SpankBangPlaylistIE(InfoExtractor): class SpankBangPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/[^/]+' _VALID_URL = r'https?://(?:[^/]+\.)?spankbang\.com/(?P<id>[\da-z]+)/playlist/(?P<display_id>[^/]+)'
_TEST = { _TEST = {
'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties', 'url': 'https://spankbang.com/ug0k/playlist/big+ass+titties',
'info_dict': { 'info_dict': {
'id': 'ug0k', 'id': 'ug0k',
'title': 'Big Ass Titties', 'title': 'Big Ass Titties',
}, },
'playlist_mincount': 50, 'playlist_mincount': 40,
} }
def _real_extract(self, url): def _real_extract(self, url):
playlist_id = self._match_id(url) mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage( webpage = self._download_webpage(
url, playlist_id, headers={'Cookie': 'country=US; mobile=on'}) url, playlist_id, headers={'Cookie': 'country=US; mobile=on'})
entries = [self.url_result( entries = [self.url_result(
'https://spankbang.com/%s/video' % video_id, urljoin(url, mobj.group('path')),
ie=SpankBangIE.ie_key(), video_id=video_id) ie=SpankBangIE.ie_key(), video_id=mobj.group('id'))
for video_id in orderedSet(re.findall( for mobj in re.finditer(
r'<a[^>]+\bhref=["\']/?([\da-z]+)/play/', webpage))] r'<a[^>]+\bhref=(["\'])(?P<path>/?[\da-z]+-(?P<id>[\da-z]+)/playlist/%s(?:(?!\1).)*)\1'
% re.escape(display_id), webpage)]
title = self._html_search_regex( title = self._html_search_regex(
r'<h1>([^<]+)\s+playlist</h1>', webpage, 'playlist title', r'<h1>([^<]+)\s+playlist\s*<', webpage, 'playlist title',
fatal=False) fatal=False)
return self.playlist_result(entries, playlist_id, title) return self.playlist_result(entries, playlist_id, title)