projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Credit @TRox1972 for tosh.cc (#9566) and localnews8 (#9539)
[youtube-dl]
/
youtube_dl
/
extractor
/
spankbang.py
diff --git
a/youtube_dl/extractor/spankbang.py
b/youtube_dl/extractor/spankbang.py
index a67db59057d9b3d732899d016b8b87d1694236b9..50433d0f678f27c348031dbe0d6fcc3774d021b7 100644
(file)
--- a/
youtube_dl/extractor/spankbang.py
+++ b/
youtube_dl/extractor/spankbang.py
@@
-7,7
+7,7
@@
from .common import InfoExtractor
class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
- _TEST
=
{
+ _TEST
S = [
{
'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7',
'info_dict': {
'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7',
'info_dict': {
@@
-19,7
+19,11
@@
class SpankBangIE(InfoExtractor):
'uploader': 'silly2587',
'age_limit': 18,
}
'uploader': 'silly2587',
'age_limit': 18,
}
- }
+ }, {
+ # 480p only
+ 'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
video_id = self._match_id(url)
def _real_extract(self, url):
video_id = self._match_id(url)
@@
-34,11
+38,12
@@
class SpankBangIE(InfoExtractor):
'ext': 'mp4',
'format_id': '%sp' % height,
'height': int(height),
'ext': 'mp4',
'format_id': '%sp' % height,
'height': int(height),
- } for height in re.findall(r'<(?:span|li)[^>]+q_(\d+)p', webpage)]
+ } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
+ self._check_formats(formats, video_id)
self._sort_formats(formats)
title = self._html_search_regex(
self._sort_formats(formats)
title = self._html_search_regex(
- r'(?s)<h1>(.+?)</h1>', webpage, 'title')
+ r'(?s)<h1
[^>]*
>(.+?)</h1>', webpage, 'title')
description = self._search_regex(
r'class="desc"[^>]*>([^<]+)',
webpage, 'description', default=None)
description = self._search_regex(
r'class="desc"[^>]*>([^<]+)',
webpage, 'description', default=None)