projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[downloader/http] Retry download when urlopen times out (#26603) (refs #10935)
[youtube-dl]
/
youtube_dl
/
extractor
/
porncom.py
diff --git
a/youtube_dl/extractor/porncom.py
b/youtube_dl/extractor/porncom.py
index d85e0294df62d7540304f2a8e87c4f989fcc2e07..5726cab3ae6763d7466d013898f71925966bed6d 100644
(file)
--- a/
youtube_dl/extractor/porncom.py
+++ b/
youtube_dl/extractor/porncom.py
@@
-22,7
+22,7
@@
class PornComIE(InfoExtractor):
'display_id': 'teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec',
'ext': 'mp4',
'title': 'Teen grabs a dildo and fucks her pussy live on 1hottie, I rec',
'display_id': 'teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec',
'ext': 'mp4',
'title': 'Teen grabs a dildo and fucks her pussy live on 1hottie, I rec',
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'thumbnail':
r
're:^https?://.*\.jpg$',
'duration': 551,
'view_count': int,
'age_limit': 18,
'duration': 551,
'view_count': int,
'age_limit': 18,
@@
-43,7
+43,8
@@
class PornComIE(InfoExtractor):
config = self._parse_json(
self._search_regex(
config = self._parse_json(
self._search_regex(
- r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*=',
+ (r'=\s*({.+?})\s*;\s*v1ar\b',
+ r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*='),
webpage, 'config', default='{}'),
display_id, transform_source=js_to_json, fatal=False)
webpage, 'config', default='{}'),
display_id, transform_source=js_to_json, fatal=False)
@@
-69,7
+70,7
@@
class PornComIE(InfoExtractor):
'height': int(height),
'filesize_approx': parse_filesize(filesize),
} for format_url, height, filesize in re.findall(
'height': int(height),
'filesize_approx': parse_filesize(filesize),
} for format_url, height, filesize in re.findall(
- r'<a[^>]+href="(/download/[^"]+)">
MPEG4 (\d+)p<span[^>]*>(\d+\s+
[a-zA-Z]+)<',
+ r'<a[^>]+href="(/download/[^"]+)">
[^<]*?(\d+)p<span[^>]*>(\d+\s*
[a-zA-Z]+)<',
webpage)]
thumbnail = None
duration = None
webpage)]
thumbnail = None
duration = None
@@
-77,12
+78,14
@@
class PornComIE(InfoExtractor):
self._sort_formats(formats)
view_count = str_to_int(self._search_regex(
self._sort_formats(formats)
view_count = str_to_int(self._search_regex(
- r'class=["\']views["\'][^>]*><p>([\d,.]+)', webpage,
+ (r'Views:\s*</span>\s*<span>\s*([\d,.]+)',
+ r'class=["\']views["\'][^>]*><p>([\d,.]+)'), webpage,
'view count', fatal=False))
def extract_list(kind):
s = self._search_regex(
'view count', fatal=False))
def extract_list(kind):
s = self._search_regex(
- r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize(),
+ (r'(?s)%s:\s*</span>\s*<span>(.+?)</span>' % kind.capitalize(),
+ r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize()),
webpage, kind, fatal=False)
return re.findall(r'<a[^>]+>([^<]+)</a>', s or '')
webpage, kind, fatal=False)
return re.findall(r'<a[^>]+>([^<]+)</a>', s or '')