X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxhamster.py;h=fd43e8854c994e5b15c661ce49636853c41d2ecd;hb=1bac34556fcff324fa17c679004284f03123d64d;hp=481d79b89e80e3e529ae9b4109019c8185bf5d43;hpb=be7a8379b47c35afe66abcc02aee597e5143b1d5;p=youtube-dl
diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 481d79b89..fd43e8854 100644
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -4,11 +4,9 @@ import re
from .common import InfoExtractor
from ..utils import (
- ExtractorError,
- unified_strdate,
- str_to_int,
+ float_or_none,
int_or_none,
- parse_duration,
+ unified_strdate,
)
@@ -22,8 +20,8 @@ class XHamsterIE(InfoExtractor):
'ext': 'mp4',
'title': 'FemaleAgent Shy beauty takes the bait',
'upload_date': '20121014',
- 'uploader_id': 'Ruseful2011',
- 'duration': 893,
+ 'uploader': 'Ruseful2011',
+ 'duration': 893.52,
'age_limit': 18,
}
},
@@ -34,8 +32,8 @@ class XHamsterIE(InfoExtractor):
'ext': 'mp4',
'title': 'Britney Spears Sexy Booty',
'upload_date': '20130914',
- 'uploader_id': 'jojo747400',
- 'duration': 200,
+ 'uploader': 'jojo747400',
+ 'duration': 200.48,
'age_limit': 18,
}
},
@@ -64,28 +62,36 @@ class XHamsterIE(InfoExtractor):
mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
webpage = self._download_webpage(mrss_url, video_id)
- title = self._html_search_regex(r'
(?P.+?) - xHamster\.com', webpage, 'title')
+ title = self._html_search_regex(
+ [r']*>([^<]+)
',
+ r']+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
+ r']*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)'],
+ webpage, 'title')
# Only a few videos have an description
mobj = re.search(r'Description: ([^<]+)', webpage)
description = mobj.group(1) if mobj else None
- upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'',
- webpage, 'upload date', fatal=False)
- if upload_date:
- upload_date = unified_strdate(upload_date)
+ upload_date = unified_strdate(self._search_regex(
+ r'hint=["\'](\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}',
+ webpage, 'upload date', fatal=False))
- uploader_id = self._html_search_regex(r']+>(?P[^<]+)',
- webpage, 'uploader id', default='anonymous')
+ uploader = self._html_search_regex(
+ r']+itemprop=["\']author[^>]+>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P.+?)',
+ webpage, 'uploader', default='anonymous')
- thumbnail = self._html_search_regex(r'