X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fxhamster.py;h=b3547174dd92beffafaf8f220b50b94a25f2fa2b;hb=fe7ef95e91cec1c1794692029561a68e2aaa7809;hp=97315750fd59198022a72eca53482efdd8d98e75;hpb=55801fc76e2813de9a84eaa830d70ed73cb44463;p=youtube-dl.git
diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 97315750f..b3547174d 100644
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -4,10 +4,10 @@ import re
from .common import InfoExtractor
from ..utils import (
- unified_strdate,
- str_to_int,
+ dict_get,
+ float_or_none,
int_or_none,
- parse_duration,
+ unified_strdate,
)
@@ -22,7 +22,7 @@ class XHamsterIE(InfoExtractor):
'title': 'FemaleAgent Shy beauty takes the bait',
'upload_date': '20121014',
'uploader': 'Ruseful2011',
- 'duration': 893,
+ 'duration': 893.52,
'age_limit': 18,
}
},
@@ -34,7 +34,7 @@ class XHamsterIE(InfoExtractor):
'title': 'Britney Spears Sexy Booty',
'upload_date': '20130914',
'uploader': 'jojo747400',
- 'duration': 200,
+ 'duration': 200.48,
'age_limit': 18,
}
},
@@ -63,19 +63,22 @@ 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 = self._html_search_regex(
- r"]+>(?P[^<]+)",
+ r']+itemprop=["\']author[^>]+>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P.+?)',
webpage, 'uploader', default='anonymous')
thumbnail = self._search_regex(
@@ -83,12 +86,13 @@ class XHamsterIE(InfoExtractor):
r'''