[test/test_utils] add more tests for update_url_query

[youtube-dl] / youtube_dl / extractor / xhamster.py

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index ccee77359761b5214eb4ff24f8051f3dda1995eb..fd43e8854c994e5b15c661ce49636853c41d2ecd 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -6,7 +6,6 @@ from .common import InfoExtractor
 from ..utils import (
     float_or_none,
     int_or_none,
-    str_to_int,
     unified_strdate,
 )
 
@@ -22,7 +21,7 @@ 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 +33,7 @@ class XHamsterIE(InfoExtractor):
                 'title': 'Britney Spears  Sexy Booty',
                 'upload_date': '20130914',
                 'uploader': 'jojo747400',
-                'duration': 200,
+                'duration': 200.48,
                 'age_limit': 18,
             }
         },
@@ -64,9 +63,10 @@ class XHamsterIE(InfoExtractor):
         webpage = self._download_webpage(mrss_url, video_id)
 
         title = self._html_search_regex(
-            [r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>',
-             r'<h1[^>]*>([^<]+)</h1>',
-             r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"'], webpage, 'title')
+            [r'<h1[^>]*>([^<]+)</h1>',
+             r'<meta[^>]+itemprop=".*?caption.*?"[^>]+content="(.+?)"',
+             r'<title[^>]*>(.+?)(?:,\s*[^,]*?\s*Porn\s*[^,]*?:\s*xHamster[^<]*| - xHamster\.com)</title>'],
+            webpage, 'title')
 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
@@ -77,7 +77,7 @@ class XHamsterIE(InfoExtractor):
             webpage, 'upload date', fatal=False))
 
         uploader = self._html_search_regex(
-            r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
+            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
             webpage, 'uploader', default='anonymous')
 
         thumbnail = self._search_regex(