[vporn] More metadata extraction fixes and tests update (#5560)

diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py
index 04ed0b38129feef337fb932934f0f3ada2b47501..92c90e5172e89b98c3309bb01dc9787f15c24859 100644 (file)
--- a/youtube_dl/extractor/vporn.py
+++ b/youtube_dl/extractor/vporn.py
@@ -27,9 +27,6 @@ class VpornIE(InfoExtractor):
                 'duration': 393,
                 'age_limit': 18,
                 'view_count': int,
-                'like_count': int,
-                'dislike_count': int,
-                'comment_count': int,
             }
         },
         {
@@ -47,9 +44,6 @@ class VpornIE(InfoExtractor):
                 'duration': 588,
                 'age_limit': 18,
                 'view_count': int,
-                'like_count': int,
-                'dislike_count': int,
-                'comment_count': int,
             }
         },
     ]
@@ -72,10 +66,10 @@ class VpornIE(InfoExtractor):
             thumbnail = 'http://www.vporn.com' + thumbnail
 
         uploader = self._html_search_regex(
-            r'(?s)Uploaded by:.*?<a href="/user/[^"]+">([^<]+)</a>',
+            r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>',
             webpage, 'uploader', fatal=False)
 
-        categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
+        categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', webpage)
 
         duration = parse_duration(self._search_regex(
             r'Runtime:\s*</span>\s*(\d+ min \d+ sec)',