[xhamster] Fix upload date extraction

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

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index b57e7c813680bfe9cf4def0c85665c11be07c986..560c38e269c7f7eed8ed01f8ac2e66d032f68240 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -4,7 +4,6 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
     unified_strdate,
     str_to_int,
     int_or_none,
@@ -22,7 +21,7 @@ class XHamsterIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'FemaleAgent Shy beauty takes the bait',
                 'upload_date': '20121014',
-                'uploader_id': 'Ruseful2011',
+                'uploader': 'Ruseful2011',
                 'duration': 893,
                 'age_limit': 18,
             }
@@ -34,7 +33,7 @@ class XHamsterIE(InfoExtractor):
                 'ext': 'mp4',
                 'title': 'Britney Spears  Sexy Booty',
                 'upload_date': '20130914',
-                'uploader_id': 'jojo747400',
+                'uploader': 'jojo747400',
                 'duration': 200,
                 'age_limit': 18,
             }
@@ -64,24 +63,27 @@ 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'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
+        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')
 
         # Only a few videos have an description
         mobj = re.search(r'<span>Description: </span>([^<]+)', 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'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
-                                              webpage, 'uploader id', default='anonymous')
+        uploader = self._html_search_regex(
+            r"<a href='[^']+xhamster\.com/user/[^>]+>(?P<uploader>[^<]+)",
+            webpage, 'uploader', default='anonymous')
 
         thumbnail = self._search_regex(
             [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''',
              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
-             webpage, 'thumbnail', fatal=False, group='thumbnail')
+            webpage, 'thumbnail', fatal=False, group='thumbnail')
 
         duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
                                                           webpage, 'duration', fatal=False))
@@ -127,7 +129,7 @@ class XHamsterIE(InfoExtractor):
             'title': title,
             'description': description,
             'upload_date': upload_date,
-            'uploader_id': uploader_id,
+            'uploader': uploader,
             'thumbnail': thumbnail,
             'duration': duration,
             'view_count': view_count,