Merge pull request #6428 from dstftw/improve-generic-smil-support

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

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 481d79b89e80e3e529ae9b4109019c8185bf5d43..97315750fd59198022a72eca53482efdd8d98e75 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,
             }
@@ -75,10 +74,14 @@ class XHamsterIE(InfoExtractor):
         if upload_date:
             upload_date = unified_strdate(upload_date)
 
-        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._html_search_regex(r'<video\s+.*?poster="([^"]+)".*?>', webpage, 'thumbnail', fatal=False)
+        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')
 
         duration = parse_duration(self._html_search_regex(r'<span>Runtime:</span> (\d+:\d+)</div>',
                                                           webpage, 'duration', fatal=False))
@@ -124,7 +127,7 @@ 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,