[xhamster] Extend _VALID_URL (closes #25789) (#25804)

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

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index a5b94d2794166d452464b728ec40b2b258459c64..72ce5e1d3750febdabb771d081188b312c597c5e 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -25,8 +25,8 @@ class XHamsterIE(InfoExtractor):
                     https?://
                         (?:.+?\.)?%s/
                         (?:
-                            movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
-                            videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
+                            movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
+                            videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
                         )
                     ''' % _DOMAINS
     _TESTS = [{
@@ -105,6 +105,9 @@ class XHamsterIE(InfoExtractor):
     }, {
         'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
         'only_matching': True,
+    }, {
+        'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -113,7 +116,7 @@ class XHamsterIE(InfoExtractor):
         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 
         desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
-        webpage = self._download_webpage(desktop_url, video_id)
+        webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
 
         error = self._html_search_regex(
             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
@@ -161,6 +164,9 @@ class XHamsterIE(InfoExtractor):
                         'ext': determine_ext(format_url, 'mp4'),
                         'height': get_height(quality),
                         'filesize': filesize,
+                        'http_headers': {
+                            'Referer': urlh.geturl(),
+                        },
                     })
             self._sort_formats(formats)