[xhamster] Improve initials regex (#26526) (closes #26353)
[youtube-dl] / youtube_dl / extractor / xhamster.py
index babe317390255ad3956ac1fe24d225ba9880efc0..76aeaf9a46a6f67a054bfbc3313b8e6d4309a7f2 100644 (file)
@@ -20,7 +20,7 @@ from ..utils import (
 
 
 class XHamsterIE(InfoExtractor):
-    _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)'
+    _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)'
     _VALID_URL = r'''(?x)
                     https?://
                         (?:.+?\.)?%s/
@@ -99,6 +99,12 @@ class XHamsterIE(InfoExtractor):
     }, {
         'url': 'https://xhamster2.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
         'only_matching': True,
+    }, {
+        'url': 'https://xhamster11.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'only_matching': True,
+    }, {
+        'url': 'https://xhamster26.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'only_matching': True,
     }, {
         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
         'only_matching': True,
@@ -132,7 +138,8 @@ class XHamsterIE(InfoExtractor):
 
         initials = self._parse_json(
             self._search_regex(
-                r'window\.initials\s*=\s*({.+?})\s*;', webpage, 'initials',
+                (r'window\.initials\s*=\s*({.+?})\s*;\s*</script>',
+                 r'window\.initials\s*=\s*({.+?})\s*;'), webpage, 'initials',
                 default='{}'),
             video_id, fatal=False)
         if initials: