[xhamster] Improve initials regex (#26526) (closes #26353)

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

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index 4297dffeee8dcbd3c637c04cbf522e520c6c66d4..76aeaf9a46a6f67a054bfbc3313b8e6d4309a7f2 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
@@ -8,6 +9,7 @@ from ..utils import (
     clean_html,
     determine_ext,
     dict_get,
+    extract_attributes,
     ExtractorError,
     int_or_none,
     parse_duration,
@@ -18,13 +20,13 @@ 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/
                         (?:
-                            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 = [{
@@ -97,12 +99,21 @@ 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,
     }, {
         '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):
@@ -111,7 +122,7 @@ 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>',
@@ -127,7 +138,8 @@ class XHamsterIE(InfoExtractor):
 
         initials = self._parse_json(
             self._search_regex(
-                r'window\.initials\s*=\s*({.+?})\s*;\s*\n', 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:
@@ -159,6 +171,9 @@ class XHamsterIE(InfoExtractor):
                         'ext': determine_ext(format_url, 'mp4'),
                         'height': get_height(quality),
                         'filesize': filesize,
+                        'http_headers': {
+                            'Referer': urlh.geturl(),
+                        },
                     })
             self._sort_formats(formats)
 
@@ -331,3 +346,49 @@ class XHamsterEmbedIE(InfoExtractor):
             video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
 
         return self.url_result(video_url, 'XHamster')
+
+
+class XHamsterUserIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.+?\.)?%s/users/(?P<id>[^/?#&]+)' % XHamsterIE._DOMAINS
+    _TESTS = [{
+        # Paginated user profile
+        'url': 'https://xhamster.com/users/netvideogirls/videos',
+        'info_dict': {
+            'id': 'netvideogirls',
+        },
+        'playlist_mincount': 267,
+    }, {
+        # Non-paginated user profile
+        'url': 'https://xhamster.com/users/firatkaan/videos',
+        'info_dict': {
+            'id': 'firatkaan',
+        },
+        'playlist_mincount': 1,
+    }]
+
+    def _entries(self, user_id):
+        next_page_url = 'https://xhamster.com/users/%s/videos/1' % user_id
+        for pagenum in itertools.count(1):
+            page = self._download_webpage(
+                next_page_url, user_id, 'Downloading page %s' % pagenum)
+            for video_tag in re.findall(
+                    r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
+                    page):
+                video = extract_attributes(video_tag)
+                video_url = url_or_none(video.get('href'))
+                if not video_url or not XHamsterIE.suitable(video_url):
+                    continue
+                video_id = XHamsterIE._match_id(video_url)
+                yield self.url_result(
+                    video_url, ie=XHamsterIE.ie_key(), video_id=video_id)
+            mobj = re.search(r'<a[^>]+data-page=["\']next[^>]+>', page)
+            if not mobj:
+                break
+            next_page = extract_attributes(mobj.group(0))
+            next_page_url = url_or_none(next_page.get('href'))
+            if not next_page_url:
+                break
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+        return self.playlist_result(self._entries(user_id), user_id)