[xhamster] Extend _VALID_URL (closes #25789) (#25804)
[youtube-dl] / youtube_dl / extractor / xhamster.py
index 52f8ded2f8b94f872d5dc8799ec4fbe2829c0754..72ce5e1d3750febdabb771d081188b312c597c5e 100644 (file)
@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+import itertools
 import re
 
 from .common import InfoExtractor
@@ -8,30 +9,32 @@ from ..utils import (
     clean_html,
     determine_ext,
     dict_get,
+    extract_attributes,
     ExtractorError,
     int_or_none,
     parse_duration,
     try_get,
     unified_strdate,
+    url_or_none,
 )
 
 
 class XHamsterIE(InfoExtractor):
+    _DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster[27]\.com)'
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:.+?\.)?xhamster\.com/
+                        (?:.+?\.)?%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 = [{
-        'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
-        'md5': '8281348b8d3c53d39fffb377d24eac4e',
+        'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'md5': '98b4687efb1ffd331c4197854dc09e8f',
         'info_dict': {
             'id': '1509445',
-            'display_id': 'femaleagent_shy_beauty_takes_the_bait',
+            'display_id': 'femaleagent-shy-beauty-takes-the-bait',
             'ext': 'mp4',
             'title': 'FemaleAgent Shy beauty takes the bait',
             'timestamp': 1350194821,
@@ -39,13 +42,12 @@ class XHamsterIE(InfoExtractor):
             'uploader': 'Ruseful2011',
             'duration': 893,
             'age_limit': 18,
-            'categories': ['Fake Hub', 'Amateur', 'MILFs', 'POV', 'Boss', 'Office', 'Oral', 'Reality', 'Sexy'],
         },
     }, {
-        'url': 'http://xhamster.com/movies/2221348/britney_spears_sexy_booty.html?hd',
+        'url': 'https://xhamster.com/videos/britney-spears-sexy-booty-2221348?hd=',
         'info_dict': {
             'id': '2221348',
-            'display_id': 'britney_spears_sexy_booty',
+            'display_id': 'britney-spears-sexy-booty',
             'ext': 'mp4',
             'title': 'Britney Spears  Sexy Booty',
             'timestamp': 1379123460,
@@ -53,13 +55,12 @@ class XHamsterIE(InfoExtractor):
             'uploader': 'jojo747400',
             'duration': 200,
             'age_limit': 18,
-            'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
         },
         'params': {
             'skip_download': True,
         },
     }, {
-        # empty seo
+        # empty seo, unavailable via new URL schema
         'url': 'http://xhamster.com/movies/5667973/.html',
         'info_dict': {
             'id': '5667973',
@@ -70,11 +71,14 @@ class XHamsterIE(InfoExtractor):
             'uploader': 'parejafree',
             'duration': 72,
             'age_limit': 18,
-            'categories': ['Amateur', 'Blowjobs'],
         },
         'params': {
             'skip_download': True,
         },
+    }, {
+        # mobile site
+        'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111',
+        'only_matching': True,
     }, {
         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
         'only_matching': True,
@@ -86,6 +90,24 @@ class XHamsterIE(InfoExtractor):
         # new URL schema
         'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
         'only_matching': True,
+    }, {
+        'url': 'https://xhamster.one/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'only_matching': True,
+    }, {
+        'url': 'https://xhamster.desi/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
+        'only_matching': True,
+    }, {
+        'url': 'https://xhamster2.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):
@@ -93,7 +115,8 @@ class XHamsterIE(InfoExtractor):
         video_id = mobj.group('id') or mobj.group('id_2')
         display_id = mobj.group('display_id') or mobj.group('display_id_2')
 
-        webpage = self._download_webpage(url, video_id)
+        desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url)
+        webpage, urlh = self._download_webpage_handle(desktop_url, video_id)
 
         error = self._html_search_regex(
             r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
@@ -132,7 +155,8 @@ class XHamsterIE(InfoExtractor):
                     else:
                         format_url = format_item
                         filesize = None
-                    if not isinstance(format_url, compat_str):
+                    format_url = url_or_none(format_url)
+                    if not format_url:
                         continue
                     formats.append({
                         'format_id': '%s-%s' % (format_id, quality),
@@ -140,6 +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)
 
@@ -193,7 +220,8 @@ class XHamsterIE(InfoExtractor):
                 default='{}'),
             video_id, fatal=False)
         for format_id, format_url in sources.items():
-            if not isinstance(format_url, compat_str):
+            format_url = url_or_none(format_url)
+            if not format_url:
                 continue
             if format_url in format_urls:
                 continue
@@ -229,8 +257,8 @@ class XHamsterIE(InfoExtractor):
             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)[^>]*>'''],
+            [r'''["']thumbUrl["']\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._search_regex(
@@ -274,15 +302,16 @@ class XHamsterIE(InfoExtractor):
 
 
 class XHamsterEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:.+?\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
     _TEST = {
         'url': 'http://xhamster.com/xembed.php?video=3328539',
         'info_dict': {
             'id': '3328539',
             'ext': 'mp4',
             'title': 'Pen Masturbation',
+            'timestamp': 1406581861,
             'upload_date': '20140728',
-            'uploader_id': 'anonymous',
+            'uploader': 'ManyakisArt',
             'duration': 5,
             'age_limit': 18,
         }
@@ -310,3 +339,49 @@ 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)