[xhamster] Add support for new URL schema (closes #13593)

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

diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
index bd8e1af2e0f6c25fc44aea36c23b813b092b4438..de9ec9b9e5346e5ba4437a66d1547a2cf14dc7c7 100644 (file)
--- a/youtube_dl/extractor/xhamster.py
+++ b/youtube_dl/extractor/xhamster.py
@@ -4,15 +4,25 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    clean_html,
     dict_get,
-    float_or_none,
+    ExtractorError,
     int_or_none,
+    parse_duration,
     unified_strdate,
 )
 
 
 class XHamsterIE(InfoExtractor):
-    _VALID_URL = r'(?P<proto>https?)://(?:.+?\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.*?)\.html(?:\?.*)?'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:.+?\.)?xhamster\.com/
+                        (?:
+                            movies/(?P<id>\d+)/(?P<display_id>[^/]*)\.html|
+                            videos/(?P<display_id_2>[^/]*)-(?P<id_2>\d+)
+                        )
+                    '''
+
     _TESTS = [{
         'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
         'md5': '8281348b8d3c53d39fffb377d24eac4e',
@@ -22,8 +32,9 @@ class XHamsterIE(InfoExtractor):
             'title': 'FemaleAgent Shy beauty takes the bait',
             'upload_date': '20121014',
             'uploader': 'Ruseful2011',
-            'duration': 893.52,
+            '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',
@@ -33,8 +44,9 @@ class XHamsterIE(InfoExtractor):
             'title': 'Britney Spears  Sexy Booty',
             'upload_date': '20130914',
             'uploader': 'jojo747400',
-            'duration': 200.48,
+            'duration': 200,
             'age_limit': 18,
+            'categories': ['Britney Spears', 'Celebrities', 'HD Videos', 'Sexy', 'Sexy Booty'],
         },
         'params': {
             'skip_download': True,
@@ -48,8 +60,9 @@ class XHamsterIE(InfoExtractor):
             'title': '....',
             'upload_date': '20160208',
             'uploader': 'parejafree',
-            'duration': 72.0,
+            'duration': 72,
             'age_limit': 18,
+            'categories': ['Amateur', 'Blowjobs'],
         },
         'params': {
             'skip_download': True,
@@ -57,6 +70,14 @@ class XHamsterIE(InfoExtractor):
     }, {
         'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html',
         'only_matching': True,
+    }, {
+        # This video is visible for marcoalfa123456's friends only
+        'url': 'https://it.xhamster.com/movies/7263980/la_mia_vicina.html',
+        'only_matching': True,
+    }, {
+        # new URL schema
+        'url': 'https://pt.xhamster.com/videos/euro-pedal-pumping-7937821',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -72,11 +93,16 @@ class XHamsterIE(InfoExtractor):
 
         mobj = re.match(self._VALID_URL, url)
 
-        video_id = mobj.group('id')
-        seo = mobj.group('seo')
-        proto = mobj.group('proto')
-        mrss_url = '%s://xhamster.com/movies/%s/%s.html' % (proto, video_id, seo)
-        webpage = self._download_webpage(mrss_url, video_id)
+        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)
+
+        error = self._html_search_regex(
+            r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>',
+            webpage, 'error', default=None)
+        if error:
+            raise ExtractorError(error, expected=True)
 
         title = self._html_search_regex(
             [r'<h1[^>]*>([^<]+)</h1>',
@@ -93,7 +119,7 @@ class XHamsterIE(InfoExtractor):
             webpage, 'upload date', fatal=False))
 
         uploader = self._html_search_regex(
-            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+href=["\'].+?xhamster\.com/user/[^>]+>(?P<uploader>.+?)</a>',
+            r'<span[^>]+itemprop=["\']author[^>]+><a[^>]+><span[^>]+>([^<]+)',
             webpage, 'uploader', default='anonymous')
 
         thumbnail = self._search_regex(
@@ -101,15 +127,15 @@ class XHamsterIE(InfoExtractor):
              r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''],
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
-        duration = float_or_none(self._search_regex(
-            r'(["\'])duration\1\s*:\s*(["\'])(?P<duration>.+?)\2',
-            webpage, 'duration', fatal=False, group='duration'))
+        duration = parse_duration(self._search_regex(
+            r'Runtime:\s*</span>\s*([\d:]+)', webpage,
+            'duration', fatal=False))
 
         view_count = int_or_none(self._search_regex(
             r'content=["\']User(?:View|Play)s:(\d+)',
             webpage, 'view count', fatal=False))
 
-        mobj = re.search(r"hint='(?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes'", webpage)
+        mobj = re.search(r'hint=[\'"](?P<likecount>\d+) Likes / (?P<dislikecount>\d+) Dislikes', webpage)
         (like_count, dislike_count) = (mobj.group('likecount'), mobj.group('dislikecount')) if mobj else (None, None)
 
         mobj = re.search(r'</label>Comments \((?P<commentcount>\d+)\)</div>', webpage)
@@ -141,6 +167,12 @@ class XHamsterIE(InfoExtractor):
 
         self._sort_formats(formats)
 
+        categories_html = self._search_regex(
+            r'(?s)<table.+?(<span>Categories:.+?)</table>', webpage,
+            'categories', default=None)
+        categories = [clean_html(category) for category in re.findall(
+            r'<a[^>]+>(.+?)</a>', categories_html)] if categories_html else None
+
         return {
             'id': video_id,
             'title': title,
@@ -154,6 +186,7 @@ class XHamsterIE(InfoExtractor):
             'dislike_count': int_or_none(dislike_count),
             'comment_count': int_or_none(comment_count),
             'age_limit': age_limit,
+            'categories': categories,
             'formats': formats,
         }