[pornhub] Detect flagged videos

youtube_dl/extractor/pornhub.py

@@ -167,6 +167,7 @@ class PornHubIE(PornHubBaseIE):
         'params': {
             'skip_download': True,
         },
+        'skip': 'Video has been flagged for verification in accordance with our trust and safety policy',
     }, {
         # subtitles
         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
@@ -265,7 +266,8 @@ class PornHubIE(PornHubBaseIE):
         webpage = dl_webpage('pc')
 
         error_msg = self._html_search_regex(
-            r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
+            (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
+             r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'),
             webpage, 'error message', default=None, group='error')
         if error_msg:
             error_msg = re.sub(r'\s+', ' ', error_msg)
@@ -394,6 +396,21 @@ class PornHubIE(PornHubBaseIE):
 
         upload_date = None
         formats = []
+
+        def add_format(format_url, height=None):
+            tbr = None
+            mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', format_url)
+            if mobj:
+                if not height:
+                    height = int(mobj.group('height'))
+                tbr = int(mobj.group('tbr'))
+            formats.append({
+                'url': format_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+                'tbr': tbr,
+            })
+
         for video_url, height in video_urls:
             if not upload_date:
                 upload_date = self._search_regex(
@@ -410,18 +427,19 @@ class PornHubIE(PornHubBaseIE):
                     video_url, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id='hls', fatal=False))
                 continue
-            tbr = None
+            if '/video/get_media' in video_url:
-            mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
+                medias = self._download_json(video_url, video_id, fatal=False)
-            if mobj:
+                if isinstance(medias, list):
-                if not height:
+                    for media in medias:
-                    height = int(mobj.group('height'))
+                        if not isinstance(media, dict):
-                tbr = int(mobj.group('tbr'))
+                            continue
-            formats.append({
+                        video_url = url_or_none(media.get('videoUrl'))
-                'url': video_url,
+                        if not video_url:
-                'format_id': '%dp' % height if height else None,
+                            continue
-                'height': height,
+                        height = int_or_none(media.get('quality'))
-                'tbr': tbr,
+                        add_format(video_url, height)
-            })
+                continue
+            add_format(video_url)
         self._sort_formats(formats)
 
         video_uploader = self._html_search_regex(