youtube_dl/extractor/tube8.py

@@ -1,4 +1,3 @@
-# coding: utf-8
 from __future__ import unicode_literals
 
 import itertools
@@ -7,15 +6,14 @@ from time import sleep
 
 from .common import InfoExtractor
 from ..utils import (
-    clean_html,
+    traverse_obj,
+    T,
+    url_or_none,
+    parse_iso8601,
     get_element_by_class,
     get_element_by_id,
     int_or_none,
     parse_qs,
-    strip_or_none,
-    T,
-    traverse_obj,    
-    url_or_none,
     urljoin,
 )
 
@@ -31,34 +29,29 @@ class Tube8IE(InfoExtractor):
             'title': 'Found dildo. She let it cum in her tight ass to keep the secret',
             'thumbnail': r're:^https?://.*\.jpg$',
             'uploader': 'MaryKrylova',
-            'age_limit': 18,
+            'timestamp': 1718961736,
+            'upload_date': '20240621',
         }
     }]
 
-    _EMBED_REGEX =  r'<iframe [^>]*\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)*\d+)'
-    
-    @classmethod
-    def _extract_urls(cls, webpage):
-        return [m.group('url') for m in re.finditer(cls._EMBED_REGEX, webpage)]
-
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        video_id = self._match_valid_url(url).group('id')
         webpage = self._download_webpage(url, video_id)
 
-        age_verify_msg = self._search_regex(
-            r'(your elected officials in \w+(?:\s+\w+){,2} are requiring us to verify your age before allowing you access to our website)',
-            webpage, 'age verification message', default=None)
-        if age_verify_msg:
-            self.raise_geo_restricted('%s said: "%s"' % (self.IE_NAME, age_verify_msg))
-
         playervars = self._search_json(
             r'\bplayervars\s*:', webpage, 'playervars', video_id)
 
-        info = self._search_json_ld(webpage, video_id, expected_type='VideoObject', default={})
+        extra_info = self._search_json(
-        for k in ('url', 'description'):
+            r'application/ld\+json[\"\']?>\s?', webpage, 'extra_info', video_id)
-            info.pop(k, None)
 
-        info['uploader'] = clean_html(get_element_by_class('submitByLink', webpage))
+        uploader = traverse_obj(extra_info, (
+            '@graph', lambda _, v: v.get('author'), 'author'))[0]
+
+        thumbnail = traverse_obj(extra_info, (
+            '@graph', lambda _, v: v.get('thumbnail'), 'thumbnail'))[0]
+
+        timestamp = parse_iso8601(traverse_obj(extra_info, (
+            '@graph', lambda _, v: v.get('datePublished'), 'datePublished'))[0])
 
         # Borrowed from youporn extractor
         def get_fmt(x):
@@ -70,9 +63,9 @@ class Tube8IE(InfoExtractor):
         defs_by_format = dict(traverse_obj(playervars, (
             'mediaDefinitions', lambda _, v: v.get('format'), T(get_fmt))))
 
-        info['title'] = strip_or_none(playervars.get('video_title')) or info.get('title') or playervars['video_title']
+        title = traverse_obj(playervars, 'video_title')
-        if not info.get('thumbnail'):
+        if not thumbnail:
-            info['thumbnail'] = traverse_obj(playervars, ('image_url', T(url_or_none)))
+            thumbnail = traverse_obj(playervars, 'image_url')
 
         # Borrowed from youporn extractor
         def get_format_data(f):
@@ -85,26 +78,29 @@ class Tube8IE(InfoExtractor):
         for mp4_url in traverse_obj(
                 get_format_data('mp4'),
                 (lambda _, v: not isinstance(v['defaultQuality'], bool), 'videoUrl'),
-                (Ellipsis, 'videoUrl'),
+                (Ellipsis, 'videoUrl')):
-                expected_type=url_or_none):
+            mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', mp4_url)
-            height, tbr = map(int_or_none, self._search_regex(r'(?i)(?P<height>\d{3,4})p_(?P<bitrate>\d+)k_\d+', mp4_url, 'media details', group=('height', 'bitrate'), fatal=False))
+            if mobj:
-            fmt_id = '%dp' % height if height else 'mp4'
+                height = int(mobj.group('height'))
+                tbr = int(mobj.group('bitrate'))
                 formats.append({
-                'format_id': fmt_id,
+                    'format_id': '%dp-%dk' % (height, tbr),
                     'url': mp4_url,
                     'ext': 'mp4',
-                'height': height,
                     'tbr': tbr,
+                    'height': height,
                 })
 
         self._sort_formats(formats)
 
-        info.update({
+        return {
             'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
             'formats': formats,
-            'age_limit': 18,
+            'uploader': uploader,
-        })
+            'timestamp': timestamp,
-        return info
+        }
 
 
 # Currently only user channels