Merge branch 'yt-dlp:master' into fix/ff-ua

yt_dlp/YoutubeDL.py

@@ -2219,6 +2219,7 @@ def _check_formats(self, formats):
                         self.report_warning(f'Unable to delete temporary file "{temp_file.name}"')
             f['__working'] = success
             if success:
+                f.pop('__needs_testing', None)
                 yield f
             else:
                 self.to_screen('[info] Unable to download format {}. Skipping...'.format(f['format_id']))
@@ -3963,6 +3964,7 @@ def simplified_codec(f, field):
                     self._format_out('UNSUPPORTED', self.Styles.BAD_FORMAT) if f.get('ext') in ('f4f', 'f4m') else None,
                     (self._format_out('Maybe DRM', self.Styles.WARNING) if f.get('has_drm') == 'maybe'
                      else self._format_out('DRM', self.Styles.BAD_FORMAT) if f.get('has_drm') else None),
+                    self._format_out('Untested', self.Styles.WARNING) if f.get('__needs_testing') else None,
                     format_field(f, 'format_note'),
                     format_field(f, 'container', ignore=(None, f.get('ext'))),
                     delim=', '), delim=' '),

yt_dlp/extractor/sproutvideo.py

@@ -41,6 +41,7 @@ class SproutVideoIE(InfoExtractor):
             'duration': 703,
             'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
         },
+        'skip': 'Account Disabled',
     }, {
         # http formats 'sd' and 'hd' are available
         'url': 'https://videos.sproutvideo.com/embed/119cd6bc1a18e6cd98/30751a1761ae5b90',
@@ -97,11 +98,21 @@ def _extract_embed_urls(cls, url, webpage):
     def _real_extract(self, url):
         url, smuggled_data = unsmuggle_url(url, {})
         video_id = self._match_id(url)
-        webpage = self._download_webpage(
+        webpage = self._download_webpage(url, video_id, headers={
-            url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}))
+            **traverse_obj(smuggled_data, {'Referer': 'referer'}),
+            # yt-dlp's default Chrome user-agents are too old
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:140.0) Gecko/20100101 Firefox/140.0',
+        })
         data = self._search_json(
-            r'var\s+dat\s*=\s*["\']', webpage, 'data', video_id, contains_pattern=r'[A-Za-z0-9+/=]+',
+            r'var\s+(?:dat|playerInfo)\s*=\s*["\']', webpage, 'player info', video_id,
-            end_pattern=r'["\'];', transform_source=lambda x: base64.b64decode(x).decode())
+            contains_pattern=r'[A-Za-z0-9+/=]+', end_pattern=r'["\'];',
+            transform_source=lambda x: base64.b64decode(x).decode())
+
+        # SproutVideo may send player info for 'SMPTE Color Monitor Test' [a791d7b71b12ecc52e]
+        # e.g. if the user-agent we used with the webpage request is too old
+        video_uid = data['videoUid']
+        if video_id != video_uid:
+            raise ExtractorError(f'{self.IE_NAME} sent the wrong video data ({video_uid})')
 
         formats, subtitles = [], {}
         headers = {

yt_dlp/extractor/youtube/_video.py

@@ -2820,6 +2820,10 @@ def _generate_player_context(cls, sts=None):
             context['signatureTimestamp'] = sts
         return {
             'playbackContext': {
+                'adPlaybackContext': {
+                    'pyv': True,
+                    'adType': 'AD_TYPE_INSTREAM',
+                },
                 'contentPlaybackContext': context,
             },
             **cls._get_checkok_params(),
@@ -3552,6 +3556,11 @@ def process_manifest_format(f, proto, client_name, itag, po_token):
                 f['format_note'] = join_nonempty(f.get('format_note'), 'MISSING POT', delim=' ')
                 f['source_preference'] -= 20
 
+            # XXX: Check if IOS HLS formats are affected by player PO token enforcement; temporary
+            # See https://github.com/yt-dlp/yt-dlp/issues/13511
+            if proto == 'hls' and client_name == 'ios':
+                f['__needs_testing'] = True
+
             itags[itag].add(key)
 
             if itag and all_formats:
@@ -4280,6 +4289,7 @@ def process_language(container, base_url, lang_code, sub_name, client_name, quer
 
         if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'):
             # Newly uploaded videos' HLS formats are potentially problematic and need to be checked
+            # XXX: This is redundant for as long as we are already checking all IOS HLS formats
             upload_datetime = datetime_from_str(upload_date).replace(tzinfo=dt.timezone.utc)
             if upload_datetime >= datetime_from_str('today-2days'):
                 for fmt in info['formats']: