Merge branch 'yt-dlp:master' into yandextelemost

README.md

@@ -1871,6 +1871,7 @@ The following extractors use this feature:
 * `pot_trace`: Enable debug logging for PO Token fetching. Either `true` or `false` (default)
 * `fetch_pot`: Policy to use for fetching a PO Token from providers. One of `always` (always try fetch a PO Token regardless if the client requires one for the given context), `never` (never fetch a PO Token), or `auto` (default; only fetch a PO Token if the client requires one for the given context)
 * `jsc_trace`: Enable debug logging for JS Challenge fetching. Either `true` or `false` (default)
+* `use_ad_playback_context`: Skip preroll ads to eliminate the mandatory wait period before download. Do NOT use this when passing premium account cookies to yt-dlp, as it will result in a loss of premium formats. Only effective with the `web`, `web_safari`, `web_music` and `mweb` player clients. Either `true` or `false` (default)
 
 #### youtube-ejs
 * `jitless`: Run suported Javascript engines in JIT-less mode. Supported runtimes are `deno`, `node` and `bun`. Provides better security at the cost of performance/speed. Do note that `node` and `bun` are still considered unsecure. Either `true` or `false` (default)

yt_dlp/extractor/archiveorg.py

@@ -704,6 +704,24 @@ class YoutubeWebArchiveIE(InfoExtractor):
                 'thumbnail': 'https://web.archive.org/web/20160108040020if_/https://i.ytimg.com/vi/SQCom7wjGDs/maxresdefault.jpg',
                 'upload_date': '20160107',
             },
+        }, {
+            # dmuxed formats
+            'url': 'https://web.archive.org/web/20240922160632/https://www.youtube.com/watch?v=z7hzvTL3k1k',
+            'info_dict': {
+                'id': 'z7hzvTL3k1k',
+                'ext': 'webm',
+                'title': 'Praise the Lord and Pass the Ammunition (BARRXN REMIX)',
+                'description': 'md5:45dbf2c71c23b0734c8dfb82dd1e94b6',
+                'uploader': 'Barrxn',
+                'uploader_id': 'TheRockstar6086',
+                'uploader_url': 'https://www.youtube.com/user/TheRockstar6086',
+                'channel_id': 'UCjJPGUTtvR9uizmawn2ThqA',
+                'channel_url': 'https://www.youtube.com/channel/UCjJPGUTtvR9uizmawn2ThqA',
+                'duration': 125,
+                'thumbnail': r're:https?://.*\.(jpg|webp)',
+                'upload_date': '20201207',
+            },
+            'params': {'format': 'bv'},
         }, {
             'url': 'https://web.archive.org/web/http://www.youtube.com/watch?v=kH-G_aIBlFw',
             'only_matching': True,
@@ -1060,6 +1078,19 @@ class YoutubeWebArchiveIE(InfoExtractor):
         capture_dates.extend([self._OLDEST_CAPTURE_DATE, self._NEWEST_CAPTURE_DATE])
         return orderedSet(filter(None, capture_dates))
 
+    def _parse_fmt(self, fmt, extra_info=None):
+        format_id = traverse_obj(fmt, ('url', {parse_qs}, 'itag', 0))
+        return {
+            'format_id': format_id,
+            **self._FORMATS.get(format_id, {}),
+            **traverse_obj(fmt, {
+                'url': ('url', {lambda x: f'https://web.archive.org/web/2id_/{x}'}),
+                'ext': ('ext', {str}),
+                'filesize': ('url', {parse_qs}, 'clen', 0, {int_or_none}),
+            }),
+            **(extra_info or {}),
+        }
+
     def _real_extract(self, url):
         video_id, url_date, url_date_2 = self._match_valid_url(url).group('id', 'date', 'date2')
         url_date = url_date or url_date_2
@@ -1090,17 +1121,14 @@ class YoutubeWebArchiveIE(InfoExtractor):
         info['thumbnails'] = self._extract_thumbnails(video_id)
 
         formats = []
-        for fmt in traverse_obj(video_info, ('formats', lambda _, v: url_or_none(v['url']))):
-            format_id = traverse_obj(fmt, ('url', {parse_qs}, 'itag', 0))
-            formats.append({
-                'format_id': format_id,
-                **self._FORMATS.get(format_id, {}),
-                **traverse_obj(fmt, {
-                    'url': ('url', {lambda x: f'https://web.archive.org/web/2id_/{x}'}),
-                    'ext': ('ext', {str}),
-                    'filesize': ('url', {parse_qs}, 'clen', 0, {int_or_none}),
-                }),
-            })
+        if video_info.get('dmux'):
+            for vf in traverse_obj(video_info, ('formats', 'video', lambda _, v: url_or_none(v['url']))):
+                formats.append(self._parse_fmt(vf, {'acodec': 'none'}))
+            for af in traverse_obj(video_info, ('formats', 'audio', lambda _, v: url_or_none(v['url']))):
+                formats.append(self._parse_fmt(af, {'vcodec': 'none'}))
+        else:
+            for fmt in traverse_obj(video_info, ('formats', lambda _, v: url_or_none(v['url']))):
+                formats.append(self._parse_fmt(fmt))
         info['formats'] = formats
 
         return info

yt_dlp/extractor/youtube/_base.py

@@ -104,6 +104,7 @@ INNERTUBE_CLIENTS = {
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
         'SUPPORTS_COOKIES': True,
+        'SUPPORTS_AD_PLAYBACK_CONTEXT': True,
         **WEB_PO_TOKEN_POLICIES,
     },
     # Safari UA returns pre-merged video+audio 144p/240p/360p/720p/1080p HLS formats
@@ -117,6 +118,7 @@ INNERTUBE_CLIENTS = {
         },
         'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
         'SUPPORTS_COOKIES': True,
+        'SUPPORTS_AD_PLAYBACK_CONTEXT': True,
         **WEB_PO_TOKEN_POLICIES,
     },
     'web_embedded': {
@@ -157,6 +159,7 @@ INNERTUBE_CLIENTS = {
             ),
         },
         'SUPPORTS_COOKIES': True,
+        'SUPPORTS_AD_PLAYBACK_CONTEXT': True,
     },
     # This client now requires sign-in for every video
     'web_creator': {
@@ -313,6 +316,7 @@ INNERTUBE_CLIENTS = {
             ),
         },
         'SUPPORTS_COOKIES': True,
+        'SUPPORTS_AD_PLAYBACK_CONTEXT': True,
     },
     'tv': {
         'INNERTUBE_CONTEXT': {
@@ -412,6 +416,7 @@ def build_innertube_clients():
         ytcfg.setdefault('SUBS_PO_TOKEN_POLICY', SubsPoTokenPolicy())
         ytcfg.setdefault('REQUIRE_AUTH', False)
         ytcfg.setdefault('SUPPORTS_COOKIES', False)
+        ytcfg.setdefault('SUPPORTS_AD_PLAYBACK_CONTEXT', False)
         ytcfg.setdefault('PLAYER_PARAMS', None)
         ytcfg.setdefault('AUTHENTICATED_USER_AGENT', None)
         ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')

yt_dlp/extractor/youtube/_video.py

@@ -2629,16 +2629,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         return {'contentCheckOk': True, 'racyCheckOk': True}
 
     @classmethod
-    def _generate_player_context(cls, sts=None):
+    def _generate_player_context(cls, sts=None, use_ad_playback_context=False):
         context = {
             'html5Preference': 'HTML5_PREF_WANTS',
         }
         if sts is not None:
             context['signatureTimestamp'] = sts
+
+        playback_context = {
+            'contentPlaybackContext': context,
+        }
+        if use_ad_playback_context:
+            playback_context['adPlaybackContext'] = {
+                'pyv': True,
+            }
+
         return {
-            'playbackContext': {
-                'contentPlaybackContext': context,
-            },
+            'playbackContext': playback_context,
             **cls._get_checkok_params(),
         }
 
@@ -2866,7 +2873,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             yt_query['serviceIntegrityDimensions'] = {'poToken': po_token}
 
         sts = self._extract_signature_timestamp(video_id, player_url, webpage_ytcfg, fatal=False) if player_url else None
-        yt_query.update(self._generate_player_context(sts))
+
+        use_ad_playback_context = (
+            self._configuration_arg('use_ad_playback_context', ['false'])[0] != 'false'
+            and traverse_obj(INNERTUBE_CLIENTS, (client, 'SUPPORTS_AD_PLAYBACK_CONTEXT', {bool})))
+
+        yt_query.update(self._generate_player_context(sts, use_ad_playback_context))
+
         return self._extract_response(
             item_id=video_id, ep='player', query=yt_query,
             ytcfg=player_ytcfg, headers=headers, fatal=True,