[ie/youtube] Request web_safari & web_creator client configs (#16198)

Closes #16144
Authored by: bashonly

README.md

@@ -1863,6 +1863,7 @@ The following extractors use this feature:
 * `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv`, `tv_downgraded`, and `tv_simply`. By default, `android_vr,web,web_safari` is used. If no JavaScript runtime/engine is available, then only `android_vr` is used. If logged-in cookies are passed to yt-dlp, then `tv_downgraded,web,web_safari` is used for free accounts and `tv_downgraded,web_creator,web` is used for premium accounts. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only successfully works around the age-restriction sometimes (e.g. if the video is embeddable), and may be added as a fallback if `android_vr` is unable to access a video. The `web_creator` client is added for age-restricted videos if account age-verification is required. Some clients, such as `web_creator` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-web`
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata.  See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
 * `webpage_skip`: Skip extraction of embedded webpage data. One or both of `player_response`, `initial_data`. Using these will not skip any network requests, and in some cases will result in additional network requests. Currently, the default is `player_response`; however, typically these are for testing purposes only
+* `webpage_client`: Client to use for the video webpage request. One of `web` or `web_safari` (default)
 * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
 * `player_js_variant`: The player javascript variant to use for n/sig deciphering. The known variants are: `main`, `tcc`, `tce`, `es5`, `es6`, `es6_tcc`, `es6_tce`, `tv`, `tv_es6`, `phone`, `house`. The default is `tv`, and the others are for debugging purposes. You can use `actual` to go with what is prescribed by the site
 * `player_js_version`: The player javascript version to use for n/sig deciphering, in the format of `signature_timestamp@hash` (e.g. `20348@0004de42`). Currently, the default is to force `20514@9f4cc5e4`. You can use `actual` to go with what is prescribed by the site

yt_dlp/extractor/youtube/_base.py

@@ -957,15 +957,23 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
         url = {
             'mweb': 'https://m.youtube.com',
             'web': 'https://www.youtube.com',
+            'web_safari': 'https://www.youtube.com',
             'web_music': 'https://music.youtube.com',
+            'web_creator': 'https://studio.youtube.com',
             'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1',
             'tv': 'https://www.youtube.com/tv',
         }.get(client)
         if not url:
             return {}
+
+        default_ytcfg = self._get_default_ytcfg(client)
+
+        if default_ytcfg['REQUIRE_AUTH'] and not self.is_authenticated:
+            return {}
+
         webpage = self._download_webpage_with_retries(
             url, video_id, note=f'Downloading {client.replace("_", " ").strip()} client config',
-            headers=traverse_obj(self._get_default_ytcfg(client), {
+            headers=traverse_obj(default_ytcfg, {
                 'User-Agent': ('INNERTUBE_CONTEXT', 'client', 'userAgent', {str}),
                 'Referer': ('INNERTUBE_CONTEXT', 'thirdParty', 'embedUrl', {str}),
             }))

yt_dlp/extractor/youtube/_video.py

@@ -140,11 +140,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     _RETURN_TYPE = 'video'  # XXX: How to handle multifeed?
 
     _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'srt', 'vtt')
-    _DEFAULT_CLIENTS = ('android_vr', 'web', 'web_safari')
+    _DEFAULT_CLIENTS = ('android_vr', 'web_safari')
     _DEFAULT_JSLESS_CLIENTS = ('android_vr',)
-    _DEFAULT_AUTHED_CLIENTS = ('tv_downgraded', 'web', 'web_safari')
+    _DEFAULT_AUTHED_CLIENTS = ('tv_downgraded', 'web_safari')
     # Premium does not require POT (except for subtitles)
-    _DEFAULT_PREMIUM_CLIENTS = ('tv_downgraded', 'web_creator', 'web')
+    _DEFAULT_PREMIUM_CLIENTS = ('tv_downgraded', 'web_creator')
+    _WEBPAGE_CLIENTS = ('web', 'web_safari')
+    _DEFAULT_WEBPAGE_CLIENT = 'web_safari'
 
     _GEO_BYPASS = False
 
@@ -2936,7 +2938,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # This can be detected with the embeds_enable_encrypted_host_flags_enforcement experiemnt flag,
         # but there is no harm in including encryptedHostFlags with all web_embedded player requests.
         encrypted_context = None
-        if client == 'web_embedded':
+        if _split_innertube_client(client)[2] == 'embedded':
             encrypted_context = traverse_obj(player_ytcfg, (
                 'WEB_PLAYER_CONTEXT_CONFIGS', 'WEB_PLAYER_CONTEXT_CONFIG_ID_EMBEDDED_PLAYER', 'encryptedHostFlags'))
 
@@ -3894,7 +3896,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         base_url = self.http_scheme() + '//www.youtube.com/'
         webpage_url = base_url + 'watch?v=' + video_id
-        webpage_client = 'web'
+        webpage_client = self._configuration_arg('webpage_client', [self._DEFAULT_WEBPAGE_CLIENT])[0]
+        if webpage_client not in self._WEBPAGE_CLIENTS:
+            self.report_warning(
+                f'Invalid webpage_client "{webpage_client}" requested; '
+                f'falling back to {self._DEFAULT_WEBPAGE_CLIENT}', only_once=True)
+            webpage_client = self._DEFAULT_WEBPAGE_CLIENT
 
         webpage, webpage_ytcfg, initial_data, is_premium_subscriber, player_responses, player_url = self._initial_extract(
             url, smuggled_data, webpage_url, webpage_client, video_id)