From c8541f8b13e743fcfa06667530d13fee8686e22a Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Wed, 15 Jan 2025 12:21:56 -0600 Subject: [PATCH] [ie/youtube] Do not use `web_creator` as a default client (#12087) Closes #12085 Authored by: bashonly --- README.md | 2 +- yt_dlp/extractor/youtube.py | 41 +++++++------------------------------ 2 files changed, 8 insertions(+), 35 deletions(-) diff --git a/README.md b/README.md index 2f848bd13..56e4458dc 100644 --- a/README.md +++ b/README.md @@ -1769,7 +1769,7 @@ The following extractors use this feature: #### youtube * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively -* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mweb`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,tv` is used, or `web_creator,tv` is used when authenticating with cookies. The `_music` variants are added for `music.youtube.com` URLs. Some clients, such as `web` and `android`, require a `po_token` for their formats to be downloadable. Some clients, such as the `_creator` variants, will only work with authentication. Not all clients support authentication via cookies. You can use `all` to use all the clients, and `default` for the default clients. You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=all,-web` +* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mweb`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `_music` variants may be added for `music.youtube.com` URLs. Some clients, such as `web` and `android`, require a `po_token` for their formats to be downloadable. Some clients, such as the `_creator` variants, 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,-ios` * `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). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp. * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side) diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index e16ec43ed..c23e65cc5 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -116,6 +116,7 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, + 'REQUIRE_PO_TOKEN': True, 'SUPPORTS_COOKIES': True, }, # This client now requires sign-in for every video @@ -127,6 +128,7 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, + 'REQUIRE_PO_TOKEN': True, 'REQUIRE_AUTH': True, 'SUPPORTS_COOKIES': True, }, @@ -211,8 +213,8 @@ INNERTUBE_CLIENTS = { }, }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, - 'REQUIRE_PO_TOKEN': True, 'REQUIRE_JS_PLAYER': False, + 'REQUIRE_PO_TOKEN': True, }, # This client now requires sign-in for every video 'ios_music': { @@ -229,6 +231,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, 'REQUIRE_JS_PLAYER': False, + 'REQUIRE_PO_TOKEN': True, 'REQUIRE_AUTH': True, }, # This client now requires sign-in for every video @@ -246,6 +249,7 @@ INNERTUBE_CLIENTS = { }, 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, 'REQUIRE_JS_PLAYER': False, + 'REQUIRE_PO_TOKEN': True, 'REQUIRE_AUTH': True, }, # mweb has 'ultralow' formats @@ -1423,8 +1427,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor): '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, } _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') - _DEFAULT_CLIENTS = ('ios', 'tv') - _DEFAULT_AUTHED_CLIENTS = ('web_creator', 'tv') + _DEFAULT_CLIENTS = ('tv', 'ios', 'web') + _DEFAULT_AUTHED_CLIENTS = ('tv', 'web') _GEO_BYPASS = False @@ -3960,15 +3964,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): if not requested_clients: raise ExtractorError('No player clients have been requested', expected=True) - if smuggled_data.get('is_music_url') or self.is_music_url(url): - for requested_client in requested_clients: - _, base_client, variant = _split_innertube_client(requested_client) - music_client = f'{base_client}_music' if base_client != 'mweb' else 'web_music' - if variant != 'music' and music_client in INNERTUBE_CLIENTS: - client_info = INNERTUBE_CLIENTS[music_client] - if not client_info['REQUIRE_AUTH'] or (self.is_authenticated and client_info['SUPPORTS_COOKIES']): - requested_clients.append(music_client) - if self.is_authenticated: unsupported_clients = [ client for client in requested_clients if not INNERTUBE_CLIENTS[client]['SUPPORTS_COOKIES'] @@ -4079,28 +4074,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor): else: prs.append(pr) - # web_embedded can work around age-gate and age-verification for some embeddable videos - if self._is_agegated(pr) and variant != 'web_embedded': - append_client(f'web_embedded.{base_client}') - # Unauthenticated users will only get web_embedded client formats if age-gated - if self._is_agegated(pr) and not self.is_authenticated: - self.to_screen( - f'{video_id}: This video is age-restricted; some formats may be missing ' - f'without authentication. {self._login_hint()}', only_once=True) - - ''' This code is pointless while web_creator is in _DEFAULT_AUTHED_CLIENTS - # EU countries require age-verification for accounts to access age-restricted videos - # If account is not age-verified, _is_agegated() will be truthy for non-embedded clients - embedding_is_disabled = variant == 'web_embedded' and self._is_unplayable(pr) - if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled): - self.to_screen( - f'{video_id}: This video is age-restricted and YouTube is requiring ' - 'account age-verification; some formats may be missing', only_once=True) - # web_creator can work around the age-verification requirement - # tv_embedded may(?) still work around age-verification if the video is embeddable - append_client('web_creator') - ''' - prs.extend(deprioritized_prs) if skipped_clients: