From 1e75d97db21152acc764b30a688e516f04b8a142 Mon Sep 17 00:00:00 2001 From: pukkandan Date: Thu, 22 Jun 2023 00:20:04 +0530 Subject: [PATCH] [extractor/youtube] Add `ios` to default clients used * IOS is affected neither by 403 or by nsig so helps mitigate them preemptively * IOS also has higher bit-rate "premium" formats though they are not labeled as such --- README.md | 2 +- yt_dlp/extractor/youtube.py | 8 ++++++-- 2 files changed, 7 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index d9b7a9e5d..d10832103 100644 --- a/README.md +++ b/README.md @@ -1798,7 +1798,7 @@ # EXTRACTOR ARGUMENTS #### 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`, `android` and `ios` with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb` and `tv_embedded` (agegate bypass) with no variants. By default, `android,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. You can use `all` to use all the clients, and `default` for the default clients. +* `player_client`: Clients to extract video data from. The main clients are `web`, `android` and `ios` with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,android,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. You can use `all` to use all the clients, and `default` for the default clients. * `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 * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side) * `max_comments`: Limit the amount of comments to gather. Comma-separated list of integers representing `max-comments,max-parents,max-replies,max-replies-per-thread`. Default is `all,all,all,all` diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index a77a626ac..a90118680 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -258,7 +258,7 @@ def build_innertube_clients(): THIRD_PARTY = { 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL } - BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb') + BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb') priority = qualities(BASE_CLIENTS[::-1]) for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): @@ -3625,7 +3625,7 @@ def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, def _get_requested_clients(self, url, smuggled_data): requested_clients = [] - default = ['android', 'web'] + default = ['ios', 'android', 'web'] allowed_clients = sorted( (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'), key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) @@ -3932,6 +3932,10 @@ def process_manifest_format(f, proto, client_name, itag): elif itag: f['format_id'] = itag + if itag in ('616', '235'): + f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ') + f['source_preference'] = (f.get('source_preference') or -1) + 100 + f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1)) if f['quality'] == -1 and f.get('height'): f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])