From 2fa669f759eae6d5c7e608e3ee628f9d60d03e83 Mon Sep 17 00:00:00 2001 From: pukkandan Date: Thu, 22 Sep 2022 01:37:44 +0530 Subject: [PATCH] [docs] Misc improvements Closes #4987, Closes #4906, Closes #4919, Closes #4977, Closes #4979 --- README.md | 34 +++++++++++++++--------------- devscripts/make_lazy_extractors.py | 2 +- setup.cfg | 8 +++++++ yt_dlp/__init__.py | 2 +- yt_dlp/extractor/common.py | 2 +- yt_dlp/extractor/cybrary.py | 5 ++--- yt_dlp/extractor/generic.py | 4 ++-- yt_dlp/extractor/niconico.py | 3 +-- yt_dlp/options.py | 4 ++-- yt_dlp/utils.py | 13 ++++++++---- yt_dlp/webvtt.py | 1 - 11 files changed, 44 insertions(+), 34 deletions(-) diff --git a/README.md b/README.md index 9f331663d5..07ed04061c 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,7 @@ [![YT-DLP](https://raw.githubusercontent.com/yt-dlp/yt-dlp/master/.github/banner.svg)](#readme) -[![Release version](https://img.shields.io/github/v/release/yt-dlp/yt-dlp?color=brightgreen&label=Download&style=for-the-badge)](##installation "Installation") +[![Release version](https://img.shields.io/github/v/release/yt-dlp/yt-dlp?color=brightgreen&label=Download&style=for-the-badge)](#installation "Installation") [![PyPi](https://img.shields.io/badge/-PyPi-blue.svg?logo=pypi&labelColor=555555&style=for-the-badge)](https://pypi.org/project/yt-dlp "PyPi") [![Donate](https://img.shields.io/badge/_-Donate-red.svg?logo=githubsponsors&labelColor=555555&style=for-the-badge)](Collaborators.md#collaborators "Donate") [![Matrix](https://img.shields.io/matrix/yt-dlp:matrix.org?color=brightgreen&labelColor=555555&label=&logo=element&style=for-the-badge)](https://matrix.to/#/#yt-dlp:matrix.org "Matrix") @@ -562,7 +562,7 @@ ## Download Options: Needs ffmpeg. This option can be used multiple times to download multiple sections, e.g. --download-sections - "*10:15-15:00" --download-sections "intro" + "*10:15-inf" --download-sections "intro" --downloader [PROTO:]NAME Name or path of the external downloader to use (optionally) prefixed by the protocols (http, ftp, m3u8, dash, rstp, rtmp, mms) to @@ -1079,9 +1079,9 @@ ## Extractor Options: --no-hls-split-discontinuity Do not split HLS playlists to different formats at discontinuities such as ad breaks (default) - --extractor-args KEY:ARGS Pass these arguments to the extractor. See - "EXTRACTOR ARGUMENTS" for details. You can - use this option multiple times to give + --extractor-args IE_KEY:ARGS Pass ARGS arguments to the IE_KEY extractor. + See "EXTRACTOR ARGUMENTS" for details. You + can use this option multiple times to give arguments for different extractors # CONFIGURATION @@ -1092,14 +1092,14 @@ # CONFIGURATION 1. **Portable Configuration**: `yt-dlp.conf` in the same directory as the bundled binary. If you are running from source-code (`/yt_dlp/__main__.py`), the root directory is used instead. 1. **Home Configuration**: `yt-dlp.conf` in the home path given by `-P`, or in the current directory if no such path is given 1. **User Configuration**: - * `%XDG_CONFIG_HOME%/yt-dlp/config` (recommended on Linux/macOS) - * `%XDG_CONFIG_HOME%/yt-dlp.conf` - * `%APPDATA%/yt-dlp/config` (recommended on Windows) - * `%APPDATA%/yt-dlp/config.txt` + * `$XDG_CONFIG_HOME/yt-dlp/config` (recommended on Linux/macOS) + * `$XDG_CONFIG_HOME/yt-dlp.conf` + * `$APPDATA/yt-dlp/config` (recommended on Windows) + * `$APPDATA/yt-dlp/config.txt` * `~/yt-dlp.conf` * `~/yt-dlp.conf.txt` - `%XDG_CONFIG_HOME%` defaults to `~/.config` if undefined. On windows, `%APPDATA%` generally points to `C:\Users\\AppData\Roaming` and `~` points to `%HOME%` if present, `%USERPROFILE%` (generally `C:\Users\`), or `%HOMEDRIVE%%HOMEPATH%` + `$XDG_CONFIG_HOME` defaults to `~/.config` if undefined. On windows, `$APPDATA` generally points to `C:\Users\\AppData\Roaming` and `~` points to `$HOME` if present, `$USERPROFILE` (generally `C:\Users\`), or `${HOMEDRIVE}${HOMEPATH}` 1. **System Configuration**: `/etc/yt-dlp.conf` @@ -1120,7 +1120,7 @@ # Save all videos under YouTube directory in your home directory -o ~/YouTube/%(title)s.%(ext)s ``` -Note that options in configuration file are just the same options aka switches used in regular command line calls; thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`. +Note that options in configuration file are just the same options aka switches used in regular command line calls; thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`. They must also be quoted when necessary as-if it were a UNIX shell. You can use `--ignore-config` if you want to disable all configuration files for a particular yt-dlp run. If `--ignore-config` is found inside any configuration file, no further configuration will be loaded. For example, having the option in the portable configuration file prevents loading of home, user, and system configurations. Additionally, (for backward compatibility) if `--ignore-config` is found inside the system configuration file, the user configuration is not loaded. @@ -1148,7 +1148,7 @@ ### Authentication with `.netrc` file ``` To activate authentication with the `.netrc` file you should pass `--netrc` to yt-dlp or place it in the [configuration file](#configuration). -The default location of the .netrc file is `$HOME` (`~`) in UNIX. On Windows, it is `%HOME%` if present, `%USERPROFILE%` (generally `C:\Users\`) or `%HOMEDRIVE%%HOMEPATH%` +The default location of the .netrc file is `$HOME` (`~`). On Windows, if `$HOME` is not present, `$USERPROFILE` (generally `C:\Users\`) or `${HOMEDRIVE}${HOMEPATH}` is used # OUTPUT TEMPLATE @@ -1627,7 +1627,7 @@ # MODIFYING METADATA The general syntax of `--parse-metadata FROM:TO` is to give the name of a field or an [output template](#output-template) to extract data from, and the format to interpret it as, separated by a colon `:`. Either a [python regular expression](https://docs.python.org/3/library/re.html#regular-expression-syntax) with named capture groups or a similar syntax to the [output template](#output-template) (only `%(field)s` formatting is supported) can be used for `TO`. The option can be used multiple times to parse and modify various fields. -Note that any field created by this can be used in the [output template](#output-template) and will also affect the media file's metadata added when using `--add-metadata`. +Note that any field created by this can be used in the [output template](#output-template) and will also affect the media file's metadata added when using `--embed-metadata`. This option also has a few special uses: @@ -1673,11 +1673,11 @@ # Set title as "Series name S01E05" $ yt-dlp --parse-metadata "%(series)s S%(season_number)02dE%(episode_number)02d:%(title)s" # Prioritize uploader as the "artist" field in video metadata -$ yt-dlp --parse-metadata "%(uploader|)s:%(meta_artist)s" --add-metadata +$ yt-dlp --parse-metadata "%(uploader|)s:%(meta_artist)s" --embed-metadata # Set "comment" field in video metadata using description instead of webpage_url, # handling multiple lines correctly -$ yt-dlp --parse-metadata "description:(?s)(?P.+)" --add-metadata +$ yt-dlp --parse-metadata "description:(?s)(?P.+)" --embed-metadata # Do not set any "synopsis" in the video metadata $ yt-dlp --parse-metadata ":(?P)" @@ -1697,16 +1697,16 @@ # EXTRACTOR ARGUMENTS The following extractors use this feature: #### youtube +* `lang`: Language code to prefer translated metadata of this language (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_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 -* `include_live_dash`: Include live dash formats even without `--live-from-start` (These formats don't download properly) * `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` * E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total +* `include_live_dash`: Include live dash formats even without `--live-from-start` (These formats don't download properly) * `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others * `innertube_key`: Innertube API key to use for all API requests -* `lang`: Language code to prefer translated metadata of this language (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 #### youtubetab (YouTube playlists, channels, feeds, etc.) * `skip`: One or more of `webpage` (skip initial webpage download), `authcheck` (allow the download of playlists requiring authentication when no initial webpage is downloaded. This may cause unwanted behavior, see [#1122](https://github.com/yt-dlp/yt-dlp/pull/1122) for more details) diff --git a/devscripts/make_lazy_extractors.py b/devscripts/make_lazy_extractors.py index 383c7e057c..2d4530eb96 100644 --- a/devscripts/make_lazy_extractors.py +++ b/devscripts/make_lazy_extractors.py @@ -2,8 +2,8 @@ # Allow direct execution import os -import sys import shutil +import sys sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) diff --git a/setup.cfg b/setup.cfg index d33c7d8549..2def390f51 100644 --- a/setup.cfg +++ b/setup.cfg @@ -10,6 +10,14 @@ per_file_ignores = devscripts/lazy_load_template.py: F401 +[autoflake] +ignore-init-module-imports = true +ignore-pass-after-docstring = true +remove-all-unused-imports = true +remove-duplicate-keys = true +remove-unused-variables = true + + [tool:pytest] addopts = -ra -v --strict-markers markers = diff --git a/yt_dlp/__init__.py b/yt_dlp/__init__.py index 29c467b0e8..9382ff43ba 100644 --- a/yt_dlp/__init__.py +++ b/yt_dlp/__init__.py @@ -489,7 +489,7 @@ def report_conflict(arg1, opt1, arg2='--allow-unplayable-formats', opt2='allow_u val1=opts.sponskrub and opts.sponskrub_cut) # Conflicts with --allow-unplayable-formats - report_conflict('--add-metadata', 'addmetadata') + report_conflict('--embed-metadata', 'addmetadata') report_conflict('--embed-chapters', 'addchapters') report_conflict('--embed-info-json', 'embed_infojson') report_conflict('--embed-subs', 'embedsubtitles') diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 4132c831cd..87660bb23b 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -1236,7 +1236,7 @@ def _search_json(self, start_pattern, string, name, video_id, *, end_pattern='', fatal, has_default = False, True json_string = self._search_regex( - rf'{start_pattern}\s*(?P{{\s*{contains_pattern}\s*}})\s*{end_pattern}', + rf'(?:{start_pattern})\s*(?P{{\s*(?:{contains_pattern})\s*}})\s*(?:{end_pattern})', string, name, group='json', fatal=fatal, default=None if has_default else NO_DEFAULT) if not json_string: return default diff --git a/yt_dlp/extractor/cybrary.py b/yt_dlp/extractor/cybrary.py index 7da581828e..73f2439b31 100644 --- a/yt_dlp/extractor/cybrary.py +++ b/yt_dlp/extractor/cybrary.py @@ -1,11 +1,10 @@ -from .common import InfoExtractor - +from .common import InfoExtractor from ..utils import ( ExtractorError, smuggle_url, str_or_none, traverse_obj, - urlencode_postdata + urlencode_postdata, ) diff --git a/yt_dlp/extractor/generic.py b/yt_dlp/extractor/generic.py index 55b3addde4..828c8a6cff 100644 --- a/yt_dlp/extractor/generic.py +++ b/yt_dlp/extractor/generic.py @@ -2623,8 +2623,8 @@ def _real_extract(self, url): url, smuggled_data = unsmuggle_url(url, {}) force_videoid = None - is_intentional = smuggled_data and smuggled_data.get('to_generic') - if smuggled_data and 'force_videoid' in smuggled_data: + is_intentional = smuggled_data.get('to_generic') + if 'force_videoid' in smuggled_data: force_videoid = smuggled_data['force_videoid'] video_id = force_videoid else: diff --git a/yt_dlp/extractor/niconico.py b/yt_dlp/extractor/niconico.py index 82fb27631e..82b60b4765 100644 --- a/yt_dlp/extractor/niconico.py +++ b/yt_dlp/extractor/niconico.py @@ -557,8 +557,7 @@ class NiconicoPlaylistBaseIE(InfoExtractor): } def _call_api(self, list_id, resource, query): - "Implement this in child class" - pass + raise NotImplementedError('Must be implemented in subclasses') @staticmethod def _parse_owner(item): diff --git a/yt_dlp/options.py b/yt_dlp/options.py index 9ad48486e8..861bbf7864 100644 --- a/yt_dlp/options.py +++ b/yt_dlp/options.py @@ -1820,14 +1820,14 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs): val.replace(r'\,', ',').strip() for val in re.split(r'(?