From 6aaf96a3d6e7d0d426e97e11a2fcf52fda00e733 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Mon, 1 Jul 2024 17:51:27 -0500 Subject: [PATCH] [cleanup] Misc (#10075) Closes #10303 Authored by: bashonly, seproDev, jucor, c-basalt Co-authored-by: sepro <4618135+seproDev@users.noreply.github.com> Co-authored-by: Julien Cornebise Co-authored-by: c-basalt <117849907+c-basalt@users.noreply.github.com> --- .github/workflows/build.yml | 4 ++ CONTRIBUTING.md | 12 +++--- Collaborators.md | 7 ++++ README.md | 66 +++++++++++++++--------------- devscripts/changelog_override.json | 6 +++ devscripts/cli_to_api.py | 2 + pyproject.toml | 2 +- test/test_jsinterp.py | 1 + test/test_youtube_signature.py | 4 ++ yt_dlp/YoutubeDL.py | 3 +- yt_dlp/cookies.py | 6 +-- yt_dlp/downloader/external.py | 2 +- yt_dlp/extractor/arcpublishing.py | 3 +- yt_dlp/extractor/arkena.py | 4 +- yt_dlp/extractor/bandcamp.py | 2 +- yt_dlp/extractor/brightcove.py | 8 +--- yt_dlp/extractor/cbsnews.py | 1 - yt_dlp/extractor/dailymail.py | 3 +- yt_dlp/extractor/eitb.py | 12 +++--- yt_dlp/extractor/eporner.py | 3 -- yt_dlp/extractor/go.py | 3 +- yt_dlp/extractor/hbo.py | 3 +- yt_dlp/extractor/hketv.py | 3 -- yt_dlp/extractor/instagram.py | 2 +- yt_dlp/extractor/iwara.py | 1 - yt_dlp/extractor/nbc.py | 5 +-- yt_dlp/extractor/nhl.py | 3 +- yt_dlp/extractor/peloton.py | 6 +-- yt_dlp/extractor/performgroup.py | 7 +--- yt_dlp/extractor/pr0gramm.py | 2 +- yt_dlp/extractor/prosiebensat1.py | 5 ++- yt_dlp/extractor/tubetugraz.py | 10 +++-- yt_dlp/extractor/twitter.py | 3 +- yt_dlp/extractor/viewlift.py | 3 +- yt_dlp/extractor/weibo.py | 1 + yt_dlp/extractor/wsj.py | 3 +- yt_dlp/extractor/yahoo.py | 8 ++-- yt_dlp/extractor/yandexdisk.py | 6 +-- yt_dlp/extractor/youtube.py | 2 +- yt_dlp/networking/_websockets.py | 2 +- yt_dlp/options.py | 6 +-- yt_dlp/postprocessor/ffmpeg.py | 3 +- 42 files changed, 132 insertions(+), 106 deletions(-) mode change 100644 => 100755 devscripts/cli_to_api.py diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 1adb62dfb1..12ec5b0d8c 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -525,6 +525,10 @@ jobs: # make sure SHA sums are also printed to stdout sha256sum -- * | tee ../SHA2-256SUMS sha512sum -- * | tee ../SHA2-512SUMS + # also print as permanent annotations to the summary page + while read -r shasum; do + echo "::notice title=${shasum##* }::sha256: ${shasum% *}" + done < ../SHA2-256SUMS - name: Make Update spec run: | diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index aeba3c44d1..dbae6476f6 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -127,7 +127,7 @@ ### Are you willing to share account details if needed? ### Is the website primarily used for piracy? -We follow [youtube-dl's policy](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free) to not support services that is primarily used for infringing copyright. Additionally, it has been decided to not to support porn sites that specialize in fakes. We also cannot support any service that serves only [DRM protected content](https://en.wikipedia.org/wiki/Digital_rights_management). +We follow [youtube-dl's policy](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free) to not support services that is primarily used for infringing copyright. Additionally, it has been decided to not to support porn sites that specialize in fakes. We also cannot support any service that serves only [DRM protected content](https://en.wikipedia.org/wiki/Digital_rights_management). @@ -215,8 +215,8 @@ ## Adding support for a new site ```python from .common import InfoExtractor - - + + class YourExtractorIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P[0-9]+)' _TESTS = [{ @@ -244,7 +244,7 @@ ## Adding support for a new site def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - + # TODO more code goes here, for example ... title = self._html_search_regex(r'

(.+?)

', webpage, 'title') @@ -320,7 +320,7 @@ #### Example ```python meta = self._download_json(url, video_id) ``` - + Assume at this point `meta`'s layout is: ```python @@ -750,7 +750,7 @@ ### Use convenience conversion and parsing functions Use `traverse_obj` and `try_call` (superseeds `dict_get` and `try_get`) for safe metadata extraction from parsed JSON. -Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. +Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction. Explore [`yt_dlp/utils/`](yt_dlp/utils/) for more useful convenience functions. diff --git a/Collaborators.md b/Collaborators.md index 894a853c9b..ee748eb7fd 100644 --- a/Collaborators.md +++ b/Collaborators.md @@ -61,3 +61,10 @@ ## [Grub4K](https://github.com/Grub4K) * Reworked internals like `traverse_obj`, various core refactors and bugs fixes * Implemented proper progress reporting for parallel downloads * Improved/fixed/added Bundestag, crunchyroll, pr0gramm, Twitter, WrestleUniverse etc + + +## [sepro](https://github.com/seproDev) + +* UX improvements: Warn when ffmpeg is missing, warn when double-clicking exe +* Code cleanup: Remove dead extractors, mark extractors as broken, enable/apply ruff rules +* Improved/fixed/added ArdMediathek, DRTV, Floatplane, MagentaMusik, Naver, Nebula, OnDemandKorea, Vbox7 etc diff --git a/README.md b/README.md index 1dffbf8e92..f265c8b558 100644 --- a/README.md +++ b/README.md @@ -141,7 +141,7 @@ ## UPDATE If you [installed with pip](https://github.com/yt-dlp/yt-dlp/wiki/Installation#with-pip), simply re-run the same command that was used to install the program -For other third-party package managers, see [the wiki](https://github.com/yt-dlp/yt-dlp/wiki/Installation#third-party-package-managers) or refer their documentation +For other third-party package managers, see [the wiki](https://github.com/yt-dlp/yt-dlp/wiki/Installation#third-party-package-managers) or refer to their documentation @@ -184,10 +184,10 @@ ## DEPENDENCIES ### Strongly recommended -* [**ffmpeg** and **ffprobe**](https://www.ffmpeg.org) - Required for [merging separate video and audio files](#format-selection) as well as for various [post-processing](#post-processing-options) tasks. License [depends on the build](https://www.ffmpeg.org/legal.html) +* [**ffmpeg** and **ffprobe**](https://www.ffmpeg.org) - Required for [merging separate video and audio files](#format-selection), as well as for various [post-processing](#post-processing-options) tasks. License [depends on the build](https://www.ffmpeg.org/legal.html) There are bugs in ffmpeg that cause various issues when used alongside yt-dlp. Since ffmpeg is such an important dependency, we provide [custom builds](https://github.com/yt-dlp/FFmpeg-Builds#ffmpeg-static-auto-builds) with patches for some of these issues at [yt-dlp/FFmpeg-Builds](https://github.com/yt-dlp/FFmpeg-Builds). See [the readme](https://github.com/yt-dlp/FFmpeg-Builds#patches-applied) for details on the specific issues solved by these builds - + **Important**: What you need is ffmpeg *binary*, **NOT** [the Python package of the same name](https://pypi.org/project/ffmpeg) ### Networking @@ -198,7 +198,7 @@ ### Networking #### Impersonation -The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting. +The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting. * [**curl_cffi**](https://github.com/yifeikong/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lwthiker/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/yifeikong/curl_cffi/blob/main/LICENSE) * Can be installed with the `curl-cffi` group, e.g. `pip install "yt-dlp[default,curl-cffi]"` @@ -275,7 +275,7 @@ ### Standalone Py2Exe Builds (Windows) ### Related scripts * **`devscripts/install_deps.py`** - Install dependencies for yt-dlp. -* **`devscripts/update-version.py`** - Update the version number based on current date. +* **`devscripts/update-version.py`** - Update the version number based on the current date. * **`devscripts/set-variant.py`** - Set the build variant of the executable. * **`devscripts/make_changelog.py`** - Create a markdown changelog using short commit messages and update `CONTRIBUTORS` file. * **`devscripts/make_lazy_extractors.py`** - Create lazy extractors. Running this before building the binaries (any variant) will improve their startup performance. Set the environment variable `YTDLP_NO_LAZY_EXTRACTORS=1` if you wish to forcefully disable lazy extractor loading. @@ -1125,7 +1125,7 @@ # CONFIGURATION * `/etc/yt-dlp/config` * `/etc/yt-dlp/config.txt` -E.g. with the following configuration file yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory: +E.g. with the following configuration file, yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory: ``` # Lines starting with # are comments @@ -1142,7 +1142,7 @@ # Save all videos under YouTube directory in your home directory -o ~/YouTube/%(title)s.%(ext)s ``` -**Note**: 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. +**Note**: 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. @@ -1154,12 +1154,12 @@ ### Configuration file encoding ### Authentication with netrc -You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every yt-dlp execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](https://stackoverflow.com/tags/.netrc/info) on a per-extractor basis. For that you will need to create a `.netrc` file in `--netrc-location` and restrict permissions to read/write by only you: +You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every yt-dlp execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](https://stackoverflow.com/tags/.netrc/info) on a per-extractor basis. For that, you will need to create a `.netrc` file in `--netrc-location` and restrict permissions to read/write by only you: ``` touch ${HOME}/.netrc chmod a-rwx,u+rw ${HOME}/.netrc ``` -After that you can add credentials for an extractor in the following format, where *extractor* is the name of the extractor in lowercase: +After that, you can add credentials for an extractor in the following format, where *extractor* is the name of the extractor in lowercase: ``` machine login password ``` @@ -1201,7 +1201,7 @@ # OUTPUT TEMPLATE The field names themselves (the part inside the parenthesis) can also have some special formatting: -1. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a dot `.` separator; e.g. `%(tags.0)s`, `%(subtitles.en.-1.ext)s`. You can do Python slicing with colon `:`; E.g. `%(id.3:7:-1)s`, `%(formats.:.format_id)s`. Curly braces `{}` can be used to build dictionaries with only specific keys; e.g. `%(formats.:.{format_id,height})#j`. An empty field name `%()s` refers to the entire infodict; e.g. `%(.{id,title})s`. Note that all the fields that become available using this method are not listed below. Use `-j` to see such fields +1. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a dot `.` separator; e.g. `%(tags.0)s`, `%(subtitles.en.-1.ext)s`. You can do Python slicing with colon `:`; E.g. `%(id.3:7)s`, `%(id.6:2:-1)s`, `%(formats.:.format_id)s`. Curly braces `{}` can be used to build dictionaries with only specific keys; e.g. `%(formats.:.{format_id,height})#j`. An empty field name `%()s` refers to the entire infodict; e.g. `%(.{id,title})s`. Note that all the fields that become available using this method are not listed below. Use `-j` to see such fields 1. **Arithmetic**: Simple arithmetic can be done on numeric fields using `+`, `-` and `*`. E.g. `%(playlist_index+10)03d`, `%(n_entries+1-playlist_index)d` @@ -1222,7 +1222,7 @@ # OUTPUT TEMPLATE %(name[.keys][addition][>strf][,alternate][&replacement][|default])[flags][width][.precision][length]type ``` -Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon `:`. The different file types supported are `subtitle`, `thumbnail`, `description`, `annotation` (deprecated), `infojson`, `link`, `pl_thumbnail`, `pl_description`, `pl_infojson`, `chapter`, `pl_video`. E.g. `-o "%(title)s.%(ext)s" -o "thumbnail:%(title)s\%(title)s.%(ext)s"` will put the thumbnails in a folder with the same name as the video. If any of the templates is empty, that type of file will not be written. E.g. `--write-thumbnail -o "thumbnail:"` will write thumbnails only for playlists and not for video. +Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon `:`. The different file types supported are `subtitle`, `thumbnail`, `description`, `annotation` (deprecated), `infojson`, `link`, `pl_thumbnail`, `pl_description`, `pl_infojson`, `chapter`, `pl_video`. E.g. `-o "%(title)s.%(ext)s" -o "thumbnail:%(title)s\%(title)s.%(ext)s"` will put the thumbnails in a folder with the same name as the video. If any of the templates is empty, that type of file will not be written. E.g. `--write-thumbnail -o "thumbnail:"` will write thumbnails only for playlists and not for video. @@ -1282,7 +1282,7 @@ # OUTPUT TEMPLATE - `n_entries` (numeric): Total number of extracted items in the playlist - `playlist_id` (string): Identifier of the playlist that contains the video - `playlist_title` (string): Name of the playlist that contains the video - - `playlist` (string): `playlist_id` or `playlist_title` + - `playlist` (string): `playlist_title` if available or else `playlist_id` - `playlist_count` (numeric): Total number of items in the playlist. May not be known if entire playlist is not extracted - `playlist_index` (numeric): Index of the video in the playlist padded with leading zeros according the final index - `playlist_autonumber` (numeric): Position of the video in the playlist download queue padded with leading zeros according to the total length of the playlist @@ -1290,7 +1290,7 @@ # OUTPUT TEMPLATE - `playlist_uploader_id` (string): Nickname or id of the playlist uploader - `playlist_channel` (string): Display name of the channel that uploaded the playlist - `playlist_channel_id` (string): Identifier of the channel that uploaded the playlist - - `webpage_url` (string): A URL to the video webpage which if given to yt-dlp should allow to get the same result again + - `webpage_url` (string): A URL to the video webpage which, if given to yt-dlp, should yield the same result again - `webpage_url_basename` (string): The basename of the webpage URL - `webpage_url_domain` (string): The domain of the webpage URL - `original_url` (string): The URL given by the user (or same as `webpage_url` for playlist entries) @@ -1306,10 +1306,10 @@ # OUTPUT TEMPLATE - `chapter_number` (numeric): Number of the chapter the video belongs to - `chapter_id` (string): Id of the chapter the video belongs to -Available for the video that is an episode of some series or programme: +Available for the video that is an episode of some series or program: - - `series` (string): Title of the series or programme the video episode belongs to - - `series_id` (string): Id of the series or programme the video episode belongs to + - `series` (string): Title of the series or program the video episode belongs to + - `series_id` (string): Id of the series or program the video episode belongs to - `season` (string): Title of the season the video episode belongs to - `season_number` (numeric): Number of the season the video episode belongs to - `season_id` (string): Id of the season the video episode belongs to @@ -1349,9 +1349,9 @@ # OUTPUT TEMPLATE - `thumbnails_table` (table): The thumbnail format table as printed by `--list-thumbnails` - `subtitles_table` (table): The subtitle format table as printed by `--list-subs` - `automatic_captions_table` (table): The automatic subtitle format table as printed by `--list-subs` - + Available only after the video is downloaded (`post_process`/`after_move`): - + - `filepath`: Actual path of downloaded video file Available only in `--sponsorblock-chapter-title`: @@ -1366,7 +1366,7 @@ # OUTPUT TEMPLATE Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. E.g. for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `yt-dlp test video` and id `BaW_jenozKc`, this will result in a `yt-dlp test video-BaW_jenozKc.mp4` file created in the current directory. -**Note**: Some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default). +**Note**: Some of the sequences are not guaranteed to be present, since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default). **Tip**: Look at the `-j` output to identify which fields are available for the particular URL @@ -1444,7 +1444,7 @@ # FORMAT SELECTION - `all`: Select **all formats** separately - `mergeall`: Select and **merge all formats** (Must be used with `--audio-multistreams`, `--video-multistreams` or both) - - `b*`, `best*`: Select the best quality format that **contains either** a video or an audio or both (ie; `vcodec!=none or acodec!=none`) + - `b*`, `best*`: Select the best quality format that **contains either** a video or an audio or both (i.e.; `vcodec!=none or acodec!=none`) - `b`, `best`: Select the best quality format that **contains both** video and audio. Equivalent to `best*[vcodec!=none][acodec!=none]` - `bv`, `bestvideo`: Select the best quality **video-only** format. Equivalent to `best*[acodec=none]` - `bv*`, `bestvideo*`: Select the best quality format that **contains video**. It may also contain audio. Equivalent to `best*[vcodec!=none]` @@ -1457,7 +1457,7 @@ # FORMAT SELECTION - `wa`, `worstaudio`: Select the worst quality audio-only format. Equivalent to `worst*[vcodec=none]` - `wa*`, `worstaudio*`: Select the worst quality format that contains audio. It may also contain video. Equivalent to `worst*[acodec!=none]` -For example, to download the worst quality video-only format you can use `-f worstvideo`. It is however recommended not to use `worst` and related options. When your format selector is `worst`, the format which is worst in all respects is selected. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-S +size` or more rigorously, `-S +size,+br,+res,+fps` instead of `-f worst`. See [Sorting Formats](#sorting-formats) for more details. +For example, to download the worst quality video-only format you can use `-f worstvideo`. It is, however, recommended not to use `worst` and related options. When your format selector is `worst`, the format which is worst in all respects is selected. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-S +size` or more rigorously, `-S +size,+br,+res,+fps` instead of `-f worst`. See [Sorting Formats](#sorting-formats) for more details. You can select the n'th best format of a type by using `best.`. For example, `best.2` will select the 2nd best combined format. Similarly, `bv*.3` will select the 3rd best format that contains a video stream. @@ -1507,7 +1507,7 @@ ## Filtering Formats Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). The comparand of a string comparison needs to be quoted with either double or single quotes if it contains spaces or special characters other than `._-`. -**Note**: None of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering. +**Note**: None of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by the particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering. Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "bv[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 kbps. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats. @@ -1546,14 +1546,14 @@ ## Sorting Formats - `abr`: Average audio bitrate in [kbps](## "1000 bits/sec") - `br`: Average bitrate in [kbps](## "1000 bits/sec"), `tbr`/`vbr`/`abr` - `asr`: Audio sample rate in Hz - + **Deprecation warning**: Many of these fields have (currently undocumented) aliases, that may be removed in a future version. It is recommended to use only the documented field names. All fields, unless specified otherwise, are sorted in descending order. To reverse this, prefix the field with a `+`. E.g. `+res` prefers format with the smallest resolution. Additionally, you can suffix a preferred value for the fields, separated by a `:`. E.g. `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two preferred values, the first for video and the second for audio. E.g. `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp9.2` > `av01` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. E.g. `filesize~1G` prefers the format with filesize closest to 1 GiB. -The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,vcodec:vp9.2,channels,acodec,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order. +The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behavior can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,vcodec:vp9.2,channels,acodec,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order. -Note that the default has `vcodec:vp9.2`; i.e. `av1` is not preferred. Similarly, the default for hdr is `hdr:12`; i.e. dolby vision is not preferred. These choices are made since DV and AV1 formats are not yet fully compatible with most devices. This may be changed in the future as more devices become capable of smoothly playing back these formats. +Note that the default has `vcodec:vp9.2`; i.e. `av1` is not preferred. Similarly, the default for hdr is `hdr:12`; i.e. Dolby Vision is not preferred. These choices are made since DV and AV1 formats are not yet fully compatible with most devices. This may be changed in the future as more devices become capable of smoothly playing back these formats. If your format selector is `worst`, the last item is selected after sorting. This means it will select the format that is worst in all respects. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps`. @@ -1765,7 +1765,7 @@ # 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`, `ios` and `android`, with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,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. The `android` clients will always be given lowest priority since their formats are broken. 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`, `ios` and `android`, with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mediaconnect`, `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,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. The `android` clients will always be given lowest priority since their formats are broken. 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 * `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) @@ -1851,7 +1851,7 @@ #### afreecatvlive * `cdn`: One or more CDN IDs to use with the API call for stream URLs, e.g. `gcp_cdn`, `gs_cdn_pc_app`, `gs_cdn_mobile_web`, `gs_cdn_pc_web` #### soundcloud -* `formats`: Formats to request from the API. Requested values should be in the format of `{protocol}_{extension}` (omitting the bitrate), e.g. `hls_opus,http_aac`. The `*` character functions as a wildcard, e.g. `*_mp3`, and can passed by itself to request all formats. Known protocols include `http`, `hls` and `hls-aes`; known extensions include `aac`, `opus` and `mp3`. Original `download` formats are always extracted. Default is `http_aac,hls_aac,http_opus,hls_opus,http_mp3,hls_mp3` +* `formats`: Formats to request from the API. Requested values should be in the format of `{protocol}_{extension}` (omitting the bitrate), e.g. `hls_opus,http_aac`. The `*` character functions as a wildcard, e.g. `*_mp3`, and can be passed by itself to request all formats. Known protocols include `http`, `hls` and `hls-aes`; known extensions include `aac`, `opus` and `mp3`. Original `download` formats are always extracted. Default is `http_aac,hls_aac,http_opus,hls_opus,http_mp3,hls_mp3` #### orfon (orf:on) * `prefer_segments_playlist`: Prefer a playlist of program segments instead of a single complete video when available. If individual segments are desired, use `--concat-playlist never --extractor-args "orfon:prefer_segments_playlist"` @@ -1868,16 +1868,16 @@ # PLUGINS Note that **all** plugins are imported even if not invoked, and that **there are no checks** performed on plugin code. **Use plugins at your own risk and only if you trust the code!** -Plugins can be of ``s `extractor` or `postprocessor`. -- Extractor plugins do not need to be enabled from the CLI and are automatically invoked when the input URL is suitable for it. -- Extractor plugins take priority over builtin extractors. +Plugins can be of ``s `extractor` or `postprocessor`. +- Extractor plugins do not need to be enabled from the CLI and are automatically invoked when the input URL is suitable for it. +- Extractor plugins take priority over built-in extractors. - Postprocessor plugins can be invoked using `--use-postprocessor NAME`. Plugins are loaded from the namespace packages `yt_dlp_plugins.extractor` and `yt_dlp_plugins.postprocessor`. In other words, the file structure on the disk looks something like: - + yt_dlp_plugins/ extractor/ myplugin.py @@ -1925,7 +1925,7 @@ ## Developing Plugins See the [yt-dlp-sample-plugins](https://github.com/yt-dlp/yt-dlp-sample-plugins) repo for a template plugin package and the [Plugin Development](https://github.com/yt-dlp/yt-dlp/wiki/Plugin-Development) section of the wiki for a plugin development guide. -All public classes with a name ending in `IE`/`PP` are imported from each file for extractors and postprocessors repectively. This respects underscore prefix (e.g. `_MyBasePluginIE` is private) and `__all__`. Modules can similarly be excluded by prefixing the module name with an underscore (e.g. `_myplugin.py`). +All public classes with a name ending in `IE`/`PP` are imported from each file for extractors and postprocessors respectively. This respects underscore prefix (e.g. `_MyBasePluginIE` is private) and `__all__`. Modules can similarly be excluded by prefixing the module name with an underscore (e.g. `_myplugin.py`). To replace an existing extractor with a subclass of one, set the `plugin_name` class keyword argument (e.g. `class MyPluginIE(ABuiltInIE, plugin_name='myplugin')` will replace `ABuiltInIE` with `MyPluginIE`). Since the extractor replaces the parent, you should exclude the subclass extractor from being imported separately by making it private using one of the methods described above. @@ -1937,7 +1937,7 @@ # EMBEDDING YT-DLP yt-dlp makes the best effort to be a good command-line program, and thus should be callable from any programming language. -Your program should avoid parsing the normal stdout since they may change in future versions. Instead they should use options such as `-J`, `--print`, `--progress-template`, `--exec` etc to create console output that you can reliably reproduce and parse. +Your program should avoid parsing the normal stdout since they may change in future versions. Instead, they should use options such as `-J`, `--print`, `--progress-template`, `--exec` etc to create console output that you can reliably reproduce and parse. From a Python program, you can embed yt-dlp in a more powerful fashion, like this: diff --git a/devscripts/changelog_override.json b/devscripts/changelog_override.json index 86e8ec2f99..f7209f3bda 100644 --- a/devscripts/changelog_override.json +++ b/devscripts/changelog_override.json @@ -169,5 +169,11 @@ "when": "5c019f6328ad40d66561eac3c4de0b3cd070d0f6", "short": "[cleanup] Misc (#9765)", "authors": ["bashonly", "Grub4K", "seproDev"] + }, + { + "action": "change", + "when": "e6a22834df1776ec4e486526f6df2bf53cb7e06f", + "short": "[ie/orf:on] Add `prefer_segments_playlist` extractor-arg (#10314)", + "authors": ["seproDev"] } ] diff --git a/devscripts/cli_to_api.py b/devscripts/cli_to_api.py old mode 100644 new mode 100755 index 2aa51eb6e9..9c2710e09f --- a/devscripts/cli_to_api.py +++ b/devscripts/cli_to_api.py @@ -1,3 +1,5 @@ +#!/usr/bin/env python3 + # Allow direct execution import os import sys diff --git a/pyproject.toml b/pyproject.toml index a2442a14d5..39986a355c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -299,7 +299,7 @@ banned-from = [ "string", "sys", "time", - "urllib", + "urllib.parse", "uuid", "xml", ] diff --git a/test/test_jsinterp.py b/test/test_jsinterp.py index 86928a6a02..7c556e4611 100644 --- a/test/test_jsinterp.py +++ b/test/test_jsinterp.py @@ -92,6 +92,7 @@ def test_operators(self): self._test('function f(){return 0 && 1 || 2;}', 2) self._test('function f(){return 0 ?? 42;}', 0) self._test('function f(){return "life, the universe and everything" < 42;}', False) + self._test('function f(){return 0 - 7 * - 6;}', 42) def test_array_access(self): self._test('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2.0] = 7; return x;}', [5, 2, 7]) diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index bfaff83a0a..b0f3269e1c 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -163,6 +163,10 @@ 'https://www.youtube.com/s/player/b7910ca8/player_ias.vflset/en_US/base.js', '_hXMCwMt9qE310D', 'LoZMgkkofRMCZQ', ), + ( + 'https://www.youtube.com/s/player/590f65a6/player_ias.vflset/en_US/base.js', + '1tm7-g_A9zsI8_Lay_', 'xI4Vem4Put_rOg', + ), ] diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index ba29b29dcb..a8d0342d53 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -4,6 +4,7 @@ import datetime as dt import errno import fileinput +import functools import http.cookiejar import io import itertools @@ -24,7 +25,7 @@ import unicodedata from .cache import Cache -from .compat import functools, urllib # isort: split +from .compat import urllib # isort: split from .compat import compat_os_name, urllib_req_to_req from .cookies import LenientSimpleCookie, load_cookies from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name diff --git a/yt_dlp/cookies.py b/yt_dlp/cookies.py index d07269a677..070d2fcb98 100644 --- a/yt_dlp/cookies.py +++ b/yt_dlp/cookies.py @@ -2,7 +2,9 @@ import collections import contextlib import datetime as dt +import functools import glob +import hashlib import http.cookiejar import http.cookies import io @@ -17,14 +19,12 @@ import time import urllib.request from enum import Enum, auto -from hashlib import pbkdf2_hmac from .aes import ( aes_cbc_decrypt_bytes, aes_gcm_decrypt_and_verify_bytes, unpad_pkcs7, ) -from .compat import functools # isort: split from .compat import compat_os_name from .dependencies import ( _SECRETSTORAGE_UNAVAILABLE_REASON, @@ -999,7 +999,7 @@ def _get_windows_v10_key(browser_root, logger): def pbkdf2_sha1(password, salt, iterations, key_length): - return pbkdf2_hmac('sha1', password, salt, iterations, key_length) + return hashlib.pbkdf2_hmac('sha1', password, salt, iterations, key_length) def _decrypt_aes_cbc_multi(ciphertext, keys, logger, initialization_vector=b' ' * 16): diff --git a/yt_dlp/downloader/external.py b/yt_dlp/downloader/external.py index 63c1085699..ae2372915b 100644 --- a/yt_dlp/downloader/external.py +++ b/yt_dlp/downloader/external.py @@ -1,4 +1,5 @@ import enum +import functools import json import os import re @@ -9,7 +10,6 @@ import uuid from .fragment import FragmentFD -from ..compat import functools from ..networking import Request from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor from ..utils import ( diff --git a/yt_dlp/extractor/arcpublishing.py b/yt_dlp/extractor/arcpublishing.py index 338bada7c8..8da9bc4ccb 100644 --- a/yt_dlp/extractor/arcpublishing.py +++ b/yt_dlp/extractor/arcpublishing.py @@ -4,6 +4,7 @@ from ..utils import ( extract_attributes, int_or_none, + join_nonempty, parse_iso8601, try_get, ) @@ -136,7 +137,7 @@ def _real_extract(self, url): else: vbr = int_or_none(s.get('bitrate')) formats.append({ - 'format_id': f'{stream_type}-{vbr}' if vbr else stream_type, + 'format_id': join_nonempty(stream_type, vbr), 'vbr': vbr, 'width': int_or_none(s.get('width')), 'height': int_or_none(s.get('height')), diff --git a/yt_dlp/extractor/arkena.py b/yt_dlp/extractor/arkena.py index b0e853d57a..aa6c5ca4d6 100644 --- a/yt_dlp/extractor/arkena.py +++ b/yt_dlp/extractor/arkena.py @@ -131,8 +131,8 @@ def _real_extract(self, url): formats.extend(self._extract_f4m_formats( href, video_id, f4m_id='hds', fatal=False)) elif mime_type == 'application/dash+xml': - formats.extend(self._extract_f4m_formats( - href, video_id, f4m_id='hds', fatal=False)) + formats.extend(self._extract_mpd_formats( + href, video_id, mpd_id='dash', fatal=False)) elif mime_type == 'application/vnd.ms-sstr+xml': formats.extend(self._extract_ism_formats( href, video_id, ism_id='mss', fatal=False)) diff --git a/yt_dlp/extractor/bandcamp.py b/yt_dlp/extractor/bandcamp.py index 6128de791b..61cbab5a7a 100644 --- a/yt_dlp/extractor/bandcamp.py +++ b/yt_dlp/extractor/bandcamp.py @@ -41,7 +41,7 @@ class BandcampIE(InfoExtractor): 'uploader_id': 'youtube-dl', 'thumbnail': 'https://f4.bcbits.com/img/a3216802731_5.jpg', }, - '_skip': 'There is a limit of 200 free downloads / month for the test song', + 'skip': 'There is a limit of 200 free downloads / month for the test song', }, { # free download 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', diff --git a/yt_dlp/extractor/brightcove.py b/yt_dlp/extractor/brightcove.py index 56d74764fd..2526f25dac 100644 --- a/yt_dlp/extractor/brightcove.py +++ b/yt_dlp/extractor/brightcove.py @@ -18,6 +18,7 @@ fix_xml_ampersands, float_or_none, int_or_none, + join_nonempty, js_to_json, mimetype2ext, parse_iso8601, @@ -538,12 +539,7 @@ def _parse_brightcove_metadata(self, json_data, video_id, headers={}): }) def build_format_id(kind): - format_id = kind - if tbr: - format_id += f'-{int(tbr)}k' - if height: - format_id += f'-{height}p' - return format_id + return join_nonempty(kind, tbr and f'{int(tbr)}k', height and f'{height}p') if src or streaming_src: f.update({ diff --git a/yt_dlp/extractor/cbsnews.py b/yt_dlp/extractor/cbsnews.py index 5a8ebb8476..972e111190 100644 --- a/yt_dlp/extractor/cbsnews.py +++ b/yt_dlp/extractor/cbsnews.py @@ -1,6 +1,5 @@ import base64 import re -import urllib.error import urllib.parse import zlib diff --git a/yt_dlp/extractor/dailymail.py b/yt_dlp/extractor/dailymail.py index 516df1b5cf..540676ac0f 100644 --- a/yt_dlp/extractor/dailymail.py +++ b/yt_dlp/extractor/dailymail.py @@ -2,6 +2,7 @@ from ..utils import ( determine_protocol, int_or_none, + join_nonempty, try_get, unescapeHTML, ) @@ -52,7 +53,7 @@ def _real_extract(self, url): is_hls = container == 'M2TS' protocol = 'm3u8_native' if is_hls else determine_protocol({'url': rendition_url}) formats.append({ - 'format_id': ('hls' if is_hls else protocol) + (f'-{tbr}' if tbr else ''), + 'format_id': join_nonempty('hls' if is_hls else protocol, tbr), 'url': rendition_url, 'width': int_or_none(rendition.get('frameWidth')), 'height': int_or_none(rendition.get('frameHeight')), diff --git a/yt_dlp/extractor/eitb.py b/yt_dlp/extractor/eitb.py index 3e27507965..18b802eb15 100644 --- a/yt_dlp/extractor/eitb.py +++ b/yt_dlp/extractor/eitb.py @@ -1,6 +1,11 @@ from .common import InfoExtractor from ..networking import Request -from ..utils import float_or_none, int_or_none, parse_iso8601 +from ..utils import ( + float_or_none, + int_or_none, + join_nonempty, + parse_iso8601, +) class EitbIE(InfoExtractor): @@ -37,12 +42,9 @@ def _real_extract(self, url): if not video_url: continue tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000) - format_id = 'http' - if tbr: - format_id += f'-{int(tbr)}' formats.append({ 'url': rendition['PMD_URL'], - 'format_id': format_id, + 'format_id': join_nonempty('http', int_or_none(tbr)), 'width': int_or_none(rendition.get('FRAME_WIDTH')), 'height': int_or_none(rendition.get('FRAME_HEIGHT')), 'tbr': tbr, diff --git a/yt_dlp/extractor/eporner.py b/yt_dlp/extractor/eporner.py index e0b6ca96fb..2d25c6b4df 100644 --- a/yt_dlp/extractor/eporner.py +++ b/yt_dlp/extractor/eporner.py @@ -29,9 +29,6 @@ class EpornerIE(InfoExtractor): 'view_count': int, 'age_limit': 18, }, - 'params': { - 'proxy': '127.0.0.1:8118', - }, }, { # New (May 2016) URL layout 'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/', diff --git a/yt_dlp/extractor/go.py b/yt_dlp/extractor/go.py index bbb23ffc0a..83c1979db8 100644 --- a/yt_dlp/extractor/go.py +++ b/yt_dlp/extractor/go.py @@ -5,6 +5,7 @@ ExtractorError, determine_ext, int_or_none, + join_nonempty, parse_age_limit, remove_end, remove_start, @@ -287,7 +288,7 @@ def _real_extract(self, url): if mobj: height = int(mobj.group(2)) f.update({ - 'format_id': (f'{format_id}-' if format_id else '') + f'{height}P', + 'format_id': join_nonempty(format_id, f'{height}P'), 'width': int(mobj.group(1)), 'height': height, }) diff --git a/yt_dlp/extractor/hbo.py b/yt_dlp/extractor/hbo.py index 146d8a23d8..34cff458d8 100644 --- a/yt_dlp/extractor/hbo.py +++ b/yt_dlp/extractor/hbo.py @@ -3,6 +3,7 @@ from .common import InfoExtractor from ..utils import ( int_or_none, + join_nonempty, parse_duration, urljoin, xpath_element, @@ -69,7 +70,7 @@ def _extract_info(self, url, display_id): height = format_info.get('height') fmt = { 'url': path, - 'format_id': 'http{}'.format(f'-{height}p' if height else ''), + 'format_id': join_nonempty('http'. height and f'{height}p'), 'width': format_info.get('width'), 'height': height, } diff --git a/yt_dlp/extractor/hketv.py b/yt_dlp/extractor/hketv.py index bffb6afe02..3998abc121 100644 --- a/yt_dlp/extractor/hketv.py +++ b/yt_dlp/extractor/hketv.py @@ -44,9 +44,6 @@ class HKETVIE(InfoExtractor): 'duration': 907, 'subtitles': {}, }, - 'params': { - 'geo_verification_proxy': '', - }, 'skip': 'Geo restricted to HK', }] diff --git a/yt_dlp/extractor/instagram.py b/yt_dlp/extractor/instagram.py index c8bf7e9c4a..754f710ae2 100644 --- a/yt_dlp/extractor/instagram.py +++ b/yt_dlp/extractor/instagram.py @@ -453,7 +453,7 @@ def _real_extract(self, url): else: self.report_warning('Main webpage is locked behind the login page. Retrying with embed webpage (some metadata might be missing).') webpage = self._download_webpage( - f'{url}/embed/', video_id, note='Downloading embed webpage', fatal=False) + f'{url}/embed/', video_id, note='Downloading embed webpage', fatal=False) or '' additional_data = self._search_json( r'window\.__additionalDataLoaded\s*\(\s*[^,]+,', webpage, 'additional data', video_id, fatal=False) if not additional_data and not media: diff --git a/yt_dlp/extractor/iwara.py b/yt_dlp/extractor/iwara.py index df2088f9e7..5b5c367ad8 100644 --- a/yt_dlp/extractor/iwara.py +++ b/yt_dlp/extractor/iwara.py @@ -2,7 +2,6 @@ import hashlib import json import time -import urllib.error import urllib.parse from .common import InfoExtractor diff --git a/yt_dlp/extractor/nbc.py b/yt_dlp/extractor/nbc.py index 1da2cad3d4..8f6fb22b17 100644 --- a/yt_dlp/extractor/nbc.py +++ b/yt_dlp/extractor/nbc.py @@ -16,6 +16,7 @@ determine_ext, float_or_none, int_or_none, + join_nonempty, mimetype2ext, parse_age_limit, parse_duration, @@ -498,10 +499,8 @@ def _real_extract(self, url): m3u8_id=format_id, fatal=False)) continue tbr = int_or_none(va.get('bitrate'), 1000) - if tbr: - format_id += f'-{tbr}' formats.append({ - 'format_id': format_id, + 'format_id': join_nonempty(format_id, tbr), 'url': public_url, 'width': int_or_none(va.get('width')), 'height': int_or_none(va.get('height')), diff --git a/yt_dlp/extractor/nhl.py b/yt_dlp/extractor/nhl.py index 83dd480cfa..ca47a81211 100644 --- a/yt_dlp/extractor/nhl.py +++ b/yt_dlp/extractor/nhl.py @@ -2,6 +2,7 @@ from ..utils import ( determine_ext, int_or_none, + join_nonempty, parse_duration, parse_iso8601, ) @@ -41,7 +42,7 @@ def _real_extract(self, url): else: height = int_or_none(playback.get('height')) formats.append({ - 'format_id': playback.get('name', 'http' + (f'-{height}p' if height else '')), + 'format_id': playback.get('name') or join_nonempty('http', height and f'{height}p'), 'url': playback_url, 'width': int_or_none(playback.get('width')), 'height': height, diff --git a/yt_dlp/extractor/peloton.py b/yt_dlp/extractor/peloton.py index c0443e9c91..5999d4a6a0 100644 --- a/yt_dlp/extractor/peloton.py +++ b/yt_dlp/extractor/peloton.py @@ -41,7 +41,7 @@ class PelotonIE(InfoExtractor): }, 'params': { 'skip_download': 'm3u8', }, - '_skip': 'Account needed', + 'skip': 'Account needed', }, { 'url': 'https://members.onepeloton.com/classes/player/26603d53d6bb4de1b340514864a6a6a8', 'info_dict': { @@ -61,7 +61,7 @@ class PelotonIE(InfoExtractor): }, 'params': { 'skip_download': 'm3u8', }, - '_skip': 'Account needed', + 'skip': 'Account needed', }] _MANIFEST_URL_TEMPLATE = '%s?hdnea=%s' @@ -199,7 +199,7 @@ class PelotonLiveIE(InfoExtractor): 'params': { 'skip_download': 'm3u8', }, - '_skip': 'Account needed', + 'skip': 'Account needed', } def _real_extract(self, url): diff --git a/yt_dlp/extractor/performgroup.py b/yt_dlp/extractor/performgroup.py index c0d5575912..df726c975b 100644 --- a/yt_dlp/extractor/performgroup.py +++ b/yt_dlp/extractor/performgroup.py @@ -1,5 +1,5 @@ from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import int_or_none, join_nonempty class PerformGroupIE(InfoExtractor): @@ -50,11 +50,8 @@ def _real_extract(self, url): if not c_url: continue tbr = int_or_none(c.get('bitrate'), 1000) - format_id = 'http' - if tbr: - format_id += f'-{tbr}' formats.append({ - 'format_id': format_id, + 'format_id': join_nonempty('http', tbr), 'url': c_url, 'tbr': tbr, 'width': int_or_none(c.get('width')), diff --git a/yt_dlp/extractor/pr0gramm.py b/yt_dlp/extractor/pr0gramm.py index f2c4e12e66..b0d6475fe4 100644 --- a/yt_dlp/extractor/pr0gramm.py +++ b/yt_dlp/extractor/pr0gramm.py @@ -1,9 +1,9 @@ import datetime as dt +import functools import json import urllib.parse from .common import InfoExtractor -from ..compat import functools from ..utils import ( ExtractorError, float_or_none, diff --git a/yt_dlp/extractor/prosiebensat1.py b/yt_dlp/extractor/prosiebensat1.py index 6a3e0971cd..e8a4712051 100644 --- a/yt_dlp/extractor/prosiebensat1.py +++ b/yt_dlp/extractor/prosiebensat1.py @@ -7,6 +7,7 @@ determine_ext, float_or_none, int_or_none, + join_nonempty, merge_dicts, unified_strdate, ) @@ -147,13 +148,13 @@ def fix_bitrate(bitrate): 'page_url': 'http://www.prosieben.de', 'tbr': tbr, 'ext': 'flv', - 'format_id': 'rtmp{}'.format(f'-{tbr}' if tbr else ''), + 'format_id': join_nonempty('rtmp', tbr), }) else: formats.append({ 'url': source_url, 'tbr': tbr, - 'format_id': 'http{}'.format(f'-{tbr}' if tbr else ''), + 'format_id': join_nonempty('http', tbr), }) return { diff --git a/yt_dlp/extractor/tubetugraz.py b/yt_dlp/extractor/tubetugraz.py index e13375f0a1..d5dbf007b1 100644 --- a/yt_dlp/extractor/tubetugraz.py +++ b/yt_dlp/extractor/tubetugraz.py @@ -21,7 +21,7 @@ def _perform_login(self, username, password): if not urlh: return - content, urlh = self._download_webpage_handle( + response = self._download_webpage_handle( urlh.url, None, fatal=False, headers={'referer': urlh.url}, note='logging in', errnote='unable to log in', data=urlencode_postdata({ @@ -30,7 +30,11 @@ def _perform_login(self, username, password): 'j_username': username, 'j_password': password, })) - if not urlh or urlh.url == 'https://tube.tugraz.at/paella/ui/index.html': + if not response: + return + + content, urlh = response + if urlh.url == 'https://tube.tugraz.at/paella/ui/index.html': return if not self._html_search_regex( @@ -39,7 +43,7 @@ def _perform_login(self, username, password): self.report_warning('unable to login: incorrect password') return - content, urlh = self._download_webpage_handle( + urlh = self._request_webpage( urlh.url, None, fatal=False, headers={'referer': urlh.url}, note='logging in with TFA', errnote='unable to log in with TFA', data=urlencode_postdata({ diff --git a/yt_dlp/extractor/twitter.py b/yt_dlp/extractor/twitter.py index 4ed48ec5ac..d056797f3c 100644 --- a/yt_dlp/extractor/twitter.py +++ b/yt_dlp/extractor/twitter.py @@ -14,6 +14,7 @@ float_or_none, format_field, int_or_none, + join_nonempty, make_archive_id, remove_end, str_or_none, @@ -107,7 +108,7 @@ def _extract_variant_formats(self, variant, video_id): tbr = int_or_none(dict_get(variant, ('bitrate', 'bit_rate')), 1000) or None f = { 'url': variant_url, - 'format_id': 'http' + (f'-{tbr}' if tbr else ''), + 'format_id': join_nonempty('http', tbr), 'tbr': tbr, } self._search_dimensions_in_video_url(f, variant_url) diff --git a/yt_dlp/extractor/viewlift.py b/yt_dlp/extractor/viewlift.py index 7ac094f2f0..4a7ba9839e 100644 --- a/yt_dlp/extractor/viewlift.py +++ b/yt_dlp/extractor/viewlift.py @@ -5,6 +5,7 @@ from ..utils import ( ExtractorError, int_or_none, + join_nonempty, parse_age_limit, traverse_obj, ) @@ -120,7 +121,7 @@ def _real_extract(self, url): 'height', default=None)) formats.append({ 'url': video_asset_url, - 'format_id': 'http{}'.format(f'-{bitrate}' if bitrate else ''), + 'format_id': join_nonempty('http', bitrate), 'tbr': bitrate, 'height': height, 'vcodec': video_asset.get('codec'), diff --git a/yt_dlp/extractor/weibo.py b/yt_dlp/extractor/weibo.py index 3e82909825..b5c0e926f8 100644 --- a/yt_dlp/extractor/weibo.py +++ b/yt_dlp/extractor/weibo.py @@ -52,6 +52,7 @@ def _update_visitor_cookies(self, visitor_url, video_id): }) def _weibo_download_json(self, url, video_id, *args, fatal=True, note='Downloading JSON metadata', **kwargs): + # XXX: Always fatal; _download_webpage_handle only returns False (not a tuple) on error webpage, urlh = self._download_webpage_handle(url, video_id, *args, fatal=fatal, note=note, **kwargs) if urllib.parse.urlparse(urlh.url).netloc == 'passport.weibo.com': self._update_visitor_cookies(urlh.url, video_id) diff --git a/yt_dlp/extractor/wsj.py b/yt_dlp/extractor/wsj.py index 7b3f6aa2ae..b6b656f7d3 100644 --- a/yt_dlp/extractor/wsj.py +++ b/yt_dlp/extractor/wsj.py @@ -2,6 +2,7 @@ from ..utils import ( float_or_none, int_or_none, + join_nonempty, unified_strdate, ) @@ -76,7 +77,7 @@ def _real_extract(self, url): tbr = int_or_none(v.get('bitrate')) formats.append({ 'url': mp4_url, - 'format_id': 'http' + (f'-{tbr}' if tbr else ''), + 'format_id': join_nonempty('http', tbr), 'tbr': tbr, 'width': int_or_none(v.get('width')), 'height': int_or_none(v.get('height')), diff --git a/yt_dlp/extractor/yahoo.py b/yt_dlp/extractor/yahoo.py index f0ba830380..35e71209c5 100644 --- a/yt_dlp/extractor/yahoo.py +++ b/yt_dlp/extractor/yahoo.py @@ -8,6 +8,7 @@ ExtractorError, clean_html, int_or_none, + join_nonempty, mimetype2ext, parse_iso8601, traverse_obj, @@ -213,7 +214,7 @@ def _extract_yahoo_video(self, video_id, country): tbr = int_or_none(s.get('bitrate')) formats.append({ 'url': s_url, - 'format_id': fmt + (f'-{tbr}' if tbr else ''), + 'format_id': join_nonempty(fmt, tbr), 'width': int_or_none(s.get('width')), 'height': int_or_none(s.get('height')), 'tbr': tbr, @@ -371,12 +372,13 @@ def _extract_formats(self, json_data, content_id): url, content_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) else: + bitrate = int_or_none(vid.get('bitrate')) formats.append({ 'url': url, - 'format_id': f'http-{vid.get("bitrate")}', + 'format_id': join_nonempty('http', bitrate), 'height': int_or_none(vid.get('height')), 'width': int_or_none(vid.get('width')), - 'tbr': int_or_none(vid.get('bitrate')), + 'tbr': bitrate, }) self._remove_duplicate_formats(formats) diff --git a/yt_dlp/extractor/yandexdisk.py b/yt_dlp/extractor/yandexdisk.py index 56aa792929..3214816701 100644 --- a/yt_dlp/extractor/yandexdisk.py +++ b/yt_dlp/extractor/yandexdisk.py @@ -5,6 +5,7 @@ determine_ext, float_or_none, int_or_none, + join_nonempty, mimetype2ext, try_get, urljoin, @@ -116,12 +117,9 @@ def call_api(action): else: size = video.get('size') or {} height = int_or_none(size.get('height')) - format_id = 'hls' - if height: - format_id += f'-{height}p' formats.append({ 'ext': 'mp4', - 'format_id': format_id, + 'format_id': join_nonempty('hls', height and f'{height}p'), 'height': height, 'protocol': 'm3u8_native', 'url': format_url, diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py index 094b1e9a36..18e0ee91c7 100644 --- a/yt_dlp/extractor/youtube.py +++ b/yt_dlp/extractor/youtube.py @@ -4,6 +4,7 @@ import copy import datetime as dt import enum +import functools import hashlib import itertools import json @@ -20,7 +21,6 @@ from .common import InfoExtractor, SearchInfoExtractor from .openload import PhantomJSwrapper -from ..compat import functools from ..jsinterp import JSInterpreter from ..networking.exceptions import HTTPError, network_exceptions from ..utils import ( diff --git a/yt_dlp/networking/_websockets.py b/yt_dlp/networking/_websockets.py index 2153080a34..15db4fe433 100644 --- a/yt_dlp/networking/_websockets.py +++ b/yt_dlp/networking/_websockets.py @@ -1,6 +1,7 @@ from __future__ import annotations import contextlib +import functools import io import logging import ssl @@ -22,7 +23,6 @@ TransportError, ) from .websocket import WebSocketRequestHandler, WebSocketResponse -from ..compat import functools from ..dependencies import websockets from ..socks import ProxyError as SocksProxyError from ..utils import int_or_none diff --git a/yt_dlp/options.py b/yt_dlp/options.py index 3d4c076610..b97c516ceb 100644 --- a/yt_dlp/options.py +++ b/yt_dlp/options.py @@ -646,7 +646,7 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs): 'You can also simply specify a field to match if the field is present, ' 'use "!field" to check if the field is not present, and "&" to check multiple conditions. ' 'Use a "\\" to escape "&" or quotes if needed. If used multiple times, ' - 'the filter matches if atleast one of the conditions are met. E.g. --match-filter ' + 'the filter matches if at least one of the conditions is met. E.g. --match-filter ' '!is_live --match-filter "like_count>?100 & description~=\'(?i)\\bcats \\& dogs\\b\'" ' 'matches only videos that are not live OR those that have a like count more than 100 ' '(or the like field is not available) and also has a description ' @@ -1479,7 +1479,7 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs): 'Optionally, the KEYRING used for decrypting Chromium cookies on Linux, ' 'the name/path of the PROFILE to load cookies from, ' 'and the CONTAINER name (if Firefox) ("none" for no container) ' - 'can be given with their respective seperators. ' + 'can be given with their respective separators. ' 'By default, all containers of the most recently accessed profile are used. ' f'Currently supported keyrings are: {", ".join(map(str.lower, sorted(SUPPORTED_KEYRINGS)))}')) filesystem.add_option( @@ -1781,7 +1781,7 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs): 'It can be one of "pre_process" (after video extraction), "after_filter" (after video passes filter), ' '"video" (after --format; before --print/--output), "before_dl" (before each video download), ' '"post_process" (after each video download; default), ' - '"after_move" (after moving video file to it\'s final locations), ' + '"after_move" (after moving video file to its final locations), ' '"after_video" (after downloading and processing all formats of a video), ' 'or "playlist" (at end of playlist). ' 'This option can be used multiple times to add different postprocessors')) diff --git a/yt_dlp/postprocessor/ffmpeg.py b/yt_dlp/postprocessor/ffmpeg.py index 1ed37af518..164c46d143 100644 --- a/yt_dlp/postprocessor/ffmpeg.py +++ b/yt_dlp/postprocessor/ffmpeg.py @@ -1,5 +1,6 @@ import collections import contextvars +import functools import itertools import json import os @@ -8,7 +9,7 @@ import time from .common import PostProcessor -from ..compat import functools, imghdr +from ..compat import imghdr from ..utils import ( MEDIA_EXTENSIONS, ISO639Utils,