From c9ce9962499e22a1e776806d0bb1acc24b1ca434 Mon Sep 17 00:00:00 2001 From: Samive Date: Wed, 1 Apr 2026 10:32:02 +0800 Subject: [PATCH] initial commit --- .dockerignore | 14 + .gitignore | 4 + Dockerfile | 19 + README.md | 2533 +---------------- test/__init__.py | 0 test/conftest.py | 94 - test/helper.py | 384 --- test/parameters.json | 48 - test/test_InfoExtractor.py | 2168 -------------- test/test_YoutubeDL.py | 1367 --------- test/test_YoutubeDLCookieJar.py | 66 - test/test_aes.py | 163 -- test/test_age_restriction.py | 55 - test/test_all_urls.py | 122 - test/test_cache.py | 57 - test/test_compat.py | 104 - test/test_config.py | 227 -- test/test_cookies.py | 357 --- test/test_devalue.py | 239 -- test/test_download.py | 309 -- test/test_downloader_external.py | 139 - test/test_downloader_http.py | 105 - test/test_execution.py | 60 - test/test_http_proxy.py | 378 --- test/test_jsc/conftest.py | 60 - test/test_jsc/test_ejs_integration.py | 153 - test/test_jsc/test_provider.py | 194 -- test/test_jsinterp.py | 576 ---- test/test_netrc.py | 28 - test/test_networking.py | 2220 --------------- test/test_networking_utils.py | 207 -- test/test_overwrites.py | 54 - test/test_plugins.py | 246 -- test/test_post_hooks.py | 70 - test/test_postprocessors.py | 636 ----- test/test_pot/conftest.py | 71 - test/test_pot/test_pot_builtin_memorycache.py | 117 - test/test_pot/test_pot_builtin_utils.py | 52 - test/test_pot/test_pot_builtin_webpospec.py | 92 - test/test_pot/test_pot_director.py | 1529 ---------- test/test_pot/test_pot_framework.py | 639 ----- test/test_socks.py | 476 ---- test/test_subtitles.py | 418 --- test/test_traversal.py | 638 ----- test/test_update.py | 305 -- test/test_utils.py | 2248 --------------- test/test_verbose_output.py | 75 - test/test_websockets.py | 517 ---- test/test_youtube_lists.py | 71 - test/test_youtube_misc.py | 26 - test/testcert.pem | 52 - test/testdata/certificate/ca.crt | 10 - test/testdata/certificate/ca.key | 5 - test/testdata/certificate/ca.srl | 1 - test/testdata/certificate/client.crt | 9 - test/testdata/certificate/client.csr | 7 - test/testdata/certificate/client.key | 5 - test/testdata/certificate/clientencrypted.key | 8 - .../certificate/clientwithencryptedkey.crt | 17 - test/testdata/certificate/clientwithkey.crt | 14 - test/testdata/certificate/instructions.md | 19 - test/testdata/cookies/httponly_cookies.txt | 6 - test/testdata/cookies/malformed_cookies.txt | 9 - test/testdata/cookies/session_cookies.txt | 6 - test/testdata/f4m/custom_base_url.f4m | 10 - test/testdata/ism/ec-3_test.Manifest | 1 - test/testdata/ism/sintel.Manifest | 988 ------- test/testdata/m3u8/bipbop_16x9.m3u8 | 38 - .../m3u8/img_bipbop_adv_example_fmp4.m3u8 | 76 - test/testdata/mpd/float_duration.mpd | 18 - test/testdata/mpd/subtitles.mpd | 351 --- test/testdata/mpd/unfragmented.mpd | 28 - test/testdata/mpd/urls_only.mpd | 218 -- test/testdata/netrc/netrc | 4 - test/testdata/netrc/print_netrc.py | 2 - .../yt_dlp_plugins/extractor/package.py | 6 - .../yt_dlp_plugins/extractor/normal.py | 10 - .../yt_dlp_plugins/postprocessor/normal.py | 5 - .../thumbnails/foo %d bar/placeholder | 0 test/testdata/xspf/foo_xspf.xspf | 34 - .../yt_dlp_plugins/extractor/_ignore.py | 5 - .../yt_dlp_plugins/extractor/ignore.py | 13 - .../yt_dlp_plugins/extractor/normal.py | 11 - .../yt_dlp_plugins/extractor/override.py | 5 - .../yt_dlp_plugins/extractor/overridetwo.py | 5 - .../yt_dlp_plugins/postprocessor/normal.py | 5 - .../yt_dlp_plugins/extractor/zipped.py | 6 - .../yt_dlp_plugins/postprocessor/zipped.py | 5 - web/.dockerignore | 8 + web/README.md | 24 + web/backend/main.py | 288 ++ web/backend/requirements.txt | 3 + web/frontend/app.js | 309 ++ web/frontend/index.html | 135 + web/frontend/style.css | 380 +++ 95 files changed, 1291 insertions(+), 22598 deletions(-) create mode 100644 .dockerignore create mode 100644 Dockerfile delete mode 100644 test/__init__.py delete mode 100644 test/conftest.py delete mode 100644 test/helper.py delete mode 100644 test/parameters.json delete mode 100644 test/test_InfoExtractor.py delete mode 100644 test/test_YoutubeDL.py delete mode 100644 test/test_YoutubeDLCookieJar.py delete mode 100644 test/test_aes.py delete mode 100644 test/test_age_restriction.py delete mode 100644 test/test_all_urls.py delete mode 100644 test/test_cache.py delete mode 100644 test/test_compat.py delete mode 100644 test/test_config.py delete mode 100644 test/test_cookies.py delete mode 100644 test/test_devalue.py delete mode 100755 test/test_download.py delete mode 100644 test/test_downloader_external.py delete mode 100644 test/test_downloader_http.py delete mode 100644 test/test_execution.py delete mode 100644 test/test_http_proxy.py delete mode 100644 test/test_jsc/conftest.py delete mode 100644 test/test_jsc/test_ejs_integration.py delete mode 100644 test/test_jsc/test_provider.py delete mode 100644 test/test_jsinterp.py delete mode 100644 test/test_netrc.py delete mode 100644 test/test_networking.py delete mode 100644 test/test_networking_utils.py delete mode 100644 test/test_overwrites.py delete mode 100644 test/test_plugins.py delete mode 100644 test/test_post_hooks.py delete mode 100644 test/test_postprocessors.py delete mode 100644 test/test_pot/conftest.py delete mode 100644 test/test_pot/test_pot_builtin_memorycache.py delete mode 100644 test/test_pot/test_pot_builtin_utils.py delete mode 100644 test/test_pot/test_pot_builtin_webpospec.py delete mode 100644 test/test_pot/test_pot_director.py delete mode 100644 test/test_pot/test_pot_framework.py delete mode 100644 test/test_socks.py delete mode 100644 test/test_subtitles.py delete mode 100644 test/test_traversal.py delete mode 100644 test/test_update.py delete mode 100644 test/test_utils.py delete mode 100644 test/test_verbose_output.py delete mode 100644 test/test_websockets.py delete mode 100644 test/test_youtube_lists.py delete mode 100644 test/test_youtube_misc.py delete mode 100644 test/testcert.pem delete mode 100644 test/testdata/certificate/ca.crt delete mode 100644 test/testdata/certificate/ca.key delete mode 100644 test/testdata/certificate/ca.srl delete mode 100644 test/testdata/certificate/client.crt delete mode 100644 test/testdata/certificate/client.csr delete mode 100644 test/testdata/certificate/client.key delete mode 100644 test/testdata/certificate/clientencrypted.key delete mode 100644 test/testdata/certificate/clientwithencryptedkey.crt delete mode 100644 test/testdata/certificate/clientwithkey.crt delete mode 100644 test/testdata/certificate/instructions.md delete mode 100644 test/testdata/cookies/httponly_cookies.txt delete mode 100644 test/testdata/cookies/malformed_cookies.txt delete mode 100644 test/testdata/cookies/session_cookies.txt delete mode 100644 test/testdata/f4m/custom_base_url.f4m delete mode 100644 test/testdata/ism/ec-3_test.Manifest delete mode 100644 test/testdata/ism/sintel.Manifest delete mode 100644 test/testdata/m3u8/bipbop_16x9.m3u8 delete mode 100644 test/testdata/m3u8/img_bipbop_adv_example_fmp4.m3u8 delete mode 100644 test/testdata/mpd/float_duration.mpd delete mode 100644 test/testdata/mpd/subtitles.mpd delete mode 100644 test/testdata/mpd/unfragmented.mpd delete mode 100644 test/testdata/mpd/urls_only.mpd delete mode 100644 test/testdata/netrc/netrc delete mode 100644 test/testdata/netrc/print_netrc.py delete mode 100644 test/testdata/plugin_packages/testpackage/yt_dlp_plugins/extractor/package.py delete mode 100644 test/testdata/reload_plugins/yt_dlp_plugins/extractor/normal.py delete mode 100644 test/testdata/reload_plugins/yt_dlp_plugins/postprocessor/normal.py delete mode 100644 test/testdata/thumbnails/foo %d bar/placeholder delete mode 100644 test/testdata/xspf/foo_xspf.xspf delete mode 100644 test/testdata/yt_dlp_plugins/extractor/_ignore.py delete mode 100644 test/testdata/yt_dlp_plugins/extractor/ignore.py delete mode 100644 test/testdata/yt_dlp_plugins/extractor/normal.py delete mode 100644 test/testdata/yt_dlp_plugins/extractor/override.py delete mode 100644 test/testdata/yt_dlp_plugins/extractor/overridetwo.py delete mode 100644 test/testdata/yt_dlp_plugins/postprocessor/normal.py delete mode 100644 test/testdata/zipped_plugins/yt_dlp_plugins/extractor/zipped.py delete mode 100644 test/testdata/zipped_plugins/yt_dlp_plugins/postprocessor/zipped.py create mode 100644 web/.dockerignore create mode 100644 web/README.md create mode 100644 web/backend/main.py create mode 100644 web/backend/requirements.txt create mode 100644 web/frontend/app.js create mode 100644 web/frontend/index.html create mode 100644 web/frontend/style.css diff --git a/.dockerignore b/.dockerignore new file mode 100644 index 000000000..de223390c --- /dev/null +++ b/.dockerignore @@ -0,0 +1,14 @@ +web/backend/downloads/ +web/backend/cookies.txt +web/.dockerignore +.venv/ +.git/ +__pycache__/ +*.pyc +*.pyo +*.egg-info/ +test/ +bundle/ +devscripts/ +*.md +!README.md diff --git a/.gitignore b/.gitignore index afc9dc9c9..0faf54aba 100644 --- a/.gitignore +++ b/.gitignore @@ -134,3 +134,7 @@ yt-dlp-plugins # Packages yt_dlp_ejs/ + +# yt-dlp web UI +web/backend/cookies.txt +web/backend/downloads/ diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 000000000..f95a93a2c --- /dev/null +++ b/Dockerfile @@ -0,0 +1,19 @@ +FROM python:3.12-slim + +# Install ffmpeg for merging video+audio streams +RUN apt-get update && apt-get install -y --no-install-recommends ffmpeg && rm -rf /var/lib/apt/lists/* + +WORKDIR /app + +# Install Python dependencies +RUN pip install --no-cache-dir yt-dlp fastapi "uvicorn[standard]" httpx + +# Copy web app +COPY web/backend ./web/backend +COPY web/frontend ./web/frontend + +RUN mkdir -p /app/web/backend/downloads + +EXPOSE 8000 + +CMD ["python", "-m", "uvicorn", "web.backend.main:app", "--host", "0.0.0.0", "--port", "8000"] diff --git a/README.md b/README.md index 915f40a38..d2b1fbcda 100644 --- a/README.md +++ b/README.md @@ -1,2493 +1,174 @@ - -
+# yt-dlp Web UI -[![YT-DLP](https://raw.githubusercontent.com/yt-dlp/yt-dlp/master/.github/banner.svg)](#readme) +A beautiful, self-hosted web application for downloading YouTube (and 1000+ other sites) videos — powered by [yt-dlp](https://github.com/yt-dlp/yt-dlp). -[![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)](Maintainers.md#maintainers "Donate") -[![Discord](https://img.shields.io/discord/807245652072857610?color=blue&labelColor=555555&label=&logo=discord&style=for-the-badge)](https://discord.gg/H5MNcFW63r "Discord") -[![Supported Sites](https://img.shields.io/badge/-Supported_Sites-brightgreen.svg?style=for-the-badge)](supportedsites.md "Supported Sites") -[![License: Unlicense](https://img.shields.io/badge/-Unlicense-blue.svg?style=for-the-badge)](LICENSE "License") -[![CI Status](https://img.shields.io/github/actions/workflow/status/yt-dlp/yt-dlp/core.yml?branch=master&label=Tests&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/actions "CI Status") -[![Commits](https://img.shields.io/github/commit-activity/m/yt-dlp/yt-dlp?label=commits&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/commits "Commit History") -[![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master?label=&style=for-the-badge&display_timestamp=committer)](https://github.com/yt-dlp/yt-dlp/pulse/monthly "Last activity") +![yt-dlp Web UI](https://img.shields.io/badge/yt--dlp-web%20ui-6366f1?style=flat-square) +![Docker](https://img.shields.io/badge/docker-ready-2496ED?style=flat-square&logo=docker) +![Python](https://img.shields.io/badge/python-3.12-3776AB?style=flat-square&logo=python) -
- +--- -yt-dlp is a feature-rich command-line audio/video downloader with support for [thousands of sites](supportedsites.md). The project is a fork of [youtube-dl](https://github.com/ytdl-org/youtube-dl) based on the now inactive [youtube-dlc](https://github.com/blackjack4494/yt-dlc). +## Features - +- Paste any YouTube (or supported site) URL and fetch video info instantly +- View thumbnail, title, uploader, duration, views, likes, and upload date +- Select from all available formats grouped by quality (Video+Audio, Video only, Audio only) +- Highest quality format pre-selected automatically +- Live download progress with percentage, speed, and ETA +- Cancel download at any time +- Clean dark UI with animated progress bar - -* [INSTALLATION](#installation) - * [Detailed instructions](https://github.com/yt-dlp/yt-dlp/wiki/Installation) - * [Release Files](#release-files) - * [Update](#update) - * [Dependencies](#dependencies) - * [Compile](#compile) -* [USAGE AND OPTIONS](#usage-and-options) - * [General Options](#general-options) - * [Network Options](#network-options) - * [Geo-restriction](#geo-restriction) - * [Video Selection](#video-selection) - * [Download Options](#download-options) - * [Filesystem Options](#filesystem-options) - * [Thumbnail Options](#thumbnail-options) - * [Internet Shortcut Options](#internet-shortcut-options) - * [Verbosity and Simulation Options](#verbosity-and-simulation-options) - * [Workarounds](#workarounds) - * [Video Format Options](#video-format-options) - * [Subtitle Options](#subtitle-options) - * [Authentication Options](#authentication-options) - * [Post-processing Options](#post-processing-options) - * [SponsorBlock Options](#sponsorblock-options) - * [Extractor Options](#extractor-options) - * [Preset Aliases](#preset-aliases) -* [CONFIGURATION](#configuration) - * [Configuration file encoding](#configuration-file-encoding) - * [Authentication with netrc](#authentication-with-netrc) - * [Notes about environment variables](#notes-about-environment-variables) -* [OUTPUT TEMPLATE](#output-template) - * [Output template examples](#output-template-examples) -* [FORMAT SELECTION](#format-selection) - * [Filtering Formats](#filtering-formats) - * [Sorting Formats](#sorting-formats) - * [Format Selection examples](#format-selection-examples) -* [MODIFYING METADATA](#modifying-metadata) - * [Modifying metadata examples](#modifying-metadata-examples) -* [EXTRACTOR ARGUMENTS](#extractor-arguments) -* [PLUGINS](#plugins) - * [Installing Plugins](#installing-plugins) - * [Developing Plugins](#developing-plugins) -* [EMBEDDING YT-DLP](#embedding-yt-dlp) - * [Embedding examples](#embedding-examples) -* [CHANGES FROM YOUTUBE-DL](#changes-from-youtube-dl) - * [New features](#new-features) - * [Differences in default behavior](#differences-in-default-behavior) - * [Deprecated options](#deprecated-options) -* [CONTRIBUTING](CONTRIBUTING.md#contributing-to-yt-dlp) - * [Opening an Issue](CONTRIBUTING.md#opening-an-issue) - * [Developer Instructions](CONTRIBUTING.md#developer-instructions) -* [WIKI](https://github.com/yt-dlp/yt-dlp/wiki) - * [FAQ](https://github.com/yt-dlp/yt-dlp/wiki/FAQ) - +--- +## Quick Start with Docker -# INSTALLATION - - -[![Windows](https://img.shields.io/badge/-Windows_x64-blue.svg?style=for-the-badge&logo=windows)](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp.exe) -[![Unix](https://img.shields.io/badge/-Linux/BSD-red.svg?style=for-the-badge&logo=linux)](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp) -[![MacOS](https://img.shields.io/badge/-MacOS-lightblue.svg?style=for-the-badge&logo=apple)](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos) -[![PyPI](https://img.shields.io/badge/-PyPI-blue.svg?logo=pypi&labelColor=555555&style=for-the-badge)](https://pypi.org/project/yt-dlp) -[![Source Tarball](https://img.shields.io/badge/-Source_tar-green.svg?style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp.tar.gz) -[![Other variants](https://img.shields.io/badge/-Other-grey.svg?style=for-the-badge)](#release-files) -[![All versions](https://img.shields.io/badge/-All_Versions-lightgrey.svg?style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/releases) - - -You can install yt-dlp using [the binaries](#release-files), [pip](https://pypi.org/project/yt-dlp) or one using a third-party package manager. See [the wiki](https://github.com/yt-dlp/yt-dlp/wiki/Installation) for detailed instructions - - - -## RELEASE FILES - -#### Recommended - -File|Description -:---|:--- -[yt-dlp](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp)|Platform-independent [zipimport](https://docs.python.org/3/library/zipimport.html) binary. Needs Python (recommended for **Linux/BSD**) -[yt-dlp.exe](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp.exe)|Windows (Win8+) standalone x64 binary (recommended for **Windows**) -[yt-dlp_macos](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos)|Universal MacOS (10.15+) standalone executable (recommended for **MacOS**) - -#### Alternatives - -File|Description -:---|:--- -[yt-dlp_linux](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux)|Linux (glibc 2.17+) standalone x86_64 binary -[yt-dlp_linux.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux.zip)|Unpackaged Linux (glibc 2.17+) x86_64 executable (no auto-update) -[yt-dlp_linux_aarch64](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux_aarch64)|Linux (glibc 2.17+) standalone aarch64 binary -[yt-dlp_linux_aarch64.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux_aarch64.zip)|Unpackaged Linux (glibc 2.17+) aarch64 executable (no auto-update) -[yt-dlp_linux_armv7l.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux_armv7l.zip)|Unpackaged Linux (glibc 2.31+) armv7l executable (no auto-update) -[yt-dlp_musllinux](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_musllinux)|Linux (musl 1.2+) standalone x86_64 binary -[yt-dlp_musllinux.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_musllinux.zip)|Unpackaged Linux (musl 1.2+) x86_64 executable (no auto-update) -[yt-dlp_musllinux_aarch64](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_musllinux_aarch64)|Linux (musl 1.2+) standalone aarch64 binary -[yt-dlp_musllinux_aarch64.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_musllinux_aarch64.zip)|Unpackaged Linux (musl 1.2+) aarch64 executable (no auto-update) -[yt-dlp_x86.exe](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_x86.exe)|Windows (Win8+) standalone x86 (32-bit) binary -[yt-dlp_win_x86.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_win_x86.zip)|Unpackaged Windows (Win8+) x86 (32-bit) executable (no auto-update) -[yt-dlp_arm64.exe](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_arm64.exe)|Windows (Win10+) standalone ARM64 binary -[yt-dlp_win_arm64.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_win_arm64.zip)|Unpackaged Windows (Win10+) ARM64 executable (no auto-update) -[yt-dlp_win.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_win.zip)|Unpackaged Windows (Win8+) x64 executable (no auto-update) -[yt-dlp_macos.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos.zip)|Unpackaged MacOS (10.15+) executable (no auto-update) - -#### Misc - -File|Description -:---|:--- -[yt-dlp.tar.gz](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp.tar.gz)|Source tarball -[SHA2-512SUMS](https://github.com/yt-dlp/yt-dlp/releases/latest/download/SHA2-512SUMS)|GNU-style SHA512 sums -[SHA2-512SUMS.sig](https://github.com/yt-dlp/yt-dlp/releases/latest/download/SHA2-512SUMS.sig)|GPG signature file for SHA512 sums -[SHA2-256SUMS](https://github.com/yt-dlp/yt-dlp/releases/latest/download/SHA2-256SUMS)|GNU-style SHA256 sums -[SHA2-256SUMS.sig](https://github.com/yt-dlp/yt-dlp/releases/latest/download/SHA2-256SUMS.sig)|GPG signature file for SHA256 sums - -The public key that can be used to verify the GPG signatures is [available here](https://github.com/yt-dlp/yt-dlp/blob/master/public.key) -Example usage: -``` -curl -L https://github.com/yt-dlp/yt-dlp/raw/master/public.key | gpg --import -gpg --verify SHA2-256SUMS.sig SHA2-256SUMS -gpg --verify SHA2-512SUMS.sig SHA2-512SUMS -``` - -#### Licensing - -While yt-dlp is licensed under the [Unlicense](LICENSE), many of the release files contain code from other projects with different licenses. - -Most notably, the PyInstaller-bundled executables include GPLv3+ licensed code, and as such the combined work is licensed under [GPLv3+](https://www.gnu.org/licenses/gpl-3.0.html). - -The zipimport Unix executable (`yt-dlp`) contains [ISC](https://github.com/meriyah/meriyah/blob/main/LICENSE.md) licensed code from [`meriyah`](https://github.com/meriyah/meriyah) and [MIT](https://github.com/davidbonnet/astring/blob/main/LICENSE) licensed code from [`astring`](https://github.com/davidbonnet/astring). - -See [THIRD_PARTY_LICENSES.txt](THIRD_PARTY_LICENSES.txt) for more details. - -The git repository, the source tarball (`yt-dlp.tar.gz`), the PyPI source distribution and the PyPI built distribution (wheel) only contain code licensed under the [Unlicense](LICENSE). - - - -**Note**: The manpages, shell completion (autocomplete) files etc. are available inside the [source tarball](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp.tar.gz) - - -## UPDATE -You can use `yt-dlp -U` to update if you are using the [release binaries](#release-files) - -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 to their documentation - - - -There are currently three release channels for binaries: `stable`, `nightly` and `master`. - -* `stable` is the default channel, and many of its changes have been tested by users of the `nightly` and `master` channels. -* The `nightly` channel has releases scheduled to build every day around midnight UTC, for a snapshot of the project's new patches and changes. This is the **recommended channel for regular users** of yt-dlp. The `nightly` releases are available from [yt-dlp/yt-dlp-nightly-builds](https://github.com/yt-dlp/yt-dlp-nightly-builds/releases) or as development releases of the `yt-dlp` PyPI package (which can be installed with pip's `--pre` flag). -* The `master` channel features releases that are built after each push to the master branch, and these will have the very latest fixes and additions, but may also be more prone to regressions. They are available from [yt-dlp/yt-dlp-master-builds](https://github.com/yt-dlp/yt-dlp-master-builds/releases). - -When using `--update`/`-U`, a release binary will only update to its current channel. -`--update-to CHANNEL` can be used to switch to a different channel when a newer version is available. `--update-to [CHANNEL@]TAG` can also be used to upgrade or downgrade to specific tags from a channel. - -You may also use `--update-to ` (`/`) to update to a channel on a completely different repository. Be careful with what repository you are updating to though, there is no verification done for binaries from different repositories. - -Example usage: - -* `yt-dlp --update-to master` switch to the `master` channel and update to its latest release -* `yt-dlp --update-to stable@2023.07.06` upgrade/downgrade to release to `stable` channel tag `2023.07.06` -* `yt-dlp --update-to 2023.10.07` upgrade/downgrade to tag `2023.10.07` if it exists on the current channel -* `yt-dlp --update-to example/yt-dlp@2023.09.24` upgrade/downgrade to the release from the `example/yt-dlp` repository, tag `2023.09.24` - -**Important**: Any user experiencing an issue with the `stable` release should install or update to the `nightly` release before submitting a bug report: -``` -# To update to nightly from stable executable/binary: -yt-dlp --update-to nightly - -# To install nightly with pip: -python -m pip install -U --pre "yt-dlp[default]" -``` - -When running a yt-dlp version that is older than 90 days, you will see a warning message suggesting to update to the latest version. -You can suppress this warning by adding `--no-update` to your command or configuration file. - -## DEPENDENCIES -Python versions 3.10+ (CPython) and 3.11+ (PyPy) are supported. Other versions and implementations may or may not work correctly. - - - -While all the other dependencies are optional, `ffmpeg`, `ffprobe`, `yt-dlp-ejs` and a supported JavaScript runtime/engine are highly recommended - -### 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) - - 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) - -* [**yt-dlp-ejs**](https://github.com/yt-dlp/ejs) - Required for full YouTube support. Licensed under [Unlicense](https://github.com/yt-dlp/ejs/blob/main/LICENSE), bundles [MIT](https://github.com/davidbonnet/astring/blob/main/LICENSE) and [ISC](https://github.com/meriyah/meriyah/blob/main/LICENSE.md) components. - - A JavaScript runtime/engine like [**deno**](https://deno.land) (recommended), [**node.js**](https://nodejs.org), [**bun**](https://bun.sh), or [**QuickJS**](https://bellard.org/quickjs/) is also required to run yt-dlp-ejs. See [the wiki](https://github.com/yt-dlp/yt-dlp/wiki/EJS). - -### Networking -* [**certifi**](https://github.com/certifi/python-certifi)\* - Provides Mozilla's root certificate bundle. Licensed under [MPLv2](https://github.com/certifi/python-certifi/blob/master/LICENSE) -* [**brotli**](https://github.com/google/brotli)\* or [**brotlicffi**](https://github.com/python-hyper/brotlicffi) - [Brotli](https://en.wikipedia.org/wiki/Brotli) content encoding support. Both licensed under MIT [1](https://github.com/google/brotli/blob/master/LICENSE) [2](https://github.com/python-hyper/brotlicffi/blob/master/LICENSE) -* [**websockets**](https://github.com/aaugustin/websockets)\* - For downloading over websocket. Licensed under [BSD-3-Clause](https://github.com/aaugustin/websockets/blob/main/LICENSE) -* [**requests**](https://github.com/psf/requests)\* - HTTP library. For HTTPS proxy and persistent connections support. Licensed under [Apache-2.0](https://github.com/psf/requests/blob/main/LICENSE) - -#### Impersonation - -The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting. - -* [**curl_cffi**](https://github.com/lexiforest/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lexiforest/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/lexiforest/curl_cffi/blob/main/LICENSE) - * Can be installed with the `curl-cffi` extra, e.g. `pip install "yt-dlp[default,curl-cffi]"` - * Currently included in most builds *except* `yt-dlp` (Unix zipimport binary), `yt-dlp_x86` (Windows 32-bit) and `yt-dlp_musllinux_aarch64` - - -### Metadata - -* [**mutagen**](https://github.com/quodlibet/mutagen)\* - For `--embed-thumbnail` in certain formats. Licensed under [GPLv2+](https://github.com/quodlibet/mutagen/blob/master/COPYING) -* [**AtomicParsley**](https://github.com/wez/atomicparsley) - For `--embed-thumbnail` in `mp4`/`m4a` files when `mutagen`/`ffmpeg` cannot. Licensed under [GPLv2+](https://github.com/wez/atomicparsley/blob/master/COPYING) -* [**xattr**](https://github.com/xattr/xattr), [**pyxattr**](https://github.com/iustin/pyxattr) or [**setfattr**](http://savannah.nongnu.org/projects/attr) - For writing xattr metadata (`--xattrs`) on **Mac** and **BSD**. Licensed under [MIT](https://github.com/xattr/xattr/blob/master/LICENSE.txt), [LGPL2.1](https://github.com/iustin/pyxattr/blob/master/COPYING) and [GPLv2+](http://git.savannah.nongnu.org/cgit/attr.git/tree/doc/COPYING) respectively - -### Misc - -* [**pycryptodomex**](https://github.com/Legrandin/pycryptodome)\* - For decrypting AES-128 HLS streams and various other data. Licensed under [BSD-2-Clause](https://github.com/Legrandin/pycryptodome/blob/master/LICENSE.rst) -* [**phantomjs**](https://github.com/ariya/phantomjs) - Used in some extractors where JavaScript needs to be run. No longer used for YouTube. To be deprecated in the near future. Licensed under [BSD-3-Clause](https://github.com/ariya/phantomjs/blob/master/LICENSE.BSD) -* [**secretstorage**](https://github.com/mitya57/secretstorage)\* - For `--cookies-from-browser` to access the **Gnome** keyring while decrypting cookies of **Chromium**-based browsers on **Linux**. Licensed under [BSD-3-Clause](https://github.com/mitya57/secretstorage/blob/master/LICENSE) -* Any external downloader that you want to use with `--downloader` - -### Deprecated - -* [**rtmpdump**](http://rtmpdump.mplayerhq.hu) - For downloading `rtmp` streams. ffmpeg can be used instead with `--downloader ffmpeg`. Licensed under [GPLv2+](http://rtmpdump.mplayerhq.hu) -* [**mplayer**](http://mplayerhq.hu/design7/info.html) or [**mpv**](https://mpv.io) - For downloading `rstp`/`mms` streams. ffmpeg can be used instead with `--downloader ffmpeg`. Licensed under [GPLv2+](https://github.com/mpv-player/mpv/blob/master/Copyright) - -To use or redistribute the dependencies, you must agree to their respective licensing terms. - -The standalone release binaries are built with the Python interpreter and the packages marked with **\*** included. - -If you do not have the necessary dependencies for a task you are attempting, yt-dlp will warn you. All the currently available dependencies are visible at the top of the `--verbose` output - - -## COMPILE - -### Standalone PyInstaller Builds -To build the standalone executable, you must have Python and `pyinstaller` (plus any of yt-dlp's [optional dependencies](#dependencies) if needed). The executable will be built for the same CPU architecture as the Python used. - -You can run the following commands: - -``` -python devscripts/install_deps.py --include-group pyinstaller -python devscripts/make_lazy_extractors.py -python -m bundle.pyinstaller -``` - -On some systems, you may need to use `py` or `python3` instead of `python`. - -`python -m bundle.pyinstaller` accepts any arguments that can be passed to `pyinstaller`, such as `--onefile/-F` or `--onedir/-D`, which is further [documented here](https://pyinstaller.org/en/stable/usage.html#what-to-generate). - -**Note**: Pyinstaller versions below 4.4 [do not support](https://github.com/pyinstaller/pyinstaller#requirements-and-tested-platforms) Python installed from the Windows store without using a virtual environment. - -**Important**: Running `pyinstaller` directly **instead of** using `python -m bundle.pyinstaller` is **not** officially supported. This may or may not work correctly. - -### Platform-independent Binary (UNIX) -You will need the build tools `python` (3.10+), `zip`, `make` (GNU), `pandoc`\* and `pytest`\*. - -After installing these, simply run `make`. - -You can also run `make yt-dlp` instead to compile only the binary without updating any of the additional files. (The build tools marked with **\*** are not needed for this) - -### Related scripts - -* **`devscripts/install_deps.py`** - Install dependencies for yt-dlp. -* **`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` to something nonempty to forcefully disable lazy extractor loading. - -Note: See their `--help` for more info. - -### Forking the project -If you fork the project on GitHub, you can run your fork's [build workflow](.github/workflows/build.yml) to automatically build the selected version(s) as artifacts. Alternatively, you can run the [release workflow](.github/workflows/release.yml) or enable the [nightly workflow](.github/workflows/release-nightly.yml) to create full (pre-)releases. - -# USAGE AND OPTIONS - - - yt-dlp [OPTIONS] [--] URL [URL...] - -Tip: Use `CTRL`+`F` (or `Command`+`F`) to search by keywords - - - -## General Options: - -h, --help Print this help text and exit - --version Print program version and exit - -U, --update Update this program to the latest version - --no-update Do not check for updates (default) - --update-to [CHANNEL]@[TAG] Upgrade/downgrade to a specific version. - CHANNEL can be a repository as well. CHANNEL - and TAG default to "stable" and "latest" - respectively if omitted; See "UPDATE" for - details. Supported channels: stable, - nightly, master - -i, --ignore-errors Ignore download and postprocessing errors. - The download will be considered successful - even if the postprocessing fails - --no-abort-on-error Continue with next video on download errors; - e.g. to skip unavailable videos in a - playlist (default) - --abort-on-error Abort downloading of further videos if an - error occurs (Alias: --no-ignore-errors) - --list-extractors List all supported extractors and exit - --extractor-descriptions Output descriptions of all supported - extractors and exit - --use-extractors NAMES Extractor names to use separated by commas. - You can also use regexes, "all", "default" - and "end" (end URL matching); e.g. --ies - "holodex.*,end,youtube". Prefix the name - with a "-" to exclude it, e.g. --ies - default,-generic. Use --list-extractors for - a list of extractor names. (Alias: --ies) - --default-search PREFIX Use this prefix for unqualified URLs. E.g. - "gvsearch2:python" downloads two videos from - google videos for the search term "python". - Use the value "auto" to let yt-dlp guess - ("auto_warning" to emit a warning when - guessing). "error" just throws an error. The - default value "fixup_error" repairs broken - URLs, but emits an error if this is not - possible instead of searching - --ignore-config Don't load any more configuration files - except those given to --config-locations. - For backward compatibility, if this option - is found inside the system configuration - file, the user configuration is not loaded. - (Alias: --no-config) - --no-config-locations Do not load any custom configuration files - (default). When given inside a configuration - file, ignore all previous --config-locations - defined in the current file - --config-locations PATH Location of the main configuration file; - either the path to the config or its - containing directory ("-" for stdin). Can be - used multiple times and inside other - configuration files - --plugin-dirs DIR Path to an additional directory to search - for plugins. This option can be used - multiple times to add multiple directories. - Use "default" to search the default plugin - directories (default) - --no-plugin-dirs Clear plugin directories to search, - including defaults and those provided by - previous --plugin-dirs - --js-runtimes RUNTIME[:PATH] Additional JavaScript runtime to enable, - with an optional location for the runtime - (either the path to the binary or its - containing directory). This option can be - used multiple times to enable multiple - runtimes. Supported runtimes are (in order - of priority, from highest to lowest): deno, - node, quickjs, bun. Only "deno" is enabled - by default. The highest priority runtime - that is both enabled and available will be - used. In order to use a lower priority - runtime when "deno" is available, --no-js- - runtimes needs to be passed before enabling - other runtimes - --no-js-runtimes Clear JavaScript runtimes to enable, - including defaults and those provided by - previous --js-runtimes - --remote-components COMPONENT Remote components to allow yt-dlp to fetch - when required. This option is currently not - needed if you are using an official - executable or have the requisite version of - the yt-dlp-ejs package installed. You can - use this option multiple times to allow - multiple components. Supported values: - ejs:npm (external JavaScript components from - npm), ejs:github (external JavaScript - components from yt-dlp-ejs GitHub). By - default, no remote components are allowed - --no-remote-components Disallow fetching of all remote components, - including any previously allowed by - --remote-components or defaults. - --flat-playlist Do not extract a playlist's URL result - entries; some entry metadata may be missing - and downloading may be bypassed - --no-flat-playlist Fully extract the videos of a playlist - (default) - --live-from-start Download livestreams from the start. - Currently experimental and only supported - for YouTube, Twitch, and TVer - --no-live-from-start Download livestreams from the current time - (default) - --wait-for-video MIN[-MAX] Wait for scheduled streams to become - available. Pass the minimum number of - seconds (or range) to wait between retries - --no-wait-for-video Do not wait for scheduled streams (default) - --mark-watched Mark videos watched (even with --simulate) - --no-mark-watched Do not mark videos watched (default) - --color [STREAM:]POLICY Whether to emit color codes in output, - optionally prefixed by the STREAM (stdout or - stderr) to apply the setting to. Can be one - of "always", "auto" (default), "never", or - "no_color" (use non color terminal - sequences). Use "auto-tty" or "no_color-tty" - to decide based on terminal support only. - Can be used multiple times - --compat-options OPTS Options that can help keep compatibility - with youtube-dl or youtube-dlc - configurations by reverting some of the - changes made in yt-dlp. See "Differences in - default behavior" for details - --alias ALIASES OPTIONS Create aliases for an option string. Unless - an alias starts with a dash "-", it is - prefixed with "--". Arguments are parsed - according to the Python string formatting - mini-language. E.g. --alias get-audio,-X "-S - aext:{0},abr -x --audio-format {0}" creates - options "--get-audio" and "-X" that takes an - argument (ARG0) and expands to "-S - aext:ARG0,abr -x --audio-format ARG0". All - defined aliases are listed in the --help - output. Alias options can trigger more - aliases; so be careful to avoid defining - recursive options. As a safety measure, each - alias may be triggered a maximum of 100 - times. This option can be used multiple times - -t, --preset-alias PRESET Applies a predefined set of options. e.g. - --preset-alias mp3. The following presets - are available: mp3, aac, mp4, mkv, sleep. - See the "Preset Aliases" section at the end - for more info. This option can be used - multiple times - -## Network Options: - --proxy URL Use the specified HTTP/HTTPS/SOCKS proxy. To - enable SOCKS proxy, specify a proper scheme, - e.g. socks5://user:pass@127.0.0.1:1080/. - Pass in an empty string (--proxy "") for - direct connection - --socket-timeout SECONDS Time to wait before giving up, in seconds - --source-address IP Client-side IP address to bind to - --impersonate CLIENT[:OS] Client to impersonate for requests. E.g. - chrome, chrome-110, chrome:windows-10. Pass - --impersonate="" to impersonate any client. - Note that forcing impersonation for all - requests may have a detrimental impact on - download speed and stability - --list-impersonate-targets List available clients to impersonate. - -4, --force-ipv4 Make all connections via IPv4 - -6, --force-ipv6 Make all connections via IPv6 - --enable-file-urls Enable file:// URLs. This is disabled by - default for security reasons. - -## Geo-restriction: - --geo-verification-proxy URL Use this proxy to verify the IP address for - some geo-restricted sites. The default proxy - specified by --proxy (or none, if the option - is not present) is used for the actual - downloading - --xff VALUE How to fake X-Forwarded-For HTTP header to - try bypassing geographic restriction. One of - "default" (only when known to be useful), - "never", an IP block in CIDR notation, or a - two-letter ISO 3166-2 country code - -## Video Selection: - -I, --playlist-items ITEM_SPEC Comma-separated playlist_index of the items - to download. You can specify a range using - "[START]:[STOP][:STEP]". For backward - compatibility, START-STOP is also supported. - Use negative indices to count from the right - and negative STEP to download in reverse - order. E.g. "-I 1:3,7,-5::2" used on a - playlist of size 15 will download the items - at index 1,2,3,7,11,13,15 - --min-filesize SIZE Abort download if filesize is smaller than - SIZE, e.g. 50k or 44.6M - --max-filesize SIZE Abort download if filesize is larger than - SIZE, e.g. 50k or 44.6M - --date DATE Download only videos uploaded on this date. - The date can be "YYYYMMDD" or in the format - [now|today|yesterday][-N[day|week|month|year]]. - E.g. "--date today-2weeks" downloads only - videos uploaded on the same day two weeks ago - --datebefore DATE Download only videos uploaded on or before - this date. The date formats accepted are the - same as --date - --dateafter DATE Download only videos uploaded on or after - this date. The date formats accepted are the - same as --date - --match-filters FILTER Generic video filter. Any "OUTPUT TEMPLATE" - field can be compared with a number or a - string using the operators defined in - "Filtering Formats". 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 at least one of the - conditions is met. E.g. --match-filters - !is_live --match-filters "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 that contains the phrase "cats & - dogs" (caseless). Use "--match-filters -" to - interactively ask whether to download each - video - --no-match-filters Do not use any --match-filters (default) - --break-match-filters FILTER Same as "--match-filters" but stops the - download process when a video is rejected - --no-break-match-filters Do not use any --break-match-filters (default) - --no-playlist Download only the video, if the URL refers - to a video and a playlist - --yes-playlist Download the playlist, if the URL refers to - a video and a playlist - --age-limit YEARS Download only videos suitable for the given - age - --download-archive FILE Download only videos not listed in the - archive file. Record the IDs of all - downloaded videos in it - --no-download-archive Do not use archive file (default) - --max-downloads NUMBER Abort after downloading NUMBER files - --break-on-existing Stop the download process when encountering - a file that is in the archive supplied with - the --download-archive option - --no-break-on-existing Do not stop the download process when - encountering a file that is in the archive - (default) - --break-per-input Alters --max-downloads, --break-on-existing, - --break-match-filters, and autonumber to - reset per input URL - --no-break-per-input --break-on-existing and similar options - terminates the entire download queue - --skip-playlist-after-errors N Number of allowed failures until the rest of - the playlist is skipped - -## Download Options: - -N, --concurrent-fragments N Number of fragments of a dash/hlsnative - video that should be downloaded concurrently - (default is 1) - -r, --limit-rate RATE Maximum download rate in bytes per second, - e.g. 50K or 4.2M - --throttled-rate RATE Minimum download rate in bytes per second - below which throttling is assumed and the - video data is re-extracted, e.g. 100K - -R, --retries RETRIES Number of retries (default is 10), or - "infinite" - --file-access-retries RETRIES Number of times to retry on file access - error (default is 3), or "infinite" - --fragment-retries RETRIES Number of retries for a fragment (default is - 10), or "infinite" (DASH, hlsnative and ISM) - --retry-sleep [TYPE:]EXPR Time to sleep between retries in seconds - (optionally) prefixed by the type of retry - (http (default), fragment, file_access, - extractor) to apply the sleep to. EXPR can - be a number, linear=START[:END[:STEP=1]] or - exp=START[:END[:BASE=2]]. This option can be - used multiple times to set the sleep for the - different retry types, e.g. --retry-sleep - linear=1::2 --retry-sleep fragment:exp=1:20 - --skip-unavailable-fragments Skip unavailable fragments for DASH, - hlsnative and ISM downloads (default) - (Alias: --no-abort-on-unavailable-fragments) - --abort-on-unavailable-fragments - Abort download if a fragment is unavailable - (Alias: --no-skip-unavailable-fragments) - --keep-fragments Keep downloaded fragments on disk after - downloading is finished - --no-keep-fragments Delete downloaded fragments after - downloading is finished (default) - --buffer-size SIZE Size of download buffer, e.g. 1024 or 16K - (default is 1024) - --resize-buffer The buffer size is automatically resized - from an initial value of --buffer-size - (default) - --no-resize-buffer Do not automatically adjust the buffer size - --http-chunk-size SIZE Size of a chunk for chunk-based HTTP - downloading, e.g. 10485760 or 10M (default - is disabled). May be useful for bypassing - bandwidth throttling imposed by a webserver - (experimental) - --playlist-random Download playlist videos in random order - --lazy-playlist Process entries in the playlist as they are - received. This disables n_entries, - --playlist-random and --playlist-reverse - --no-lazy-playlist Process videos in the playlist only after - the entire playlist is parsed (default) - --hls-use-mpegts Use the mpegts container for HLS videos; - allowing some players to play the video - while downloading, and reducing the chance - of file corruption if download is - interrupted. This is enabled by default for - live streams - --no-hls-use-mpegts Do not use the mpegts container for HLS - videos. This is default when not downloading - live streams - --download-sections REGEX Download only chapters that match the - regular expression. A "*" prefix denotes - time-range instead of chapter. Negative - timestamps are calculated from the end. - "*from-url" can be used to download between - the "start_time" and "end_time" extracted - from the URL. Needs ffmpeg. This option can - be used multiple times to download multiple - sections, e.g. --download-sections - "*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 - use it for. Currently supports native, - aria2c, axel, curl, ffmpeg, httpie, wget. - You can use this option multiple times to - set different downloaders for different - protocols. E.g. --downloader aria2c - --downloader "dash,m3u8:native" will use - aria2c for http/ftp downloads, and the - native downloader for dash/m3u8 downloads - (Alias: --external-downloader) - --downloader-args NAME:ARGS Give these arguments to the external - downloader. Specify the downloader name and - the arguments separated by a colon ":". For - ffmpeg, arguments can be passed to different - positions using the same syntax as - --postprocessor-args. You can use this - option multiple times to give different - arguments to different downloaders (Alias: - --external-downloader-args) - -## Filesystem Options: - -a, --batch-file FILE File containing URLs to download ("-" for - stdin), one URL per line. Lines starting - with "#", ";" or "]" are considered as - comments and ignored - --no-batch-file Do not read URLs from batch file (default) - -P, --paths [TYPES:]PATH The paths where the files should be - downloaded. Specify the type of file and the - path separated by a colon ":". All the same - TYPES as --output are supported. - Additionally, you can also provide "home" - (default) and "temp" paths. All intermediary - files are first downloaded to the temp path - and then the final files are moved over to - the home path after download is finished. - This option is ignored if --output is an - absolute path - -o, --output [TYPES:]TEMPLATE Output filename template; see "OUTPUT - TEMPLATE" for details - --output-na-placeholder TEXT Placeholder for unavailable fields in - --output (default: "NA") - --restrict-filenames Restrict filenames to only ASCII characters, - and avoid "&" and spaces in filenames - --no-restrict-filenames Allow Unicode characters, "&" and spaces in - filenames (default) - --windows-filenames Force filenames to be Windows-compatible - --no-windows-filenames Sanitize filenames only minimally - --trim-filenames LENGTH Limit the filename length (excluding - extension) to the specified number of - characters - -w, --no-overwrites Do not overwrite any files - --force-overwrites Overwrite all video and metadata files. This - option includes --no-continue - --no-force-overwrites Do not overwrite the video, but overwrite - related files (default) - -c, --continue Resume partially downloaded files/fragments - (default) - --no-continue Do not resume partially downloaded - fragments. If the file is not fragmented, - restart download of the entire file - --part Use .part files instead of writing directly - into output file (default) - --no-part Do not use .part files - write directly into - output file - --mtime Use the Last-modified header to set the file - modification time - --no-mtime Do not use the Last-modified header to set - the file modification time (default) - --write-description Write video description to a .description file - --no-write-description Do not write video description (default) - --write-info-json Write video metadata to a .info.json file - (this may contain personal information) - --no-write-info-json Do not write video metadata (default) - --write-playlist-metafiles Write playlist metadata in addition to the - video metadata when using --write-info-json, - --write-description etc. (default) - --no-write-playlist-metafiles Do not write playlist metadata when using - --write-info-json, --write-description etc. - --clean-info-json Remove some internal metadata such as - filenames from the infojson (default) - --no-clean-info-json Write all fields to the infojson - --write-comments Retrieve video comments to be placed in the - infojson. The comments are fetched even - without this option if the extraction is - known to be quick (Alias: --get-comments) - --no-write-comments Do not retrieve video comments unless the - extraction is known to be quick (Alias: - --no-get-comments) - --load-info-json FILE JSON file containing the video information - (created with the "--write-info-json" option) - --cookies FILE Netscape formatted file to read cookies from - and dump cookie jar in - --no-cookies Do not read/dump cookies from/to file - (default) - --cookies-from-browser BROWSER[+KEYRING][:PROFILE][::CONTAINER] - The name of the browser to load cookies - from. Currently supported browsers are: - brave, chrome, chromium, edge, firefox, - opera, safari, vivaldi, whale. 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 separators. By default, all - containers of the most recently accessed - profile are used. Currently supported - keyrings are: basictext, gnomekeyring, - kwallet, kwallet5, kwallet6 - --no-cookies-from-browser Do not load cookies from browser (default) - --cache-dir DIR Location in the filesystem where yt-dlp can - store some downloaded information (such as - client ids and signatures) permanently. By - default ${XDG_CACHE_HOME}/yt-dlp - --no-cache-dir Disable filesystem caching - --rm-cache-dir Delete all filesystem cache files - -## Thumbnail Options: - --write-thumbnail Write thumbnail image to disk - --no-write-thumbnail Do not write thumbnail image to disk (default) - --write-all-thumbnails Write all thumbnail image formats to disk - --list-thumbnails List available thumbnails of each video. - Simulate unless --no-simulate is used - -## Internet Shortcut Options: - --write-link Write an internet shortcut file, depending - on the current platform (.url, .webloc or - .desktop). The URL may be cached by the OS - --write-url-link Write a .url Windows internet shortcut. The - OS caches the URL based on the file path - --write-webloc-link Write a .webloc macOS internet shortcut - --write-desktop-link Write a .desktop Linux internet shortcut - -## Verbosity and Simulation Options: - -q, --quiet Activate quiet mode. If used with --verbose, - print the log to stderr - --no-quiet Deactivate quiet mode. (Default) - --no-warnings Ignore warnings - -s, --simulate Do not download the video and do not write - anything to disk - --no-simulate Download the video even if printing/listing - options are used - --ignore-no-formats-error Ignore "No video formats" error. Useful for - extracting metadata even if the videos are - not actually available for download - (experimental) - --no-ignore-no-formats-error Throw error when no downloadable video - formats are found (default) - --skip-download Do not download the video but write all - related files (Alias: --no-download) - -O, --print [WHEN:]TEMPLATE Field name or output template to print to - screen, optionally prefixed with when to - print it, separated by a ":". Supported - values of "WHEN" are the same as that of - --use-postprocessor (default: video). - Implies --quiet. Implies --simulate unless - --no-simulate or later stages of WHEN are - used. This option can be used multiple times - --print-to-file [WHEN:]TEMPLATE FILE - Append given template to the file. The - values of WHEN and TEMPLATE are the same as - that of --print. FILE uses the same syntax - as the output template. This option can be - used multiple times - -j, --dump-json Quiet, but print JSON information for each - video. Simulate unless --no-simulate is - used. See "OUTPUT TEMPLATE" for a - description of available keys - -J, --dump-single-json Quiet, but print JSON information for each - URL or infojson passed. Simulate unless - --no-simulate is used. If the URL refers to - a playlist, the whole playlist information - is dumped in a single line - --force-write-archive Force download archive entries to be written - as far as no errors occur, even if -s or - another simulation option is used (Alias: - --force-download-archive) - --newline Output progress bar as new lines - --no-progress Do not print progress bar - --progress Show progress bar, even if in quiet mode - --console-title Display progress in console titlebar - --progress-template [TYPES:]TEMPLATE - Template for progress outputs, optionally - prefixed with one of "download:" (default), - "download-title:" (the console title), - "postprocess:", or "postprocess-title:". - The video's fields are accessible under the - "info" key and the progress attributes are - accessible under "progress" key. E.g. - --console-title --progress-template - "download-title:%(info.id)s-%(progress.eta)s" - --progress-delta SECONDS Time between progress output (default: 0) - -v, --verbose Print various debugging information - --dump-pages Print downloaded pages encoded using base64 - to debug problems (very verbose) - --write-pages Write downloaded intermediary pages to files - in the current directory to debug problems - --print-traffic Display sent and read HTTP traffic - -## Workarounds: - --encoding ENCODING Force the specified encoding (experimental) - --legacy-server-connect Explicitly allow HTTPS connection to servers - that do not support RFC 5746 secure - renegotiation - --no-check-certificates Suppress HTTPS certificate validation - --prefer-insecure Use an unencrypted connection to retrieve - information about the video (Currently - supported only for YouTube) - --add-headers FIELD:VALUE Specify a custom HTTP header and its value, - separated by a colon ":". You can use this - option multiple times - --bidi-workaround Work around terminals that lack - bidirectional text support. Requires bidiv - or fribidi executable in PATH - --sleep-requests SECONDS Number of seconds to sleep between requests - during data extraction - --sleep-interval SECONDS Number of seconds to sleep before each - download. This is the minimum time to sleep - when used along with --max-sleep-interval - (Alias: --min-sleep-interval) - --max-sleep-interval SECONDS Maximum number of seconds to sleep. Can only - be used along with --min-sleep-interval - --sleep-subtitles SECONDS Number of seconds to sleep before each - subtitle download - -## Video Format Options: - -f, --format FORMAT Video format code, see "FORMAT SELECTION" - for more details - -S, --format-sort SORTORDER Sort the formats by the fields given, see - "Sorting Formats" for more details - --format-sort-reset Disregard previous user specified sort order - and reset to the default - --format-sort-force Force user specified sort order to have - precedence over all fields, see "Sorting - Formats" for more details (Alias: --S-force) - --no-format-sort-force Some fields have precedence over the user - specified sort order (default) - --video-multistreams Allow multiple video streams to be merged - into a single file - --no-video-multistreams Only one video stream is downloaded for each - output file (default) - --audio-multistreams Allow multiple audio streams to be merged - into a single file - --no-audio-multistreams Only one audio stream is downloaded for each - output file (default) - --prefer-free-formats Prefer video formats with free containers - over non-free ones of the same quality. Use - with "-S ext" to strictly prefer free - containers irrespective of quality - --no-prefer-free-formats Don't give any special preference to free - containers (default) - --check-formats Make sure formats are selected only from - those that are actually downloadable - --check-all-formats Check all formats for whether they are - actually downloadable - --no-check-formats Do not check that the formats are actually - downloadable - -F, --list-formats List available formats of each video. - Simulate unless --no-simulate is used - --merge-output-format FORMAT Containers that may be used when merging - formats, separated by "/", e.g. "mp4/mkv". - Ignored if no merge is required. (currently - supported: avi, flv, mkv, mov, mp4, webm) - -## Subtitle Options: - --write-subs Write subtitle file - --no-write-subs Do not write subtitle file (default) - --write-auto-subs Write automatically generated subtitle file - (Alias: --write-automatic-subs) - --no-write-auto-subs Do not write auto-generated subtitles - (default) (Alias: --no-write-automatic-subs) - --list-subs List available subtitles of each video. - Simulate unless --no-simulate is used - --sub-format FORMAT Subtitle format; accepts formats preference - separated by "/", e.g. "srt" or "ass/srt/best" - --sub-langs LANGS Languages of the subtitles to download (can - be regex) or "all" separated by commas, e.g. - --sub-langs "en.*,ja" (where "en.*" is a - regex pattern that matches "en" followed by - 0 or more of any character). You can prefix - the language code with a "-" to exclude it - from the requested languages, e.g. --sub- - langs all,-live_chat. Use --list-subs for a - list of available language tags - -## Authentication Options: - -u, --username USERNAME Login with this account ID - -p, --password PASSWORD Account password. If this option is left - out, yt-dlp will ask interactively - -2, --twofactor TWOFACTOR Two-factor authentication code - -n, --netrc Use .netrc authentication data - --netrc-location PATH Location of .netrc authentication data; - either the path or its containing directory. - Defaults to ~/.netrc - --netrc-cmd NETRC_CMD Command to execute to get the credentials - for an extractor. - --video-password PASSWORD Video-specific password - --ap-mso MSO Adobe Pass multiple-system operator (TV - provider) identifier, use --ap-list-mso for - a list of available MSOs - --ap-username USERNAME Multiple-system operator account login - --ap-password PASSWORD Multiple-system operator account password. - If this option is left out, yt-dlp will ask - interactively - --ap-list-mso List all supported multiple-system operators - --client-certificate CERTFILE Path to client certificate file in PEM - format. May include the private key - --client-certificate-key KEYFILE - Path to private key file for client - certificate - --client-certificate-password PASSWORD - Password for client certificate private key, - if encrypted. If not provided, and the key - is encrypted, yt-dlp will ask interactively - -## Post-Processing Options: - -x, --extract-audio Convert video files to audio-only files - (requires ffmpeg and ffprobe) - --audio-format FORMAT Format to convert the audio to when -x is - used. (currently supported: best (default), - aac, alac, flac, m4a, mp3, opus, vorbis, - wav). You can specify multiple rules using - similar syntax as --remux-video - --audio-quality QUALITY Specify ffmpeg audio quality to use when - converting the audio with -x. Insert a value - between 0 (best) and 10 (worst) for VBR or a - specific bitrate like 128K (default 5) - --remux-video FORMAT Remux the video into another container if - necessary (currently supported: avi, flv, - gif, mkv, mov, mp4, webm, aac, aiff, alac, - flac, m4a, mka, mp3, ogg, opus, vorbis, - wav). If the target container does not - support the video/audio codec, remuxing will - fail. You can specify multiple rules; e.g. - "aac>m4a/mov>mp4/mkv" will remux aac to m4a, - mov to mp4 and anything else to mkv - --recode-video FORMAT Re-encode the video into another format if - necessary. The syntax and supported formats - are the same as --remux-video - --postprocessor-args NAME:ARGS Give these arguments to the postprocessors. - Specify the postprocessor/executable name - and the arguments separated by a colon ":" - to give the argument to the specified - postprocessor/executable. Supported PP are: - Merger, ModifyChapters, SplitChapters, - ExtractAudio, VideoRemuxer, VideoConvertor, - Metadata, EmbedSubtitle, EmbedThumbnail, - SubtitlesConvertor, ThumbnailsConvertor, - FixupStretched, FixupM4a, FixupM3u8, - FixupTimestamp and FixupDuration. The - supported executables are: AtomicParsley, - FFmpeg and FFprobe. You can also specify - "PP+EXE:ARGS" to give the arguments to the - specified executable only when being used by - the specified postprocessor. Additionally, - for ffmpeg/ffprobe, "_i"/"_o" can be - appended to the prefix optionally followed - by a number to pass the argument before the - specified input/output file, e.g. --ppa - "Merger+ffmpeg_i1:-v quiet". You can use - this option multiple times to give different - arguments to different postprocessors. - (Alias: --ppa) - -k, --keep-video Keep the intermediate video file on disk - after post-processing - --no-keep-video Delete the intermediate video file after - post-processing (default) - --post-overwrites Overwrite post-processed files (default) - --no-post-overwrites Do not overwrite post-processed files - --embed-subs Embed subtitles in the video (only for mp4, - webm and mkv videos) - --no-embed-subs Do not embed subtitles (default) - --embed-thumbnail Embed thumbnail in the video as cover art - --no-embed-thumbnail Do not embed thumbnail (default) - --embed-metadata Embed metadata to the video file. Also - embeds chapters/infojson if present unless - --no-embed-chapters/--no-embed-info-json are - used (Alias: --add-metadata) - --no-embed-metadata Do not add metadata to file (default) - (Alias: --no-add-metadata) - --embed-chapters Add chapter markers to the video file - (Alias: --add-chapters) - --no-embed-chapters Do not add chapter markers (default) (Alias: - --no-add-chapters) - --embed-info-json Embed the infojson as an attachment to - mkv/mka video files - --no-embed-info-json Do not embed the infojson as an attachment - to the video file - --parse-metadata [WHEN:]FROM:TO - Parse additional metadata like title/artist - from other fields; see "MODIFYING METADATA" - for details. Supported values of "WHEN" are - the same as that of --use-postprocessor - (default: pre_process) - --replace-in-metadata [WHEN:]FIELDS REGEX REPLACE - Replace text in a metadata field using the - given regex. This option can be used - multiple times. Supported values of "WHEN" - are the same as that of --use-postprocessor - (default: pre_process) - --xattrs Write metadata to the video file's xattrs - (using Dublin Core and XDG standards) - --concat-playlist POLICY Concatenate videos in a playlist. One of - "never", "always", or "multi_video" - (default; only when the videos form a single - show). All the video files must have the - same codecs and number of streams to be - concatenable. The "pl_video:" prefix can be - used with "--paths" and "--output" to set - the output filename for the concatenated - files. See "OUTPUT TEMPLATE" for details - --fixup POLICY Automatically correct known faults of the - file. One of never (do nothing), warn (only - emit a warning), detect_or_warn (the - default; fix the file if we can, warn - otherwise), force (try fixing even if the - file already exists) - --ffmpeg-location PATH Location of the ffmpeg binary; either the - path to the binary or its containing directory - --exec [WHEN:]CMD Execute a command, optionally prefixed with - when to execute it, separated by a ":". - Supported values of "WHEN" are the same as - that of --use-postprocessor (default: - after_move). The same syntax as the output - template can be used to pass any field as - arguments to the command. If no fields are - passed, %(filepath,_filename|)q is appended - to the end of the command. This option can - be used multiple times - --no-exec Remove any previously defined --exec - --convert-subs FORMAT Convert the subtitles to another format - (currently supported: ass, lrc, srt, vtt). - Use "--convert-subs none" to disable - conversion (default) (Alias: --convert- - subtitles) - --convert-thumbnails FORMAT Convert the thumbnails to another format - (currently supported: jpg, png, webp). You - can specify multiple rules using similar - syntax as "--remux-video". Use "--convert- - thumbnails none" to disable conversion - (default) - --split-chapters Split video into multiple files based on - internal chapters. The "chapter:" prefix can - be used with "--paths" and "--output" to set - the output filename for the split files. See - "OUTPUT TEMPLATE" for details - --no-split-chapters Do not split video based on chapters (default) - --remove-chapters REGEX Remove chapters whose title matches the - given regular expression. The syntax is the - same as --download-sections. This option can - be used multiple times - --no-remove-chapters Do not remove any chapters from the file - (default) - --force-keyframes-at-cuts Force keyframes at cuts when - downloading/splitting/removing sections. - This is slow due to needing a re-encode, but - the resulting video may have fewer artifacts - around the cuts - --no-force-keyframes-at-cuts Do not force keyframes around the chapters - when cutting/splitting (default) - --use-postprocessor NAME[:ARGS] - The (case-sensitive) name of plugin - postprocessors to be enabled, and - (optionally) arguments to be passed to it, - separated by a colon ":". ARGS are a - semicolon ";" delimited list of NAME=VALUE. - The "when" argument determines when the - postprocessor is invoked. 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 the video file to its final - location), "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 - -## SponsorBlock Options: -Make chapter entries for, or remove various segments (sponsor, - introductions, etc.) from downloaded YouTube videos using the - [SponsorBlock API](https://sponsor.ajay.app) - - --sponsorblock-mark CATS SponsorBlock categories to create chapters - for, separated by commas. Available - categories are sponsor, intro, outro, - selfpromo, preview, filler, interaction, - music_offtopic, hook, poi_highlight, - chapter, all and default (=all). You can - prefix the category with a "-" to exclude - it. See [1] for descriptions of the - categories. E.g. --sponsorblock-mark - all,-preview - [1] https://wiki.sponsor.ajay.app/w/Segment_Categories - --sponsorblock-remove CATS SponsorBlock categories to be removed from - the video file, separated by commas. If a - category is present in both mark and remove, - remove takes precedence. The syntax and - available categories are the same as for - --sponsorblock-mark except that "default" - refers to "all,-filler" and poi_highlight, - chapter are not available - --sponsorblock-chapter-title TEMPLATE - An output template for the title of the - SponsorBlock chapters created by - --sponsorblock-mark. The only available - fields are start_time, end_time, category, - categories, name, category_names. Defaults - to "[SponsorBlock]: %(category_names)l" - --no-sponsorblock Disable both --sponsorblock-mark and - --sponsorblock-remove - --sponsorblock-api URL SponsorBlock API location, defaults to - https://sponsor.ajay.app - -## Extractor Options: - --extractor-retries RETRIES Number of retries for known extractor errors - (default is 3), or "infinite" - --allow-dynamic-mpd Process dynamic DASH manifests (default) - (Alias: --no-ignore-dynamic-mpd) - --ignore-dynamic-mpd Do not process dynamic DASH manifests - (Alias: --no-allow-dynamic-mpd) - --hls-split-discontinuity Split HLS playlists to different formats at - discontinuities such as ad breaks - --no-hls-split-discontinuity Do not split HLS playlists into different - formats at discontinuities such as ad breaks - (default) - --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 - -## Preset Aliases: -Predefined aliases for convenience and ease of use. Note that future - versions of yt-dlp may add or adjust presets, but the existing preset - names will not be changed or removed - - -t mp3 -f 'ba[acodec^=mp3]/ba/b' -x --audio-format - mp3 - - -t aac -f - 'ba[acodec^=aac]/ba[acodec^=mp4a.40.]/ba/b' - -x --audio-format aac - - -t mp4 --merge-output-format mp4 --remux-video mp4 - -S vcodec:h264,lang,quality,res,fps,hdr:12,a - codec:aac - - -t mkv --merge-output-format mkv --remux-video mkv - - -t sleep --sleep-subtitles 5 --sleep-requests 0.75 - --sleep-interval 10 --max-sleep-interval 20 - -# CONFIGURATION - -You can configure yt-dlp by placing any supported command line option in a configuration file. The configuration is loaded from the following locations: - -1. **Main Configuration**: - * The file given to `--config-locations` -1. **Portable Configuration**: (Recommended for portable installations) - * If using a binary, `yt-dlp.conf` in the same directory as the binary - * If running from source-code, `yt-dlp.conf` in the parent directory of `yt_dlp` -1. **Home Configuration**: - * `yt-dlp.conf` in the home path given to `-P` - * If `-P` is not given, the current directory is searched -1. **User Configuration**: - * `${XDG_CONFIG_HOME}/yt-dlp.conf` - * `${XDG_CONFIG_HOME}/yt-dlp/config` (recommended on Linux/macOS) - * `${XDG_CONFIG_HOME}/yt-dlp/config.txt` - * `${APPDATA}/yt-dlp.conf` - * `${APPDATA}/yt-dlp/config` (recommended on Windows) - * `${APPDATA}/yt-dlp/config.txt` - * `~/yt-dlp.conf` - * `~/yt-dlp.conf.txt` - * `~/.yt-dlp/config` - * `~/.yt-dlp/config.txt` - - See also: [Notes about environment variables](#notes-about-environment-variables) -1. **System Configuration**: - * `/etc/yt-dlp.conf` - * `/etc/yt-dlp/config` - * `/etc/yt-dlp/config.txt` - -E.g. with the following configuration file, yt-dlp will always extract the audio, copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory: -``` -# Lines starting with # are comments - -# Always extract audio --x - -# Copy the mtime ---mtime - -# Use this proxy ---proxy 127.0.0.1:3128 - -# Save all videos under YouTube directory in your home directory --o ~/YouTube/%(title)s.%(ext)s -``` - -**Note**: Options in a 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. - -### Configuration file encoding - -The configuration files are decoded according to the UTF BOM if present, and in the encoding from system locale otherwise. - -If you want your file to be decoded differently, add `# coding: ENCODING` to the beginning of the file (e.g. `# coding: shift-jis`). There must be no characters before that, even spaces or BOM. - -### 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: -``` -touch ${HOME}/.netrc -chmod a-rwx,u+rw ${HOME}/.netrc -``` -After that, you can add credentials for an extractor in the following format, where *extractor* is the name of the extractor in lowercase: -``` -machine login password -``` -E.g. -``` -machine youtube login myaccount@gmail.com password my_youtube_password -machine twitch login my_twitch_account_name password my_twitch_password -``` -To activate authentication with the `.netrc` file you should pass `--netrc` to yt-dlp or place it in the [configuration file](#configuration). - -The default location of the .netrc file is `~` (see below). - -As an alternative to using the `.netrc` file, which has the disadvantage of keeping your passwords in a plain text file, you can configure a custom shell command to provide the credentials for an extractor. This is done by providing the `--netrc-cmd` parameter, it shall output the credentials in the netrc format and return `0` on success, other values will be treated as an error. `{}` in the command will be replaced by the name of the extractor to make it possible to select the credentials for the right extractor. - -E.g. To use an encrypted `.netrc` file stored as `.authinfo.gpg` -``` -yt-dlp --netrc-cmd 'gpg --decrypt ~/.authinfo.gpg' 'https://www.youtube.com/watch?v=BaW_jenozKc' -``` - - -### Notes about environment variables -* Environment variables are normally specified as `${VARIABLE}`/`$VARIABLE` on UNIX and `%VARIABLE%` on Windows; but is always shown as `${VARIABLE}` in this documentation -* yt-dlp also allows using UNIX-style variables on Windows for path-like options; e.g. `--output`, `--config-locations` -* If unset, `${XDG_CONFIG_HOME}` defaults to `~/.config` and `${XDG_CACHE_HOME}` to `~/.cache` -* On Windows, `~` points to `${HOME}` if present; or, `${USERPROFILE}` or `${HOMEDRIVE}${HOMEPATH}` otherwise -* On Windows, `${USERPROFILE}` generally points to `C:\Users\` and `${APPDATA}` to `${USERPROFILE}\AppData\Roaming` - -# OUTPUT TEMPLATE - -The `-o` option is used to indicate a template for the output file names while `-P` option is used to specify the path each type of file should be saved to. - - -**tl;dr:** [navigate me to examples](#output-template-examples). - - -The simplest usage of `-o` is not to set any template arguments when downloading a single file, like in `yt-dlp -o funny_video.flv "https://some/video"` (hard-coding file extension like this is _not_ recommended and could break some post-processing). - -It may however also contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [Python string formatting operations](https://docs.python.org/3/library/stdtypes.html#printf-style-string-formatting), e.g. `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. - -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)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` - -1. **Date/time Formatting**: Date/time fields can be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it separated from the field name using a `>`. E.g. `%(duration>%H-%M-%S)s`, `%(upload_date>%Y-%m-%d)s`, `%(epoch-3600>%H-%M-%S)s` - -1. **Alternatives**: Alternate fields can be specified separated with a `,`. E.g. `%(release_date>%Y,upload_date>%Y|Unknown)s` - -1. **Replacement**: A replacement value can be specified using a `&` separator according to the [`str.format` mini-language](https://docs.python.org/3/library/string.html#format-specification-mini-language). If the field is *not* empty, this replacement value will be used instead of the actual field content. This is done after alternate fields are considered; thus the replacement is used if *any* of the alternative fields is *not* empty. E.g. `%(chapters&has chapters|no chapters)s`, `%(title&TITLE={:>20}|NO TITLE)s` - -1. **Default**: A literal default value can be specified for when the field is empty using a `|` separator. This overrides `--output-na-placeholder`. E.g. `%(uploader|Unknown)s` - -1. **More Conversions**: In addition to the normal format types `diouxXeEfFgGcrs`, yt-dlp additionally supports converting to `B` = **B**ytes, `j` = **j**son (flag `#` for pretty-printing, `+` for Unicode), `h` = HTML escaping, `l` = a comma-separated **l**ist (flag `#` for `\n` newline-separated), `q` = a string **q**uoted for the terminal (flag `#` to split a list into different arguments), `D` = add **D**ecimal suffixes (e.g. 10M) (flag `#` to use 1024 as factor), and `S` = **S**anitize as filename (flag `#` for restricted) - -1. **Unicode normalization**: The format type `U` can be used for NFC [Unicode normalization](https://docs.python.org/3/library/unicodedata.html#unicodedata.normalize). The alternate form flag (`#`) changes the normalization to NFD and the conversion flag `+` can be used for NFKC/NFKD compatibility equivalence normalization. E.g. `%(title)+.100U` is NFKC - -To summarize, the general syntax for a field is: -``` -%(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. - - - -**Note**: Due to post-processing (i.e. merging etc.), the actual output filename might differ. Use `--print after_move:filepath` to get the name after all post-processing is complete. - -The available fields are: - - - `id` (string): Video identifier - - `title` (string): Video title - - `fulltitle` (string): Video title ignoring live timestamp and generic title - - `ext` (string): Video filename extension - - `alt_title` (string): A secondary title of the video - - `description` (string): The description of the video - - `display_id` (string): An alternative identifier for the video - - `uploader` (string): Full name of the video uploader - - `uploader_id` (string): Nickname or id of the video uploader - - `uploader_url` (string): URL to the video uploader's profile - - `license` (string): License name the video is licensed under - - `creators` (list): The creators of the video - - `creator` (string): The creators of the video; comma-separated - - `timestamp` (numeric): UNIX timestamp of the moment the video became available - - `upload_date` (string): Video upload date in UTC (YYYYMMDD) - - `release_timestamp` (numeric): UNIX timestamp of the moment the video was released - - `release_date` (string): The date (YYYYMMDD) when the video was released in UTC - - `release_year` (numeric): Year (YYYY) when the video or album was released - - `modified_timestamp` (numeric): UNIX timestamp of the moment the video was last modified - - `modified_date` (string): The date (YYYYMMDD) when the video was last modified in UTC - - `channel` (string): Full name of the channel the video is uploaded on - - `channel_id` (string): Id of the channel - - `channel_url` (string): URL of the channel - - `channel_follower_count` (numeric): Number of followers of the channel - - `channel_is_verified` (boolean): Whether the channel is verified on the platform - - `location` (string): Physical location where the video was filmed - - `duration` (numeric): Length of the video in seconds - - `duration_string` (string): Length of the video (HH:mm:ss) - - `view_count` (numeric): How many users have watched the video on the platform - - `concurrent_view_count` (numeric): How many users are currently watching the video on the platform. - - `like_count` (numeric): Number of positive ratings of the video - - `dislike_count` (numeric): Number of negative ratings of the video - - `repost_count` (numeric): Number of reposts of the video - - `average_rating` (numeric): Average rating given by users, the scale used depends on the webpage - - `comment_count` (numeric): Number of comments on the video (For some extractors, comments are only downloaded at the end, and so this field cannot be used) - - `save_count` (numeric): Number of times the video has been saved or bookmarked - - `age_limit` (numeric): Age restriction for the video (years) - - `live_status` (string): One of "not_live", "is_live", "is_upcoming", "was_live", "post_live" (was live, but VOD is not yet processed) - - `is_live` (boolean): Whether this video is a live stream or a fixed-length video - - `was_live` (boolean): Whether this video was originally a live stream - - `playable_in_embed` (string): Whether this video is allowed to play in embedded players on other sites - - `availability` (string): Whether the video is "private", "premium_only", "subscriber_only", "needs_auth", "unlisted" or "public" - - `media_type` (string): The type of media as classified by the site, e.g. "episode", "clip", "trailer" - - `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL - - `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL - - `extractor` (string): Name of the extractor - - `extractor_key` (string): Key name of the extractor - - `epoch` (numeric): Unix epoch of when the information extraction was completed - - `autonumber` (numeric): Number that will be increased with each download, starting at `--autonumber-start`, padded with leading zeros to 5 digits - - `video_autonumber` (numeric): Number that will be increased with each video - - `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_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 - - `playlist_uploader` (string): Full name of the playlist uploader - - `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 - - `playlist_webpage_url` (string): URL of the playlist webpage - - `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 the same as `webpage_url` for playlist entries) - - `categories` (list): List of categories the video belongs to - - `tags` (list): List of tags assigned to the video - - `cast` (list): List of cast members - -All the fields in [Filtering Formats](#filtering-formats) can also be used - -Available for the video that belongs to some logical chapter or section: - - - `chapter` (string): Name or title of the chapter the video belongs to - - `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 program: - - - `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 - - `episode` (string): Title of the video episode - - `episode_number` (numeric): Number of the video episode within a season - - `episode_id` (string): Id of the video episode - -Available for the media that is a track or a part of a music album: - - - `track` (string): Title of the track - - `track_number` (numeric): Number of the track within an album or a disc - - `track_id` (string): Id of the track - - `artists` (list): Artist(s) of the track - - `artist` (string): Artist(s) of the track; comma-separated - - `genres` (list): Genre(s) of the track - - `genre` (string): Genre(s) of the track; comma-separated - - `composers` (list): Composer(s) of the piece - - `composer` (string): Composer(s) of the piece; comma-separated - - `album` (string): Title of the album the track belongs to - - `album_type` (string): Type of the album - - `album_artists` (list): All artists appeared on the album - - `album_artist` (string): All artists appeared on the album; comma-separated - - `disc_number` (numeric): Number of the disc or other physical medium the track belongs to - -Available only when using `--download-sections` and for `chapter:` prefix when using `--split-chapters` for videos with internal chapters: - - - `section_title` (string): Title of the chapter - - `section_number` (numeric): Number of the chapter within the file - - `section_start` (numeric): Start time of the chapter in seconds - - `section_end` (numeric): End time of the chapter in seconds - -Available only when used in `--print`: - - - `urls` (string): The URLs of all requested formats, one in each line - - `filename` (string): Name of the video file. Note that the [actual filename may differ](#outtmpl-postprocess-note) - - `formats_table` (table): The video format table as printed by `--list-formats` - - `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`: - - - `start_time` (numeric): Start time of the chapter in seconds - - `end_time` (numeric): End time of the chapter in seconds - - `categories` (list): The [SponsorBlock categories](https://wiki.sponsor.ajay.app/w/Types#Category) the chapter belongs to - - `category` (string): The smallest SponsorBlock category the chapter belongs to - - `category_names` (list): Friendly names of the categories - - `name` (string): Friendly name of the smallest category - - `type` (string): The [SponsorBlock action type](https://wiki.sponsor.ajay.app/w/Types#Action_Type) of the chapter - -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). - -**Tip**: Look at the `-j` output to identify which fields are available for the particular URL - -For numeric sequences, you can use [numeric related formatting](https://docs.python.org/3/library/stdtypes.html#printf-style-string-formatting); e.g. `%(view_count)05d` will result in a string with view count padded with zeros up to 5 characters, like in `00042`. - -Output templates can also contain arbitrary hierarchical path, e.g. `-o "%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s"` which will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you. - -To use percent literals in an output template use `%%`. To output to stdout use `-o -`. - -The current default template is `%(title)s [%(id)s].%(ext)s`. - -In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title. - -#### Output template examples +### Pull and run from Docker Hub ```bash -$ yt-dlp --print filename -o "test video.%(ext)s" BaW_jenozKc -test video.webm # Literal name with correct extension - -$ yt-dlp --print filename -o "%(title)s.%(ext)s" BaW_jenozKc -youtube-dl test video ''_ä↭𝕐.webm # All kinds of weird characters - -$ yt-dlp --print filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames -youtube-dl_test_video_.webm # Restricted file name - -# Download YouTube playlist videos in separate directory indexed by video order in a playlist -$ yt-dlp -o "%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s" "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re" - -# Download YouTube playlist videos in separate directories according to their uploaded year -$ yt-dlp -o "%(upload_date>%Y)s/%(title)s.%(ext)s" "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re" - -# Prefix playlist index with " - " separator, but only if it is available -$ yt-dlp -o "%(playlist_index&{} - |)s%(title)s.%(ext)s" BaW_jenozKc "https://www.youtube.com/user/TheLinuxFoundation/playlists" - -# Download all playlists of YouTube channel/user keeping each playlist in separate directory: -$ yt-dlp -o "%(uploader)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s" "https://www.youtube.com/user/TheLinuxFoundation/playlists" - -# Download Udemy course keeping each chapter in separate directory under MyVideos directory in your home -$ yt-dlp -u user -p password -P "~/MyVideos" -o "%(playlist)s/%(chapter_number)s - %(chapter)s/%(title)s.%(ext)s" "https://www.udemy.com/java-tutorial" - -# Download entire series season keeping each series and each season in separate directory under C:/MyVideos -$ yt-dlp -P "C:/MyVideos" -o "%(series)s/%(season_number)s - %(season)s/%(episode_number)s - %(episode)s.%(ext)s" "https://videomore.ru/kino_v_detalayah/5_sezon/367617" - -# Download video as "C:\MyVideos\uploader\title.ext", subtitles as "C:\MyVideos\subs\uploader\title.ext" -# and put all temporary files in "C:\MyVideos\tmp" -$ yt-dlp -P "C:/MyVideos" -P "temp:tmp" -P "subtitle:subs" -o "%(uploader)s/%(title)s.%(ext)s" BaW_jenozKc --write-subs - -# Download video as "C:\MyVideos\uploader\title.ext" and subtitles as "C:\MyVideos\uploader\subs\title.ext" -$ yt-dlp -P "C:/MyVideos" -o "%(uploader)s/%(title)s.%(ext)s" -o "subtitle:%(uploader)s/subs/%(title)s.%(ext)s" BaW_jenozKc --write-subs - -# Stream the video being downloaded to stdout -$ yt-dlp -o - BaW_jenozKc +docker pull samive/yt-dlp-web:latest +docker run -d -p 8000:8000 --name yt-dlp-web samive/yt-dlp-web:latest ``` -# FORMAT SELECTION +Then open **http://localhost:8000** in your browser. -By default, yt-dlp tries to download the best available quality if you **don't** pass any options. -This is generally equivalent to using `-f bestvideo*+bestaudio/best`. However, if multiple audiostreams is enabled (`--audio-multistreams`), the default format changes to `-f bestvideo+bestaudio/best`. Similarly, if ffmpeg is unavailable, or if you use yt-dlp to stream to `stdout` (`-o -`), the default becomes `-f best/bestvideo+bestaudio`. - -**Deprecation warning**: Latest versions of yt-dlp can stream multiple formats to the stdout simultaneously using ffmpeg. So, in future versions, the default for this will be set to `-f bv*+ba/b` similar to normal downloads. If you want to preserve the `-f b/bv+ba` setting, it is recommended to explicitly specify it in the configuration options. - -The general syntax for format selection is `-f FORMAT` (or `--format FORMAT`) where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download. - - -**tl;dr:** [navigate me to examples](#format-selection-examples). - - -The simplest case is requesting a specific format; e.g. with `-f 22` you can download the format with format code equal to 22. You can get the list of available format codes for particular video using `--list-formats` or `-F`. Note that these format codes are extractor specific. - -You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download the best quality format of a particular file extension served as a single file, e.g. `-f webm` will download the best quality format with the `webm` extension served as a single file. - -You can use `-f -` to interactively provide the format selector *for each video* - -You can also use special names to select particular edge case formats: - - - `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 (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]` - - `ba`, `bestaudio`: Select the best quality **audio-only** format. Equivalent to `best*[vcodec=none]` - - `ba*`, `bestaudio*`: Select the best quality format that **contains audio**. It may also contain video. Equivalent to `best*[acodec!=none]` ([Do not use!](https://github.com/yt-dlp/yt-dlp/issues/979#issuecomment-919629354)) - - `w*`, `worst*`: Select the worst quality format that contains either a video or an audio - - `w`, `worst`: Select the worst quality format that contains both video and audio. Equivalent to `worst*[vcodec!=none][acodec!=none]` - - `wv`, `worstvideo`: Select the worst quality video-only format. Equivalent to `worst*[acodec=none]` - - `wv*`, `worstvideo*`: Select the worst quality format that contains video. It may also contain audio. Equivalent to `worst*[vcodec!=none]` - - `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. - -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. - -If you want to download multiple videos, and they don't have the same formats available, you can specify the order of preference using slashes. Note that formats on the left hand side are preferred; e.g. `-f 22/17/18` will download format 22 if it's available, otherwise it will download format 17 if it's available, otherwise it will download format 18 if it's available, otherwise it will complain that no suitable formats are available for download. - -If you want to download several formats of the same video use a comma as a separator, e.g. `-f 22,17,18` will download all these three formats, of course if they are available. Or a more sophisticated example combined with the precedence feature: `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. - -You can merge the video and audio of multiple formats into a single file using `-f ++...` (requires ffmpeg installed); e.g. `-f bestvideo+bestaudio` will download the best video-only format, the best audio-only format and mux them together with ffmpeg. - -**Deprecation warning**: Since the *below* described behavior is complex and counter-intuitive, this will be removed and multistreams will be enabled by default in the future. A new operator will be instead added to limit formats to single audio/video - -Unless `--video-multistreams` is used, all formats with a video stream except the first one are ignored. Similarly, unless `--audio-multistreams` is used, all formats with an audio stream except the first one are ignored. E.g. `-f bestvideo+best+bestaudio --video-multistreams --audio-multistreams` will download and merge all 3 given formats. The resulting file will have 2 video streams and 2 audio streams. But `-f bestvideo+best+bestaudio --no-video-multistreams` will download and merge only `bestvideo` and `bestaudio`. `best` is ignored since another format containing a video stream (`bestvideo`) has already been selected. The order of the formats is therefore important. `-f best+bestaudio --no-audio-multistreams` will download only `best` while `-f bestaudio+best --no-audio-multistreams` will ignore `best` and download only `bestaudio`. - -## Filtering Formats - -You can also filter the video formats by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"` since filters without a selector are interpreted as `best`). - -The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `>=`, `=` (equals), `!=` (not equals): - - - `filesize`: The number of bytes, if known in advance - - `filesize_approx`: An estimate for the number of bytes - - `width`: Width of the video, if known - - `height`: Height of the video, if known - - `aspect_ratio`: Aspect ratio of the video, if known - - `tbr`: Average bitrate of audio and video in [kbps](## "1000 bits/sec") - - `abr`: Average audio bitrate in [kbps](## "1000 bits/sec") - - `vbr`: Average video bitrate in [kbps](## "1000 bits/sec") - - `asr`: Audio sampling rate in Hertz - - `fps`: Frame rate - - `audio_channels`: The number of audio channels - - `stretched_ratio`: `width:height` of the video's pixels, if not square - -Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains), `~=` (matches regex) and following string meta fields: - - - `url`: Video URL - - `ext`: File extension - - `acodec`: Name of the audio codec in use - - `vcodec`: Name of the video codec in use - - `container`: Name of the container format - - `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`) - - `language`: Language code - - `dynamic_range`: The dynamic range of the video - - `format_id`: A short description of the format - - `format`: A human-readable description of the format - - `format_note`: Additional info about the format - - `resolution`: Textual description of width and height - -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 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. - -Format selectors can also be grouped using parentheses; e.g. `-f "(mp4,webm)[height<480]"` will download the best pre-merged mp4 and webm formats with a height lower than 480. - -## Sorting Formats - -You can change the criteria for being considered the `best` by using `-S` (`--format-sort`). The general format for this is `--format-sort field1,field2...`. - -The available fields are: - - - `hasvid`: Gives priority to formats that have a video stream - - `hasaud`: Gives priority to formats that have an audio stream - - `ie_pref`: The format preference - - `lang`: The language preference as determined by the extractor (e.g. original language preferred over audio description) - - `quality`: The quality of the format - - `source`: The preference of the source - - `proto`: Protocol used for download (`https`/`ftps` > `http`/`ftp` > `m3u8_native`/`m3u8` > `http_dash_segments`> `websocket_frag` > `mms`/`rtsp` > `f4f`/`f4m`) - - `vcodec`: Video Codec (`av01` > `vp9.2` > `vp9` > `h265` > `h264` > `vp8` > `h263` > `theora` > other) - - `acodec`: Audio Codec (`flac`/`alac` > `wav`/`aiff` > `opus` > `vorbis` > `aac` > `mp4a` > `mp3` > `ac4` > `eac3` > `ac3` > `dts` > other) - - `codec`: Equivalent to `vcodec,acodec` - - `vext`: Video Extension (`mp4` > `mov` > `webm` > `flv` > other). If `--prefer-free-formats` is used, `webm` is preferred. - - `aext`: Audio Extension (`m4a` > `aac` > `mp3` > `ogg` > `opus` > `webm` > other). If `--prefer-free-formats` is used, the order changes to `ogg` > `opus` > `webm` > `mp3` > `m4a` > `aac` - - `ext`: Equivalent to `vext,aext` - - `filesize`: Exact filesize, if known in advance - - `fs_approx`: Approximate filesize - - `size`: Exact filesize if available, otherwise approximate filesize - - `height`: Height of video - - `width`: Width of video - - `res`: Video resolution, calculated as the smallest dimension. - - `fps`: Framerate of video - - `hdr`: The dynamic range of the video (`DV` > `HDR12` > `HDR10+` > `HDR10` > `HLG` > `SDR`) - - `channels`: The number of audio channels - - `tbr`: Total average bitrate in [kbps](## "1000 bits/sec") - - `vbr`: Average video bitrate in [kbps](## "1000 bits/sec") - - `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 behavior can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,vcodec,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 for hdr is `hdr:12`; i.e. Dolby Vision is not preferred. This choice was made since DV formats are not yet fully compatible with most devices. This may be changed in the future. - -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`. - -If you use the `-S`/`--format-sort` option multiple times, each subsequent sorting argument will be prepended to the previous one, and only the highest priority entry of any duplicated field will be preserved. E.g. `-S proto -S res` is equivalent to `-S res,proto`, and `-S res:720,fps -S vcodec,res:1080` is equivalent to `-S vcodec,res:1080,fps`. You can use `--format-sort-reset` to disregard any previously passed `-S`/`--format-sort` arguments and reset to the default order. - -**Tip**: You can use the `-v -F` to see how the formats have been sorted (worst to best). - -## Format Selection examples +### Persist downloads to your machine ```bash -# Download and merge the best video-only format and the best audio-only format, -# or download the best combined format if video-only format is not available -$ yt-dlp -f "bv+ba/b" - -# Download best format that contains video, -# and if it doesn't already have an audio stream, merge it with best audio-only format -$ yt-dlp -f "bv*+ba/b" - -# Same as above -$ yt-dlp - -# Download the best video-only format and the best audio-only format without merging them -# For this case, an output template should be used since -# by default, bestvideo and bestaudio will have the same file name. -$ yt-dlp -f "bv,ba" -o "%(title)s.f%(format_id)s.%(ext)s" - -# Download and merge the best format that has a video stream, -# and all audio-only formats into one file -$ yt-dlp -f "bv*+mergeall[vcodec=none]" --audio-multistreams - -# Download and merge the best format that has a video stream, -# and the best 2 audio-only formats into one file -$ yt-dlp -f "bv*+ba+ba.2" --audio-multistreams - - -# The following examples show the old method (without -S) of format selection -# and how to use -S to achieve a similar but (generally) better result - -# Download the worst video available (old method) -$ yt-dlp -f "wv*+wa/w" - -# Download the best video available but with the smallest resolution -$ yt-dlp -S "+res" - -# Download the smallest video available -$ yt-dlp -S "+size,+br" - - - -# Download the best mp4 video available, or the best video if no mp4 available -$ yt-dlp -f "bv*[ext=mp4]+ba[ext=m4a]/b[ext=mp4] / bv*+ba/b" - -# Download the best video with the best extension -# (For video, mp4 > mov > webm > flv. For audio, m4a > aac > mp3 ...) -$ yt-dlp -S "ext" - - - -# Download the best video available but no better than 480p, -# or the worst video if there is no video under 480p -$ yt-dlp -f "bv*[height<=480]+ba/b[height<=480] / wv*+ba/w" - -# Download the best video available with the largest height but no better than 480p, -# or the best video with the smallest resolution if there is no video under 480p -$ yt-dlp -S "height:480" - -# Download the best video available with the largest resolution but no better than 480p, -# or the best video with the smallest resolution if there is no video under 480p -# Resolution is determined by using the smallest dimension. -# So this works correctly for vertical videos as well -$ yt-dlp -S "res:480" - - - -# Download the best video (that also has audio) but no bigger than 50 MB, -# or the worst video (that also has audio) if there is no video under 50 MB -$ yt-dlp -f "b[filesize<50M] / w" - -# Download the largest video (that also has audio) but no bigger than 50 MB, -# or the smallest video (that also has audio) if there is no video under 50 MB -$ yt-dlp -f "b" -S "filesize:50M" - -# Download the best video (that also has audio) that is closest in size to 50 MB -$ yt-dlp -f "b" -S "filesize~50M" - - - -# Download best video available via direct link over HTTP/HTTPS protocol, -# or the best video available via any protocol if there is no such video -$ yt-dlp -f "(bv*+ba/b)[protocol^=http][protocol!*=dash] / (bv*+ba/b)" - -# Download best video available via the best protocol -# (https/ftps > http/ftp > m3u8_native > m3u8 > http_dash_segments ...) -$ yt-dlp -S "proto" - - - -# Download the best video with either h264 or h265 codec, -# or the best video if there is no such video -$ yt-dlp -f "(bv*[vcodec~='^((he|a)vc|h26[45])']+ba) / (bv*+ba/b)" - -# Download the best video with best codec no better than h264, -# or the best video with worst codec if there is no such video -$ yt-dlp -S "codec:h264" - -# Download the best video with worst codec no worse than h264, -# or the best video with best codec if there is no such video -$ yt-dlp -S "+codec:h264" - - - -# More complex examples - -# Download the best video no better than 720p preferring framerate greater than 30, -# or the worst video (still preferring framerate greater than 30) if there is no such video -$ yt-dlp -f "((bv*[fps>30]/bv*)[height<=720]/(wv*[fps>30]/wv*)) + ba / (b[fps>30]/b)[height<=720]/(w[fps>30]/w)" - -# Download the video with the largest resolution no better than 720p, -# or the video with the smallest resolution available if there is no such video, -# preferring larger framerate for formats with the same resolution -$ yt-dlp -S "res:720,fps" - - - -# Download the video with smallest resolution no worse than 480p, -# or the video with the largest resolution available if there is no such video, -# preferring better codec and then larger total bitrate for the same resolution -$ yt-dlp -S "+res:480,codec,br" +docker run -d \ + -p 8000:8000 \ + -v $(pwd)/downloads:/app/web/backend/downloads \ + --name yt-dlp-web \ + samive/yt-dlp-web:latest ``` -# MODIFYING METADATA - -The metadata obtained by the extractors can be modified by using `--parse-metadata` and `--replace-in-metadata` - -`--replace-in-metadata FIELDS REGEX REPLACE` is used to replace text in any metadata field using [Python regular expression](https://docs.python.org/3/library/re.html#regular-expression-syntax). [Backreferences](https://docs.python.org/3/library/re.html?highlight=backreferences#re.sub) can be used in the replace string for advanced use. - -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, a single field name, 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 these options preserve their relative order, allowing replacements to be made in parsed fields and vice versa. Also, any field thus created 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: - -* You can download an additional URL based on the metadata of the currently downloaded video. To do this, set the field `additional_urls` to the URL that you want to download. E.g. `--parse-metadata "description:(?Phttps?://www\.vimeo\.com/\d+)"` will download the first vimeo video found in the description - -* You can use this to change the metadata that is embedded in the media file. To do this, set the value of the corresponding field with a `meta_` prefix. For example, any value you set to `meta_description` field will be added to the `description` field in the file - you can use this to set a different "description" and "synopsis". To modify the metadata of individual streams, use the `meta_` prefix (e.g. `meta1_language`). Any value set to the `meta_` field will overwrite all default values. - -**Note**: Metadata modification happens before format selection, post-extraction and other post-processing operations. Some fields may be added or changed during these steps, overriding your changes. - -For reference, these are the fields yt-dlp adds by default to the file metadata: - -Metadata fields | From -:--------------------------|:------------------------------------------------ -`title` | `track` or `title` -`date` | `upload_date` -`description`, `synopsis` | `description` -`purl`, `comment` | `webpage_url` -`track` | `track_number` -`artist` | `artist`, `artists`, `creator`, `creators`, `uploader` or `uploader_id` -`composer` | `composer` or `composers` -`genre` | `genre`, `genres`, `categories` or `tags` -`album` | `album` or `series` -`album_artist` | `album_artist` or `album_artists` -`disc` | `disc_number` -`show` | `series` -`season_number` | `season_number` -`episode_id` | `episode` or `episode_id` -`episode_sort` | `episode_number` -`language` of each stream | the format's `language` - -**Note**: The file format may not support some of these fields - - -## Modifying metadata examples +### Stop / remove the container ```bash -# Interpret the title as "Artist - Title" -$ yt-dlp --parse-metadata "title:%(artist)s - %(title)s" - -# Regex example -$ yt-dlp --parse-metadata "description:Artist - (?P.+)" - -# Copy the episode field to the title field (with FROM and TO as single fields) -$ yt-dlp --parse-metadata "episode:title" - -# 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" --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.+)" --embed-metadata - -# Do not set any "synopsis" in the video metadata -$ yt-dlp --parse-metadata ":(?P)" - -# Remove "formats" field from the infojson by setting it to an empty string -$ yt-dlp --parse-metadata "video::(?P)" --write-info-json - -# Replace all spaces and "_" in title and uploader with a `-` -$ yt-dlp --replace-in-metadata "title,uploader" "[ _]" "-" - +docker stop yt-dlp-web +docker rm yt-dlp-web ``` -# EXTRACTOR ARGUMENTS +--- -Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=tv,mweb;formats=incomplete" --extractor-args "twitter:api=syndication"` +## Build from Source -Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"` +### Prerequisites -The following extractors use this feature: +- [Docker](https://docs.docker.com/get-docker/) installed -#### 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/_base.py](https://github.com/yt-dlp/yt-dlp/blob/415b4c9f955b1a0391204bd24a7132590e7b3bdb/yt_dlp/extractor/youtube/_base.py#L402-L409) for the 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 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_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_safari` is used for free accounts and `tv_downgraded,web_creator` 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_safari` -* `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`. These options are for testing purposes and don't skip any network requests. Neither is skipped by default; however, if a `player_js_version` value other than `actual` is used, then `webpage_skip=player_response` is implied -* `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 `main`, 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`). The default is to use what is prescribed by the site, and can be selected with `actual`. Using any other value will imply `webpage_skip=player_response` -* `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,max-depth`. Default is `all,all,all,all,all` - * A `max-depth` value of `1` will discard all replies, regardless of the `max-replies` or `max-replies-per-thread` values given - * E.g. `all,all,1000,10,2` will get a maximum of 1000 replies total, with up to 10 replies per thread, and only 2 levels of depth (i.e. top-level comments plus their immediate replies). `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total -* `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash, live adaptive https, and post-live m3u8), `missing_pot` (include formats that require a PO Token but are missing one) -* `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. By default, no API key is used -* `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning -* `data_sync_id`: Overrides the account Data Sync ID used in Innertube API requests. This may be needed if you are using an account with `youtube:player_skip=webpage,configs` or `youtubetab:skip=webpage` -* `visitor_data`: Overrides the Visitor Data used in Innertube API requests. This should be used with `player_skip=webpage,configs` and without cookies. Note: this may have adverse effects if used improperly. If a session from a browser is wanted, you should pass cookies instead (which contain the Visitor ID) -* `po_token`: Proof of Origin (PO) Token(s) to use. Comma-separated list of PO Tokens in the format `CLIENT.CONTEXT+PO_TOKEN`, e.g. `youtube:po_token=web.gvs+XXX,web.player=XXX,web_safari.gvs+YYY`. Context can be any of `gvs` (Google Video Server URLs), `player` (Innertube player request) or `subs` (Subtitles) -* `pot_trace`: Enable debug logging for PO Token fetching. Either `true` or `false` (default) -* `fetch_pot`: Policy to use for fetching a PO Token from providers. One of `always` (always try fetch a PO Token regardless if the client requires one for the given context), `never` (never fetch a PO Token), or `auto` (default; only fetch a PO Token if the client requires one for the given context) -* `jsc_trace`: Enable debug logging for JS Challenge fetching. Either `true` or `false` (default) -* `use_ad_playback_context`: Skip preroll ads to eliminate the mandatory wait period before download. Do NOT use this when passing premium account cookies to yt-dlp, as it will result in a loss of premium formats. Only effective with the `mweb` and `web_music` player clients. Either `true` or `false` (default) +### Build the image -#### youtube-ejs -* `jitless`: Run supported Javascript engines in JIT-less mode. Supported runtimes are `deno`, `node` and `bun`. Provides better security at the cost of performance/speed. Do note that `node` and `bun` are still considered insecure. Either `true` or `false` (default) - -#### youtubepot-webpo -* `bind_to_visitor_id`: Whether to use the Visitor ID instead of Visitor Data for caching WebPO tokens. Either `true` (default) or `false` - -#### 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) -* `approximate_date`: Extract approximate `upload_date` and `timestamp` in flat-playlist. This may cause date-based filters to be slightly off - -#### generic -* `fragment_query`: Passthrough any query in mpd/m3u8 manifest URLs to their fragments if no value is provided, or else apply the query string given as `fragment_query=VALUE`. Note that if the stream has an HLS AES-128 key, then the query parameters will be passed to the key URI as well, unless the `key_query` extractor-arg is passed, or unless an external key URI is provided via the `hls_key` extractor-arg. Does not apply to ffmpeg -* `variant_query`: Passthrough the master m3u8 URL query to its variant playlist URLs if no value is provided, or else apply the query string given as `variant_query=VALUE` -* `key_query`: Passthrough the master m3u8 URL query to its HLS AES-128 decryption key URI if no value is provided, or else apply the query string given as `key_query=VALUE`. Note that this will have no effect if the key URI is provided via the `hls_key` extractor-arg. Does not apply to ffmpeg -* `hls_key`: An HLS AES-128 key URI *or* key (as hex), and optionally the IV (as hex), in the form of `(URI|KEY)[,IV]`; e.g. `generic:hls_key=ABCDEF1234567980,0xFEDCBA0987654321`. Passing any of these values will force usage of the native HLS downloader and override the corresponding values found in the m3u8 playlist -* `is_live`: Bypass live HLS detection and manually set `live_status` - a value of `false` will set `not_live`, any other value (or no value) will set `is_live` -* `impersonate`: Target(s) to try and impersonate with the initial webpage request; e.g. `generic:impersonate=safari,chrome-110`. Use `generic:impersonate` to impersonate any available target, and use `generic:impersonate=false` to disable impersonation (default) - -#### vikichannel -* `video_types`: Types of videos to download - one or more of `episodes`, `movies`, `clips`, `trailers` - -#### youtubewebarchive -* `check_all`: Try to check more at the cost of more requests. One or more of `thumbnails`, `captures` - -#### gamejolt -* `comment_sort`: `hot` (default), `you` (cookies needed), `top`, `new` - choose comment sorting mode (on GameJolt's side) - -#### hotstar -* `res`: resolution to ignore - one or more of `sd`, `hd`, `fhd` -* `vcodec`: vcodec to ignore - one or more of `h264`, `h265`, `dvh265` -* `dr`: dynamic range to ignore - one or more of `sdr`, `hdr10`, `dv` - -#### instagram -* `app_id`: The value of the `X-IG-App-ID` header used for API requests. Default is the web app ID, `936619743392459` - -#### niconicochannelplus -* `max_comments`: Maximum number of comments to extract - default is `120` - -#### tiktok -* `api_hostname`: Hostname to use for mobile API calls, e.g. `api22-normal-c-alisg.tiktokv.com` -* `app_name`: Default app name to use with mobile API calls, e.g. `trill` -* `app_version`: Default app version to use with mobile API calls - should be set along with `manifest_app_version`, e.g. `34.1.2` -* `manifest_app_version`: Default numeric app version to use with mobile API calls, e.g. `2023401020` -* `aid`: Default app ID to use with mobile API calls, e.g. `1180` -* `app_info`: Enable mobile API extraction with one or more app info strings in the format of `/[app_name]/[app_version]/[manifest_app_version]/[aid]`, where `iid` is the unique app install ID. `iid` is the only required value; all other values and their `/` separators can be omitted, e.g. `tiktok:app_info=1234567890123456789` or `tiktok:app_info=123,456/trill///1180,789//34.0.1/340001` -* `device_id`: Enable mobile API extraction with a genuine device ID to be used with mobile API calls. Default is a random 19-digit string - -#### rokfinchannel -* `tab`: Which tab to download - one of `new`, `top`, `videos`, `podcasts`, `streams`, `stacks` - -#### twitter -* `api`: Select one of `graphql` (default), `legacy` or `syndication` as the API for tweet extraction. Has no effect if logged in - -#### stacommu, wrestleuniverse -* `device_id`: UUID value assigned by the website and used to enforce device limits for paid livestream content. Can be found in browser local storage - -#### twitch -* `client_id`: Client ID value to be sent with GraphQL requests, e.g. `twitch:client_id=kimne78kx3ncx6brgo4mv6wki5h1ko` - -#### nhkradirulive (NHK らじる★らじる LIVE) -* `area`: Which regional variation to extract. Valid areas are: `sapporo`, `sendai`, `tokyo`, `nagoya`, `osaka`, `hiroshima`, `matsuyama`, `fukuoka`. Defaults to `tokyo` - -#### nflplusreplay -* `type`: Type(s) of game replays to extract. Valid types are: `full_game`, `full_game_spanish`, `condensed_game` and `all_22`. You can use `all` to extract all available replay types, which is the default - -#### jiocinema -* `refresh_token`: The `refreshToken` UUID from browser local storage can be passed to extend the life of your login session when logging in with `token` as username and the `accessToken` from browser local storage as password - -#### jiosaavn -* `bitrate`: Audio bitrates to request. One or more of `16`, `32`, `64`, `128`, `320`. Default is `128,320` - -#### 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}_{codec}`, 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 codecs 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"` - -#### bilibili -* `prefer_multi_flv`: Prefer extracting flv formats over mp4 for older videos that still provide legacy formats - -#### sonylivseries -* `sort_order`: Episode sort order for series extraction - one of `asc` (ascending, oldest first) or `desc` (descending, newest first). Default is `asc` - -#### tver -* `backend`: Backend API to use for extraction - one of `streaks` (default) or `brightcove` (deprecated) - -#### vimeo -* `client`: Client to extract video data from. The currently available clients are `android`, `ios`, `macos` and `web`. Only one client can be used. The `macos` client is used by default, but the `web` client is used when logged-in. The `web` client only works with account cookies or login credentials. The `android` and `ios` clients only work with previously cached OAuth tokens -* `original_format_policy`: Policy for when to try extracting original formats. One of `always`, `never`, or `auto`. The default `auto` policy tries to avoid exceeding the web client's API rate-limit by only making an extra request when Vimeo publicizes the video's downloadability - -**Note**: These options may be changed/removed in the future without concern for backward compatibility - - - - -# 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 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 - postprocessor/ - myplugin.py - -yt-dlp looks for these `yt_dlp_plugins` namespace folders in many locations (see below) and loads in plugins from **all** of them. -Set the environment variable `YTDLP_NO_PLUGINS` to something nonempty to disable loading plugins entirely. - -See the [wiki for some known plugins](https://github.com/yt-dlp/yt-dlp/wiki/Plugins) - -## Installing Plugins - -Plugins can be installed using various methods and locations. - -1. **Configuration directories**: - Plugin packages (containing a `yt_dlp_plugins` namespace folder) can be dropped into the following standard [configuration locations](#configuration): - * **User Plugins** - * `${XDG_CONFIG_HOME}/yt-dlp/plugins//yt_dlp_plugins/` (recommended on Linux/macOS) - * `${XDG_CONFIG_HOME}/yt-dlp-plugins//yt_dlp_plugins/` - * `${APPDATA}/yt-dlp/plugins//yt_dlp_plugins/` (recommended on Windows) - * `${APPDATA}/yt-dlp-plugins//yt_dlp_plugins/` - * `~/.yt-dlp/plugins//yt_dlp_plugins/` - * `~/yt-dlp-plugins//yt_dlp_plugins/` - * **System Plugins** - * `/etc/yt-dlp/plugins//yt_dlp_plugins/` - * `/etc/yt-dlp-plugins//yt_dlp_plugins/` -2. **Executable location**: Plugin packages can similarly be installed in a `yt-dlp-plugins` directory under the executable location (recommended for portable installations): - * Binary: where `/yt-dlp.exe`, `/yt-dlp-plugins//yt_dlp_plugins/` - * Source: where `/yt_dlp/__main__.py`, `/yt-dlp-plugins//yt_dlp_plugins/` - -3. **pip and other locations in `PYTHONPATH`** - * Plugin packages can be installed and managed using `pip`. See [yt-dlp-sample-plugins](https://github.com/yt-dlp/yt-dlp-sample-plugins) for an example. - * Note: plugin files between plugin packages installed with pip must have unique filenames. - * Any path in `PYTHONPATH` is searched in for the `yt_dlp_plugins` namespace folder. - * Note: This does not apply for Pyinstaller builds. - - -`.zip`, `.egg` and `.whl` archives containing a `yt_dlp_plugins` namespace folder in their root are also supported as plugin packages. - -* e.g. `${XDG_CONFIG_HOME}/yt-dlp/plugins/mypluginpkg.zip` where `mypluginpkg.zip` contains `yt_dlp_plugins//myplugin.py` - -Run yt-dlp with `--verbose` to check if the plugin has been loaded. - -## 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 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. - -If you are a plugin author, add [yt-dlp-plugins](https://github.com/topics/yt-dlp-plugins) as a topic to your repository for discoverability. - -See the [Developer Instructions](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#developer-instructions) on how to write and test an extractor. - -# 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. - -From a Python program, you can embed yt-dlp in a more powerful fashion, like this: - -```python -from yt_dlp import YoutubeDL - -URLS = ['https://www.youtube.com/watch?v=BaW_jenozKc'] -with YoutubeDL() as ydl: - ydl.download(URLS) +```bash +git clone https://github.com/YOUR_GITHUB_USERNAME/yt-dlp-web.git +cd yt-dlp-web +docker build -t yt-dlp-web . ``` -Most likely, you'll want to use various options. For a list of options available, have a look at [`yt_dlp/YoutubeDL.py`](yt_dlp/YoutubeDL.py#L183) or `help(yt_dlp.YoutubeDL)` in a Python shell. If you are already familiar with the CLI, you can use [`devscripts/cli_to_api.py`](https://github.com/yt-dlp/yt-dlp/blob/master/devscripts/cli_to_api.py) to translate any CLI switches to `YoutubeDL` params. +### Run the image -**Tip**: If you are porting your code from youtube-dl to yt-dlp, one important point to look out for is that we do not guarantee the return value of `YoutubeDL.extract_info` to be json serializable, or even be a dictionary. It will be dictionary-like, but if you want to ensure it is a serializable dictionary, pass it through `YoutubeDL.sanitize_info` as shown in the [example below](#extracting-information) - -## Embedding examples - -#### Extracting information - -```python -import json -import yt_dlp - -URL = 'https://www.youtube.com/watch?v=BaW_jenozKc' - -# ℹ️ See help(yt_dlp.YoutubeDL) for a list of available options and public functions -ydl_opts = {} -with yt_dlp.YoutubeDL(ydl_opts) as ydl: - info = ydl.extract_info(URL, download=False) - - # ℹ️ ydl.sanitize_info makes the info json-serializable - print(json.dumps(ydl.sanitize_info(info))) -``` -#### Download using an info-json - -```python -import yt_dlp - -INFO_FILE = 'path/to/video.info.json' - -with yt_dlp.YoutubeDL() as ydl: - error_code = ydl.download_with_info_file(INFO_FILE) - -print('Some videos failed to download' if error_code - else 'All videos successfully downloaded') +```bash +docker run -d -p 8000:8000 --name yt-dlp-web yt-dlp-web ``` -#### Extract audio +Open **http://localhost:8000**. -```python -import yt_dlp +--- -URLS = ['https://www.youtube.com/watch?v=BaW_jenozKc'] +## Run without Docker (Development) -ydl_opts = { - 'format': 'm4a/bestaudio/best', - # ℹ️ See help(yt_dlp.postprocessor) for a list of available Postprocessors and their arguments - 'postprocessors': [{ # Extract audio using ffmpeg - 'key': 'FFmpegExtractAudio', - 'preferredcodec': 'm4a', - }] -} +### Prerequisites -with yt_dlp.YoutubeDL(ydl_opts) as ydl: - error_code = ydl.download(URLS) +- Python 3.10+ +- ffmpeg installed and on PATH ([download](https://ffmpeg.org/download.html)) + +### Setup + +```bash +# Install yt-dlp from source +pip install -e ".[default]" + +# Install backend dependencies +pip install fastapi "uvicorn[standard]" httpx + +# Start the server +python -m uvicorn web.backend.main:app --reload --port 8000 ``` -#### Filter videos +Open **http://localhost:8000**. -```python -import yt_dlp +--- -URLS = ['https://www.youtube.com/watch?v=BaW_jenozKc'] +## Usage Guide -def longer_than_a_minute(info, *, incomplete): - """Download only videos longer than a minute (or with unknown duration)""" - duration = info.get('duration') - if duration and duration < 60: - return 'The video is too short' +1. **Paste a URL** — Paste any YouTube (or supported site) link into the input field and click **Fetch** +2. **Review video info** — Thumbnail, title, uploader, duration, views, likes, and upload date are shown +3. **Select a format** — Choose from the dropdown (highest quality is pre-selected) +4. **Download** — Click the **Download** button and watch the live progress bar +5. **Cancel** — Click **Cancel** at any time to stop the download -ydl_opts = { - 'match_filter': longer_than_a_minute, -} +### YouTube authentication (optional) -with yt_dlp.YoutubeDL(ydl_opts) as ydl: - error_code = ydl.download(URLS) +Some videos require sign-in. Export your cookies using the [Get cookies.txt LOCALLY](https://chrome.google.com/webstore/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc) browser extension and mount them: + +```bash +docker run -d \ + -p 8000:8000 \ + -v $(pwd)/cookies.txt:/app/web/backend/cookies.txt:ro \ + --name yt-dlp-web \ + samive/yt-dlp-web:latest ``` -#### Adding logger and progress hook +> **Note:** Using cookies with Chrome on Windows may cause issues due to DPAPI encryption. Firefox or Edge cookies work more reliably. -```python -import yt_dlp +--- -URLS = ['https://www.youtube.com/watch?v=BaW_jenozKc'] +## Publish to Docker Hub -class MyLogger: - def debug(self, msg): - # For compatibility with youtube-dl, both debug and info are passed into debug - # You can distinguish them by the prefix '[debug] ' - if msg.startswith('[debug] '): - pass - else: - self.info(msg) +### 1. Create a Docker Hub account - def info(self, msg): - pass +Sign up at [hub.docker.com](https://hub.docker.com) and create a public repository named `yt-dlp-web`. - def warning(self, msg): - pass +### 2. Log in from terminal - def error(self, msg): - print(msg) - - -# ℹ️ See "progress_hooks" in help(yt_dlp.YoutubeDL) -def my_hook(d): - if d['status'] == 'finished': - print('Done downloading, now post-processing ...') - - -ydl_opts = { - 'logger': MyLogger(), - 'progress_hooks': [my_hook], -} - -with yt_dlp.YoutubeDL(ydl_opts) as ydl: - ydl.download(URLS) +```bash +docker login ``` -#### Add a custom PostProcessor +### 3. Build and tag the image -```python -import yt_dlp - -URLS = ['https://www.youtube.com/watch?v=BaW_jenozKc'] - -# ℹ️ See help(yt_dlp.postprocessor.PostProcessor) -class MyCustomPP(yt_dlp.postprocessor.PostProcessor): - def run(self, info): - self.to_screen('Doing stuff') - return [], info - - -with yt_dlp.YoutubeDL() as ydl: - # ℹ️ "when" can take any value in yt_dlp.utils.POSTPROCESS_WHEN - ydl.add_post_processor(MyCustomPP(), when='pre_process') - ydl.download(URLS) +```bash +docker build -t samive/yt-dlp-web:latest . ``` +### 4. Push to Docker Hub -#### Use a custom format selector - -```python -import yt_dlp - -URLS = ['https://www.youtube.com/watch?v=BaW_jenozKc'] - -def format_selector(ctx): - """ Select the best video and the best audio that won't result in an mkv. - NOTE: This is just an example and does not handle all cases """ - - # formats are already sorted worst to best - formats = ctx.get('formats')[::-1] - - # acodec='none' means there is no audio - best_video = next(f for f in formats - if f['vcodec'] != 'none' and f['acodec'] == 'none') - - # find compatible audio extension - audio_ext = {'mp4': 'm4a', 'webm': 'webm'}[best_video['ext']] - # vcodec='none' means there is no video - best_audio = next(f for f in formats if ( - f['acodec'] != 'none' and f['vcodec'] == 'none' and f['ext'] == audio_ext)) - - # These are the minimum required fields for a merged format - yield { - 'format_id': f'{best_video["format_id"]}+{best_audio["format_id"]}', - 'ext': best_video['ext'], - 'requested_formats': [best_video, best_audio], - # Must be + separated list of protocols - 'protocol': f'{best_video["protocol"]}+{best_audio["protocol"]}' - } - - -ydl_opts = { - 'format': format_selector, -} - -with yt_dlp.YoutubeDL(ydl_opts) as ydl: - ydl.download(URLS) +```bash +docker push samive/yt-dlp-web:latest ``` +### 5. (Optional) Tag a version -# CHANGES FROM YOUTUBE-DL +```bash +docker tag samive/yt-dlp-web:latest samive/yt-dlp-web:1.0.0 +docker push samive/yt-dlp-web:1.0.0 +``` -### New features +Anyone can now pull and run your image with: -* Forked from [**yt-dlc@f9401f2**](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee) and merged with [**youtube-dl@a08f2b7**](https://github.com/ytdl-org/youtube-dl/commit/a08f2b7e4567cdc50c0614ee0a4ffdff49b8b6e6) ([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21)) +```bash +docker pull samive/yt-dlp-web:latest +``` -* **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in YouTube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API +--- -* **[Format Sorting](#sorting-formats)**: The default format sorting options have been changed so that higher resolution and better codecs will be now preferred instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection than what is possible by simply using `--format` ([examples](#format-selection-examples)) +## Tech Stack -* **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--write-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, playlist infojson etc. See [#31](https://github.com/yt-dlp/yt-dlp/pull/31) for details. +- **Backend** — Python, [FastAPI](https://fastapi.tiangolo.com/), [yt-dlp](https://github.com/yt-dlp/yt-dlp) +- **Frontend** — Vanilla HTML/CSS/JS (no framework) +- **Container** — Docker with ffmpeg -* **YouTube improvements**: - * Supports Clips, Stories (`ytstories:`), Search (including filters)**\***, YouTube Music Search, Channel-specific search, Search prefix (`ytsearch:`)**\***, Mixes, and Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`, `:ytnotif`) - * Fix for [n-sig based throttling](https://github.com/ytdl-org/youtube-dl/issues/29326) **\*** - * Download livestreams from the start using `--live-from-start` (*experimental*) - * Channel URLs download all uploads of the channel, including shorts and live +--- -* **Cookies from browser**: Cookies can be automatically extracted from all major web browsers using `--cookies-from-browser BROWSER[+KEYRING][:PROFILE][::CONTAINER]` +## License -* **Download time range**: Videos can be downloaded partially based on either timestamps or chapters using `--download-sections` - -* **Split video by chapters**: Videos can be split into multiple files based on chapters using `--split-chapters` - -* **Multi-threaded fragment downloads**: Download multiple fragments of m3u8/mpd videos in parallel. Use `--concurrent-fragments` (`-N`) option to set the number of threads used - -* **Aria2c with HLS/DASH**: You can use `aria2c` as the external downloader for DASH(mpd) and HLS(m3u8) formats - -* **New and fixed extractors**: Many new extractors have been added and a lot of existing ones have been fixed. See the [changelog](Changelog.md) or the [list of supported sites](supportedsites.md) - -* **New MSOs**: Philo, Spectrum, SlingTV, Cablevision, RCN etc. - -* **Subtitle extraction from manifests**: Subtitles can be extracted from streaming media manifests. See [commit/be6202f](https://github.com/yt-dlp/yt-dlp/commit/be6202f12b97858b9d716e608394b51065d0419f) for details - -* **Multiple paths and output templates**: You can give different [output templates](#output-template) and download paths for different types of files. You can also set a temporary path where intermediary files are downloaded to using `--paths` (`-P`) - -* **Portable Configuration**: Configuration files are automatically loaded from the home and root directories. See [CONFIGURATION](#configuration) for details - -* **Output template improvements**: Output templates can now have date-time formatting, numeric offsets, object traversal etc. See [output template](#output-template) for details. Even more advanced operations can also be done with the help of `--parse-metadata` and `--replace-in-metadata` - -* **Other new options**: Many new options have been added such as `--alias`, `--print`, `--concat-playlist`, `--wait-for-video`, `--retry-sleep`, `--sleep-requests`, `--convert-thumbnails`, `--force-download-archive`, `--force-overwrites`, `--break-match-filters` etc - -* **Improvements**: Regex and other operators in `--format`/`--match-filters`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc - -* **Plugins**: Extractors and PostProcessors can be loaded from an external file. See [plugins](#plugins) for details - -* **Self updater**: The releases can be updated using `yt-dlp -U`, and downgraded using `--update-to` if required - -* **Automated builds**: [Nightly/master builds](#update-channels) can be used with `--update-to nightly` and `--update-to master` - -See [changelog](Changelog.md) or [commits](https://github.com/yt-dlp/yt-dlp/commits) for the full list of changes - -Features marked with a **\*** have been back-ported to youtube-dl - -### Differences in default behavior - -Some of yt-dlp's default options are different from that of youtube-dl and youtube-dlc: - -* yt-dlp supports only [Python 3.10+](## "Windows 8"), and will remove support for more versions as they [become EOL](https://devguide.python.org/versions/#python-release-cycle); while [youtube-dl still supports Python 2.6+ and 3.2+](https://github.com/ytdl-org/youtube-dl/issues/30568#issue-1118238743) -* The options `--auto-number` (`-A`), `--title` (`-t`) and `--literal` (`-l`), no longer work. See [removed options](#Removed) for details -* `avconv` is not supported as an alternative to `ffmpeg` -* yt-dlp stores config files in slightly different locations to youtube-dl. See [CONFIGURATION](#configuration) for a list of correct locations -* The default [output template](#output-template) is `%(title)s [%(id)s].%(ext)s`. There is no real reason for this change. This was changed before yt-dlp was ever made public and now there are no plans to change it back to `%(title)s-%(id)s.%(ext)s`. Instead, you may use `--compat-options filename` -* The default [format sorting](#sorting-formats) is different from youtube-dl and prefers higher resolution and better codecs rather than higher bitrates. You can use the `--format-sort` option to change this to any order you prefer, or use `--compat-options format-sort` to use youtube-dl's sorting order. Older versions of yt-dlp preferred VP9 due to its broader compatibility; you can use `--compat-options prefer-vp9-sort` to revert to that format sorting preference. These two compat options cannot be used together -* The default format selector is `bv*+ba/b`. This means that if a combined video + audio format that is better than the best video-only format is found, the former will be preferred. Use `-f bv+ba/b` or `--compat-options format-spec` to revert this -* Unlike youtube-dlc, yt-dlp does not allow merging multiple audio/video streams into one file by default (since this conflicts with the use of `-f bv*+ba`). If needed, this feature must be enabled using `--audio-multistreams` and `--video-multistreams`. You can also use `--compat-options multistreams` to enable both -* `--no-abort-on-error` is enabled by default. Use `--abort-on-error` or `--compat-options abort-on-error` to abort on errors instead -* When writing metadata files such as thumbnails, description or infojson, the same information (if available) is also written for playlists. Use `--no-write-playlist-metafiles` or `--compat-options no-playlist-metafiles` to not write these files -* `--add-metadata` attaches the `infojson` to `mkv` files in addition to writing the metadata when used with `--write-info-json`. Use `--no-embed-info-json` or `--compat-options no-attach-info-json` to revert this -* Some metadata are embedded into different fields when using `--add-metadata` as compared to youtube-dl. Most notably, `comment` field contains the `webpage_url` and `synopsis` contains the `description`. You can [use `--parse-metadata`](#modifying-metadata) to modify this to your liking or use `--compat-options embed-metadata` to revert this -* `playlist_index` behaves differently when used with options like `--playlist-reverse` and `--playlist-items`. See [#302](https://github.com/yt-dlp/yt-dlp/issues/302) for details. You can use `--compat-options playlist-index` if you want to keep the earlier behavior -* The output of `-F` is listed in a new format. Use `--compat-options list-formats` to revert this -* Live chats (if available) are considered as subtitles. Use `--sub-langs all,-live_chat` to download all subtitles except live chat. You can also use `--compat-options no-live-chat` to prevent any live chat/danmaku from downloading -* YouTube channel URLs download all uploads of the channel. To download only the videos in a specific tab, pass the tab's URL. If the channel does not show the requested tab, an error will be raised. Also, `/live` URLs raise an error if there are no live videos instead of silently downloading the entire channel. You may use `--compat-options no-youtube-channel-redirect` to revert all these redirections -* Unavailable videos are also listed for YouTube playlists. Use `--compat-options no-youtube-unavailable-videos` to remove this -* The upload dates extracted from YouTube are in UTC. -* If `ffmpeg` is used as the downloader, the downloading and merging of formats happen in a single step when possible. Use `--compat-options no-direct-merge` to revert this -* Thumbnail embedding in `mp4` is done with mutagen if possible. Use `--compat-options embed-thumbnail-atomicparsley` to force the use of AtomicParsley instead -* Some internal metadata such as filenames are removed by default from the infojson. Use `--no-clean-infojson` or `--compat-options no-clean-infojson` to revert this -* When `--embed-subs` and `--write-subs` are used together, the subtitles are written to disk and also embedded in the media file. You can use just `--embed-subs` to embed the subs and automatically delete the separate file. See [#630 (comment)](https://github.com/yt-dlp/yt-dlp/issues/630#issuecomment-893659460) for more info. `--compat-options no-keep-subs` can be used to revert this -* `certifi` will be used for SSL root certificates, if installed. If you want to use system certificates (e.g. self-signed), use `--compat-options no-certifi` -* yt-dlp's sanitization of invalid characters in filenames is different/smarter than in youtube-dl. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior -* ~~yt-dlp tries to parse the external downloader outputs into the standard progress output if possible (Currently implemented: [aria2c](https://github.com/yt-dlp/yt-dlp/issues/5931)). You can use `--compat-options no-external-downloader-progress` to get the downloader output as-is~~ -* yt-dlp versions between 2021.09.01 and 2023.01.02 applies `--match-filters` to nested playlists. This was an unintentional side-effect of [8f18ac](https://github.com/yt-dlp/yt-dlp/commit/8f18aca8717bb0dd49054555af8d386e5eda3a88) and is fixed in [d7b460](https://github.com/yt-dlp/yt-dlp/commit/d7b460d0e5fc710950582baed2e3fc616ed98a80). Use `--compat-options playlist-match-filter` to revert this -* yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values -* yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests. -* The sub-modules `swfinterp`, `casefold` are removed. -* Passing `--simulate` (or calling `extract_info` with `download=False`) no longer alters the default format selection. See [#9843](https://github.com/yt-dlp/yt-dlp/issues/9843) for details. -* yt-dlp no longer applies the server modified time to downloaded files by default. Use `--mtime` or `--compat-options mtime-by-default` to revert this. - -For convenience, there are some compat option aliases available to use: - -* `--compat-options all`: Use all compat options (**Do NOT use this!**) -* `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext,-prefer-vp9-sort` -* `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext,-prefer-vp9-sort` -* `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization` -* `--compat-options 2022`: Same as `--compat-options 2023,playlist-match-filter,no-external-downloader-progress,prefer-legacy-http-handler,manifest-filesize-approx` -* `--compat-options 2023`: Same as `--compat-options 2024,prefer-vp9-sort` -* `--compat-options 2024`: Same as `--compat-options 2025,mtime-by-default` -* `--compat-options 2025`: Currently does nothing. Use this to enable all future compat options - -Using one of the yearly compat option aliases will pin yt-dlp's default behavior to what it was at the *end* of that calendar year. - -The following compat options restore vulnerable behavior from before security patches: - -* `--compat-options allow-unsafe-ext`: Allow files with any extension (including unsafe ones) to be downloaded ([GHSA-79w7-vh3h-8g4j]()) - - > :warning: Only use if a valid file download is rejected because its extension is detected as uncommon - > - > **This option can enable remote code execution! Consider [opening an issue]() instead!** - -### Deprecated options - -These are all the deprecated options and the current alternative to achieve the same effect - -#### Almost redundant options -While these options are almost the same as their new counterparts, there are some differences that prevents them being redundant - - -j, --dump-json --print "%()j" - -F, --list-formats --print formats_table - --list-thumbnails --print thumbnails_table --print playlist:thumbnails_table - --list-subs --print automatic_captions_table --print subtitles_table - -#### Redundant options -While these options are redundant, they are still expected to be used due to their ease of use - - --get-description --print description - --get-duration --print duration_string - --get-filename --print filename - --get-format --print format - --get-id --print id - --get-thumbnail --print thumbnail - -e, --get-title --print title - -g, --get-url --print urls - --match-title REGEX --match-filters "title ~= (?i)REGEX" - --reject-title REGEX --match-filters "title !~= (?i)REGEX" - --min-views COUNT --match-filters "view_count >=? COUNT" - --max-views COUNT --match-filters "view_count <=? COUNT" - --break-on-reject Use --break-match-filters - --user-agent UA --add-headers "User-Agent:UA" - --referer URL --add-headers "Referer:URL" - --playlist-start NUMBER -I NUMBER: - --playlist-end NUMBER -I :NUMBER - --playlist-reverse -I ::-1 - --no-playlist-reverse Default - --no-colors --color no_color - -#### Not recommended -While these options still work, their use is not recommended since there are other alternatives to achieve the same - - --force-generic-extractor --ies generic,default - --exec-before-download CMD --exec "before_dl:CMD" - --no-exec-before-download --no-exec - --all-formats -f all - --all-subs --sub-langs all --write-subs - --print-json -j --no-simulate - --autonumber-size NUMBER Use string formatting, e.g. %(autonumber)03d - --autonumber-start NUMBER Use internal field formatting like %(autonumber+NUMBER)s - --id -o "%(id)s.%(ext)s" - --metadata-from-title FORMAT --parse-metadata "%(title)s:FORMAT" - --hls-prefer-native --downloader "m3u8:native" - --hls-prefer-ffmpeg --downloader "m3u8:ffmpeg" - --list-formats-old --compat-options list-formats (Alias: --no-list-formats-as-table) - --list-formats-as-table --compat-options -list-formats [Default] - --geo-bypass --xff "default" - --no-geo-bypass --xff "never" - --geo-bypass-country CODE --xff CODE - --geo-bypass-ip-block IP_BLOCK --xff IP_BLOCK - -#### Developer options -These options are not intended to be used by the end-user - - --test Download only part of video for testing extractors - --load-pages Load pages dumped by --write-pages - --allow-unplayable-formats List unplayable formats also - --no-allow-unplayable-formats Default - -#### Old aliases -These are aliases that are no longer documented for various reasons - - --clean-infojson --clean-info-json - --force-write-download-archive --force-write-archive - --no-clean-infojson --no-clean-info-json - --no-split-tracks --no-split-chapters - --no-write-srt --no-write-subs - --prefer-unsecure --prefer-insecure - --rate-limit RATE --limit-rate RATE - --split-tracks --split-chapters - --srt-lang LANGS --sub-langs LANGS - --trim-file-names LENGTH --trim-filenames LENGTH - --write-srt --write-subs - --yes-overwrites --force-overwrites - -#### Sponskrub Options -Support for [SponSkrub](https://github.com/faissaloo/SponSkrub) has been removed in favor of the `--sponsorblock` options - - --sponskrub --sponsorblock-mark all - --no-sponskrub --no-sponsorblock - --sponskrub-cut --sponsorblock-remove all - --no-sponskrub-cut --sponsorblock-remove -all - --sponskrub-force Not applicable - --no-sponskrub-force Not applicable - --sponskrub-location Not applicable - --sponskrub-args Not applicable - -#### No longer supported -These options may no longer work as intended - - --prefer-avconv avconv is not officially supported by yt-dlp (Alias: --no-prefer-ffmpeg) - --prefer-ffmpeg Default (Alias: --no-prefer-avconv) - -C, --call-home Not implemented - --no-call-home Default - --include-ads No longer supported - --no-include-ads Default - --write-annotations No supported site has annotations now - --no-write-annotations Default - --avconv-location Removed alias for --ffmpeg-location - --cn-verification-proxy URL Removed alias for --geo-verification-proxy URL - --dump-headers Removed alias for --print-traffic - --dump-intermediate-pages Removed alias for --dump-pages - --youtube-skip-dash-manifest Removed alias for --extractor-args "youtube:skip=dash" (Alias: --no-youtube-include-dash-manifest) - --youtube-skip-hls-manifest Removed alias for --extractor-args "youtube:skip=hls" (Alias: --no-youtube-include-hls-manifest) - --youtube-include-dash-manifest Default (Alias: --no-youtube-skip-dash-manifest) - --youtube-include-hls-manifest Default (Alias: --no-youtube-skip-hls-manifest) - --youtube-print-sig-code Removed testing functionality - --dump-user-agent No longer supported - --xattr-set-filesize No longer supported - --compat-options seperate-video-versions No longer needed - --compat-options no-youtube-prefer-utc-upload-date No longer supported - -#### Removed -These options were deprecated since 2014 and have now been entirely removed - - -A, --auto-number -o "%(autonumber)s-%(id)s.%(ext)s" - -t, -l, --title, --literal -o "%(title)s-%(id)s.%(ext)s" - - -# CONTRIBUTING -See [CONTRIBUTING.md](CONTRIBUTING.md#contributing-to-yt-dlp) for instructions on [Opening an Issue](CONTRIBUTING.md#opening-an-issue) and [Contributing code to the project](CONTRIBUTING.md#developer-instructions) - -# WIKI -See the [Wiki](https://github.com/yt-dlp/yt-dlp/wiki) for more information +This project uses yt-dlp which is licensed under [The Unlicense](LICENSE). diff --git a/test/__init__.py b/test/__init__.py deleted file mode 100644 index e69de29bb..000000000 diff --git a/test/conftest.py b/test/conftest.py deleted file mode 100644 index 9d3198619..000000000 --- a/test/conftest.py +++ /dev/null @@ -1,94 +0,0 @@ -import inspect - -import pytest - -from yt_dlp.networking import RequestHandler -from yt_dlp.networking.common import _REQUEST_HANDLERS -from yt_dlp.utils._utils import _YDLLogger as FakeLogger - - -@pytest.fixture -def handler(request): - RH_KEY = getattr(request, 'param', None) - if not RH_KEY: - return - if inspect.isclass(RH_KEY) and issubclass(RH_KEY, RequestHandler): - handler = RH_KEY - elif RH_KEY in _REQUEST_HANDLERS: - handler = _REQUEST_HANDLERS[RH_KEY] - else: - pytest.skip(f'{RH_KEY} request handler is not available') - - class HandlerWrapper(handler): - RH_KEY = handler.RH_KEY - - def __init__(self, **kwargs): - super().__init__(logger=FakeLogger, **kwargs) - - return HandlerWrapper - - -@pytest.fixture(autouse=True) -def skip_handler(request, handler): - """usage: pytest.mark.skip_handler('my_handler', 'reason')""" - for marker in request.node.iter_markers('skip_handler'): - if marker.args[0] == handler.RH_KEY: - pytest.skip(marker.args[1] if len(marker.args) > 1 else '') - - -@pytest.fixture(autouse=True) -def skip_handler_if(request, handler): - """usage: pytest.mark.skip_handler_if('my_handler', lambda request: True, 'reason')""" - for marker in request.node.iter_markers('skip_handler_if'): - if marker.args[0] == handler.RH_KEY and marker.args[1](request): - pytest.skip(marker.args[2] if len(marker.args) > 2 else '') - - -@pytest.fixture(autouse=True) -def skip_handlers_if(request, handler): - """usage: pytest.mark.skip_handlers_if(lambda request, handler: True, 'reason')""" - for marker in request.node.iter_markers('skip_handlers_if'): - if handler and marker.args[0](request, handler): - pytest.skip(marker.args[1] if len(marker.args) > 1 else '') - - -@pytest.fixture(autouse=True) -def handler_flaky(request, handler): - """Mark a certain handler as being flaky. - - This will skip the test if pytest does not get run using `--allow-flaky` - - usage: - pytest.mark.handler_flaky('my_handler', os.name != 'nt', reason='reason') - """ - for marker in request.node.iter_markers(handler_flaky.__name__): - if ( - marker.args[0] == handler.RH_KEY - and (not marker.args[1:] or any(marker.args[1:])) - and request.config.getoption('disallow_flaky') - ): - reason = marker.kwargs.get('reason') - pytest.skip(f'flaky: {reason}' if reason else 'flaky') - - -def pytest_addoption(parser, pluginmanager): - parser.addoption( - '--disallow-flaky', - action='store_true', - help='disallow flaky tests from running.', - ) - - -def pytest_configure(config): - config.addinivalue_line( - 'markers', 'skip_handler(handler): skip test for the given handler', - ) - config.addinivalue_line( - 'markers', 'skip_handler_if(handler): skip test for the given handler if condition is true', - ) - config.addinivalue_line( - 'markers', 'skip_handlers_if(handler): skip test for handlers when the condition is true', - ) - config.addinivalue_line( - 'markers', 'handler_flaky(handler): mark handler as flaky if condition is true', - ) diff --git a/test/helper.py b/test/helper.py deleted file mode 100644 index 4f65a09d1..000000000 --- a/test/helper.py +++ /dev/null @@ -1,384 +0,0 @@ -import errno -import hashlib -import json -import os.path -import re -import ssl -import sys -import types - -import yt_dlp.extractor -from yt_dlp import YoutubeDL -from yt_dlp.utils import preferredencoding, try_call, write_string, find_available_port - -if 'pytest' in sys.modules: - import pytest - is_download_test = pytest.mark.download -else: - def is_download_test(test_class): - return test_class - - -def get_params(override=None): - PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), - 'parameters.json') - LOCAL_PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), - 'local_parameters.json') - with open(PARAMETERS_FILE, encoding='utf-8') as pf: - parameters = json.load(pf) - if os.path.exists(LOCAL_PARAMETERS_FILE): - with open(LOCAL_PARAMETERS_FILE, encoding='utf-8') as pf: - parameters.update(json.load(pf)) - if override: - parameters.update(override) - return parameters - - -def try_rm(filename): - """ Remove a file if it exists """ - try: - os.remove(filename) - except OSError as ose: - if ose.errno != errno.ENOENT: - raise - - -def report_warning(message, *args, **kwargs): - """ - Print the message to stderr, it will be prefixed with 'WARNING:' - If stderr is a tty file the 'WARNING:' will be colored - """ - if sys.stderr.isatty() and os.name != 'nt': - _msg_header = '\033[0;33mWARNING:\033[0m' - else: - _msg_header = 'WARNING:' - output = f'{_msg_header} {message}\n' - if 'b' in getattr(sys.stderr, 'mode', ''): - output = output.encode(preferredencoding()) - sys.stderr.write(output) - - -class FakeYDL(YoutubeDL): - def __init__(self, override=None): - # Different instances of the downloader can't share the same dictionary - # some test set the "sublang" parameter, which would break the md5 checks. - params = get_params(override=override) - super().__init__(params, auto_init=False) - self.result = [] - - def to_screen(self, s, *args, **kwargs): - print(s) - - def trouble(self, s, *args, **kwargs): - raise Exception(s) - - def download(self, x): - self.result.append(x) - - def expect_warning(self, regex): - # Silence an expected warning matching a regex - old_report_warning = self.report_warning - - def report_warning(self, message, *args, **kwargs): - if re.match(regex, message): - return - old_report_warning(message, *args, **kwargs) - self.report_warning = types.MethodType(report_warning, self) - - -def gettestcases(include_onlymatching=False): - for ie in yt_dlp.extractor.gen_extractors(): - yield from ie.get_testcases(include_onlymatching) - - -def getwebpagetestcases(): - for ie in yt_dlp.extractor.gen_extractors(): - for tc in ie.get_webpage_testcases(): - tc.setdefault('add_ie', []).append('Generic') - yield tc - - -md5 = lambda s: hashlib.md5(s.encode()).hexdigest() - - -def _iter_differences(got, expected, field): - if isinstance(expected, str): - op, _, val = expected.partition(':') - if op in ('mincount', 'maxcount', 'count'): - if not isinstance(got, (list, dict)): - yield field, f'expected either {list.__name__} or {dict.__name__}, got {type(got).__name__}' - return - - expected_num = int(val) - got_num = len(got) - if op == 'mincount': - if got_num < expected_num: - yield field, f'expected at least {val} items, got {got_num}' - return - - if op == 'maxcount': - if got_num > expected_num: - yield field, f'expected at most {val} items, got {got_num}' - return - - assert op == 'count' - if got_num != expected_num: - yield field, f'expected exactly {val} items, got {got_num}' - return - - if not isinstance(got, str): - yield field, f'expected {str.__name__}, got {type(got).__name__}' - return - - if op == 're': - if not re.match(val, got): - yield field, f'should match {val!r}, got {got!r}' - return - - if op == 'startswith': - if not got.startswith(val): - yield field, f'should start with {val!r}, got {got!r}' - return - - if op == 'contains': - if not val.startswith(got): - yield field, f'should contain {val!r}, got {got!r}' - return - - if op == 'md5': - hash_val = md5(got) - if hash_val != val: - yield field, f'expected hash {val}, got {hash_val}' - return - - if got != expected: - yield field, f'expected {expected!r}, got {got!r}' - return - - if isinstance(expected, dict) and isinstance(got, dict): - for key, expected_val in expected.items(): - if key not in got: - yield field, f'missing key: {key!r}' - continue - - field_name = key if field is None else f'{field}.{key}' - yield from _iter_differences(got[key], expected_val, field_name) - return - - if isinstance(expected, type): - if not isinstance(got, expected): - yield field, f'expected {expected.__name__}, got {type(got).__name__}' - return - - if isinstance(expected, list) and isinstance(got, list): - # TODO: clever diffing algorithm lmao - if len(expected) != len(got): - yield field, f'expected length of {len(expected)}, got {len(got)}' - return - - for index, (got_val, expected_val) in enumerate(zip(got, expected, strict=True)): - field_name = str(index) if field is None else f'{field}.{index}' - yield from _iter_differences(got_val, expected_val, field_name) - return - - if got != expected: - yield field, f'expected {expected!r}, got {got!r}' - - -def _expect_value(message, got, expected, field): - mismatches = list(_iter_differences(got, expected, field)) - if not mismatches: - return - - fields = [field for field, _ in mismatches if field is not None] - return ''.join(( - message, f' ({", ".join(fields)})' if fields else '', - *(f'\n\t{field}: {message}' for field, message in mismatches))) - - -def expect_value(self, got, expected, field): - if message := _expect_value('values differ', got, expected, field): - self.fail(message) - - -def expect_dict(self, got_dict, expected_dict): - if message := _expect_value('dictionaries differ', got_dict, expected_dict, None): - self.fail(message) - - -def sanitize_got_info_dict(got_dict): - IGNORED_FIELDS = ( - *YoutubeDL._format_fields, - - # Lists - 'formats', 'thumbnails', 'subtitles', 'automatic_captions', 'comments', 'entries', - - # Auto-generated - 'autonumber', 'playlist', 'format_index', 'video_ext', 'audio_ext', 'duration_string', 'epoch', 'n_entries', - 'fulltitle', 'extractor', 'extractor_key', 'filename', 'filepath', 'infojson_filename', 'original_url', - - # Only live_status needs to be checked - 'is_live', 'was_live', - ) - - IGNORED_PREFIXES = ('', 'playlist', 'requested', 'webpage') - - def sanitize(key, value): - if isinstance(value, str) and len(value) > 100 and key != 'thumbnail': - return f'md5:{md5(value)}' - elif isinstance(value, list) and len(value) > 10: - return f'count:{len(value)}' - elif key.endswith('_count') and isinstance(value, int): - return int - return value - - test_info_dict = { - key: sanitize(key, value) for key, value in got_dict.items() - if value is not None and key not in IGNORED_FIELDS and ( - not any(key.startswith(f'{prefix}_') for prefix in IGNORED_PREFIXES) - or key == '_old_archive_ids') - } - - # display_id may be generated from id - if test_info_dict.get('display_id') == test_info_dict.get('id'): - test_info_dict.pop('display_id') - - # Remove deprecated fields - for old in YoutubeDL._deprecated_multivalue_fields: - test_info_dict.pop(old, None) - - # release_year may be generated from release_date - if try_call(lambda: test_info_dict['release_year'] == int(test_info_dict['release_date'][:4])): - test_info_dict.pop('release_year') - - # Check url for flat entries - if got_dict.get('_type', 'video') != 'video' and got_dict.get('url'): - test_info_dict['url'] = got_dict['url'] - - return test_info_dict - - -def expect_info_dict(self, got_dict, expected_dict): - ALLOWED_KEYS_SORT_ORDER = ( - # NB: Keep in sync with the docstring of extractor/common.py - 'ie_key', 'url', 'id', 'ext', 'direct', 'display_id', 'title', 'alt_title', 'description', 'media_type', - 'uploader', 'uploader_id', 'uploader_url', 'channel', 'channel_id', 'channel_url', 'channel_is_verified', - 'channel_follower_count', 'comment_count', 'view_count', 'concurrent_view_count', 'save_count', - 'like_count', 'dislike_count', 'repost_count', 'average_rating', 'age_limit', 'duration', 'thumbnail', 'heatmap', - 'chapters', 'chapter', 'chapter_number', 'chapter_id', 'start_time', 'end_time', 'section_start', 'section_end', - 'categories', 'tags', 'cast', 'composers', 'artists', 'album_artists', 'creators', 'genres', - 'track', 'track_number', 'track_id', 'album', 'album_type', 'disc_number', - 'series', 'series_id', 'season', 'season_number', 'season_id', 'episode', 'episode_number', 'episode_id', - 'timestamp', 'upload_date', 'release_timestamp', 'release_date', 'release_year', 'modified_timestamp', 'modified_date', - 'playable_in_embed', 'availability', 'live_status', 'location', 'license', '_old_archive_ids', - ) - - expect_dict(self, got_dict, expected_dict) - # Check for the presence of mandatory fields - if got_dict.get('_type') not in ('playlist', 'multi_video'): - mandatory_fields = ['id', 'title'] - if expected_dict.get('ext'): - mandatory_fields.extend(('url', 'ext')) - for key in mandatory_fields: - self.assertTrue(got_dict.get(key), f'Missing mandatory field {key}') - # Check for mandatory fields that are automatically set by YoutubeDL - if got_dict.get('_type', 'video') == 'video': - for key in ['webpage_url', 'extractor', 'extractor_key']: - self.assertTrue(got_dict.get(key), f'Missing field: {key}') - - test_info_dict = sanitize_got_info_dict(got_dict) - - # Check for invalid/misspelled field names being returned by the extractor - invalid_keys = sorted(test_info_dict.keys() - ALLOWED_KEYS_SORT_ORDER) - self.assertFalse(invalid_keys, f'Invalid fields returned by the extractor: {", ".join(invalid_keys)}') - - missing_keys = sorted( - test_info_dict.keys() - expected_dict.keys(), - key=ALLOWED_KEYS_SORT_ORDER.index) - if missing_keys: - def _repr(v): - if isinstance(v, str): - return "'{}'".format(v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')) - elif isinstance(v, type): - return v.__name__ - else: - return repr(v) - info_dict_str = ''.join( - f' {_repr(k)}: {_repr(v)},\n' - for k, v in test_info_dict.items() if k not in missing_keys) - if info_dict_str: - info_dict_str += '\n' - info_dict_str += ''.join( - f' {_repr(k)}: {_repr(test_info_dict[k])},\n' - for k in missing_keys) - info_dict_str = '\n\'info_dict\': {\n' + info_dict_str + '},\n' - write_string(info_dict_str.replace('\n', '\n '), out=sys.stderr) - self.assertFalse( - missing_keys, - 'Missing keys in test definition: {}'.format(', '.join(sorted(missing_keys)))) - - -def assertRegexpMatches(self, text, regexp, msg=None): - if hasattr(self, 'assertRegexp'): - return self.assertRegexp(text, regexp, msg) - else: - m = re.match(regexp, text) - if not m: - note = f'Regexp didn\'t match: {regexp!r} not found' - if len(text) < 1000: - note += f' in {text!r}' - if msg is None: - msg = note - else: - msg = note + ', ' + msg - self.assertTrue(m, msg) - - -def assertGreaterEqual(self, got, expected, msg=None): - if not (got >= expected): - if msg is None: - msg = f'{got!r} not greater than or equal to {expected!r}' - self.assertTrue(got >= expected, msg) - - -def assertLessEqual(self, got, expected, msg=None): - if not (got <= expected): - if msg is None: - msg = f'{got!r} not less than or equal to {expected!r}' - self.assertTrue(got <= expected, msg) - - -def assertEqual(self, got, expected, msg=None): - if got != expected: - if msg is None: - msg = f'{got!r} not equal to {expected!r}' - self.assertTrue(got == expected, msg) - - -def expect_warnings(ydl, warnings_re): - real_warning = ydl.report_warning - - def _report_warning(w, *args, **kwargs): - if not any(re.search(w_re, w) for w_re in warnings_re): - real_warning(w, *args, **kwargs) - - ydl.report_warning = _report_warning - - -def http_server_port(httpd): - if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket): - # In Jython SSLSocket is not a subclass of socket.socket - sock = httpd.socket.sock - else: - sock = httpd.socket - return sock.getsockname()[1] - - -def verify_address_availability(address): - if find_available_port(address) is None: - pytest.skip(f'Unable to bind to source address {address} (address may not exist)') - - -def validate_and_send(rh, req): - rh.validate(req) - return rh.send(req) diff --git a/test/parameters.json b/test/parameters.json deleted file mode 100644 index d08748a50..000000000 --- a/test/parameters.json +++ /dev/null @@ -1,48 +0,0 @@ -{ - "check_formats": false, - "consoletitle": false, - "continuedl": true, - "forcedescription": false, - "forcefilename": false, - "forceformat": false, - "forcethumbnail": false, - "forcetitle": false, - "forceurl": false, - "force_write_download_archive": false, - "format": "b/bv", - "ignoreerrors": false, - "listformats": null, - "logtostderr": false, - "matchtitle": null, - "max_downloads": null, - "overwrites": null, - "nopart": false, - "noprogress": false, - "outtmpl": "%(id)s.%(ext)s", - "password": null, - "playliststart": 1, - "prefer_free_formats": false, - "quiet": false, - "ratelimit": null, - "rejecttitle": null, - "retries": 10, - "simulate": false, - "subtitleslang": null, - "subtitlesformat": "best", - "test": true, - "updatetime": true, - "usenetrc": false, - "username": null, - "verbose": true, - "writedescription": false, - "writeinfojson": true, - "writelink": false, - "writeurllink": false, - "writewebloclink": false, - "writedesktoplink": false, - "writesubtitles": false, - "allsubtitles": false, - "listsubtitles": false, - "fixup": "never", - "allow_playlist_files": false -} diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py deleted file mode 100644 index f66fdbf8d..000000000 --- a/test/test_InfoExtractor.py +++ /dev/null @@ -1,2168 +0,0 @@ -#!/usr/bin/env python3 - -# Allow direct execution -import os -import sys -import unittest - -sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) - - -import http.server -import threading - -from test.helper import FakeYDL, expect_dict, expect_value, http_server_port -from yt_dlp.compat import compat_etree_fromstring -from yt_dlp.extractor import YoutubeIE, get_info_extractor -from yt_dlp.extractor.common import InfoExtractor -from yt_dlp.utils import ( - ExtractorError, - RegexNotFoundError, - encode_data_uri, - strip_jsonp, -) - -TEAPOT_RESPONSE_STATUS = 418 -TEAPOT_RESPONSE_BODY = "

418 I'm a teapot

" - - -class InfoExtractorTestRequestHandler(http.server.BaseHTTPRequestHandler): - def log_message(self, format, *args): - pass - - def do_GET(self): - if self.path == '/teapot': - self.send_response(TEAPOT_RESPONSE_STATUS) - self.send_header('Content-Type', 'text/html; charset=utf-8') - self.end_headers() - self.wfile.write(TEAPOT_RESPONSE_BODY.encode()) - elif self.path == '/fake.m3u8': - self.send_response(200) - self.send_header('Content-Length', '1024') - self.end_headers() - self.wfile.write(1024 * b'\x00') - elif self.path == '/bipbop.m3u8': - with open('test/testdata/m3u8/bipbop_16x9.m3u8', 'rb') as f: - data = f.read() - self.send_response(200) - self.send_header('Content-Length', str(len(data))) - self.end_headers() - self.wfile.write(data) - else: - assert False - - -class DummyIE(InfoExtractor): - def _sort_formats(self, formats, field_preference=[]): - self._downloader.sort_formats( - {'formats': formats, '_format_sort_fields': field_preference}) - - -class TestInfoExtractor(unittest.TestCase): - def setUp(self): - self.ie = DummyIE(FakeYDL()) - - def test_ie_key(self): - self.assertEqual(get_info_extractor(YoutubeIE.ie_key()), YoutubeIE) - - def test_get_netrc_login_info(self): - for params in [ - {'usenetrc': True, 'netrc_location': './test/testdata/netrc/netrc'}, - {'netrc_cmd': f'{sys.executable} ./test/testdata/netrc/print_netrc.py'}, - ]: - ie = DummyIE(FakeYDL(params)) - self.assertEqual(ie._get_netrc_login_info(netrc_machine='normal_use'), ('user', 'pass')) - self.assertEqual(ie._get_netrc_login_info(netrc_machine='empty_user'), ('', 'pass')) - self.assertEqual(ie._get_netrc_login_info(netrc_machine='empty_pass'), ('user', '')) - self.assertEqual(ie._get_netrc_login_info(netrc_machine='both_empty'), ('', '')) - self.assertEqual(ie._get_netrc_login_info(netrc_machine='nonexistent'), (None, None)) - with self.assertRaises(ExtractorError): - ie._get_netrc_login_info(netrc_machine=';echo rce') - - def test_html_search_regex(self): - html = '

Watch this video

' - search = lambda re, *args: self.ie._html_search_regex(re, html, *args) - self.assertEqual(search(r'

(.+?)

', 'foo'), 'Watch this video') - - def test_opengraph(self): - ie = self.ie - html = ''' - - - - - - - - - - ''' - self.assertEqual(ie._og_search_title(html), 'Foo') - self.assertEqual(ie._og_search_description(html), 'Some video\'s description ') - self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2') - self.assertEqual(ie._og_search_video_url(html, default=None), None) - self.assertEqual(ie._og_search_property('foobar', html), 'Foo') - self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar') - self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar') - self.assertEqual(ie._og_search_property('test3', html), 'Ill-formatted opengraph') - self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar') - self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True) - self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True) - self.assertEqual(ie._og_search_property('test4', html), 'unquoted-value') - - def test_html_search_meta(self): - ie = self.ie - html = ''' - - - - - - - ''' - - self.assertEqual(ie._html_search_meta('a', html), '1') - self.assertEqual(ie._html_search_meta('b', html), '2') - self.assertEqual(ie._html_search_meta('c', html), '3') - self.assertEqual(ie._html_search_meta('d', html), '4') - self.assertEqual(ie._html_search_meta('e', html), '5') - self.assertEqual(ie._html_search_meta('f', html), '6') - self.assertEqual(ie._html_search_meta(('a', 'b', 'c'), html), '1') - self.assertEqual(ie._html_search_meta(('c', 'b', 'a'), html), '3') - self.assertEqual(ie._html_search_meta(('z', 'x', 'c'), html), '3') - self.assertRaises(RegexNotFoundError, ie._html_search_meta, 'z', html, None, fatal=True) - self.assertRaises(RegexNotFoundError, ie._html_search_meta, ('z', 'x'), html, None, fatal=True) - - def test_search_json_ld_realworld(self): - _TESTS = [ - # https://github.com/ytdl-org/youtube-dl/issues/23306 - ( - r'''''', - { - 'title': '1 On 1 With Kleio', - 'description': 'Kleio Valentien', - 'url': 'https://gvideo.eporner.com/xN49A1cT3eB/xN49A1cT3eB.mp4', - 'timestamp': 1449347075, - 'duration': 743.0, - 'view_count': 1120958, - 'width': 1920, - 'height': 1080, - }, - {}, - ), - ( - r'''''', - { - 'timestamp': 1636523400, - 'title': 'md5:91fe569e952e4d146485740ae927662b', - }, - {'expected_type': 'NewsArticle'}, - ), - ( - r''' - ''', - { - 'chapters': [ - {'title': 'Explosie Turnhout', 'start_time': 70, 'end_time': 440}, - {'title': 'Jaarwisseling', 'start_time': 440, 'end_time': 1179}, - {'title': 'Natuurbranden Colorado', 'start_time': 1179, 'end_time': 1263}, - {'title': 'Klimaatverandering', 'start_time': 1263, 'end_time': 1367}, - {'title': 'Zacht weer', 'start_time': 1367, 'end_time': 1383}, - {'title': 'Financiële balans', 'start_time': 1383, 'end_time': 1484}, - {'title': 'Club Brugge', 'start_time': 1484, 'end_time': 1575}, - {'title': 'Mentale gezondheid bij topsporters', 'start_time': 1575, 'end_time': 1728}, - {'title': 'Olympische Winterspelen', 'start_time': 1728, 'end_time': 1873}, - {'title': 'Sober oudjaar in Nederland', 'start_time': 1873, 'end_time': 2079.23}, - ], - 'title': 'Het journaal - Aflevering 365 (Seizoen 2021)', - }, {}, - ), - ( - # test multiple thumbnails in a list - r''' -''', - { - 'thumbnails': [{'url': 'https://www.rainews.it/cropgd/640x360/dl/img/2021/12/30/1640886376927_GettyImages.jpg'}], - }, - {}, - ), - ( - # test single thumbnail - r''' -''', - { - 'thumbnails': [{'url': 'https://www.rainews.it/cropgd/640x360/dl/img/2021/12/30/1640886376927_GettyImages.jpg'}], - }, - {}, - ), - ( - # test thumbnail_url key without URL scheme - r''' -''', - { - 'thumbnails': [{'url': 'https://www.nobelprize.org/images/12693-landscape-medium-gallery.jpg'}], - }, - {}, - ), - ] - for html, expected_dict, search_json_ld_kwargs in _TESTS: - expect_dict( - self, - self.ie._search_json_ld(html, None, **search_json_ld_kwargs), - expected_dict, - ) - - def test_download_json(self): - uri = encode_data_uri(b'{"foo": "blah"}', 'application/json') - self.assertEqual(self.ie._download_json(uri, None), {'foo': 'blah'}) - uri = encode_data_uri(b'callback({"foo": "blah"})', 'application/javascript') - self.assertEqual(self.ie._download_json(uri, None, transform_source=strip_jsonp), {'foo': 'blah'}) - uri = encode_data_uri(b'{"foo": invalid}', 'application/json') - self.assertRaises(ExtractorError, self.ie._download_json, uri, None) - self.assertEqual(self.ie._download_json(uri, None, fatal=False), None) - - def test_parse_html5_media_entries(self): - # inline video tag - expect_dict( - self, - self.ie._parse_html5_media_entries( - 'https://127.0.0.1/video.html', - r'