diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 00000000..269438fa --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,12 @@ +# To get started with Dependabot version updates, you'll need to specify which +# package ecosystems to update and where the package manifests are located. +# Please see the documentation for all configuration options: +# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file + +version: 2 +updates: + - package-ecosystem: "pip" # See documentation for possible values + directory: "/" + target-branch: "dev" + schedule: + interval: "weekly" diff --git a/.github/workflows/codeql.yml b/.github/workflows/codeql.yml new file mode 100644 index 00000000..a6d4e276 --- /dev/null +++ b/.github/workflows/codeql.yml @@ -0,0 +1,92 @@ +# For most projects, this workflow file will not need changing; you simply need +# to commit it to your repository. +# +# You may wish to alter this file to override the set of languages analyzed, +# or to provide custom queries or build logic. +# +# ******** NOTE ******** +# We have attempted to detect the languages in your repository. Please check +# the `language` matrix defined below to confirm you have the correct set of +# supported CodeQL languages. +# +name: "CodeQL" + +on: + push: + branches: [ "dev" ] + pull_request: + branches: [ "dev" ] + schedule: + - cron: '33 17 * * 6' + +jobs: + analyze: + name: Analyze (${{ matrix.language }}) + # Runner size impacts CodeQL analysis time. To learn more, please see: + # - https://gh.io/recommended-hardware-resources-for-running-codeql + # - https://gh.io/supported-runners-and-hardware-resources + # - https://gh.io/using-larger-runners (GitHub.com only) + # Consider using larger runners or machines with greater resources for possible analysis time improvements. + runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }} + timeout-minutes: ${{ (matrix.language == 'swift' && 120) || 360 }} + permissions: + # required for all workflows + security-events: write + + # required to fetch internal or private CodeQL packs + packages: read + + # only required for workflows in private repositories + actions: read + contents: read + + strategy: + fail-fast: false + matrix: + include: + - language: python + build-mode: none + # CodeQL supports the following values keywords for 'language': 'c-cpp', 'csharp', 'go', 'java-kotlin', 'javascript-typescript', 'python', 'ruby', 'swift' + # Use `c-cpp` to analyze code written in C, C++ or both + # Use 'java-kotlin' to analyze code written in Java, Kotlin or both + # Use 'javascript-typescript' to analyze code written in JavaScript, TypeScript or both + # To learn more about changing the languages that are analyzed or customizing the build mode for your analysis, + # see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/customizing-your-advanced-setup-for-code-scanning. + # If you are analyzing a compiled language, you can modify the 'build-mode' for that language to customize how + # your codebase is analyzed, see https://docs.github.com/en/code-security/code-scanning/creating-an-advanced-setup-for-code-scanning/codeql-code-scanning-for-compiled-languages + steps: + - name: Checkout repository + uses: actions/checkout@v4 + + # Initializes the CodeQL tools for scanning. + - name: Initialize CodeQL + uses: github/codeql-action/init@v3 + with: + languages: ${{ matrix.language }} + build-mode: ${{ matrix.build-mode }} + # If you wish to specify custom queries, you can do so here or in a config file. + # By default, queries listed here will override any specified in a config file. + # Prefix the list here with "+" to use these queries and those in the config file. + + # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs + # queries: security-extended,security-and-quality + + # If the analyze step fails for one of the languages you are analyzing with + # "We were unable to automatically build your code", modify the matrix above + # to set the build mode to "manual" for that language. Then modify this step + # to build your code. + # ℹī¸ Command-line programs to run using the OS shell. + # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun + - if: matrix.build-mode == 'manual' + run: | + echo 'If you are using a "manual" build mode for one or more of the' \ + 'languages you are analyzing, replace this with the commands to build' \ + 'your code, for example:' + echo ' make bootstrap' + echo ' make release' + exit 1 + + - name: Perform CodeQL Analysis + uses: github/codeql-action/analyze@v3 + with: + category: "/language:${{matrix.language}}" diff --git a/README.md b/README.md index 4d1bcf0d..3b2372a2 100644 --- a/README.md +++ b/README.md @@ -124,8 +124,8 @@ curl -fsSL 'https://get.archivebox.io' | sh ## Key Features -- [**Free & open source**](https://github.com/ArchiveBox/ArchiveBox/blob/dev/LICENSE), doesn't require signing up online, stores all data locally -- [**Powerful, intuitive command line interface**](https://github.com/ArchiveBox/ArchiveBox/wiki/Usage#CLI-Usage) with [modular optional dependencies](#dependencies) +- [**Free & open source**](https://github.com/ArchiveBox/ArchiveBox/blob/dev/LICENSE), own your own data & maintain your privacy by self-hosting +- [**Powerful command line interface**](https://github.com/ArchiveBox/ArchiveBox/wiki/Usage#CLI-Usage) with [modular dependencies](#dependencies) and [support for Google Drive/NFS/SMB/S3/B2/etc.](https://github.com/ArchiveBox/ArchiveBox/wiki/Setting-Up-Storage) - [**Comprehensive documentation**](https://github.com/ArchiveBox/ArchiveBox/wiki), [active development](https://github.com/ArchiveBox/ArchiveBox/wiki/Roadmap), and [rich community](https://github.com/ArchiveBox/ArchiveBox/wiki/Web-Archiving-Community) - [**Extracts a wide variety of content out-of-the-box**](https://github.com/ArchiveBox/ArchiveBox/issues/51): [media (yt-dlp), articles (readability), code (git), etc.](#output-formats) - [**Supports scheduled/realtime importing**](https://github.com/ArchiveBox/ArchiveBox/wiki/Scheduled-Archiving) from [many types of sources](#input-formats) @@ -669,7 +669,7 @@ docker run -it -v $PWD:/data archivebox/archivebox add --depth=1 'https://exampl ```bash # archivebox add --help archivebox add 'https://example.com/some/page' -archivebox add < ~/Downloads/firefox_bookmarks_export.html +archivebox add --parser=generic_rss < ~/Downloads/some_feed.xml archivebox add --depth=1 'https://news.ycombinator.com#2020-12-12' echo 'http://example.com' | archivebox add echo 'any text with urls in it' | archivebox add @@ -865,6 +865,7 @@ Each snapshot subfolder data/archive/TIMESTAMP/ includes a static <

Learn More