├── .github ├── FUNDING.yml ├── stale.yml └── workflows │ ├── DailyTests.yaml │ ├── Publish.yml │ ├── PublishDockerDevImage.yaml │ ├── QA.yaml │ ├── Tests.yaml │ └── update-zim-offliner-definition.yaml ├── .gitignore ├── .pre-commit-config.yaml ├── CHANGELOG.md ├── Dockerfile ├── LICENSE ├── README.md ├── offliner-definition.json ├── pyproject.toml ├── src └── zimit │ ├── __about__.py │ ├── constants.py │ ├── utils.py │ └── zimit.py ├── tasks.py ├── tests-daily ├── Dockerfile └── daily.py ├── tests-integration ├── README.md └── integration.py └── tests └── test_dummy.py /.github/FUNDING.yml: -------------------------------------------------------------------------------- 1 | # These are supported funding model platforms 2 | 3 | github: kiwix # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2] 4 | patreon: # Replace with a single Patreon username 5 | open_collective: # Replace with a single Open Collective username 6 | ko_fi: # Replace with a single Ko-fi username 7 | tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel 8 | community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry 9 | liberapay: # Replace with a single Liberapay username 10 | issuehunt: # Replace with a single IssueHunt username 11 | otechie: # Replace with a single Otechie username 12 | custom: # https://kiwix.org/support-us/ 13 | -------------------------------------------------------------------------------- /.github/stale.yml: -------------------------------------------------------------------------------- 1 | daysUntilClose: false 2 | staleLabel: stale 3 | 4 | issues: 5 | daysUntilStale: 60 6 | markComment: > 7 | This issue has been automatically marked as stale because it has not had 8 | recent activity. It will be now be reviewed manually. Thank you 9 | for your contributions. 10 | pulls: 11 | daysUntilStale: 7 12 | markComment: > 13 | This pull request has been automatically marked as stale because it has not had 14 | recent activity. It will be now be reviewed manually. Thank you 15 | for your contributions. 16 | -------------------------------------------------------------------------------- /.github/workflows/DailyTests.yaml: -------------------------------------------------------------------------------- 1 | name: DailyTests 2 | 3 | on: 4 | schedule: 5 | - cron: "0 4 * * *" 6 | workflow_dispatch: 7 | 8 | 9 | jobs: 10 | run-daily-tests: 11 | runs-on: ubuntu-22.04 12 | 13 | steps: 14 | - name: checkout 15 | uses: actions/checkout@v4 16 | 17 | - name: build zimit image 18 | run: docker build -t local-zimit . 19 | 20 | - name: run crawl of test website 21 | run: docker run -v $PWD/output:/output local-zimit zimit --seeds https://website.test.openzim.org/ --name tests_eng_test-website --zim-file tests_eng_test-website.zim 22 | 23 | - name: archive ZIM 24 | uses: actions/upload-artifact@v4 25 | with: 26 | name: tests_eng_test-website.zim 27 | path: output/tests_eng_test-website.zim 28 | retention-days: 30 29 | 30 | - name: build tests-daily Docker image 31 | run: docker build -t local-tests-daily tests-daily 32 | 33 | - name: run integration test suite 34 | run: docker run -e SKIP_YOUTUBE_TEST="True" -v $PWD/tests-daily/daily.py:/app/daily.py -v $PWD/output:/output local-tests-daily bash -c "cd /app && pytest -v --log-level=INFO --log-format='%(levelname)s - %(message)s' daily.py" 35 | -------------------------------------------------------------------------------- /.github/workflows/Publish.yml: -------------------------------------------------------------------------------- 1 | name: Publish released version 2 | 3 | on: 4 | release: 5 | types: [published] 6 | 7 | jobs: 8 | publish-amd64: 9 | runs-on: ubuntu-24.04 10 | name: "Publish for AMD64" 11 | 12 | steps: 13 | - uses: actions/checkout@v4 14 | 15 | - name: Build and push Docker image 16 | uses: openzim/docker-publish-action@v10 17 | with: 18 | image-name: openzim/zimit 19 | tag-pattern: /^v([0-9.]+)$/ 20 | latest-on-tag: true 21 | restrict-to: openzim/zimit 22 | registries: ghcr.io 23 | credentials: | 24 | GHCRIO_USERNAME=${{ secrets.GHCR_USERNAME }} 25 | GHCRIO_TOKEN=${{ secrets.GHCR_TOKEN }} 26 | repo_description: auto 27 | repo_overview: auto 28 | platforms: | 29 | linux/amd64 30 | 31 | # Disabled for now, see https://github.com/openzim/zimit/issues/463 32 | # publish-arm64: 33 | # runs-on: ubuntu-24.04 34 | # name: "Publish for ARM64" 35 | # 36 | # steps: 37 | # - uses: actions/checkout@v4 38 | # 39 | # - name: Build and push Docker image 40 | # uses: openzim/docker-publish-action@v10 41 | # with: 42 | # image-name: openzim/zimit 43 | # tag-pattern: /^v([0-9.]+)$/ 44 | # latest-on-tag: true 45 | # restrict-to: openzim/zimit 46 | # registries: ghcr.io 47 | # credentials: | 48 | # GHCRIO_USERNAME=${{ secrets.GHCR_USERNAME }} 49 | # GHCRIO_TOKEN=${{ secrets.GHCR_TOKEN }} 50 | # repo_description: auto 51 | # repo_overview: auto 52 | # platforms: | 53 | # linux/arm64 54 | -------------------------------------------------------------------------------- /.github/workflows/PublishDockerDevImage.yaml: -------------------------------------------------------------------------------- 1 | name: Publish Docker dev image 2 | 3 | on: 4 | push: 5 | branches: 6 | - main 7 | workflow_dispatch: 8 | 9 | jobs: 10 | publish-amd64: 11 | runs-on: ubuntu-24.04 12 | name: "Publish for AMD64" 13 | 14 | steps: 15 | - uses: actions/checkout@v4 16 | 17 | - name: Build and push Docker image 18 | uses: openzim/docker-publish-action@v10 19 | with: 20 | image-name: openzim/zimit 21 | manual-tag: dev 22 | latest-on-tag: false 23 | restrict-to: openzim/zimit 24 | registries: ghcr.io 25 | credentials: | 26 | GHCRIO_USERNAME=${{ secrets.GHCR_USERNAME }} 27 | GHCRIO_TOKEN=${{ secrets.GHCR_TOKEN }} 28 | repo_description: auto 29 | repo_overview: auto 30 | platforms: | 31 | linux/amd64 32 | 33 | # Disabled for now, see https://github.com/openzim/zimit/issues/463 34 | # publish-arm64: 35 | # runs-on: ubuntu-24.04-arm 36 | # name: "Publish for ARM64" 37 | # 38 | # steps: 39 | # - uses: actions/checkout@v4 40 | # 41 | # - name: Build and push Docker image 42 | # uses: openzim/docker-publish-action@v10 43 | # with: 44 | # image-name: openzim/zimit 45 | # manual-tag: dev 46 | # latest-on-tag: false 47 | # restrict-to: openzim/zimit 48 | # registries: ghcr.io 49 | # credentials: | 50 | # GHCRIO_USERNAME=${{ secrets.GHCR_USERNAME }} 51 | # GHCRIO_TOKEN=${{ secrets.GHCR_TOKEN }} 52 | # repo_description: auto 53 | # repo_overview: auto 54 | # platforms: | 55 | # linux/arm64 56 | -------------------------------------------------------------------------------- /.github/workflows/QA.yaml: -------------------------------------------------------------------------------- 1 | name: QA 2 | 3 | on: 4 | pull_request: 5 | push: 6 | branches: 7 | - main 8 | 9 | jobs: 10 | check-qa: 11 | runs-on: ubuntu-22.04 12 | 13 | steps: 14 | - uses: actions/checkout@v4 15 | 16 | - name: Set up Python 17 | uses: actions/setup-python@v5 18 | with: 19 | python-version-file: pyproject.toml 20 | architecture: x64 21 | 22 | - name: Install dependencies (and project) 23 | run: | 24 | pip install -U pip 25 | pip install -e .[lint,scripts,test,check] 26 | 27 | - name: Check black formatting 28 | run: inv lint-black 29 | 30 | - name: Check ruff 31 | run: inv lint-ruff 32 | 33 | - name: Check pyright 34 | run: inv check-pyright 35 | -------------------------------------------------------------------------------- /.github/workflows/Tests.yaml: -------------------------------------------------------------------------------- 1 | name: Tests 2 | 3 | on: 4 | pull_request: 5 | push: 6 | branches: 7 | - main 8 | 9 | jobs: 10 | run-tests: 11 | runs-on: ubuntu-22.04 12 | 13 | steps: 14 | - uses: actions/checkout@v4 15 | 16 | - name: Set up Python 17 | uses: actions/setup-python@v5 18 | with: 19 | python-version-file: pyproject.toml 20 | architecture: x64 21 | 22 | - name: Install dependencies (and project) 23 | run: | 24 | pip install -U pip 25 | pip install -e .[test,scripts] 26 | 27 | - name: Run the tests 28 | run: inv coverage --args "-vvv" 29 | 30 | - name: Upload coverage report to codecov 31 | uses: codecov/codecov-action@v4 32 | with: 33 | token: ${{ secrets.CODECOV_TOKEN }} 34 | 35 | build_python: 36 | runs-on: ubuntu-22.04 37 | steps: 38 | - uses: actions/checkout@v4 39 | 40 | - name: Set up Python 41 | uses: actions/setup-python@v5 42 | with: 43 | python-version-file: pyproject.toml 44 | architecture: x64 45 | 46 | - name: Ensure we can build Python targets 47 | run: | 48 | pip install -U pip build 49 | python3 -m build --sdist --wheel 50 | 51 | # this job replaces the standard "build_docker" job since it builds the docker image 52 | run-integration-tests: 53 | runs-on: ubuntu-22.04 54 | 55 | steps: 56 | - name: checkout 57 | uses: actions/checkout@v4 58 | 59 | - name: build image 60 | run: docker build -t local-zimit . 61 | 62 | - name: ensure help display without issue 63 | run: docker run -v $PWD/output:/output local-zimit zimit --help 64 | 65 | - name: run crawl with soft size limit 66 | run: docker run -v $PWD/output:/output local-zimit zimit --seeds http://website.test.openzim.org/ --sizeSoftLimit 8192 --name tests_en_sizesoftlimit --zim-file tests_en_sizesoftlimit.zim --adminEmail test@example.com --mobileDevice "Pixel 5" --zimit-progress-file /output/stats_sizesoftlimit.json 67 | 68 | - name: run crawl with hard size limit 69 | run: docker run -v $PWD/output:/output local-zimit zimit --seeds http://website.test.openzim.org/ --sizeHardLimit 8192 --name tests_en_sizehardlimit --zim-file tests_en_sizehardlimit.zim --adminEmail test@example.com --mobileDevice "Pixel 5" --zimit-progress-file /output/stats_sizehardlimit.json || true 70 | 71 | - name: run crawl with soft time limit 72 | run: docker run -v $PWD/output:/output local-zimit zimit --seeds http://website.test.openzim.org/ --timeSoftLimit 1 --name tests_en_timesoftlimit --zim-file tests_en_timesoftlimit.zim --adminEmail test@example.com --mobileDevice "Pixel 5" --zimit-progress-file /output/stats_timesoftlimit.json 73 | 74 | - name: run crawl with hard time limit 75 | run: docker run -v $PWD/output:/output local-zimit zimit --seeds http://website.test.openzim.org/ --timeHardLimit 1 --name tests_en_timehardlimit --zim-file tests_en_timehardlimit.zim --adminEmail test@example.com --mobileDevice "Pixel 5" --zimit-progress-file /output/stats_timehardlimit.json || true 76 | 77 | - name: run standard crawl 78 | run: docker run -v $PWD/output:/output local-zimit zimit --seeds http://website.test.openzim.org/http-return-codes.html --name tests_en_onepage --zim-file tests_en_onepage.zim --adminEmail test@example.com --mobileDevice "Pixel 5" --zimit-progress-file /output/stats.json --statsFilename /output/crawl.json --warc2zim-progress-file /output/warc2zim.json --keep 79 | 80 | - name: run integration test suite 81 | run: docker run -v $PWD/tests-integration/integration.py:/app/integration.py -v $PWD/output:/output local-zimit bash -c "/app/zimit/bin/pip install pytest; /app/zimit/bin/pytest -v /app/integration.py" 82 | -------------------------------------------------------------------------------- /.github/workflows/update-zim-offliner-definition.yaml: -------------------------------------------------------------------------------- 1 | name: Update ZIMFarm Definitions 2 | 3 | on: 4 | push: 5 | branches: [main] 6 | paths: 7 | - "offliner-definition.json" 8 | release: 9 | types: [published] 10 | 11 | workflow_dispatch: 12 | inputs: 13 | version: 14 | description: "Version to publish" 15 | required: false 16 | default: "dev" 17 | 18 | jobs: 19 | prepare-json: 20 | runs-on: ubuntu-24.04 21 | outputs: 22 | offliner_definition_b64: ${{ steps.read-json.outputs.offliner_definition_b64 }} 23 | steps: 24 | - name: Checkout repository 25 | uses: actions/checkout@v4 26 | with: 27 | fetch-depth: 0 28 | 29 | - id: read-json 30 | run: | 31 | if [ ! -f "offliner-definition.json" ]; then 32 | echo "File not found!" >&2 33 | exit 1 34 | fi 35 | json_b64=$(base64 -w0 <<< "$(jq -c . offliner-definition.json)") 36 | echo "offliner_definition_b64=$json_b64" >> $GITHUB_OUTPUT 37 | call-workflow: 38 | needs: prepare-json 39 | uses: openzim/overview/.github/workflows/update-zimfarm-offliner-definition.yaml@main 40 | with: 41 | version: ${{ github.event_name == 'release' && github.event.release.tag_name || (github.event.inputs.version || 'dev') }} 42 | offliner: zimit 43 | offliner_definition_b64: ${{ needs.prepare-json.outputs.offliner_definition_b64 }} 44 | secrets: 45 | zimfarm_ci_secret: ${{ secrets.ZIMFARM_CI_SECRET }} 46 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Created by https://www.toptal.com/developers/gitignore/api/linux,macos,python,visualstudiocode,intellij 2 | # Edit at https://www.toptal.com/developers/gitignore?templates=linux,macos,python,visualstudiocode,intellij 3 | 4 | ### Intellij ### 5 | # Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider 6 | # Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839 7 | 8 | # User-specific stuff 9 | .idea/**/workspace.xml 10 | .idea/**/tasks.xml 11 | .idea/**/usage.statistics.xml 12 | .idea/**/dictionaries 13 | .idea/**/shelf 14 | 15 | # AWS User-specific 16 | .idea/**/aws.xml 17 | 18 | # Generated files 19 | .idea/**/contentModel.xml 20 | 21 | # Sensitive or high-churn files 22 | .idea/**/dataSources/ 23 | .idea/**/dataSources.ids 24 | .idea/**/dataSources.local.xml 25 | .idea/**/sqlDataSources.xml 26 | .idea/**/dynamic.xml 27 | .idea/**/uiDesigner.xml 28 | .idea/**/dbnavigator.xml 29 | 30 | # Gradle 31 | .idea/**/gradle.xml 32 | .idea/**/libraries 33 | 34 | # Gradle and Maven with auto-import 35 | # When using Gradle or Maven with auto-import, you should exclude module files, 36 | # since they will be recreated, and may cause churn. Uncomment if using 37 | # auto-import. 38 | # .idea/artifacts 39 | # .idea/compiler.xml 40 | # .idea/jarRepositories.xml 41 | # .idea/modules.xml 42 | # .idea/*.iml 43 | # .idea/modules 44 | # *.iml 45 | # *.ipr 46 | 47 | # CMake 48 | cmake-build-*/ 49 | 50 | # Mongo Explorer plugin 51 | .idea/**/mongoSettings.xml 52 | 53 | # File-based project format 54 | *.iws 55 | 56 | # IntelliJ 57 | out/ 58 | 59 | # mpeltonen/sbt-idea plugin 60 | .idea_modules/ 61 | 62 | # JIRA plugin 63 | atlassian-ide-plugin.xml 64 | 65 | # Cursive Clojure plugin 66 | .idea/replstate.xml 67 | 68 | # SonarLint plugin 69 | .idea/sonarlint/ 70 | 71 | # Crashlytics plugin (for Android Studio and IntelliJ) 72 | com_crashlytics_export_strings.xml 73 | crashlytics.properties 74 | crashlytics-build.properties 75 | fabric.properties 76 | 77 | # Editor-based Rest Client 78 | .idea/httpRequests 79 | 80 | # Android studio 3.1+ serialized cache file 81 | .idea/caches/build_file_checksums.ser 82 | 83 | ### Intellij Patch ### 84 | # Comment Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-215987721 85 | 86 | # *.iml 87 | # modules.xml 88 | # .idea/misc.xml 89 | # *.ipr 90 | 91 | # Sonarlint plugin 92 | # https://plugins.jetbrains.com/plugin/7973-sonarlint 93 | .idea/**/sonarlint/ 94 | 95 | # SonarQube Plugin 96 | # https://plugins.jetbrains.com/plugin/7238-sonarqube-community-plugin 97 | .idea/**/sonarIssues.xml 98 | 99 | # Markdown Navigator plugin 100 | # https://plugins.jetbrains.com/plugin/7896-markdown-navigator-enhanced 101 | .idea/**/markdown-navigator.xml 102 | .idea/**/markdown-navigator-enh.xml 103 | .idea/**/markdown-navigator/ 104 | 105 | # Cache file creation bug 106 | # See https://youtrack.jetbrains.com/issue/JBR-2257 107 | .idea/$CACHE_FILE$ 108 | 109 | # CodeStream plugin 110 | # https://plugins.jetbrains.com/plugin/12206-codestream 111 | .idea/codestream.xml 112 | 113 | # Azure Toolkit for IntelliJ plugin 114 | # https://plugins.jetbrains.com/plugin/8053-azure-toolkit-for-intellij 115 | .idea/**/azureSettings.xml 116 | 117 | ### Linux ### 118 | *~ 119 | 120 | # temporary files which can be created if a process still has a handle open of a deleted file 121 | .fuse_hidden* 122 | 123 | # KDE directory preferences 124 | .directory 125 | 126 | # Linux trash folder which might appear on any partition or disk 127 | .Trash-* 128 | 129 | # .nfs files are created when an open file is removed but is still being accessed 130 | .nfs* 131 | 132 | ### macOS ### 133 | # General 134 | .DS_Store 135 | .AppleDouble 136 | .LSOverride 137 | 138 | # Icon must end with two \r 139 | Icon 140 | 141 | 142 | # Thumbnails 143 | ._* 144 | 145 | # Files that might appear in the root of a volume 146 | .DocumentRevisions-V100 147 | .fseventsd 148 | .Spotlight-V100 149 | .TemporaryItems 150 | .Trashes 151 | .VolumeIcon.icns 152 | .com.apple.timemachine.donotpresent 153 | 154 | # Directories potentially created on remote AFP share 155 | .AppleDB 156 | .AppleDesktop 157 | Network Trash Folder 158 | Temporary Items 159 | .apdisk 160 | 161 | ### macOS Patch ### 162 | # iCloud generated files 163 | *.icloud 164 | 165 | ### Python ### 166 | # Byte-compiled / optimized / DLL files 167 | __pycache__/ 168 | *.py[cod] 169 | *$py.class 170 | 171 | # C extensions 172 | *.so 173 | 174 | # Distribution / packaging 175 | .Python 176 | build/ 177 | develop-eggs/ 178 | dist/ 179 | downloads/ 180 | eggs/ 181 | .eggs/ 182 | lib/ 183 | lib64/ 184 | parts/ 185 | sdist/ 186 | var/ 187 | wheels/ 188 | share/python-wheels/ 189 | *.egg-info/ 190 | .installed.cfg 191 | *.egg 192 | MANIFEST 193 | 194 | # PyInstaller 195 | # Usually these files are written by a python script from a template 196 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 197 | *.manifest 198 | *.spec 199 | 200 | # Installer logs 201 | pip-log.txt 202 | pip-delete-this-directory.txt 203 | 204 | # Unit test / coverage reports 205 | htmlcov/ 206 | .tox/ 207 | .nox/ 208 | .coverage 209 | .coverage.* 210 | .cache 211 | nosetests.xml 212 | coverage.xml 213 | *.cover 214 | *.py,cover 215 | .hypothesis/ 216 | .pytest_cache/ 217 | cover/ 218 | 219 | # Translations 220 | *.mo 221 | *.pot 222 | 223 | # Django stuff: 224 | *.log 225 | local_settings.py 226 | db.sqlite3 227 | db.sqlite3-journal 228 | 229 | # Flask stuff: 230 | instance/ 231 | .webassets-cache 232 | 233 | # Scrapy stuff: 234 | .scrapy 235 | 236 | # Sphinx documentation 237 | docs/_build/ 238 | 239 | # PyBuilder 240 | .pybuilder/ 241 | target/ 242 | 243 | # Jupyter Notebook 244 | .ipynb_checkpoints 245 | 246 | # IPython 247 | profile_default/ 248 | ipython_config.py 249 | 250 | # pyenv 251 | # For a library or package, you might want to ignore these files since the code is 252 | # intended to run in multiple environments; otherwise, check them in: 253 | # .python-version 254 | 255 | # pipenv 256 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 257 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 258 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 259 | # install all needed dependencies. 260 | #Pipfile.lock 261 | 262 | # poetry 263 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 264 | # This is especially recommended for binary packages to ensure reproducibility, and is more 265 | # commonly ignored for libraries. 266 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 267 | #poetry.lock 268 | 269 | # pdm 270 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 271 | #pdm.lock 272 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 273 | # in version control. 274 | # https://pdm.fming.dev/#use-with-ide 275 | .pdm.toml 276 | 277 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 278 | __pypackages__/ 279 | 280 | # Celery stuff 281 | celerybeat-schedule 282 | celerybeat.pid 283 | 284 | # SageMath parsed files 285 | *.sage.py 286 | 287 | # Environments 288 | .env 289 | .venv 290 | env/ 291 | venv/ 292 | ENV/ 293 | env.bak/ 294 | venv.bak/ 295 | 296 | # Spyder project settings 297 | .spyderproject 298 | .spyproject 299 | 300 | # Rope project settings 301 | .ropeproject 302 | 303 | # mkdocs documentation 304 | /site 305 | 306 | # mypy 307 | .mypy_cache/ 308 | .dmypy.json 309 | dmypy.json 310 | 311 | # Pyre type checker 312 | .pyre/ 313 | 314 | # pytype static type analyzer 315 | .pytype/ 316 | 317 | # Cython debug symbols 318 | cython_debug/ 319 | 320 | # PyCharm 321 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 322 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 323 | # and can be added to the global gitignore or merged into this file. For a more nuclear 324 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 325 | #.idea/ 326 | 327 | ### Python Patch ### 328 | # Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration 329 | poetry.toml 330 | 331 | # ruff 332 | .ruff_cache/ 333 | 334 | # LSP config files 335 | pyrightconfig.json 336 | 337 | ### VisualStudioCode ### 338 | .vscode/* 339 | !.vscode/settings.json 340 | !.vscode/tasks.json 341 | !.vscode/launch.json 342 | !.vscode/extensions.json 343 | !.vscode/*.code-snippets 344 | 345 | # Local History for Visual Studio Code 346 | .history/ 347 | 348 | # Built Visual Studio Code Extensions 349 | *.vsix 350 | 351 | ### VisualStudioCode Patch ### 352 | # Ignore all local history of files 353 | .history 354 | .ionide 355 | 356 | # End of https://www.toptal.com/developers/gitignore/api/linux,macos,python,visualstudiocode,intellij 357 | 358 | # output dir 359 | output 360 | 361 | # ignore all vscode, this editor specific, not maintained by openzim 362 | .vscode 363 | -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- 1 | # See https://pre-commit.com for more information 2 | # See https://pre-commit.com/hooks.html for more hooks 3 | repos: 4 | - repo: https://github.com/pre-commit/pre-commit-hooks 5 | rev: v5.0.0 6 | hooks: 7 | - id: trailing-whitespace 8 | - id: end-of-file-fixer 9 | - repo: https://github.com/psf/black 10 | rev: "25.1.0" 11 | hooks: 12 | - id: black 13 | - repo: https://github.com/astral-sh/ruff-pre-commit 14 | rev: v0.9.4 15 | hooks: 16 | - id: ruff 17 | - repo: https://github.com/RobertCraigie/pyright-python 18 | rev: v1.1.393 19 | hooks: 20 | - id: pyright 21 | name: pyright (system) 22 | description: 'pyright static type checker' 23 | entry: pyright 24 | language: system 25 | 'types_or': [python, pyi] 26 | require_serial: true 27 | minimum_pre_commit_version: '2.9.2' 28 | -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- 1 | ## Changelog 2 | 3 | All notable changes to this project are documented in this file. 4 | 5 | The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 6 | and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html) (as of version 1.2.0). 7 | 8 | ## [Unreleased] 9 | 10 | ## [3.0.5] - 2024-04-11 11 | 12 | ### Changed 13 | 14 | - Upgrade to browsertrix crawler 1.6.0 (#493) 15 | 16 | ## [3.0.4] - 2024-04-04 17 | 18 | ### Changed 19 | 20 | - Upgrade to browsertrix crawler 1.5.10 (#491) 21 | 22 | ## [3.0.3] - 2024-02-28 23 | 24 | ### Changed 25 | 26 | - Upgrade to browsertrix crawler 1.5.7 (#483) 27 | 28 | ## [3.0.2] - 2024-02-27 29 | 30 | ### Changed 31 | 32 | - Upgrade to browsertrix crawler 1.5.6 (#482) 33 | 34 | ## [3.0.1] - 2024-02-24 35 | 36 | ### Changed 37 | 38 | - Upgrade to browsertrix crawler 1.5.4 (#476) 39 | 40 | ## [3.0.0] - 2024-02-17 41 | 42 | ### Changed 43 | 44 | - Change solution to report partial ZIM to the Zimfarm and other clients (#304) 45 | - Keep temporary folder when crawler or warc2zim fails, even if not asked for (#468) 46 | - Add many missing Browsertrix Crawler arguments ; drop default overrides by zimit ; drop `--noMobileDevice` setting (not needed anymore) (#433) 47 | - Document all Browsertrix Crawler default arguments values (#416) 48 | - Use preferred Browsertrix Crawler arguments names: (part of #471) 49 | - `--seeds` instead of `--url` 50 | - `--seedFile` instead of `--urlFile` 51 | - `--pageLimit` instead of `--limit` 52 | - `--pageLoadTimeout` instead of `--timeout` 53 | - `--scopeIncludeRx` instead of `--include` 54 | - `--scopeExcludeRx` instead of `--exclude` 55 | - `--pageExtraDelay` instead of `--delay` 56 | - Remove confusion between zimit, warc2zim and crawler stats filenames (part of #471) 57 | - `--statsFilename` is now the crawler stats file (since it is the same name, just like other arguments) 58 | - `--zimit-progress-file` is now the zimit stats location 59 | - `--warc2zim-progress-file` is the warc2zim stats location 60 | - all are optional values, if not set and needed temporary files are used 61 | 62 | ### Fixed 63 | 64 | - Do not create the ZIM when crawl is incomplete (#444) 65 | 66 | ## [2.1.8] - 2024-02-07 67 | 68 | ### Changed 69 | 70 | - Upgrade to browsertrix crawler 1.5.1, Python 3.13 and others (#462 + #464) 71 | 72 | ## [2.1.7] - 2024-01-10 73 | 74 | ### Changed 75 | 76 | - Upgrade to browsertrix crawler 1.4.2 (#450) 77 | - Upgrade to warc2zim 2.2.0 78 | 79 | ## [2.1.6] - 2024-11-07 80 | 81 | ### Changed 82 | 83 | - Upgrade to browsertrix crawler 1.3.5 (#426) 84 | 85 | ## [2.1.5] - 2024-11-01 86 | 87 | ### Changed 88 | 89 | - Upgrade to browsertrix crawler 1.3.4 and warc2zim 2.1.3 (#424) 90 | 91 | ## [2.1.4] - 2024-10-11 92 | 93 | ### Changed 94 | 95 | - Upgrade to browsertrix crawler 1.3.3 (#411) 96 | 97 | ## [2.1.3] - 2024-10-08 98 | 99 | ### Changed 100 | 101 | - Upgrade to browsertrix crawler 1.3.2, warc2zim 2.1.2 and other dependencies (#406) 102 | 103 | ### Fixed 104 | 105 | - Fix help (#393) 106 | 107 | ## [2.1.2] - 2024-09-09 108 | 109 | ### Changed 110 | 111 | - Upgrade to browsertrix crawler 1.3.0-beta.1 (#387) (fixes "Ziming a website with huge assets (e.g. PDFs) is failing to proceed" - #380) 112 | 113 | ## [2.1.1] - 2024-09-05 114 | 115 | ### Added 116 | 117 | - Add support for uncompressed tar archive in --warcs (#369) 118 | 119 | ### Changed 120 | 121 | - Upgrade to browsertrix crawler 1.3.0-beta.0 (#379), including upgrage to Ubuntu Noble (#307) 122 | 123 | ### Fixed 124 | 125 | - Stream files downloads to not exhaust memory (#373) 126 | - Fix documentation on `--diskUtilization` setting (#375) 127 | 128 | ## [2.1.0] - 2024-08-09 129 | 130 | ### Added 131 | 132 | - Add `--custom-behaviors` argument to support path/HTTP(S) URL custom behaviors to pass to the crawler (#313) 133 | - Add daily automated end-to-end tests of a page with Youtube player (#330) 134 | - Add `--warcs` option to directly process WARC files (#301) 135 | 136 | ### Changed 137 | 138 | - Make it clear that `--profile` argument can be an HTTP(S) URL (and not only a path) (#288) 139 | - Fix README imprecisions + add back warc2zim availability in docker image (#314) 140 | - Enhance integration test to assert final content of the ZIM (#287) 141 | - Stop fetching and passing browsertrix crawler version as scraperSuffix to warc2zim (#354) 142 | - Do not log number of WARC files found (#357) 143 | - Upgrade dependencies (warc2zim 2.1.0) 144 | 145 | ### Fixed 146 | 147 | - Sort WARC directories found by modification time (#366) 148 | 149 | ## [2.0.6] - 2024-08-02 150 | 151 | ### Changed 152 | 153 | - Upgraded Browsertrix Crawler to 1.2.6 154 | 155 | ## [2.0.5] - 2024-07-24 156 | 157 | ### Changed 158 | 159 | - Upgraded Browsertrix Crawler to 1.2.5 160 | - Upgraded warc2zim to 2.0.3 161 | 162 | ## [2.0.4] - 2024-07-15 163 | 164 | ### Changed 165 | 166 | - Upgraded Browsertrix Crawler to 1.2.4 (fixes retrieve automatically the assets present in a data-xxx tag #316) 167 | 168 | ## [2.0.3] - 2024-06-24 169 | 170 | ### Changed 171 | 172 | - Upgraded Browsertrix Crawler to 1.2.0 (fixes Youtube videos issue #323) 173 | 174 | ## [2.0.2] - 2024-06-18 175 | 176 | ### Changed 177 | 178 | - Upgrade dependencies (mainly warc2zim 2.0.2) 179 | 180 | 181 | ## [2.0.1] - 2024-06-13 182 | 183 | ### Changed 184 | 185 | - Upgrade dependencies (especially warc2zim 2.0.1 and browsertrix crawler 1.2.0-beta.0) (#318) 186 | 187 | ### Fixed 188 | 189 | - Crawler is not correctly checking disk size / usage (#305) 190 | 191 | ## [2.0.0] - 2024-06-04 192 | 193 | ### Added 194 | 195 | - New `--version` flag to display Zimit version (#234) 196 | - New `--logging` flag to adjust Browsertrix Crawler logging (#273) 197 | - Use new `--scraper-suffix` flag of warc2zim to enhance ZIM "Scraper" metadata (#275) 198 | - New `--noMobileDevice` CLI argument 199 | - Publish Docker image for `linux/arm64` (in addition to `linux/amd64`) (#178) 200 | 201 | ### Changed 202 | 203 | - **Use `warc2zim` version 2**, which works without Service Worker anymore (#193) 204 | - Upgraded Browsertrix Crawler to 1.1.3 205 | - Adopt Python bootstrap conventions 206 | - Upgrade to Python 3.12 + upgrade dependencies 207 | - Removed handling of redirects by zimit, they are handled by browsertrix crawler and detected properly by warc2zim (#284) 208 | - Drop initial check of URL in Python (#256) 209 | - `--userAgent` CLI argument overrides again the `--userAgentSuffix` and `--adminEmail` values 210 | - `--userAgent` CLI arguement is not mandatory anymore 211 | 212 | ### Fixed 213 | 214 | - Fix support for Youtube videos (#291) 215 | - Fix crawler `--waitUntil` values (#289) 216 | 217 | ## [1.6.3] - 2024-01-18 218 | 219 | ### Changed 220 | 221 | - Adapt to new `warc2zim` code structure 222 | - Using browsertrix-crawler 0.12.4 223 | - Using warc2zim 1.5.5 224 | 225 | ### Added 226 | 227 | - New `--build` parameter (optional) to specify the directory holding Browsertrix files ; if not set, `--output` 228 | directory is used ; zimit creates one subdir of this folder per invocation to isolate datasets ; subdir is kept only 229 | if `--keep` is set. 230 | 231 | ### Fixed 232 | 233 | - `--collection` parameter was not working (#252) 234 | 235 | ## [1.6.2] - 2023-11-17 236 | 237 | ### Changed 238 | 239 | - Using browsertrix-crawler 0.12.3 240 | 241 | ### Fixed 242 | 243 | - Fix logic passing args to crawler to support value '0' (#245) 244 | - Fix documentation about Chrome and headless (#248) 245 | 246 | ## [1.6.1] - 2023-11-06 247 | 248 | ### Changed 249 | 250 | - Using browsertrix-crawler 0.12.1 251 | 252 | ## [1.6.0] - 2023-11-02 253 | 254 | ### Changed 255 | 256 | - Scraper fails for all HTTP error codes returned when checking URL at startup (#223) 257 | - User-Agent now has a default value (#228) 258 | - Manipulation of spaces with UA suffix and adminEmail has been modified 259 | - Same User-Agent is used for check_url (Python) and Browsertrix crawler (#227) 260 | - Using browsertrix-crawler 0.12.0 261 | 262 | ## [1.5.3] - 2023-10-02 263 | 264 | ### Changed 265 | 266 | - Using browsertrix-crawler 0.11.2 267 | 268 | ## [1.5.2] - 2023-09-19 269 | 270 | ### Changed 271 | 272 | - Using browsertrix-crawler 0.11.1 273 | 274 | ## [1.5.1] - 2023-09-18 275 | 276 | ### Changed 277 | 278 | - Using browsertrix-crawler 0.11.0 279 | - Scraper stat file is not created empty (#211) 280 | - Crawler statistics are not available anymore (#213) 281 | - Using warc2zim 1.5.4 282 | 283 | ## [1.5.0] - 2023-08-23 284 | 285 | ### Added 286 | 287 | - `--long-description` param 288 | 289 | ## [1.4.1] - 2023-08-23 290 | 291 | ### Changed 292 | 293 | - Using browsertrix-crawler 0.10.4 294 | - Using warc2zim 1.5.3 295 | 296 | ## [1.4.0] - 2023-08-02 297 | 298 | ### Added 299 | 300 | - `--title` to set ZIM title 301 | - `--description` to set ZIM description 302 | - New crawler options: `--maxPageLimit`, `--delay`, `--diskUtilization` 303 | - `--zim-lang` param to set warc2zim's `--lang` (ISO-639-3) 304 | 305 | ### Changed 306 | 307 | - Using browsertrix-crawler 0.10.2 308 | - Default and accepted values for `--waitUntil` from crawler's update 309 | - Using warc2zim 1.5.2 310 | - Disabled Chrome updates to prevent incidental inclusion of update data in WARC/ZIM (#172) 311 | - `--failOnFailedSeed` used inconditionally 312 | - `--lang` now passed to crawler (ISO-639-1) 313 | 314 | ### Removed 315 | 316 | - `--newContext` from crawler's update 317 | 318 | ## [1.3.1] - 2023-02-06 319 | 320 | ### Changed 321 | 322 | - Using browsertrix-crawler 0.8.0 323 | - Using warc2zim version 1.5.1 with wabac.js 2.15.2 324 | 325 | ## [1.3.0] - 2023-02-02 326 | 327 | ### Added 328 | 329 | - Initial url check normalizes homepage redirects to standart ports – 80/443 (#137) 330 | 331 | ### Changed 332 | 333 | - Using warc2zim version 1.5.0 with scope conflict fix and videos fix 334 | - Using browsertrix-crawler 0.8.0-beta.1 335 | - Fixed `--allowHashUrls` being a boolean param 336 | - Increased `check_url` timeout (12s to connect, 27s to read) instead of 10s 337 | 338 | ## [1.2.0] - 2022-06-21 339 | 340 | ### Added 341 | 342 | - `--urlFile` browsertrix crawler parameter 343 | - `--depth` browsertrix crawler parameter 344 | - `--extraHops`, parameter 345 | - `--collection` browsertrix crawler parameter 346 | - `--allowHashUrls` browsertrix crawler parameter 347 | - `--userAgentSuffix` browsertrix crawler parameter 348 | - `--behaviors`, parameter 349 | - `--behaviorTimeout` browsertrix crawler parameter 350 | - `--profile` browsertrix crawler parameter 351 | - `--sizeLimit` browsertrix crawler parameter 352 | - `--timeLimit` browsertrix crawler parameter 353 | - `--healthCheckPort`, parameter 354 | - `--overwrite` parameter 355 | 356 | ### Changed 357 | 358 | - using browsertrix-crawler `0.6.0` and warc2zim `1.4.2` 359 | - default WARC location after crawl changed 360 | from `collections/capture-*/archive/` to `collections/crawl-*/archive/` 361 | 362 | ### Removed 363 | 364 | - `--scroll` browsertrix crawler parameter (see `--behaviors`) 365 | - `--scope` browsertrix crawler parameter (see `--scopeType`, `--include` and `--exclude`) 366 | 367 | 368 | ## [1.1.5] 369 | 370 | - using crawler 0.3.2 and warc2zim 1.3.6 371 | 372 | ## [1.1.4] 373 | 374 | - Defaults to `load,networkidle0` for waitUntil param (same as crawler) 375 | - Allows setting combinations of values for waitUntil param 376 | - Updated warc2zim to 1.3.5 377 | - Updated browsertrix-crawler to 0.3.1 378 | - Warc to zim now written to `{temp_root_dir}/collections/capture-*/archive/` where 379 | `capture-*` is dynamic and includes the datetime. (from browsertrix-crawler) 380 | 381 | ## [1.1.3] 382 | 383 | - allows same first-level-domain redirects 384 | - fixed redirects to URL in scope 385 | - updated crawler to 0.2.0 386 | - `statsFilename` now informs whether limit was hit or not 387 | 388 | ## [1.1.2] 389 | 390 | - added support for --custom-css 391 | - added domains block list (dfault) 392 | 393 | ## [1.1.1] 394 | 395 | - updated browsertrix-crawler to 0.1.4 396 | - autofetcher script to be injected by defaultDriver to capture srcsets + URLs in dynamically added stylesheets 397 | 398 | ## [1.0] 399 | 400 | - initial version using browsertrix-crawler:0.1.3 and warc2zim:1.3.3 401 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM webrecorder/browsertrix-crawler:1.6.0 2 | LABEL org.opencontainers.image.source=https://github.com/openzim/zimit 3 | 4 | # add deadsnakes ppa for latest Python on Ubuntu 5 | RUN add-apt-repository ppa:deadsnakes/ppa -y 6 | 7 | RUN apt-get update \ 8 | && apt-get install -qqy --no-install-recommends \ 9 | libmagic1 \ 10 | python3.13-venv \ 11 | && rm -rf /var/lib/apt/lists/* \ 12 | # python setup (in venv not to conflict with browsertrix) 13 | && python3.13 -m venv /app/zimit \ 14 | # placeholder (default output location) 15 | && mkdir -p /output \ 16 | # disable chrome upgrade 17 | && printf "repo_add_once=\"false\"\nrepo_reenable_on_distupgrade=\"false\"\n" > /etc/default/google-chrome \ 18 | # download list of bad domains to filter-out. intentionnaly ran post-install \ 19 | # so it's not cached in earlier layers (url stays same but content updated) \ 20 | && mkdir -p /tmp/ads \ 21 | && cd /tmp/ads \ 22 | && curl -L -O https://hosts.anudeep.me/mirror/adservers.txt \ 23 | && curl -L -O https://hosts.anudeep.me/mirror/CoinMiner.txt \ 24 | && curl -L -O https://hosts.anudeep.me/mirror/facebook.txt \ 25 | && cat ./*.txt > /etc/blocklist.txt \ 26 | && rm ./*.txt \ 27 | && printf '#!/bin/sh\ncat /etc/blocklist.txt >> /etc/hosts\nexec "$@"' > /usr/local/bin/entrypoint.sh \ 28 | && chmod +x /usr/local/bin/entrypoint.sh 29 | 30 | # Copy pyproject.toml and its dependencies 31 | COPY pyproject.toml README.md /src/ 32 | COPY src/zimit/__about__.py /src/src/zimit/__about__.py 33 | 34 | # Install Python dependencies 35 | RUN . /app/zimit/bin/activate && python -m pip install --no-cache-dir /src 36 | 37 | # Copy code + associated artifacts 38 | COPY src /src/src 39 | COPY *.md /src/ 40 | 41 | # Install + cleanup 42 | RUN . /app/zimit/bin/activate && python -m pip install --no-cache-dir /src \ 43 | && ln -s /app/zimit/bin/zimit /usr/bin/zimit \ 44 | && ln -s /app/zimit/bin/warc2zim /usr/bin/warc2zim \ 45 | && chmod +x /usr/bin/zimit \ 46 | && rm -rf /src 47 | 48 | ENTRYPOINT ["entrypoint.sh"] 49 | CMD ["zimit", "--help"] 50 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | Zimit 2 | ===== 3 | 4 | Zimit is a scraper allowing to create [ZIM file](https://en.wikipedia.org/wiki/ZIM_(file_format)) from any Web site. 5 | 6 | [![CodeFactor](https://www.codefactor.io/repository/github/openzim/zimit/badge)](https://www.codefactor.io/repository/github/openzim/zimit) 7 | [![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0) 8 | [![Docker](https://ghcr-badge.egpl.dev/openzim/zimit/latest_tag?label=docker)](https://ghcr.io/openzim/zimit) 9 | 10 | Zimit adheres to openZIM's [Contribution Guidelines](https://github.com/openzim/overview/wiki/Contributing). 11 | 12 | Zimit has implemented openZIM's [Python bootstrap, conventions and policies](https://github.com/openzim/_python-bootstrap/blob/main/docs/Policy.md) **v1.0.1**. 13 | 14 | Capabilities and known limitations 15 | -------------------- 16 | 17 | While we would like to support as many websites as possible, making an offline archive of any website with a versatile tool obviously has some limitations. 18 | 19 | Most capabilities and known limitations are documented in [warc2zim README](https://github.com/openzim/warc2zim/blob/main/README.md). There are also some limitations in Browsertrix Crawler (used to fetch the website) and wombat (used to properly replay dynamic web requests), but these are not (yet?) clearly documented. 20 | 21 | Technical background 22 | -------------------- 23 | 24 | Zimit runs a fully automated browser-based crawl of a website property and produces a ZIM of the crawled content. Zimit runs in a Docker container. 25 | 26 | The system: 27 | - runs a website crawl with [Browsertrix Crawler](https://github.com/webrecorder/browsertrix-crawler), which produces WARC files 28 | - converts the crawled WARC files to a single ZIM using [warc2zim](https://github.com/openzim/warc2zim) 29 | 30 | The `zimit.py` is the entrypoint for the system. 31 | 32 | After the crawl is done, warc2zim is used to write a zim to the `/output` directory, which should be mounted as a volume to not loose the ZIM created when container stops. 33 | 34 | Using the `--keep` flag, the crawled WARCs and few other artifacts will also be kept in a temp directory inside `/output` 35 | 36 | Usage 37 | ----- 38 | 39 | `zimit` is intended to be run in Docker. Docker image is published at https://github.com/orgs/openzim/packages/container/package/zimit. 40 | 41 | The image accepts the following parameters, **as well as any of the [Browsertrix crawler](https://crawler.docs.browsertrix.com/user-guide/cli-options/) and [warc2zim](https://github.com/openzim/warc2zim) ones**: 42 | 43 | - Required: `--seeds URL` - the url to start crawling from ; multiple URLs can be separated by a comma (even if **usually not needed**, these are just the **seeds** of the crawl) ; first seed URL is used as ZIM homepage 44 | - Required: `--name` - Name of ZIM file 45 | - `--output` - output directory (defaults to `/output`) 46 | - `--pageLimit U` - Limit capture to at most U URLs 47 | - `--scopeExcludeRx ` - skip URLs that match the regex from crawling. Can be specified multiple times. An example is `--scopeExcludeRx="(\?q=|signup-landing\?|\?cid=)"`, where URLs that contain either `?q=` or `signup-landing?` or `?cid=` will be excluded. 48 | - `--workers N` - number of crawl workers to be run in parallel 49 | - `--waitUntil` - Puppeteer setting for how long to wait for page load. See [page.goto waitUntil options](https://github.com/puppeteer/puppeteer/blob/main/docs/api.md#pagegotourl-options). The default is `load`, but for static sites, `--waitUntil domcontentloaded` may be used to speed up the crawl (to avoid waiting for ads to load for example). 50 | - `--keep` - in case of failure, WARC files and other temporary files (which are stored as a subfolder of output directory) are always kept, otherwise they are automatically deleted. Use this flag to always keep WARC files, even in case of success. 51 | 52 | Example command: 53 | 54 | ```bash 55 | docker run ghcr.io/openzim/zimit zimit --help 56 | docker run ghcr.io/openzim/zimit warc2zim --help 57 | docker run -v /output:/output ghcr.io/openzim/zimit zimit --seeds URL --name myzimfile 58 | ``` 59 | 60 | **Note**: Image automatically filters out a large number of ads by using the 3 blocklists from [anudeepND](https://github.com/anudeepND/blacklist). If you don't want this filtering, disable the image's entrypoint in your container (`docker run --entrypoint="" ghcr.io/openzim/zimit ...`). 61 | 62 | To re-build the Docker image locally run: 63 | 64 | ```bash 65 | docker build -t ghcr.io/openzim/zimit . 66 | ``` 67 | 68 | FAQ 69 | --- 70 | 71 | The Zimit contributor's team maintains [a page with most Frequently Asked Questions](https://github.com/openzim/zimit/wiki/Frequently-Asked-Questions). 72 | 73 | Nota bene 74 | --------- 75 | 76 | While Zimit 1.x relied on a Service Worker to display the ZIM content, this is not anymore the case 77 | since Zimit 2.x which does not have any special requirements anymore. 78 | 79 | It should also be noted that a first version of a generic HTTP scraper was created in 2016 during 80 | the [Wikimania Esino Lario 81 | Hackathon](https://wikimania2016.wikimedia.org/wiki/Programme/Kiwix-dedicated_Hackathon). 82 | 83 | That version is now considered outdated and [archived in `2016` 84 | branch](https://github.com/openzim/zimit/tree/2016). 85 | 86 | License 87 | ------- 88 | 89 | [GPLv3](https://www.gnu.org/licenses/gpl-3.0) or later, see 90 | [LICENSE](LICENSE) for more details. 91 | -------------------------------------------------------------------------------- /offliner-definition.json: -------------------------------------------------------------------------------- 1 | { 2 | "offliner_id": "zimit", 3 | "stdOutput": true, 4 | "stdStats": "zimit-progress-file", 5 | "flags": { 6 | "seeds": { 7 | "type": "string", 8 | "required": false, 9 | "title": "Seeds", 10 | "description": "The seed URL(s) to start crawling from. Multile seed URL must be separated by a comma (usually not needed, these are just the crawl seeds). First seed URL is used as ZIM homepage" 11 | }, 12 | "seed_file": { 13 | "type": "string", 14 | "required": false, 15 | "title": "Seed File", 16 | "description": "If set, read a list of seed urls, one per line. HTTPS URL to an online file." 17 | }, 18 | "lang": { 19 | "type": "string", 20 | "required": false, 21 | "title": "Browser Language", 22 | "description": "If set, sets the language used by the browser, should be ISO 639 language[-country] code, e.g. `en` or `en-GB`" 23 | }, 24 | "title": { 25 | "type": "string", 26 | "required": false, 27 | "title": "Title", 28 | "description": "Custom title for your ZIM. Defaults to title of main page", 29 | "minLength": 1, 30 | "maxLength": 30 31 | }, 32 | "description": { 33 | "type": "string", 34 | "required": false, 35 | "title": "Description", 36 | "description": "Description for ZIM", 37 | "minLength": 1, 38 | "maxLength": 80 39 | }, 40 | "favicon": { 41 | "type": "url", 42 | "required": false, 43 | "title": "Illustration", 44 | "description": "URL for Illustration. " 45 | }, 46 | "tags": { 47 | "type": "string", 48 | "required": false, 49 | "title": "ZIM Tags", 50 | "description": "Single string with individual tags separated by a semicolon." 51 | }, 52 | "creator": { 53 | "type": "string", 54 | "required": false, 55 | "title": "Creator", 56 | "description": "Name of content creator" 57 | }, 58 | "publisher": { 59 | "type": "string", 60 | "required": false, 61 | "title": "Publisher", 62 | "isPublisher": true, 63 | "description": "Custom publisher name (ZIM metadata). openZIM otherwise" 64 | }, 65 | "source": { 66 | "type": "string", 67 | "required": false, 68 | "title": "Source", 69 | "description": "Source name/URL of content" 70 | }, 71 | "workers": { 72 | "type": "integer", 73 | "required": false, 74 | "title": "Workers", 75 | "description": "The number of workers to run in parallel. Defaults to 1", 76 | "min": 1 77 | }, 78 | "wait_until": { 79 | "type": "string", 80 | "required": false, 81 | "title": "WaitUntil", 82 | "description": "Puppeteer page.goto() condition to wait for before continuing. One of load, domcontentloaded, networkidle0 or networkidle2, or a comma-separated combination of those. Default is load,networkidle2" 83 | }, 84 | "extra_hops": { 85 | "type": "integer", 86 | "required": false, 87 | "title": "Extra Hops", 88 | "description": "Number of extra 'hops' to follow, beyond the current scope. Default is 0", 89 | "min": 0 90 | }, 91 | "page_limit": { 92 | "type": "integer", 93 | "required": false, 94 | "title": "Page Limit", 95 | "description": "Limit crawl to this number of pages. Default is 0 (no-limit).", 96 | "min": 0 97 | }, 98 | "max_page_limit": { 99 | "type": "integer", 100 | "required": false, 101 | "title": "Max Page Limit", 102 | "description": "Maximum pages to crawl, overriding pageLimit if both are set. Default is 0 (no-limit)", 103 | "min": 0 104 | }, 105 | "page_load_timeout": { 106 | "type": "integer", 107 | "required": false, 108 | "title": "Page Load Timeout", 109 | "description": "Timeout for each page to load (in seconds). Default is 90", 110 | "min": 0 111 | }, 112 | "scope_type": { 113 | "type": "string-enum", 114 | "required": false, 115 | "title": "Scope Type", 116 | "description": "A predfined scope of the crawl. For more customization, use 'custom' and set scopeIncludeRx/scopeExcludeRx regexes. Default is custom if scopeIncludeRx is set, prefix otherwise.", 117 | "choices": [ 118 | { 119 | "title": "Page", 120 | "value": "page" 121 | }, 122 | { 123 | "title": "Page SPA", 124 | "value": "page-spa" 125 | }, 126 | { 127 | "title": "Prefix", 128 | "value": "prefix" 129 | }, 130 | { 131 | "title": "Host", 132 | "value": "host" 133 | }, 134 | { 135 | "title": "Domain", 136 | "value": "domain" 137 | }, 138 | { 139 | "title": "Any", 140 | "value": "any" 141 | }, 142 | { 143 | "title": "Custom", 144 | "value": "custom" 145 | } 146 | ] 147 | }, 148 | "scope_include_rx": { 149 | "type": "string", 150 | "required": false, 151 | "title": "Scope Include Regex", 152 | "description": "Regex of page URLs that should be included in the crawl (defaults to the immediate directory of seed)" 153 | }, 154 | "scope_exclude_rx": { 155 | "type": "string", 156 | "required": false, 157 | "title": "Scope Exclude Regex", 158 | "description": "Regex of page URLs that should be excluded from the crawl" 159 | }, 160 | "allow_hash_urls": { 161 | "type": "boolean", 162 | "required": false, 163 | "title": "Allow Hashtag URLs", 164 | "description": "Allow Hashtag URLs, useful for single-page-application crawling or when different hashtags load dynamic content" 165 | }, 166 | "mobile_device": { 167 | "type": "string-enum", 168 | "required": false, 169 | "title": "As device", 170 | "description": "Device to crawl as. See Pupeeter's Device.ts for a list", 171 | "choices": [ 172 | { 173 | "title": "Blackberry Playbook", 174 | "value": "Blackberry PlayBook" 175 | }, 176 | { 177 | "title": "Blackberry Playbook Landscape", 178 | "value": "Blackberry PlayBook landscape" 179 | }, 180 | { 181 | "title": "Blackberry Z30", 182 | "value": "BlackBerry Z30" 183 | }, 184 | { 185 | "title": "Blackberry Z30 Landscape", 186 | "value": "BlackBerry Z30 landscape" 187 | }, 188 | { 189 | "title": "Galaxy Note 3", 190 | "value": "Galaxy Note 3" 191 | }, 192 | { 193 | "title": "Galaxy Note 3 Landscape", 194 | "value": "Galaxy Note 3 landscape" 195 | }, 196 | { 197 | "title": "Galaxy Note II", 198 | "value": "Galaxy Note II" 199 | }, 200 | { 201 | "title": "Galaxy Note II Landscape", 202 | "value": "Galaxy Note II landscape" 203 | }, 204 | { 205 | "title": "Galaxy S III", 206 | "value": "Galaxy S III" 207 | }, 208 | { 209 | "title": "Galaxy S III Landscape", 210 | "value": "Galaxy S III landscape" 211 | }, 212 | { 213 | "title": "Galaxy S5", 214 | "value": "Galaxy S5" 215 | }, 216 | { 217 | "title": "Galaxy S5 Landscape", 218 | "value": "Galaxy S5 landscape" 219 | }, 220 | { 221 | "title": "Galaxy S8", 222 | "value": "Galaxy S8" 223 | }, 224 | { 225 | "title": "Galaxy S8 Landscape", 226 | "value": "Galaxy S8 landscape" 227 | }, 228 | { 229 | "title": "Galaxy S9 Plus", 230 | "value": "Galaxy S9+" 231 | }, 232 | { 233 | "title": "Galaxy S9 Plus Landscape", 234 | "value": "Galaxy S9+ landscape" 235 | }, 236 | { 237 | "title": "Galaxy Tab S4", 238 | "value": "Galaxy Tab S4" 239 | }, 240 | { 241 | "title": "Galaxy Tab S4 Landscape", 242 | "value": "Galaxy Tab S4 landscape" 243 | }, 244 | { 245 | "title": "iPad", 246 | "value": "iPad" 247 | }, 248 | { 249 | "title": "iPad Landscape", 250 | "value": "iPad landscape" 251 | }, 252 | { 253 | "title": "iPad Gen 6", 254 | "value": "iPad (gen 6)" 255 | }, 256 | { 257 | "title": "iPad Gen 6 Landscape", 258 | "value": "iPad (gen 6) landscape" 259 | }, 260 | { 261 | "title": "iPad Gen 7", 262 | "value": "iPad (gen 7)" 263 | }, 264 | { 265 | "title": "iPad Gen 7 Landscape", 266 | "value": "iPad (gen 7) landscape" 267 | }, 268 | { 269 | "title": "iPad Mini", 270 | "value": "iPad Mini" 271 | }, 272 | { 273 | "title": "iPad Mini Landscape", 274 | "value": "iPad Mini landscape" 275 | }, 276 | { 277 | "title": "iPad Pro", 278 | "value": "iPad Pro" 279 | }, 280 | { 281 | "title": "iPad Pro Landscape", 282 | "value": "iPad Pro landscape" 283 | }, 284 | { 285 | "title": "iPad Pro 11", 286 | "value": "iPad Pro 11" 287 | }, 288 | { 289 | "title": "iPad Pro 11 Landscape", 290 | "value": "iPad Pro 11 landscape" 291 | }, 292 | { 293 | "title": "iPhone 4", 294 | "value": "iPhone 4" 295 | }, 296 | { 297 | "title": "iPhone 4 Landscape", 298 | "value": "iPhone 4 landscape" 299 | }, 300 | { 301 | "title": "iPhone 5", 302 | "value": "iPhone 5" 303 | }, 304 | { 305 | "title": "iPhone 5 Landscape", 306 | "value": "iPhone 5 landscape" 307 | }, 308 | { 309 | "title": "iPhone 6", 310 | "value": "iPhone 6" 311 | }, 312 | { 313 | "title": "iPhone 6 Landscape", 314 | "value": "iPhone 6 landscape" 315 | }, 316 | { 317 | "title": "iPhone 6 Plus", 318 | "value": "iPhone 6 Plus" 319 | }, 320 | { 321 | "title": "iPhone 6 Plus Landscape", 322 | "value": "iPhone 6 Plus landscape" 323 | }, 324 | { 325 | "title": "iPhone 7", 326 | "value": "iPhone 7" 327 | }, 328 | { 329 | "title": "iPhone 7 Landscape", 330 | "value": "iPhone 7 landscape" 331 | }, 332 | { 333 | "title": "iPhone 7 Plus", 334 | "value": "iPhone 7 Plus" 335 | }, 336 | { 337 | "title": "iPhone 7 Plus Landscape", 338 | "value": "iPhone 7 Plus landscape" 339 | }, 340 | { 341 | "title": "iPhone 8", 342 | "value": "iPhone 8" 343 | }, 344 | { 345 | "title": "iPhone 8 Landscape", 346 | "value": "iPhone 8 landscape" 347 | }, 348 | { 349 | "title": "iPhone 8 Plus", 350 | "value": "iPhone 8 Plus" 351 | }, 352 | { 353 | "title": "iPhone 8 Plus Landscape", 354 | "value": "iPhone 8 Plus landscape" 355 | }, 356 | { 357 | "title": "iPhone SE", 358 | "value": "iPhone SE" 359 | }, 360 | { 361 | "title": "iPhone SE Landscape", 362 | "value": "iPhone SE landscape" 363 | }, 364 | { 365 | "title": "iPhone X", 366 | "value": "iPhone X" 367 | }, 368 | { 369 | "title": "iPhone X Landscape", 370 | "value": "iPhone X landscape" 371 | }, 372 | { 373 | "title": "iPhone XR", 374 | "value": "iPhone XR" 375 | }, 376 | { 377 | "title": "iPhone XR Landscape", 378 | "value": "iPhone XR landscape" 379 | }, 380 | { 381 | "title": "iPhone 11", 382 | "value": "iPhone 11" 383 | }, 384 | { 385 | "title": "iPhone 11 Landscape", 386 | "value": "iPhone 11 landscape" 387 | }, 388 | { 389 | "title": "iPhone 11 Pro", 390 | "value": "iPhone 11 Pro" 391 | }, 392 | { 393 | "title": "iPhone 11 Pro Landscape", 394 | "value": "iPhone 11 Pro landscape" 395 | }, 396 | { 397 | "title": "iPhone 11 Pro Max", 398 | "value": "iPhone 11 Pro Max" 399 | }, 400 | { 401 | "title": "iPhone 11 Pro Max Landscape", 402 | "value": "iPhone 11 Pro Max landscape" 403 | }, 404 | { 405 | "title": "iPhone 12", 406 | "value": "iPhone 12" 407 | }, 408 | { 409 | "title": "iPhone 12 Landscape", 410 | "value": "iPhone 12 landscape" 411 | }, 412 | { 413 | "title": "iPhone 12 Pro", 414 | "value": "iPhone 12 Pro" 415 | }, 416 | { 417 | "title": "iPhone 12 Pro Landscape", 418 | "value": "iPhone 12 Pro landscape" 419 | }, 420 | { 421 | "title": "iPhone 12 Pro Max", 422 | "value": "iPhone 12 Pro Max" 423 | }, 424 | { 425 | "title": "iPhone 12 Pro Max Landscape", 426 | "value": "iPhone 12 Pro Max landscape" 427 | }, 428 | { 429 | "title": "iPhone 12 Mini", 430 | "value": "iPhone 12 Mini" 431 | }, 432 | { 433 | "title": "iPhone 12 Mini Landscape", 434 | "value": "iPhone 12 Mini landscape" 435 | }, 436 | { 437 | "title": "iPhone 13", 438 | "value": "iPhone 13" 439 | }, 440 | { 441 | "title": "iPhone 13 Landscape", 442 | "value": "iPhone 13 landscape" 443 | }, 444 | { 445 | "title": "iPhone 13 Pro", 446 | "value": "iPhone 13 Pro" 447 | }, 448 | { 449 | "title": "iPhone 13 Pro Landscape", 450 | "value": "iPhone 13 Pro landscape" 451 | }, 452 | { 453 | "title": "iPhone 13 Pro Max", 454 | "value": "iPhone 13 Pro Max" 455 | }, 456 | { 457 | "title": "iPhone 13 Pro Max Landscape", 458 | "value": "iPhone 13 Pro Max landscape" 459 | }, 460 | { 461 | "title": "iPhone 13 Mini", 462 | "value": "iPhone 13 Mini" 463 | }, 464 | { 465 | "title": "iPhone 13 Mini Landscape", 466 | "value": "iPhone 13 Mini landscape" 467 | }, 468 | { 469 | "title": "Jio Phone 2", 470 | "value": "JioPhone 2" 471 | }, 472 | { 473 | "title": "Jio Phone 2 Landscape", 474 | "value": "JioPhone 2 landscape" 475 | }, 476 | { 477 | "title": "Kindle Fire HDX", 478 | "value": "Kindle Fire HDX" 479 | }, 480 | { 481 | "title": "Kindle Fire HDX Landscape", 482 | "value": "Kindle Fire HDX landscape" 483 | }, 484 | { 485 | "title": "LG Optimus L70", 486 | "value": "LG Optimus L70" 487 | }, 488 | { 489 | "title": "LG Optimus L70 Landscape", 490 | "value": "LG Optimus L70 landscape" 491 | }, 492 | { 493 | "title": "Microsoft Lumia 550", 494 | "value": "Microsoft Lumia 550" 495 | }, 496 | { 497 | "title": "Microsoft Lumia 950", 498 | "value": "Microsoft Lumia 950" 499 | }, 500 | { 501 | "title": "Microsoft Lumia 950 Landscape", 502 | "value": "Microsoft Lumia 950 landscape" 503 | }, 504 | { 505 | "title": "Nexus 10", 506 | "value": "Nexus 10" 507 | }, 508 | { 509 | "title": "Nexus 10 Landscape", 510 | "value": "Nexus 10 landscape" 511 | }, 512 | { 513 | "title": "Nexus 4", 514 | "value": "Nexus 4" 515 | }, 516 | { 517 | "title": "Nexus 4 Landscape", 518 | "value": "Nexus 4 landscape" 519 | }, 520 | { 521 | "title": "Nexus 5", 522 | "value": "Nexus 5" 523 | }, 524 | { 525 | "title": "Nexus 5 Landscape", 526 | "value": "Nexus 5 landscape" 527 | }, 528 | { 529 | "title": "Nexus 5X", 530 | "value": "Nexus 5X" 531 | }, 532 | { 533 | "title": "Nexus 5X Landscape", 534 | "value": "Nexus 5X landscape" 535 | }, 536 | { 537 | "title": "Nexus 6", 538 | "value": "Nexus 6" 539 | }, 540 | { 541 | "title": "Nexus 6 Landscape", 542 | "value": "Nexus 6 landscape" 543 | }, 544 | { 545 | "title": "Nexus 6P", 546 | "value": "Nexus 6P" 547 | }, 548 | { 549 | "title": "Nexus 6P Landscape", 550 | "value": "Nexus 6P landscape" 551 | }, 552 | { 553 | "title": "Nexus 7", 554 | "value": "Nexus 7" 555 | }, 556 | { 557 | "title": "Nexus 7 Landscape", 558 | "value": "Nexus 7 landscape" 559 | }, 560 | { 561 | "title": "Nokia Lumia 520", 562 | "value": "Nokia Lumia 520" 563 | }, 564 | { 565 | "title": "Nokia Lumia 520 Landscape", 566 | "value": "Nokia Lumia 520 landscape" 567 | }, 568 | { 569 | "title": "Nokia N9", 570 | "value": "Nokia N9" 571 | }, 572 | { 573 | "title": "Nokia N9 Landscape", 574 | "value": "Nokia N9 landscape" 575 | }, 576 | { 577 | "title": "Pixel 2", 578 | "value": "Pixel 2" 579 | }, 580 | { 581 | "title": "Pixel 2 Landscape", 582 | "value": "Pixel 2 landscape" 583 | }, 584 | { 585 | "title": "Pixel 2 XL", 586 | "value": "Pixel 2 XL" 587 | }, 588 | { 589 | "title": "Pixel 2 XL Landscape", 590 | "value": "Pixel 2 XL landscape" 591 | }, 592 | { 593 | "title": "Pixel 3", 594 | "value": "Pixel 3" 595 | }, 596 | { 597 | "title": "Pixel 3 Landscape", 598 | "value": "Pixel 3 landscape" 599 | }, 600 | { 601 | "title": "Pixel 4", 602 | "value": "Pixel 4" 603 | }, 604 | { 605 | "title": "Pixel 4 Landscape", 606 | "value": "Pixel 4 landscape" 607 | }, 608 | { 609 | "title": "Pixel 4A 5G", 610 | "value": "Pixel 4a (5G)" 611 | }, 612 | { 613 | "title": "Pixel 4A 5G Landscape", 614 | "value": "Pixel 4a (5G) landscape" 615 | }, 616 | { 617 | "title": "Pixel 5", 618 | "value": "Pixel 5" 619 | }, 620 | { 621 | "title": "Pixel 5 Landscape", 622 | "value": "Pixel 5 landscape" 623 | }, 624 | { 625 | "title": "Moto G4", 626 | "value": "Moto G4" 627 | }, 628 | { 629 | "title": "Moto G4 Landscape", 630 | "value": "Moto G4 landscape" 631 | } 632 | ] 633 | }, 634 | "select_links": { 635 | "type": "string", 636 | "required": false, 637 | "title": "Select Links", 638 | "description": "One or more selectors for extracting links, in the format [css selector]->[property to use],[css selector]->@[attribute to use]" 639 | }, 640 | "click_selector": { 641 | "type": "string", 642 | "required": false, 643 | "title": "Click Selector", 644 | "description": "Selector for elements to click when using the autoclick behavior. Default is 'a'" 645 | }, 646 | "block_rules": { 647 | "type": "string", 648 | "required": false, 649 | "title": "Block Rules", 650 | "description": "Additional rules for blocking certain URLs from being loaded, by URL regex and optionally via text match in an iframe" 651 | }, 652 | "block_message": { 653 | "type": "string", 654 | "required": false, 655 | "title": "Block Message", 656 | "description": "If specified, when a URL is blocked, a record with this error message is added instead" 657 | }, 658 | "block_ads": { 659 | "type": "boolean", 660 | "required": false, 661 | "title": "Block Ads", 662 | "description": "If set, block advertisements from being loaded (based on Stephen Black's blocklist). Note that some bad domains are also blocked by zimit configuration even if this option is not set." 663 | }, 664 | "ad_block_message": { 665 | "type": "string", 666 | "required": false, 667 | "title": "Ads Block Message", 668 | "description": "If specified, when an ad is blocked, a record with this error message is added instead" 669 | }, 670 | "user_agent": { 671 | "type": "string", 672 | "required": false, 673 | "title": "User Agent", 674 | "description": "Override user-agent with specified" 675 | }, 676 | "user_agent_suffix": { 677 | "type": "string", 678 | "required": false, 679 | "title": "User Agent Suffix", 680 | "description": "Append suffix to existing browser user-agent. Defaults to +Zimit" 681 | }, 682 | "use_sitemap": { 683 | "type": "string", 684 | "required": false, 685 | "title": "Sitemap URL", 686 | "description": "Use as sitemap to get additional URLs for the crawl (usually at /sitemap.xml)" 687 | }, 688 | "sitemap_from_date": { 689 | "type": "string", 690 | "required": false, 691 | "title": "Sitemap From Date", 692 | "description": "If set, filter URLs from sitemaps to those greater than or equal to (>=) provided ISO Date string (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS or partial date)" 693 | }, 694 | "sitemap_to_date": { 695 | "type": "string", 696 | "required": false, 697 | "title": "Sitemap To Date", 698 | "description": "If set, filter URLs from sitemaps to those less than or equal to (<=) provided ISO Date string (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS or partial date)" 699 | }, 700 | "behavior_timeout": { 701 | "type": "integer", 702 | "required": false, 703 | "title": "Behavior Timeout", 704 | "description": "If >0, timeout (in seconds) for in-page behavior will run on each page. If 0, a behavior can run until finish. Default is 90.", 705 | "min": 0 706 | }, 707 | "post_load_delay": { 708 | "type": "integer", 709 | "required": false, 710 | "title": "Post Load Delay", 711 | "description": "If >0, amount of time to sleep (in seconds) after page has loaded, before taking screenshots / getting text / running behaviors. Default is 0.", 712 | "min": 0 713 | }, 714 | "page_extra_delay": { 715 | "type": "integer", 716 | "required": false, 717 | "title": "Page Extra Delay", 718 | "description": "If >0, amount of time to sleep (in seconds) after behaviors before moving on to next page. Default is 0.", 719 | "min": 0 720 | }, 721 | "dedup_policy": { 722 | "type": "string-enum", 723 | "required": false, 724 | "title": "Dedup Policy", 725 | "description": "Deduplication policy. One of skip, revisit or keep. Default is skip", 726 | "choices": [ 727 | { 728 | "title": "Skip", 729 | "value": "skip" 730 | }, 731 | { 732 | "title": "Revisit", 733 | "value": "revisit" 734 | }, 735 | { 736 | "title": "Keep", 737 | "value": "keep" 738 | } 739 | ] 740 | }, 741 | "screenshot": { 742 | "type": "string", 743 | "required": false, 744 | "title": "Screenshot", 745 | "description": "Screenshot options for crawler. One of view, thumbnail, fullPage, fullPageFinal or a comma-separated combination of those." 746 | }, 747 | "size_soft_limit": { 748 | "type": "integer", 749 | "required": false, 750 | "title": "Size Soft Limit", 751 | "description": "If set, save crawl state and stop crawl if WARC size exceeds this value. ZIM will still be created.", 752 | "min": 0 753 | }, 754 | "size_hard_limit": { 755 | "type": "integer", 756 | "required": false, 757 | "title": "Size Hard Limit", 758 | "description": "If set, exit crawler and fail the scraper immediately if WARC size exceeds this value", 759 | "min": 0 760 | }, 761 | "disk_utilization": { 762 | "type": "integer", 763 | "required": false, 764 | "title": "Disk Utilization", 765 | "description": "Save state and exit if disk utilization exceeds this percentage value. Default (if not set) is 90%. Set to 0 to disable disk utilization check.", 766 | "min": 0 767 | }, 768 | "time_soft_limit": { 769 | "type": "integer", 770 | "required": false, 771 | "title": "Time Soft Limit", 772 | "description": "If set, save crawl state and stop crawl if WARC(s) creation takes longer than this value, in seconds. ZIM will still be created.", 773 | "min": 0 774 | }, 775 | "time_hard_limit": { 776 | "type": "integer", 777 | "required": false, 778 | "title": "Time Hard Limit", 779 | "description": "If set, exit crawler and fail the scraper immediately if WARC(s) creation takes longer than this value, in seconds", 780 | "min": 0 781 | }, 782 | "net_idle_wait": { 783 | "type": "integer", 784 | "required": false, 785 | "title": "Net Idle Wait", 786 | "description": "If set, wait for network idle after page load and after behaviors are done (in seconds). If -1 (default), determine based on scope." 787 | }, 788 | "origin_override": { 789 | "type": "string", 790 | "required": false, 791 | "title": "Origin Override", 792 | "description": "If set, will redirect requests from each origin in key to origin in the value, eg. https://host:port=http://alt-host:alt-port." 793 | }, 794 | "max_page_retries": { 795 | "type": "integer", 796 | "required": false, 797 | "title": "Max Page Retries", 798 | "description": "If set, number of times to retry a page that failed to load before page is considered to have failed. Default is 2.", 799 | "min": 0 800 | }, 801 | "fail_on_failed_seed": { 802 | "type": "boolean", 803 | "required": false, 804 | "title": "Fail on failed seed", 805 | "description": "Whether to display additional logs" 806 | }, 807 | "fail_on_invalid_status": { 808 | "type": "boolean", 809 | "required": false, 810 | "title": "Fail on invalid status", 811 | "description": "If set, will treat pages with 4xx or 5xx response as failures. When combined with --failOnFailedLimit or --failOnFailedSeed may result in crawl failing due to non-200 responses" 812 | }, 813 | "fail_on_failed_limit": { 814 | "type": "integer", 815 | "required": false, 816 | "title": "Fail on failed - Limit", 817 | "description": "If set, save state and exit if number of failed pages exceeds this value.", 818 | "min": 0 819 | }, 820 | "warcs": { 821 | "type": "string", 822 | "required": false, 823 | "title": "WARC files", 824 | "description": "Comma-separated list of WARC files to use as input." 825 | }, 826 | "verbose": { 827 | "type": "boolean", 828 | "required": false, 829 | "title": "Verbose mode", 830 | "description": "Whether to display additional logs" 831 | }, 832 | "keep": { 833 | "type": "boolean", 834 | "required": false, 835 | "title": "Keep", 836 | "description": "Should be True. Developer option: must be True if we want to keep the WARC files for artifacts archiving.", 837 | "default": true 838 | }, 839 | "output": { 840 | "type": "string", 841 | "required": false, 842 | "title": "Output folder", 843 | "description": "Output folder for ZIM file(s). Leave it as `/output`", 844 | "pattern": "^/output$" 845 | }, 846 | "admin_email": { 847 | "type": "email", 848 | "required": false, 849 | "title": "Admin Email", 850 | "description": "Admin Email for crawler: used in UserAgent so website admin can contact us", 851 | "default": "contact+zimfarm@kiwix.org" 852 | }, 853 | "profile": { 854 | "type": "string", 855 | "required": false, 856 | "title": "Browser profile", 857 | "description": "Path or HTTP(S) URL to tar.gz file which contains the browser profile directory for Browsertrix crawler." 858 | }, 859 | "behaviors": { 860 | "type": "string", 861 | "required": false, 862 | "title": "Behaviors", 863 | "description": "Which background behaviors to enable on each page. Defaults to autoplay,autofetch,siteSpecific." 864 | }, 865 | "depth": { 866 | "type": "integer", 867 | "required": false, 868 | "title": "Depth", 869 | "description": "The depth of the crawl for all seeds. Default is -1 (infinite).", 870 | "min": -1 871 | }, 872 | "zim_lang": { 873 | "type": "string", 874 | "required": false, 875 | "title": "ZIM Language", 876 | "description": "Language metadata of ZIM (warc2zim --lang param). ISO-639-3 code. Retrieved from homepage if found, fallback to `eng`", 877 | "alias": "zim-lang", 878 | "customValidator": "language_code" 879 | }, 880 | "long_description": { 881 | "type": "string", 882 | "required": false, 883 | "title": "Long description", 884 | "description": "Optional long description for your ZIM", 885 | "minLength": 1, 886 | "maxLength": 4000, 887 | "alias": "long-description" 888 | }, 889 | "custom_css": { 890 | "type": "url", 891 | "required": false, 892 | "title": "Custom CSS", 893 | "description": "URL to a CSS file to inject into pages", 894 | "alias": "custom-css" 895 | }, 896 | "charsets_to_try": { 897 | "type": "string", 898 | "required": false, 899 | "title": "Charsets to try", 900 | "description": "List of charsets to try decode content when charset is not found", 901 | "alias": "charsets-to-try" 902 | }, 903 | "ignore_content_header_charsets": { 904 | "type": "boolean", 905 | "required": false, 906 | "title": "Ignore Content Header Charsets", 907 | "description": "Ignore the charsets specified in content headers - first bytes - typically because they are wrong.", 908 | "alias": "ignore-content-header-charsets" 909 | }, 910 | "content_header_bytes_length": { 911 | "type": "integer", 912 | "required": false, 913 | "title": "Content Header Bytes Length", 914 | "description": "How many bytes to consider when searching for content charsets in header (default is 1024).", 915 | "alias": "content-header-bytes-length", 916 | "min": 0 917 | }, 918 | "ignore_http_header_charsets": { 919 | "type": "boolean", 920 | "required": false, 921 | "title": "Ignore HTTP Header Charsets", 922 | "description": "Ignore the charsets specified in HTTP `Content-Type` headers, typically because they are wrong.", 923 | "alias": "ignore-http-header-charsets" 924 | }, 925 | "encoding_aliases": { 926 | "type": "string", 927 | "required": false, 928 | "title": "Encoding Aliases", 929 | "description": "List of encoding/charset aliases to decode WARC content. Aliases are used when the encoding specified in upstream server exists in Python under a different name. This parameter is single string, multiple values are separated by a comma, like in alias1=encoding1,alias2=encoding2.", 930 | "alias": "encoding-aliases" 931 | }, 932 | "custom_behaviors": { 933 | "type": "string", 934 | "required": false, 935 | "title": "Custom Behaviors", 936 | "description": "JS code for custom behaviors to customize crawler. Single string with individual JS files URL/path separated by a comma.", 937 | "alias": "custom-behaviours" 938 | }, 939 | "zimit_progress_file": { 940 | "type": "string", 941 | "required": false, 942 | "title": "Zimit Progress File", 943 | "description": "Scraping progress file. Leave it as `/output/task_progress.json`", 944 | "alias": "zimit-progress-file", 945 | "pattern": "^/output/task_progress\\.json$" 946 | }, 947 | "replay_viewer_source": { 948 | "type": "url", 949 | "required": false, 950 | "title": "Replay Viewer Source", 951 | "description": "URL from which to load the ReplayWeb.page replay viewer from", 952 | "alias": "replay-viewer-source" 953 | }, 954 | "zim_file": { 955 | "type": "string", 956 | "required": false, 957 | "title": "ZIM filename", 958 | "description": "ZIM file name (based on --name if not provided). Include {period} to insert date period dynamically", 959 | "alias": "zim-file", 960 | "pattern": "^([a-z0-9\\-\\.]+_)([a-z\\-]+_)([a-z0-9\\-\\.]+_)([a-z0-9\\-\\.]+_|)([\\d]{4}-[\\d]{2}|\\{period\\}).zim$", 961 | "relaxedPattern": "^[A-Za-z0-9._-]+$" 962 | }, 963 | "name": { 964 | "type": "string", 965 | "required": true, 966 | "title": "ZIM name", 967 | "description": "Name of the ZIM.", 968 | "alias": "name", 969 | "pattern": "^([a-z0-9\\-\\.]+_)([a-z\\-]+_)([a-z0-9\\-\\.]+)$", 970 | "relaxedPattern": "^[A-Za-z0-9._-]+$" 971 | } 972 | } 973 | } 974 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [build-system] 2 | requires = ["hatchling", "hatch-openzim"] 3 | build-backend = "hatchling.build" 4 | 5 | [project] 6 | name = "zimit" 7 | requires-python = ">=3.13,<3.14" 8 | description = "Make ZIM file from any website through crawling" 9 | readme = "README.md" 10 | dependencies = [ 11 | "requests==2.32.3", 12 | "inotify==0.2.10", 13 | "tld==0.13", 14 | "warc2zim @ git+https://github.com/openzim/warc2zim@main", 15 | ] 16 | dynamic = ["authors", "classifiers", "keywords", "license", "version", "urls"] 17 | 18 | [tool.hatch.metadata.hooks.openzim-metadata] 19 | kind = "scraper" 20 | 21 | [tool.hatch.metadata] 22 | allow-direct-references = true # to be removed once we use a released warc2zim version 23 | 24 | [project.optional-dependencies] 25 | scripts = [ 26 | "invoke==2.2.0", 27 | ] 28 | lint = [ 29 | "black==25.1.0", 30 | "ruff==0.9.4", 31 | ] 32 | check = [ 33 | "pyright==1.1.393", 34 | ] 35 | test = [ 36 | "pytest==8.3.4", 37 | "coverage==7.6.10", 38 | ] 39 | dev = [ 40 | "pre-commit==4.1.0", 41 | "debugpy==1.8.12", 42 | "selenium==4.28.1", # used in daily tests, convenient for dev purpose (autocompletion) 43 | "zimit[scripts]", 44 | "zimit[lint]", 45 | "zimit[test]", 46 | "zimit[check]", 47 | ] 48 | 49 | [project.scripts] 50 | zimit = "zimit:zimit.zimit" 51 | 52 | [tool.hatch.version] 53 | path = "src/zimit/__about__.py" 54 | 55 | [tool.hatch.build] 56 | exclude = [ 57 | "/.github", 58 | ] 59 | 60 | [tool.hatch.build.targets.wheel] 61 | packages = ["src/zimit"] 62 | 63 | [tool.hatch.envs.default] 64 | features = ["dev"] 65 | 66 | [tool.hatch.envs.test] 67 | features = ["scripts", "test"] 68 | 69 | [tool.hatch.envs.test.scripts] 70 | run = "inv test --args '{args}'" 71 | run-cov = "inv test-cov --args '{args}'" 72 | report-cov = "inv report-cov" 73 | coverage = "inv coverage --args '{args}'" 74 | html = "inv coverage --html --args '{args}'" 75 | 76 | [tool.hatch.envs.lint] 77 | template = "lint" 78 | skip-install = false 79 | features = ["scripts", "lint"] 80 | 81 | [tool.hatch.envs.lint.scripts] 82 | black = "inv lint-black --args '{args}'" 83 | ruff = "inv lint-ruff --args '{args}'" 84 | all = "inv lintall --args '{args}'" 85 | fix-black = "inv fix-black --args '{args}'" 86 | fix-ruff = "inv fix-ruff --args '{args}'" 87 | fixall = "inv fixall --args '{args}'" 88 | 89 | [tool.hatch.envs.check] 90 | features = ["scripts", "check"] 91 | 92 | [tool.hatch.envs.check.scripts] 93 | pyright = "inv check-pyright --args '{args}'" 94 | all = "inv checkall --args '{args}'" 95 | 96 | [tool.black] 97 | line-length = 88 98 | target-version = ['py313'] 99 | 100 | [tool.ruff] 101 | target-version = "py313" 102 | line-length = 88 103 | src = ["src"] 104 | 105 | [tool.ruff.lint] 106 | select = [ 107 | "A", # flake8-builtins 108 | # "ANN", # flake8-annotations 109 | "ARG", # flake8-unused-arguments 110 | # "ASYNC", # flake8-async 111 | "B", # flake8-bugbear 112 | # "BLE", # flake8-blind-except 113 | "C4", # flake8-comprehensions 114 | "C90", # mccabe 115 | # "COM", # flake8-commas 116 | # "D", # pydocstyle 117 | # "DJ", # flake8-django 118 | "DTZ", # flake8-datetimez 119 | "E", # pycodestyle (default) 120 | "EM", # flake8-errmsg 121 | # "ERA", # eradicate 122 | # "EXE", # flake8-executable 123 | "F", # Pyflakes (default) 124 | # "FA", # flake8-future-annotations 125 | "FBT", # flake8-boolean-trap 126 | # "FLY", # flynt 127 | # "G", # flake8-logging-format 128 | "I", # isort 129 | "ICN", # flake8-import-conventions 130 | # "INP", # flake8-no-pep420 131 | # "INT", # flake8-gettext 132 | "ISC", # flake8-implicit-str-concat 133 | "N", # pep8-naming 134 | # "NPY", # NumPy-specific rules 135 | # "PD", # pandas-vet 136 | # "PGH", # pygrep-hooks 137 | # "PIE", # flake8-pie 138 | # "PL", # Pylint 139 | "PLC", # Pylint: Convention 140 | "PLE", # Pylint: Error 141 | "PLR", # Pylint: Refactor 142 | "PLW", # Pylint: Warning 143 | # "PT", # flake8-pytest-style 144 | # "PTH", # flake8-use-pathlib 145 | # "PYI", # flake8-pyi 146 | "Q", # flake8-quotes 147 | # "RET", # flake8-return 148 | # "RSE", # flake8-raise 149 | "RUF", # Ruff-specific rules 150 | "S", # flake8-bandit 151 | # "SIM", # flake8-simplify 152 | # "SLF", # flake8-self 153 | "T10", # flake8-debugger 154 | "T20", # flake8-print 155 | # "TCH", # flake8-type-checking 156 | # "TD", # flake8-todos 157 | "TID", # flake8-tidy-imports 158 | # "TRY", # tryceratops 159 | "UP", # pyupgrade 160 | "W", # pycodestyle 161 | "YTT", # flake8-2020 162 | ] 163 | ignore = [ 164 | # Allow non-abstract empty methods in abstract base classes 165 | "B027", 166 | # Remove flake8-errmsg since we consider they bloat the code and provide limited value 167 | "EM", 168 | # Allow boolean positional values in function calls, like `dict.get(... True)` 169 | "FBT003", 170 | # Ignore checks for possible passwords 171 | "S105", "S106", "S107", 172 | # Ignore warnings on subprocess.run / popen 173 | "S603", 174 | # Ignore complexity 175 | "C901", "PLR0911", "PLR0912", "PLR0913", "PLR0915", 176 | ] 177 | unfixable = [ 178 | # Don't touch unused imports 179 | "F401", 180 | ] 181 | 182 | [tool.ruff.lint.isort] 183 | known-first-party = ["zimit"] 184 | 185 | [tool.ruff.lint.flake8-bugbear] 186 | # add exceptions to B008 for fastapi. 187 | extend-immutable-calls = ["fastapi.Depends", "fastapi.Query"] 188 | 189 | [tool.ruff.lint.flake8-tidy-imports] 190 | ban-relative-imports = "all" 191 | 192 | [tool.ruff.lint.per-file-ignores] 193 | # Tests can use magic values, assertions, and relative imports 194 | "tests**/**/*" = ["PLR2004", "S101", "TID252"] 195 | 196 | [tool.pytest.ini_options] 197 | minversion = "7.3" 198 | testpaths = ["tests"] 199 | pythonpath = [".", "src"] 200 | 201 | [tool.coverage.paths] 202 | zimit = ["src/zimit"] 203 | tests = ["tests"] 204 | 205 | [tool.coverage.run] 206 | source_pkgs = ["zimit"] 207 | branch = true 208 | parallel = true 209 | omit = [ 210 | "src/zimit/__about__.py", 211 | ] 212 | 213 | [tool.coverage.report] 214 | exclude_lines = [ 215 | "no cov", 216 | "if __name__ == .__main__.:", 217 | "if TYPE_CHECKING:", 218 | ] 219 | 220 | [tool.pyright] 221 | include = ["src", "tests", "tasks.py"] 222 | exclude = [".env/**", ".venv/**"] 223 | extraPaths = ["src"] 224 | pythonVersion = "3.13" 225 | typeCheckingMode="basic" 226 | -------------------------------------------------------------------------------- /src/zimit/__about__.py: -------------------------------------------------------------------------------- 1 | __version__ = "3.0.6-dev0" 2 | -------------------------------------------------------------------------------- /src/zimit/constants.py: -------------------------------------------------------------------------------- 1 | import logging 2 | 3 | from zimscraperlib.logging import getLogger 4 | 5 | EXIT_CODE_WARC2ZIM_CHECK_FAILED = 2 6 | EXIT_CODE_CRAWLER_SIZE_LIMIT_HIT = 14 7 | EXIT_CODE_CRAWLER_TIME_LIMIT_HIT = 15 8 | NORMAL_WARC2ZIM_EXIT_CODE = 100 9 | REQUESTS_TIMEOUT = 10 10 | 11 | logger = getLogger(name="zimit", level=logging.INFO) 12 | -------------------------------------------------------------------------------- /src/zimit/utils.py: -------------------------------------------------------------------------------- 1 | from pathlib import Path 2 | 3 | import requests 4 | 5 | from zimit.constants import REQUESTS_TIMEOUT 6 | 7 | 8 | def download_file(url: str, fpath: Path): 9 | """Download file from url to fpath with streaming""" 10 | with requests.get(url, timeout=REQUESTS_TIMEOUT, stream=True) as resp: 11 | resp.raise_for_status() 12 | with open(fpath, "wb") as f: 13 | for chunk in resp.iter_content(chunk_size=8192): 14 | f.write(chunk) 15 | -------------------------------------------------------------------------------- /src/zimit/zimit.py: -------------------------------------------------------------------------------- 1 | """ 2 | Main zimit run script 3 | This script validates arguments with warc2zim, checks permissions 4 | and then calls the Node based driver 5 | """ 6 | 7 | import atexit 8 | import json 9 | import re 10 | import shutil 11 | import signal 12 | import subprocess 13 | import sys 14 | import tarfile 15 | import tempfile 16 | import urllib.parse 17 | from argparse import ArgumentParser 18 | from multiprocessing import Process 19 | from pathlib import Path 20 | 21 | import inotify 22 | import inotify.adapters 23 | from warc2zim.main import main as warc2zim 24 | from zimscraperlib.uri import rebuild_uri 25 | 26 | from zimit.__about__ import __version__ 27 | from zimit.constants import ( 28 | EXIT_CODE_CRAWLER_SIZE_LIMIT_HIT, 29 | EXIT_CODE_CRAWLER_TIME_LIMIT_HIT, 30 | EXIT_CODE_WARC2ZIM_CHECK_FAILED, 31 | NORMAL_WARC2ZIM_EXIT_CODE, 32 | logger, 33 | ) 34 | from zimit.utils import download_file 35 | 36 | temp_root_dir: Path | None = None 37 | 38 | 39 | class ProgressFileWatcher: 40 | def __init__( 41 | self, crawl_stats_path: Path, warc2zim_stats_path, zimit_stats_path: Path 42 | ): 43 | self.crawl_stats_path = crawl_stats_path 44 | self.warc2zim_stats_path = warc2zim_stats_path 45 | self.zimit_stats_path = zimit_stats_path 46 | 47 | # touch them all so inotify is not unhappy on add_watch 48 | self.crawl_stats_path.touch() 49 | self.warc2zim_stats_path.touch() 50 | self.process = None 51 | 52 | def stop(self): 53 | if not self.process: 54 | return 55 | self.process.join(0.1) 56 | self.process.terminate() 57 | 58 | def watch(self): 59 | self.process = Process( 60 | target=self.inotify_watcher, 61 | args=( 62 | str(self.crawl_stats_path), 63 | str(self.warc2zim_stats_path), 64 | str(self.zimit_stats_path), 65 | ), 66 | ) 67 | self.process.daemon = True 68 | self.process.start() 69 | 70 | def inotify_watcher(self, crawl_fpath: str, warc2zim_fpath: str, zimit_fpath: str): 71 | ino = inotify.adapters.Inotify() 72 | ino.add_watch(crawl_fpath, inotify.constants.IN_MODIFY) # pyright: ignore 73 | ino.add_watch(warc2zim_fpath, inotify.constants.IN_MODIFY) # pyright: ignore 74 | 75 | def crawl_conv(data): 76 | # we consider crawl to be 90% of the workload so total = craw_total * 90% 77 | return { 78 | "done": data["crawled"], 79 | "total": int(data["total"] / 0.9), 80 | } 81 | 82 | def warc2zim_conv(data): 83 | # we consider warc2zim to be 10% of the workload so 84 | # warc2zim_total = 10% and total = 90 + warc2zim_total * 10% 85 | return { 86 | "done": int( 87 | data["total"] 88 | * (0.9 + (float(data["written"]) / data["total"]) / 10) 89 | ), 90 | "total": data["total"], 91 | } 92 | 93 | for _, _, fpath, _ in ino.event_gen(yield_nones=False): # pyright: ignore 94 | func = {crawl_fpath: crawl_conv, warc2zim_fpath: warc2zim_conv}.get(fpath) 95 | if not func: 96 | continue 97 | # open input and output separatly as to not clear output on error 98 | with open(fpath) as ifh: 99 | try: 100 | out = func(json.load(ifh)) 101 | except Exception: # nosec # noqa: S112 102 | # simply ignore progress update should an error arise 103 | # might be malformed input for instance 104 | continue 105 | if not out: 106 | continue 107 | with open(zimit_fpath, "w") as ofh: 108 | json.dump(out, ofh) 109 | 110 | 111 | def cleanup(): 112 | if not temp_root_dir: 113 | logger.warning("Temporary root dir not already set, cannot clean this up") 114 | return 115 | logger.info("") 116 | logger.info("----------") 117 | logger.info(f"Cleanup, removing temp dir: {temp_root_dir}") 118 | shutil.rmtree(temp_root_dir) 119 | 120 | 121 | def cancel_cleanup(): 122 | logger.info( 123 | f"Temporary files have been kept in {temp_root_dir}, please clean them" 124 | " up manually once you don't need them anymore" 125 | ) 126 | atexit.unregister(cleanup) 127 | 128 | 129 | def run(raw_args): 130 | parser = ArgumentParser( 131 | description="Run a browser-based crawl on the specified URL and convert to ZIM" 132 | ) 133 | 134 | parser.add_argument( 135 | "--seeds", 136 | help="The seed URL(s) to start crawling from. Multile seed URL must be " 137 | "separated by a comma (usually not needed, these are just the crawl seeds). " 138 | "First seed URL is used as ZIM homepage", 139 | ) 140 | 141 | parser.add_argument("--title", help="WARC and ZIM title") 142 | parser.add_argument("--description", help="WARC and ZIM description") 143 | parser.add_argument("--long-description", help="ZIM long description metadata") 144 | 145 | parser.add_argument( 146 | "--seedFile", 147 | help="If set, read a list of seed urls, one per line. Can be a local file or " 148 | "the HTTP(s) URL to an online file.", 149 | ) 150 | 151 | parser.add_argument( 152 | "-w", "--workers", type=int, help="Number of parallel workers. Default is 1." 153 | ) 154 | 155 | parser.add_argument( 156 | "--crawlId", 157 | help="A user provided ID for this crawl or crawl configuration (can also be " 158 | "set via CRAWL_ID env var, defaults to machine hostname)", 159 | ) 160 | 161 | parser.add_argument( 162 | "--waitUntil", 163 | help="Puppeteer page.goto() condition to wait for before continuing. One of " 164 | "load, domcontentloaded, networkidle0 or networkidle2, or a " 165 | "comma-separated combination of those. Default is load,networkidle2", 166 | ) 167 | 168 | parser.add_argument( 169 | "--depth", 170 | help="The depth of the crawl for all seeds. Default is -1 (infinite).", 171 | type=int, 172 | ) 173 | 174 | parser.add_argument( 175 | "--extraHops", 176 | help="Number of extra 'hops' to follow, beyond the current scope. " 177 | "Default is 0.", 178 | type=int, 179 | ) 180 | 181 | parser.add_argument( 182 | "--pageLimit", 183 | help="Limit crawl to this number of pages. Default is 0 (no limit).", 184 | type=int, 185 | ) 186 | 187 | parser.add_argument( 188 | "--maxPageLimit", 189 | help="Maximum pages to crawl, overriding pageLimit if both are set. Default is " 190 | "0 (no limit)", 191 | type=int, 192 | ) 193 | 194 | parser.add_argument( 195 | "--pageLoadTimeout", 196 | help="Timeout for each page to load (in seconds). Default is 90 secs.", 197 | type=int, 198 | ) 199 | 200 | parser.add_argument( 201 | "--scopeType", 202 | help="A predfined scope of the crawl. For more customization, " 203 | "use 'custom' and set scopeIncludeRx/scopeExcludeRx regexes. Default is custom" 204 | "if scopeIncludeRx is set, prefix otherwise.", 205 | choices=["page", "page-spa", "prefix", "host", "domain", "any", "custom"], 206 | ) 207 | 208 | parser.add_argument( 209 | "--scopeIncludeRx", 210 | help="Regex of page URLs that should be included in the crawl (defaults to " 211 | "the immediate directory of URL)", 212 | ) 213 | 214 | parser.add_argument( 215 | "--scopeExcludeRx", 216 | help="Regex of page URLs that should be excluded from the crawl", 217 | ) 218 | 219 | parser.add_argument( 220 | "--allowHashUrls", 221 | help="Allow Hashtag URLs, useful for single-page-application crawling or " 222 | "when different hashtags load dynamic content", 223 | action="store_true", 224 | ) 225 | 226 | parser.add_argument( 227 | "--selectLinks", 228 | help="One or more selectors for extracting links, in the format " 229 | "[css selector]->[property to use],[css selector]->@[attribute to use]", 230 | ) 231 | 232 | parser.add_argument( 233 | "--clickSelector", 234 | help="Selector for elements to click when using the autoclick behavior. Default" 235 | " is 'a'", 236 | ) 237 | 238 | parser.add_argument( 239 | "--blockRules", 240 | help="Additional rules for blocking certain URLs from being loaded, by URL " 241 | "regex and optionally via text match in an iframe", 242 | ) 243 | 244 | parser.add_argument( 245 | "--blockMessage", 246 | help="If specified, when a URL is blocked, a record with this error message is" 247 | " added instead", 248 | ) 249 | 250 | parser.add_argument( 251 | "--blockAds", 252 | help="If set, block advertisements from being loaded (based on Stephen Black's" 253 | " blocklist). Note that some bad domains are also blocked by zimit" 254 | " configuration even if this option is not set.", 255 | ) 256 | 257 | parser.add_argument( 258 | "--adBlockMessage", 259 | help="If specified, when an ad is blocked, a record with this error message is" 260 | " added instead", 261 | ) 262 | 263 | parser.add_argument( 264 | "--collection", 265 | help="Collection name to crawl to (replay will be accessible " 266 | "under this name in pywb preview). Default is crawl-@ts.", 267 | ) 268 | 269 | parser.add_argument( 270 | "--headless", 271 | help="Run in headless mode, otherwise start xvfb", 272 | action="store_true", 273 | ) 274 | 275 | parser.add_argument( 276 | "--driver", 277 | help="Custom driver for the crawler, if any", 278 | ) 279 | 280 | parser.add_argument( 281 | "--generateCDX", 282 | help="If set, generate index (CDXJ) for use with pywb after crawl is done", 283 | action="store_true", 284 | ) 285 | 286 | parser.add_argument( 287 | "--combineWARC", 288 | help="If set, combine the warcs", 289 | action="store_true", 290 | ) 291 | 292 | parser.add_argument( 293 | "--rolloverSize", 294 | help="If set, declare the rollover size. Default is 1000000000.", 295 | type=int, 296 | ) 297 | 298 | parser.add_argument( 299 | "--generateWACZ", 300 | help="If set, generate WACZ on disk", 301 | action="store_true", 302 | ) 303 | 304 | parser.add_argument( 305 | "--logging", 306 | help="Crawler logging configuration", 307 | ) 308 | 309 | parser.add_argument( 310 | "--logLevel", 311 | help="Comma-separated list of log levels to include in logs", 312 | ) 313 | 314 | parser.add_argument( 315 | "--logContext", 316 | help="Comma-separated list of contexts to include in logs", 317 | choices=[ 318 | "general", 319 | "worker", 320 | "recorder", 321 | "recorderNetwork", 322 | "writer", 323 | "state", 324 | "redis", 325 | "storage", 326 | "text", 327 | "exclusion", 328 | "screenshots", 329 | "screencast", 330 | "originOverride", 331 | "healthcheck", 332 | "browser", 333 | "blocking", 334 | "behavior", 335 | "behaviorScript", 336 | "jsError", 337 | "fetch", 338 | "pageStatus", 339 | "memoryStatus", 340 | "crawlStatus", 341 | "links", 342 | "sitemap", 343 | "wacz", 344 | "replay", 345 | "proxy", 346 | ], 347 | ) 348 | 349 | parser.add_argument( 350 | "--logExcludeContext", 351 | help="Comma-separated list of contexts to NOT include in logs. Default is " 352 | "recorderNetwork,jsError,screencast", 353 | choices=[ 354 | "general", 355 | "worker", 356 | "recorder", 357 | "recorderNetwork", 358 | "writer", 359 | "state", 360 | "redis", 361 | "storage", 362 | "text", 363 | "exclusion", 364 | "screenshots", 365 | "screencast", 366 | "originOverride", 367 | "healthcheck", 368 | "browser", 369 | "blocking", 370 | "behavior", 371 | "behaviorScript", 372 | "jsError", 373 | "fetch", 374 | "pageStatus", 375 | "memoryStatus", 376 | "crawlStatus", 377 | "links", 378 | "sitemap", 379 | "wacz", 380 | "replay", 381 | "proxy", 382 | ], 383 | ) 384 | 385 | parser.add_argument( 386 | "--text", 387 | help="Extract initial (default) or final text to pages.jsonl or WARC resource" 388 | " record(s)", 389 | ) 390 | 391 | # cwd is manipulated directly by zimit, based on --output / --build, we do not want 392 | # to expose this setting 393 | 394 | parser.add_argument( 395 | "--mobileDevice", 396 | help="Emulate mobile device by name from " 397 | "https://github.com/puppeteer/puppeteer/blob/" 398 | "main/packages/puppeteer-core/src/common/Device.ts", 399 | ) 400 | 401 | parser.add_argument( 402 | "--userAgent", 403 | help="Override default user-agent with specified value ; --userAgentSuffix and " 404 | "--adminEmail have no effect when this is set", 405 | ) 406 | 407 | parser.add_argument( 408 | "--userAgentSuffix", 409 | help="Append suffix to existing browser user-agent " 410 | "(ex: +MyCrawler, info@example.com)", 411 | default="+Zimit", 412 | ) 413 | 414 | parser.add_argument( 415 | "--useSitemap", 416 | help="If set, use the URL as sitemap to get additional URLs for the crawl " 417 | "(usually /sitemap.xml)", 418 | ) 419 | 420 | parser.add_argument( 421 | "--sitemapFromDate", 422 | help="If set, filter URLs from sitemaps to those greater than or equal to (>=)" 423 | " provided ISO Date string (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS or partial date)", 424 | ) 425 | 426 | parser.add_argument( 427 | "--sitemapToDate", 428 | help="If set, filter URLs from sitemaps to those less than or equal to (<=) " 429 | "provided ISO Date string (YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS or partial date)", 430 | ) 431 | 432 | parser.add_argument( 433 | "--statsFilename", 434 | help="If set, output crawl stats as JSON to this file. Relative filename " 435 | "resolves to output directory, see --output.", 436 | ) 437 | 438 | parser.add_argument( 439 | "--zimit-progress-file", 440 | help="If set, output zimit stats as JSON to this file. Forces the creation of" 441 | "crawler and warc2zim stats as well. If --statsFilename and/or " 442 | "--warc2zim-progress-file are not set, default temporary files will be used. " 443 | "Relative filename resolves to output directory, see --output.", 444 | ) 445 | 446 | parser.add_argument( 447 | "--warc2zim-progress-file", 448 | help="If set, output warc2zim stats as JSON to this file. Relative filename " 449 | "resolves to output directory, see --output.", 450 | ) 451 | 452 | parser.add_argument( 453 | "--behaviors", 454 | help="Which background behaviors to enable on each page. Default is autoplay," 455 | "autofetch,autoscroll,siteSpecific", 456 | ) 457 | 458 | parser.add_argument( 459 | "--behaviorTimeout", 460 | help="If >0, timeout (in seconds) for in-page behavior will run on each page. " 461 | "If 0, a behavior can run until finish. Default is 90.", 462 | type=int, 463 | ) 464 | 465 | parser.add_argument( 466 | "--postLoadDelay", 467 | help="If >0, amount of time to sleep (in seconds) after page has loaded, before" 468 | " taking screenshots / getting text / running behaviors. Default is 0.", 469 | type=int, 470 | ) 471 | 472 | parser.add_argument( 473 | "--pageExtraDelay", 474 | help="If >0, amount of time to sleep (in seconds) after behaviors " 475 | "before moving on to next page. Default is 0.", 476 | type=int, 477 | ) 478 | 479 | parser.add_argument( 480 | "--dedupPolicy", 481 | help="Deduplication policy. Default is skip", 482 | choices=["skip", "revisit", "keep"], 483 | ) 484 | 485 | parser.add_argument( 486 | "--profile", 487 | help="Path or HTTP(S) URL to tar.gz file which contains the browser profile " 488 | "directory", 489 | ) 490 | 491 | parser.add_argument( 492 | "--screenshot", 493 | help="Screenshot options for crawler. One of view, thumbnail, fullPage, " 494 | "fullPageFinal or a comma-separated combination of those.", 495 | ) 496 | 497 | parser.add_argument( 498 | "--screencastPort", 499 | help="If set to a non-zero value, starts an HTTP server with screencast " 500 | "accessible on this port.", 501 | type=int, 502 | ) 503 | 504 | parser.add_argument( 505 | "--screencastRedis", 506 | help="If set, will use the state store redis pubsub for screencasting", 507 | action="store_true", 508 | ) 509 | 510 | parser.add_argument( 511 | "--warcInfo", 512 | help="Optional fields added to the warcinfo record in combined WARCs", 513 | ) 514 | 515 | parser.add_argument( 516 | "--saveState", 517 | help="If the crawl state should be serialized to the crawls/ directory. " 518 | "Defaults to 'partial', only saved when crawl is interrupted", 519 | choices=["never", "partial", "always"], 520 | ) 521 | 522 | parser.add_argument( 523 | "--saveStateInterval", 524 | help="If save state is set to 'always', also save state during the crawl at " 525 | "this interval (in seconds). Default to 300.", 526 | type=int, 527 | ) 528 | 529 | parser.add_argument( 530 | "--saveStateHistory", 531 | help="Number of save states to keep during the duration of a crawl. " 532 | "Default to 5.", 533 | type=int, 534 | ) 535 | 536 | size_group = parser.add_mutually_exclusive_group() 537 | size_group.add_argument( 538 | "--sizeSoftLimit", 539 | help="If set, save crawl state and stop crawl if WARC size exceeds this value. " 540 | "ZIM will still be created.", 541 | type=int, 542 | ) 543 | size_group.add_argument( 544 | "--sizeHardLimit", 545 | help="If set, exit crawler and fail the scraper immediately if WARC size " 546 | "exceeds this value", 547 | type=int, 548 | ) 549 | 550 | parser.add_argument( 551 | "--diskUtilization", 552 | help="Save state and exit if disk utilization exceeds this percentage value." 553 | " Default (if not set) is 90%%. Set to 0 to disable disk utilization check.", 554 | type=int, 555 | default=90, 556 | ) 557 | 558 | time_group = parser.add_mutually_exclusive_group() 559 | time_group.add_argument( 560 | "--timeSoftLimit", 561 | help="If set, save crawl state and stop crawl if WARC WARC(s) creation takes " 562 | "longer than this value, in seconds. ZIM will still be created.", 563 | type=int, 564 | ) 565 | time_group.add_argument( 566 | "--timeHardLimit", 567 | help="If set, exit crawler and fail the scraper immediately if WARC(s) creation" 568 | " takes longer than this value, in seconds", 569 | type=int, 570 | ) 571 | 572 | parser.add_argument( 573 | "--healthCheckPort", 574 | help="port to run healthcheck on", 575 | type=int, 576 | ) 577 | 578 | parser.add_argument( 579 | "--overwrite", 580 | help="overwrite current crawl data: if set, existing collection directory " 581 | "will be deleted before crawl is started", 582 | action="store_true", 583 | ) 584 | 585 | parser.add_argument( 586 | "--waitOnDone", 587 | help="if set, wait for interrupt signal when finished instead of exiting", 588 | action="store_true", 589 | ) 590 | 591 | parser.add_argument( 592 | "--restartsOnError", 593 | help="if set, assume will be restarted if interrupted, don't run post-crawl " 594 | "processes on interrupt", 595 | action="store_true", 596 | ) 597 | 598 | parser.add_argument( 599 | "--netIdleWait", 600 | help="If set, wait for network idle after page load and after behaviors are " 601 | "done (in seconds). if -1 (default), determine based on scope.", 602 | type=int, 603 | ) 604 | 605 | parser.add_argument( 606 | "--lang", 607 | help="if set, sets the language used by the browser, should be ISO 639 " 608 | "language[-country] code", 609 | ) 610 | 611 | parser.add_argument( 612 | "--originOverride", 613 | help="if set, will redirect requests from each origin in key to origin in the " 614 | "value, eg. --originOverride https://host:port=http://alt-host:alt-port", 615 | ) 616 | 617 | parser.add_argument( 618 | "--logErrorsToRedis", 619 | help="If set, write error messages to redis", 620 | action="store_true", 621 | ) 622 | 623 | parser.add_argument( 624 | "--writePagesToRedis", 625 | help="If set, write page objects to redis", 626 | action="store_true", 627 | ) 628 | 629 | parser.add_argument( 630 | "--maxPageRetries", 631 | help="If set, number of times to retry a page that failed to load before page" 632 | " is considered to have failed. Default is 2.", 633 | type=int, 634 | ) 635 | 636 | parser.add_argument( 637 | "--failOnFailedSeed", 638 | help="If set, crawler will fail with exit code 1 if any seed fails. When " 639 | "combined with --failOnInvalidStatus, will result in crawl failing with exit " 640 | "code 1 if any seed has a 4xx/5xx response", 641 | action="store_true", 642 | ) 643 | 644 | parser.add_argument( 645 | "--failOnFailedLimit", 646 | help="If set, save state and exit if number of failed pages exceeds this value", 647 | action="store_true", 648 | ) 649 | 650 | parser.add_argument( 651 | "--failOnInvalidStatus", 652 | help="If set, will treat pages with 4xx or 5xx response as failures. When " 653 | "combined with --failOnFailedLimit or --failOnFailedSeed may result in crawl " 654 | "failing due to non-200 responses", 655 | action="store_true", 656 | ) 657 | 658 | # customBehaviors not included because it has special handling 659 | # debugAccessRedis not included due to custom redis engine in zimit 660 | 661 | parser.add_argument( 662 | "--debugAccessBrowser", 663 | help="if set, allow debugging browser on port 9222 via CDP", 664 | action="store_true", 665 | ) 666 | 667 | parser.add_argument( 668 | "--warcPrefix", 669 | help="prefix for WARC files generated, including WARCs added to WACZ", 670 | ) 671 | 672 | parser.add_argument( 673 | "--serviceWorker", 674 | help="service worker handling: disabled, enabled or disabled-if-profile. " 675 | "Default: disabled.", 676 | ) 677 | 678 | parser.add_argument( 679 | "--proxyServer", 680 | help="if set, will use specified proxy server. Takes precedence over any env " 681 | "var proxy settings", 682 | ) 683 | 684 | parser.add_argument( 685 | "--dryRun", 686 | help="If true, no archive data is written to disk, only pages and logs (and " 687 | "optionally saved state).", 688 | action="store_true", 689 | ) 690 | 691 | parser.add_argument( 692 | "--qaSource", 693 | help="Required for QA mode. Path to the source WACZ or multi WACZ file for QA", 694 | ) 695 | 696 | parser.add_argument( 697 | "--qaDebugImageDiff", 698 | help="if specified, will write crawl.png, replay.png and diff.png for each " 699 | "page where they're different", 700 | action="store_true", 701 | ) 702 | 703 | parser.add_argument( 704 | "--sshProxyPrivateKeyFile", 705 | help="path to SSH private key for SOCKS5 over SSH proxy connection", 706 | ) 707 | 708 | parser.add_argument( 709 | "--sshProxyKnownHostsFile", 710 | help="path to SSH known hosts file for SOCKS5 over SSH proxy connection", 711 | ) 712 | 713 | parser.add_argument( 714 | "--keep", 715 | help="In case of failure, WARC files and other temporary files (which are " 716 | "stored as a subfolder of output directory) are always kept, otherwise " 717 | "they are automatically deleted. Use this flag to always keep WARC files, " 718 | "even in case of success.", 719 | action="store_true", 720 | ) 721 | 722 | parser.add_argument( 723 | "--output", 724 | help="Output directory for ZIM. Default to /output.", 725 | default="/output", 726 | ) 727 | 728 | parser.add_argument( 729 | "--build", 730 | help="Build directory for WARC files (if not set, output directory is used)", 731 | ) 732 | 733 | parser.add_argument("--adminEmail", help="Admin Email for Zimit crawler") 734 | 735 | parser.add_argument( 736 | "--custom-css", 737 | help="[warc2zim] Custom CSS file URL/path to inject into all articles", 738 | ) 739 | 740 | parser.add_argument( 741 | "--config", 742 | help="Path to YAML config file. If set, browsertrix-crawler will use this file" 743 | "to configure the crawling behaviour if not set via argument.", 744 | ) 745 | 746 | parser.add_argument( 747 | "--version", 748 | help="Display scraper version and exit", 749 | action="version", 750 | version=f"Zimit {__version__}", 751 | ) 752 | 753 | parser.add_argument( 754 | "--zim-lang", 755 | help="Language metadata of ZIM " 756 | "(warc2zim --lang param). ISO-639-3 code. " 757 | "Retrieved from homepage if found, fallback to `eng`", 758 | ) 759 | 760 | parser.add_argument( 761 | "--custom-behaviors", 762 | help="JS code for custom behaviors to customize crawler. Single string with " 763 | "individual JS files URL/path separated by a comma", 764 | ) 765 | 766 | parser.add_argument( 767 | "--warcs", 768 | help="Directly convert WARC archives to ZIM, by-passing the crawling phase. " 769 | "This argument must contain the path or HTTP(S) URL to either warc.gz files or" 770 | "to a tar or tar.gz containing the warc.gz files. Single value with individual " 771 | "path/URLs separated by comma", 772 | ) 773 | 774 | parser.add_argument( 775 | "--acceptable-crawler-exit-codes", 776 | help="Non-zero crawler exit codes to consider as acceptable to continue with " 777 | " conversion of WARC to ZIM. Flag partialZim will be set in statsFilename (if " 778 | " used). Single value with individual error codes separated by comma", 779 | ) 780 | 781 | # by design, all unknown args are for warc2zim ; known one are either for crawler 782 | # or shared 783 | known_args, warc2zim_args = parser.parse_known_args(raw_args) 784 | 785 | # pass a scraper suffix to warc2zim so that both zimit and warc2zim versions are 786 | # associated with the ZIM ; make it a CSV for easier parsing 787 | warc2zim_args.append("--scraper-suffix") 788 | warc2zim_args.append(f"zimit {__version__}") 789 | 790 | # pass url and output to warc2zim also 791 | if known_args.output: 792 | warc2zim_args.append("--output") 793 | warc2zim_args.append(known_args.output) 794 | 795 | user_agent_suffix = known_args.userAgentSuffix 796 | if known_args.adminEmail: 797 | user_agent_suffix += f" {known_args.adminEmail}" 798 | 799 | # make temp dir for this crawl 800 | global temp_root_dir # noqa: PLW0603 801 | if known_args.build: 802 | temp_root_dir = Path(tempfile.mkdtemp(dir=known_args.build, prefix=".tmp")) 803 | else: 804 | temp_root_dir = Path(tempfile.mkdtemp(dir=known_args.output, prefix=".tmp")) 805 | 806 | seeds = [] 807 | if known_args.seeds: 808 | seeds += [get_cleaned_url(url) for url in known_args.seeds.split(",")] 809 | if known_args.seedFile: 810 | if re.match(r"^https?\://", known_args.seedFile): 811 | with tempfile.NamedTemporaryFile( 812 | dir=temp_root_dir, 813 | prefix="seeds_", 814 | suffix=".txt", 815 | delete_on_close=True, 816 | ) as filename: 817 | seed_file = Path(filename.name) 818 | download_file(known_args.seedFile, seed_file) 819 | seeds += [ 820 | get_cleaned_url(url) for url in seed_file.read_text().splitlines() 821 | ] 822 | else: 823 | seeds += [ 824 | get_cleaned_url(url) 825 | for url in Path(known_args.seedFile).read_text().splitlines() 826 | ] 827 | warc2zim_args.append("--url") 828 | warc2zim_args.append(seeds[0]) 829 | 830 | if known_args.custom_css: 831 | warc2zim_args += ["--custom-css", known_args.custom_css] 832 | 833 | if known_args.title: 834 | warc2zim_args.append("--title") 835 | warc2zim_args.append(known_args.title) 836 | 837 | if known_args.description: 838 | warc2zim_args.append("--description") 839 | warc2zim_args.append(known_args.description) 840 | 841 | if known_args.long_description: 842 | warc2zim_args.append("--long-description") 843 | warc2zim_args.append(known_args.long_description) 844 | 845 | if known_args.zim_lang: 846 | warc2zim_args.append("--lang") 847 | warc2zim_args.append(known_args.zim_lang) 848 | 849 | logger.info("----------") 850 | logger.info("Testing warc2zim args") 851 | logger.info("Running: warc2zim " + " ".join(warc2zim_args)) 852 | res = warc2zim(warc2zim_args) 853 | if res != NORMAL_WARC2ZIM_EXIT_CODE: 854 | logger.info("Exiting, invalid warc2zim params") 855 | return EXIT_CODE_WARC2ZIM_CHECK_FAILED 856 | 857 | if not known_args.keep: 858 | atexit.register(cleanup) 859 | 860 | # copy / download custom behaviors to one single folder and configure crawler 861 | if known_args.custom_behaviors: 862 | behaviors_dir = temp_root_dir / "custom-behaviors" 863 | behaviors_dir.mkdir() 864 | for custom_behavior in [ 865 | custom_behavior.strip() 866 | for custom_behavior in known_args.custom_behaviors.split(",") 867 | ]: 868 | behaviors_file = tempfile.NamedTemporaryFile( 869 | dir=behaviors_dir, 870 | prefix="behavior_", 871 | suffix=".js", 872 | delete_on_close=False, 873 | ) 874 | if re.match(r"^https?\://", custom_behavior): 875 | logger.info( 876 | f"Downloading browser profile from {custom_behavior} " 877 | f"to {behaviors_file.name}" 878 | ) 879 | download_file(custom_behavior, Path(behaviors_file.name)) 880 | else: 881 | logger.info( 882 | f"Copying browser profile from {custom_behavior} " 883 | f"to {behaviors_file.name}" 884 | ) 885 | shutil.copy(custom_behavior, behaviors_file.name) 886 | known_args.customBehaviors = str(behaviors_dir) 887 | else: 888 | known_args.customBehaviors = None 889 | 890 | crawler_args = get_crawler_cmd_line(known_args) 891 | for seed in seeds: 892 | crawler_args.append("--seeds") 893 | crawler_args.append(seed) 894 | 895 | crawler_args.append("--userAgentSuffix") 896 | crawler_args.append(user_agent_suffix) 897 | 898 | crawler_args.append("--cwd") 899 | crawler_args.append(str(temp_root_dir)) 900 | 901 | output_dir = Path(known_args.output) 902 | warc2zim_stats_file = ( 903 | Path(known_args.warc2zim_progress_file) 904 | if known_args.warc2zim_progress_file 905 | else temp_root_dir / "warc2zim.json" 906 | ) 907 | if not warc2zim_stats_file.is_absolute(): 908 | warc2zim_stats_file = output_dir / warc2zim_stats_file 909 | warc2zim_stats_file.parent.mkdir(parents=True, exist_ok=True) 910 | warc2zim_stats_file.unlink(missing_ok=True) 911 | 912 | crawler_stats_file = ( 913 | Path(known_args.statsFilename) 914 | if known_args.statsFilename 915 | else temp_root_dir / "crawl.json" 916 | ) 917 | if not crawler_stats_file.is_absolute(): 918 | crawler_stats_file = output_dir / crawler_stats_file 919 | crawler_stats_file.parent.mkdir(parents=True, exist_ok=True) 920 | crawler_stats_file.unlink(missing_ok=True) 921 | 922 | zimit_stats_file = ( 923 | Path(known_args.zimit_progress_file) 924 | if known_args.zimit_progress_file 925 | else temp_root_dir / "stats.json" 926 | ) 927 | if not zimit_stats_file.is_absolute(): 928 | zimit_stats_file = output_dir / zimit_stats_file 929 | zimit_stats_file.parent.mkdir(parents=True, exist_ok=True) 930 | zimit_stats_file.unlink(missing_ok=True) 931 | 932 | if known_args.zimit_progress_file: 933 | # setup inotify crawler progress watcher 934 | watcher = ProgressFileWatcher( 935 | zimit_stats_path=zimit_stats_file, 936 | crawl_stats_path=crawler_stats_file, 937 | warc2zim_stats_path=warc2zim_stats_file, 938 | ) 939 | logger.info( 940 | f"Writing zimit progress to {watcher.zimit_stats_path}, crawler progress to" 941 | f" {watcher.crawl_stats_path} and warc2zim progress to " 942 | f"{watcher.warc2zim_stats_path}" 943 | ) 944 | # update crawler command 945 | crawler_args.append("--statsFilename") 946 | crawler_args.append(str(crawler_stats_file)) 947 | # update warc2zim command 948 | warc2zim_args.append("-v") 949 | warc2zim_args.append("--progress-file") 950 | warc2zim_args.append(str(warc2zim_stats_file)) 951 | watcher.watch() 952 | else: 953 | if known_args.statsFilename: 954 | logger.info(f"Writing crawler progress to {crawler_stats_file}") 955 | crawler_args.append("--statsFilename") 956 | crawler_args.append(str(crawler_stats_file)) 957 | if known_args.warc2zim_progress_file: 958 | logger.info(f"Writing warc2zim progress to {warc2zim_stats_file}") 959 | warc2zim_args.append("-v") 960 | warc2zim_args.append("--progress-file") 961 | warc2zim_args.append(str(warc2zim_stats_file)) 962 | 963 | cmd_line = " ".join(crawler_args) 964 | 965 | logger.info("") 966 | logger.info("----------") 967 | logger.info( 968 | f"Output to tempdir: {temp_root_dir} - " 969 | f"{'will keep' if known_args.keep else 'will delete'}" 970 | ) 971 | 972 | partial_zim = False 973 | 974 | # if warc files are passed, do not run browsertrix crawler but fetch the files if 975 | # they are provided as an HTTP URL + extract the archive if it is a tar.gz 976 | warc_files: list[Path] = [] 977 | if known_args.warcs: 978 | for warc_location in [ 979 | warc_location.strip() for warc_location in known_args.warcs.split(",") 980 | ]: 981 | suffix = "".join(Path(urllib.parse.urlparse(warc_location).path).suffixes) 982 | if suffix not in {".tar", ".tar.gz", ".warc", ".warc.gz"}: 983 | raise Exception(f"Unsupported file at {warc_location}") 984 | 985 | filename = tempfile.NamedTemporaryFile( 986 | dir=temp_root_dir, 987 | prefix="warc_", 988 | suffix=suffix, 989 | delete_on_close=False, 990 | ) 991 | 992 | if not re.match(r"^https?\://", warc_location): 993 | # warc_location is not a URL, so it is a path, simply add it to the list 994 | if not Path(warc_location).exists(): 995 | raise Exception(f"Impossible to find file at {warc_location}") 996 | 997 | # if it is a plain warc or warc.gz, simply add it to the list 998 | if suffix in {".warc", ".warc.gz"}: 999 | warc_files.append(Path(warc_location)) 1000 | continue 1001 | 1002 | # otherwise extract tar.gz but do not delete it afterwards 1003 | extract_path = temp_root_dir / f"{filename.name}_files" 1004 | logger.info( 1005 | f"Extracting WARC(s) from {warc_location} to {extract_path}" 1006 | ) 1007 | with tarfile.open(warc_location, "r") as fh: 1008 | # Extract all the contents to the specified directory 1009 | fh.extractall(path=extract_path, filter="data") 1010 | warc_files.append(Path(extract_path)) 1011 | continue 1012 | 1013 | # warc_location is a URL, let's download it to a temp name to avoid name 1014 | # collisions 1015 | warc_file = Path(filename.name) 1016 | logger.info(f"Downloading WARC(s) from {warc_location} to {warc_file}") 1017 | download_file(warc_location, warc_file) 1018 | 1019 | # if it is a plain warc or warc.gz, simply add it to the list 1020 | if suffix in {".warc", ".warc.gz"}: 1021 | warc_files.append(warc_file) 1022 | continue 1023 | 1024 | # otherwise extract tar.gz and delete it afterwards 1025 | extract_path = temp_root_dir / f"{filename.name}_files" 1026 | logger.info(f"Extracting WARC(s) from {warc_file} to {extract_path}") 1027 | with tarfile.open(warc_file, "r") as fh: 1028 | # Extract all the contents to the specified directory 1029 | fh.extractall(path=extract_path, filter="data") 1030 | logger.info(f"Deleting archive at {warc_file}") 1031 | warc_file.unlink() 1032 | warc_files.append(Path(extract_path)) 1033 | 1034 | else: 1035 | 1036 | logger.info(f"Running browsertrix-crawler crawl: {cmd_line}") 1037 | crawl = subprocess.run(crawler_args, check=False) 1038 | if ( 1039 | crawl.returncode == EXIT_CODE_CRAWLER_SIZE_LIMIT_HIT 1040 | and known_args.sizeSoftLimit 1041 | ): 1042 | logger.info( 1043 | "Crawl size soft limit hit. Continuing with warc2zim conversion." 1044 | ) 1045 | if known_args.zimit_progress_file: 1046 | partial_zim = True 1047 | elif ( 1048 | crawl.returncode == EXIT_CODE_CRAWLER_TIME_LIMIT_HIT 1049 | and known_args.timeSoftLimit 1050 | ): 1051 | logger.info( 1052 | "Crawl time soft limit hit. Continuing with warc2zim conversion." 1053 | ) 1054 | if known_args.zimit_progress_file: 1055 | partial_zim = True 1056 | elif crawl.returncode != 0: 1057 | logger.error( 1058 | f"Crawl returned an error: {crawl.returncode}, scraper exiting" 1059 | ) 1060 | cancel_cleanup() 1061 | return crawl.returncode 1062 | 1063 | if known_args.collection: 1064 | warc_files = [ 1065 | temp_root_dir.joinpath(f"collections/{known_args.collection}/archive/") 1066 | ] 1067 | 1068 | else: 1069 | warc_dirs = sorted( 1070 | temp_root_dir.rglob("collections/crawl-*/archive/"), 1071 | key=lambda path: path.lstat().st_mtime, 1072 | ) 1073 | if len(warc_dirs) == 0: 1074 | raise RuntimeError( 1075 | "Failed to find directory where WARC files have been created" 1076 | ) 1077 | elif len(warc_dirs) > 1: 1078 | logger.info( 1079 | "Found many WARC files directories, only most recently modified one" 1080 | " will be used" 1081 | ) 1082 | for directory in warc_dirs: 1083 | logger.info(f"- {directory}") 1084 | warc_files = [warc_dirs[-1]] 1085 | 1086 | logger.info("") 1087 | logger.info("----------") 1088 | logger.info( 1089 | f"Processing WARC files in/at " 1090 | f'{" ".join(str(warc_file) for warc_file in warc_files)}' 1091 | ) 1092 | warc2zim_args.extend(str(warc_file) for warc_file in warc_files) 1093 | 1094 | logger.info(f"Calling warc2zim with these args: {warc2zim_args}") 1095 | 1096 | warc2zim_exit_code = warc2zim(warc2zim_args) 1097 | 1098 | if known_args.zimit_progress_file: 1099 | stats_content = json.loads(zimit_stats_file.read_bytes()) 1100 | stats_content["partialZim"] = partial_zim 1101 | zimit_stats_file.write_text(json.dumps(stats_content)) 1102 | 1103 | # also call cancel_cleanup when --keep, even if it is not supposed to be registered, 1104 | # so that we will display temporary files location just like in other situations 1105 | if warc2zim_exit_code or known_args.keep: 1106 | cancel_cleanup() 1107 | 1108 | return warc2zim_exit_code 1109 | 1110 | 1111 | def get_cleaned_url(url: str): 1112 | parsed_url = urllib.parse.urlparse(url) 1113 | 1114 | # remove explicit port in URI for default-for-scheme as browsers does it 1115 | if parsed_url.scheme == "https" and parsed_url.port == 443: # noqa: PLR2004 1116 | parsed_url = rebuild_uri(parsed_url, port="") 1117 | if parsed_url.scheme == "http" and parsed_url.port == 80: # noqa: PLR2004 1118 | parsed_url = rebuild_uri(parsed_url, port="") 1119 | 1120 | return parsed_url.geturl() 1121 | 1122 | 1123 | def get_crawler_cmd_line(args): 1124 | """Build the command line for Browsertrix crawler""" 1125 | node_cmd = ["crawl"] 1126 | for arg in [ 1127 | "title", 1128 | "description", 1129 | "workers", 1130 | "crawlId", 1131 | "waitUntil", 1132 | "depth", 1133 | "extraHops", 1134 | "pageLimit", 1135 | "maxPageLimit", 1136 | "pageLoadTimeout", 1137 | "scopeType", 1138 | "scopeIncludeRx", 1139 | "scopeExcludeRx", 1140 | "collection", 1141 | "allowHashUrls", 1142 | "selectLinks", 1143 | "clickSelector", 1144 | "blockRules", 1145 | "blockMessage", 1146 | "blockAds", 1147 | "adBlockMessage", 1148 | "collection", 1149 | "headless", 1150 | "driver", 1151 | "generateCDX", 1152 | "combineWARC", 1153 | "rolloverSize", 1154 | "generateWACZ", 1155 | "logging", 1156 | "logLevel", 1157 | "logContext", 1158 | "logExcludeContext", 1159 | "text", 1160 | "mobileDevice", 1161 | "userAgent", 1162 | # userAgentSuffix (manipulated), 1163 | "useSitemap", 1164 | "sitemapFromDate", 1165 | "sitemapToDate", 1166 | # statsFilename (manipulated), 1167 | "behaviors", 1168 | "behaviorTimeout", 1169 | "postLoadDelay", 1170 | "pageExtraDelay", 1171 | "dedupPolicy", 1172 | "profile", 1173 | "screenshot", 1174 | "screencastPort", 1175 | "screencastRedis", 1176 | "warcInfo", 1177 | "saveState", 1178 | "saveStateInterval", 1179 | "saveStateHistory", 1180 | "sizeSoftLimit", 1181 | "sizeHardLimit", 1182 | "diskUtilization", 1183 | "timeSoftLimit", 1184 | "timeHardLimit", 1185 | "healthCheckPort", 1186 | "overwrite", 1187 | "waitOnDone", 1188 | "restartsOnError", 1189 | "netIdleWait", 1190 | "lang", 1191 | "originOverride", 1192 | "logErrorsToRedis", 1193 | "writePagesToRedis", 1194 | "maxPageRetries", 1195 | "failOnFailedSeed", 1196 | "failOnFailedLimit", 1197 | "failOnInvalidStatus", 1198 | "debugAccessBrowser", 1199 | "warcPrefix", 1200 | "serviceWorker", 1201 | "proxyServer", 1202 | "dryRun", 1203 | "qaSource", 1204 | "qaDebugImageDiff", 1205 | "sshProxyPrivateKeyFile", 1206 | "sshProxyKnownHostsFile", 1207 | "customBehaviors", 1208 | "config", 1209 | ]: 1210 | value = getattr(args, arg) 1211 | if arg == "userAgent": 1212 | # - strip leading whitespace which are not allowed on some websites 1213 | # - strip trailing whitespace which are either not allowed if no suffix is 1214 | # used, or duplicate with the automatically added one if a suffix is there 1215 | # - value is None when userAgent is not passed 1216 | if value: 1217 | value = value.strip() 1218 | if not value: 1219 | # ignore empty userAgent arg and keep crawler default value if empty 1220 | continue 1221 | if value is None or (isinstance(value, bool) and value is False): 1222 | continue 1223 | node_cmd.append( 1224 | "--" 1225 | + ( 1226 | "sizeLimit" 1227 | if arg in ["sizeSoftLimit", "sizeHardLimit"] 1228 | else "timeLimit" if arg in ["timeSoftLimit", "timeHardLimit"] else arg 1229 | ) 1230 | ) 1231 | if not isinstance(value, bool): 1232 | node_cmd.append(str(value)) 1233 | 1234 | return node_cmd 1235 | 1236 | 1237 | def sigint_handler(*args): # noqa: ARG001 1238 | logger.info("") 1239 | logger.info("") 1240 | logger.info("SIGINT/SIGTERM received, stopping zimit") 1241 | logger.info("") 1242 | logger.info("") 1243 | sys.exit(3) 1244 | 1245 | 1246 | def zimit(): 1247 | sys.exit(run(sys.argv[1:])) 1248 | 1249 | 1250 | signal.signal(signal.SIGINT, sigint_handler) 1251 | signal.signal(signal.SIGTERM, sigint_handler) 1252 | 1253 | 1254 | if __name__ == "__main__": 1255 | zimit() 1256 | -------------------------------------------------------------------------------- /tasks.py: -------------------------------------------------------------------------------- 1 | # pyright: strict, reportUntypedFunctionDecorator=false 2 | import os 3 | 4 | from invoke.context import Context 5 | from invoke.tasks import task # pyright: ignore [reportUnknownVariableType] 6 | 7 | use_pty = not os.getenv("CI", "") 8 | 9 | 10 | @task(optional=["args"], help={"args": "pytest additional arguments"}) 11 | def test(ctx: Context, args: str = ""): 12 | """run tests (without coverage)""" 13 | ctx.run(f"pytest {args}", pty=use_pty) 14 | 15 | 16 | @task(optional=["args"], help={"args": "pytest additional arguments"}) 17 | def test_cov(ctx: Context, args: str = ""): 18 | """run test vith coverage""" 19 | ctx.run(f"coverage run -m pytest {args}", pty=use_pty) 20 | 21 | 22 | @task(optional=["html"], help={"html": "flag to export html report"}) 23 | def report_cov(ctx: Context, *, html: bool = False): 24 | """report coverage""" 25 | ctx.run("coverage combine", warn=True, pty=use_pty) 26 | ctx.run("coverage report --show-missing", pty=use_pty) 27 | if html: 28 | ctx.run("coverage html", pty=use_pty) 29 | 30 | 31 | @task( 32 | optional=["args", "html"], 33 | help={ 34 | "args": "pytest additional arguments", 35 | "html": "flag to export html report", 36 | }, 37 | ) 38 | def coverage(ctx: Context, args: str = "", *, html: bool = False): 39 | """run tests and report coverage""" 40 | test_cov(ctx, args=args) 41 | report_cov(ctx, html=html) 42 | 43 | 44 | @task(optional=["args"], help={"args": "black additional arguments"}) 45 | def lint_black(ctx: Context, args: str = "."): 46 | args = args or "." # needed for hatch script 47 | ctx.run("black --version", pty=use_pty) 48 | ctx.run(f"black --check --diff {args}", pty=use_pty) 49 | 50 | 51 | @task(optional=["args"], help={"args": "ruff additional arguments"}) 52 | def lint_ruff(ctx: Context, args: str = "."): 53 | args = args or "." # needed for hatch script 54 | ctx.run("ruff --version", pty=use_pty) 55 | ctx.run(f"ruff check {args}", pty=use_pty) 56 | 57 | 58 | @task( 59 | optional=["args"], 60 | help={ 61 | "args": "linting tools (black, ruff) additional arguments, typically a path", 62 | }, 63 | ) 64 | def lintall(ctx: Context, args: str = "."): 65 | """Check linting""" 66 | args = args or "." # needed for hatch script 67 | lint_black(ctx, args) 68 | lint_ruff(ctx, args) 69 | 70 | 71 | @task(optional=["args"], help={"args": "check tools (pyright) additional arguments"}) 72 | def check_pyright(ctx: Context, args: str = ""): 73 | """check static types with pyright""" 74 | ctx.run("pyright --version") 75 | ctx.run(f"pyright {args}", pty=use_pty) 76 | 77 | 78 | @task(optional=["args"], help={"args": "check tools (pyright) additional arguments"}) 79 | def checkall(ctx: Context, args: str = ""): 80 | """check static types""" 81 | check_pyright(ctx, args) 82 | 83 | 84 | @task(optional=["args"], help={"args": "black additional arguments"}) 85 | def fix_black(ctx: Context, args: str = "."): 86 | """fix black formatting""" 87 | args = args or "." # needed for hatch script 88 | ctx.run(f"black {args}", pty=use_pty) 89 | 90 | 91 | @task(optional=["args"], help={"args": "ruff additional arguments"}) 92 | def fix_ruff(ctx: Context, args: str = "."): 93 | """fix all ruff rules""" 94 | args = args or "." # needed for hatch script 95 | ctx.run(f"ruff check --fix {args}", pty=use_pty) 96 | 97 | 98 | @task( 99 | optional=["args"], 100 | help={ 101 | "args": "linting tools (black, ruff) additional arguments, typically a path", 102 | }, 103 | ) 104 | def fixall(ctx: Context, args: str = "."): 105 | """Fix everything automatically""" 106 | args = args or "." # needed for hatch script 107 | fix_black(ctx, args) 108 | fix_ruff(ctx, args) 109 | lintall(ctx, args) 110 | -------------------------------------------------------------------------------- /tests-daily/Dockerfile: -------------------------------------------------------------------------------- 1 | # Let's extract kiwix-tools as usual on alpine temporary build container 2 | FROM alpine:3.21 as kiwix-serve 3 | LABEL org.opencontainers.image.source https://github.com/openzim/kiwix-tools 4 | 5 | # TARGETPLATFORM is injected by docker build 6 | ARG TARGETPLATFORM 7 | ARG KIWIX_TOOLS_VERSION 8 | 9 | RUN set -e && \ 10 | # default (no KIWIX_TOOLS_VERSION set) to today's nightly 11 | if [ -z "$KIWIX_TOOLS_VERSION" ] ; then KIWIX_TOOLS_VERSION=$(date +"%Y-%m-%d") ; fi && \ 12 | apk --no-cache add dumb-init curl && \ 13 | echo "TARGETPLATFORM: $TARGETPLATFORM" && \ 14 | if [ "$TARGETPLATFORM" = "linux/386" ]; then ARCH="i586"; \ 15 | # linux/arm64/v8 points to linux/arm64 16 | elif [ "$TARGETPLATFORM" = "linux/arm64/v8" \ 17 | -o "$TARGETPLATFORM" = "linux/arm64" ]; then ARCH="aarch64"; \ 18 | # linux/arm translates to linux/arm/v7 19 | elif [ "$TARGETPLATFORM" = "linux/arm/v7" ]; then ARCH="armv8"; \ 20 | elif [ "$TARGETPLATFORM" = "linux/arm/v6" ]; then ARCH="armv6"; \ 21 | elif [ "$TARGETPLATFORM" = "linux/amd64/v3" \ 22 | -o "$TARGETPLATFORM" = "linux/amd64/v2" \ 23 | -o "$TARGETPLATFORM" = "linux/amd64" ]; then ARCH="x86_64"; \ 24 | # we dont suppot any other arch so let it fail 25 | else ARCH="unknown"; fi && \ 26 | # download requested kiwix-tools version 27 | url="http://mirror.download.kiwix.org/nightly/$KIWIX_TOOLS_VERSION/kiwix-tools_linux-$ARCH-$KIWIX_TOOLS_VERSION.tar.gz" && \ 28 | echo "URL: $url" && \ 29 | mkdir /kiwix-serve && \ 30 | curl -k -L $url | tar -xz -C /kiwix-serve --strip-components 1 31 | 32 | # Build real "workload" container 33 | FROM python:3.13-slim-bookworm 34 | 35 | # Add kiwix-serve 36 | COPY --from=kiwix-serve /kiwix-serve /usr/local/bin 37 | 38 | # Update apt + install dependencies + install Google Chrome dependencies + clean-up apt lists 39 | RUN apt-get update -y && \ 40 | apt-get install -qqy wget xvfb unzip jq && \ 41 | apt-get install -qqy libxss1 libappindicator1 libgconf-2-4 \ 42 | fonts-liberation libasound2 libnspr4 libnss3 libx11-xcb1 libxtst6 lsb-release xdg-utils \ 43 | libgbm1 libnss3 libatk-bridge2.0-0 libgtk-3-0 libx11-xcb1 libxcb-dri3-0 && \ 44 | rm -rf /var/lib/apt/lists/* 45 | 46 | # Fetch the latest version numbers and URLs for Chrome and ChromeDriver 47 | RUN wget -q -O /tmp/versions.json https://googlechromelabs.github.io/chrome-for-testing/last-known-good-versions-with-downloads.json 48 | 49 | # Install chrome 50 | RUN CHROME_URL=$(jq -r '.channels.Stable.downloads.chrome[] | select(.platform=="linux64") | .url' /tmp/versions.json) && \ 51 | wget -q --continue -O /tmp/chrome-linux64.zip $CHROME_URL && \ 52 | unzip /tmp/chrome-linux64.zip -d /opt/chrome 53 | 54 | RUN chmod +x /opt/chrome/chrome-linux64/chrome 55 | 56 | # Install chromedriver 57 | RUN CHROMEDRIVER_URL=$(jq -r '.channels.Stable.downloads.chromedriver[] | select(.platform=="linux64") | .url' /tmp/versions.json) && \ 58 | wget -q --continue -O /tmp/chromedriver-linux64.zip $CHROMEDRIVER_URL && \ 59 | unzip /tmp/chromedriver-linux64.zip -d /opt/chromedriver && \ 60 | chmod +x /opt/chromedriver/chromedriver-linux64/chromedriver 61 | 62 | # Set up Chromedriver Environment variables 63 | ENV CHROMEDRIVER_DIR /opt/chromedriver 64 | ENV PATH $CHROMEDRIVER_DIR:$PATH 65 | 66 | # Clean up 67 | RUN rm /tmp/chrome-linux64.zip /tmp/chromedriver-linux64.zip /tmp/versions.json 68 | 69 | # Update pip, install selenium, create work directory 70 | RUN \ 71 | python -m pip install --no-cache-dir -U \ 72 | pip \ 73 | selenium==4.28.1 \ 74 | pytest==8.3.4 \ 75 | && mkdir -p /work 76 | -------------------------------------------------------------------------------- /tests-daily/daily.py: -------------------------------------------------------------------------------- 1 | import logging 2 | import os 3 | import subprocess 4 | from time import sleep 5 | 6 | import pytest 7 | from selenium import webdriver 8 | from selenium.webdriver.chrome.options import Options 9 | from selenium.webdriver.chrome.service import Service as ChromeService 10 | from selenium.webdriver.common.by import By 11 | from selenium.webdriver.support import expected_conditions 12 | from selenium.webdriver.support.ui import WebDriverWait 13 | 14 | KIWIX_SERVE_START_SLEEP = 1 15 | 16 | ZIM_NAME = "tests_eng_test-website" 17 | YOUTUBE_VIDEO_PATH = "youtube.fuzzy.replayweb.page/embed/g5skcrNXdDM" 18 | 19 | SKIP_YOUTUBE_TEST = os.getenv("SKIP_YOUTUBE_TEST", "False").lower() == "true" 20 | 21 | CHECK_VIDEO_IS_PLAYING_AFTER_SECS = 30 22 | 23 | logger = logging.getLogger(__name__) 24 | 25 | 26 | @pytest.fixture(scope="module") 27 | def chrome_driver(): 28 | """Start chrome and setup chrome driver / selenium""" 29 | 30 | logger.info("Starting Chrome") 31 | chrome_options = Options() 32 | chrome_options.add_argument("--headless") 33 | chrome_options.add_argument("--no-sandbox") 34 | # Other options of interest: 35 | # --disable-dev-shm-usage (not needed anymore with recent chrome versions) 36 | # --disable-gpu (important for some versions of Chrome) 37 | # --remote-debugging-port=9222 (should you need to remote debug) 38 | 39 | # Set path to Chrome binary 40 | chrome_options.binary_location = "/opt/chrome/chrome-linux64/chrome" 41 | 42 | # Set path to ChromeDriver 43 | chrome_service = ChromeService( 44 | executable_path="/opt/chromedriver/chromedriver-linux64/chromedriver" 45 | ) 46 | 47 | # Set up driver 48 | driver = webdriver.Chrome(service=chrome_service, options=chrome_options) 49 | 50 | yield driver 51 | 52 | # Cleanup 53 | logger.info("Quitting Chrome") 54 | driver.quit() 55 | 56 | 57 | @pytest.fixture(scope="module") 58 | def kiwix_serve(): 59 | """Start kiwix-serve with given ZIM""" 60 | 61 | logger.info("Starting kiwix-serve") 62 | process = subprocess.Popen( 63 | [ 64 | "/usr/bin/env", 65 | "/usr/local/bin/kiwix-serve", 66 | f"/output/{ZIM_NAME}.zim", 67 | ] 68 | ) 69 | 70 | logger.info( 71 | f"Waiting {KIWIX_SERVE_START_SLEEP} secs to be 'sure' that kiwix-serve is ready" 72 | ) 73 | sleep(KIWIX_SERVE_START_SLEEP) 74 | 75 | if process.poll() is not None: 76 | raise Exception("kiwix-serve has terminated too early") 77 | 78 | yield process 79 | 80 | # Cleanup 81 | logger.info("Quitting kiwix-serve") 82 | process.terminate() 83 | 84 | 85 | @pytest.mark.skipif(SKIP_YOUTUBE_TEST, reason="Youtube test disabled by environment") 86 | def test_youtube_video(chrome_driver, kiwix_serve): # noqa: ARG001 87 | """Test that youtube video loads, and still plays after a while""" 88 | 89 | chrome_driver.get(f"http://localhost:80/content/{ZIM_NAME}/{YOUTUBE_VIDEO_PATH}") 90 | 91 | if chrome_driver.title == "Content not found": 92 | raise Exception("Wrong URL, kiwix-serve said that content is not found") 93 | 94 | button = WebDriverWait(chrome_driver, 1).until( 95 | expected_conditions.presence_of_element_located( 96 | (By.XPATH, "//button[@title='Play']") 97 | ) 98 | ) 99 | 100 | logger.info("Play button found in page") 101 | 102 | button.click() 103 | 104 | video = WebDriverWait(chrome_driver, 1).until( 105 | expected_conditions.presence_of_element_located((By.TAG_NAME, "video")) 106 | ) 107 | 108 | logger.info("Video found in page") 109 | 110 | # arguments[0] is the video tag passed to execute_script 111 | if not chrome_driver.execute_script("return arguments[0].paused === false", video): 112 | raise Exception("Video is not playing, failed to start probably") 113 | 114 | logger.info("Video is playing") 115 | 116 | logger.info( 117 | f"Waiting {CHECK_VIDEO_IS_PLAYING_AFTER_SECS} secs to check video is still " 118 | "playing" 119 | ) 120 | sleep(CHECK_VIDEO_IS_PLAYING_AFTER_SECS) 121 | 122 | # arguments[0] is the video tag passed to execute_script 123 | if not chrome_driver.execute_script("return arguments[0].paused === false", video): 124 | raise Exception( 125 | "Video is not playing anymore after " 126 | f"{CHECK_VIDEO_IS_PLAYING_AFTER_SECS} secs" 127 | ) 128 | logger.info("Video is still playing") 129 | -------------------------------------------------------------------------------- /tests-integration/README.md: -------------------------------------------------------------------------------- 1 | These are integration tests, meant to be ran inside the CI (because we need to first perform a zimit run on a given website and then check its output) 2 | -------------------------------------------------------------------------------- /tests-integration/integration.py: -------------------------------------------------------------------------------- 1 | import glob 2 | import json 3 | import os 4 | from pathlib import Path 5 | 6 | import pytest 7 | from warcio import ArchiveIterator 8 | from zimscraperlib.zim import Archive 9 | 10 | 11 | @pytest.mark.parametrize( 12 | "filename", 13 | [ 14 | pytest.param("/output/tests_en_onepage.zim", id="onepage"), 15 | pytest.param("/output/tests_en_sizesoftlimit.zim", id="sizesoftlimit"), 16 | pytest.param("/output/tests_en_timesoftlimit.zim", id="timesoftlimit"), 17 | ], 18 | ) 19 | def test_zim_created(filename): 20 | """Ensure ZIM file exists""" 21 | assert os.path.isfile(filename) 22 | 23 | 24 | @pytest.mark.parametrize( 25 | "filename", 26 | [ 27 | pytest.param("/output/tests_en_sizehardlimit.zim", id="sizehardlimit"), 28 | pytest.param("/output/tests_en_timehardlimit.zim", id="timehardlimit"), 29 | ], 30 | ) 31 | def test_zim_not_created(filename): 32 | """Ensure ZIM file does not exists""" 33 | assert not os.path.exists(filename) 34 | 35 | 36 | def test_zim_main_page(): 37 | """Main page specified, http://website.test.openzim.org/http-return-codes.html, 38 | was a redirect to https 39 | Ensure main page is the redirected page""" 40 | 41 | main_entry = Archive(Path("/output/tests_en_onepage.zim")).main_entry 42 | assert main_entry.is_redirect 43 | assert ( 44 | main_entry.get_redirect_entry().path 45 | == "website.test.openzim.org/http-return-codes.html" 46 | ) 47 | 48 | 49 | def test_zim_scraper(): 50 | """Check content of scraper metadata""" 51 | 52 | zim_fh = Archive(Path("/output/tests_en_onepage.zim")) 53 | scraper = zim_fh.get_text_metadata("Scraper") 54 | assert "zimit " in scraper 55 | assert "warc2zim " in scraper 56 | assert "Browsertrix-Crawler " in scraper 57 | 58 | 59 | def test_files_list(): 60 | """Check that expected files are present in the ZIM at proper path""" 61 | zim_fh = Archive(Path("/output/tests_en_onepage.zim")) 62 | for expected_entry in [ 63 | "_zim_static/__wb_module_decl.js", 64 | "_zim_static/wombat.js", 65 | "_zim_static/wombatSetup.js", 66 | "website.test.openzim.org/http-return-codes.html", 67 | "website.test.openzim.org/200-response", 68 | "website.test.openzim.org/201-response", 69 | "website.test.openzim.org/202-response", 70 | "website.test.openzim.org/301-external-redirect-ok", 71 | "website.test.openzim.org/301-internal-redirect-ok", 72 | "website.test.openzim.org/302-external-redirect-ok", 73 | "website.test.openzim.org/302-internal-redirect-ok", 74 | "website.test.openzim.org/307-external-redirect-ok", 75 | "website.test.openzim.org/307-internal-redirect-ok", 76 | "website.test.openzim.org/308-external-redirect-ok", 77 | "website.test.openzim.org/308-internal-redirect-ok", 78 | "website.test.openzim.org/http-return-codes.html", 79 | "website.test.openzim.org/icons/favicon.ico", 80 | "website.test.openzim.org/icons/site.webmanifest", 81 | "website.test.openzim.org/internal_redirect_target.html", 82 | "www.example.com/", 83 | ]: 84 | assert zim_fh.get_content(expected_entry) 85 | 86 | 87 | def test_user_agent(): 88 | """Test that mobile user agent was used 89 | 90 | Check is done in WARC request records with custom Zimit and email suffix 91 | """ 92 | 93 | found = False 94 | for warc in glob.glob("/output/.tmp*/collections/crawl-*/archive/*.warc.gz"): 95 | with open(warc, "rb") as fh: 96 | for record in ArchiveIterator(fh): 97 | if record.rec_type == "request": 98 | print(record.http_headers) # noqa: T201 99 | ua = record.http_headers.get_header("User-Agent") 100 | if ua: 101 | assert "Mozilla" in ua 102 | assert ua.endswith(" +Zimit test@example.com") 103 | found = True 104 | 105 | # should find at least one 106 | assert found 107 | 108 | 109 | def test_stats_output_standard(): 110 | assert json.loads(Path("/output/crawl.json").read_bytes()) == { 111 | "crawled": 17, 112 | "pending": 0, 113 | "pendingPages": [], 114 | "total": 35, 115 | "failed": 18, 116 | "limit": {"max": 0, "hit": False}, 117 | } 118 | 119 | assert json.loads(Path("/output/warc2zim.json").read_bytes()) == { 120 | "written": 8, 121 | "total": 8, 122 | } 123 | 124 | assert json.loads(Path("/output/stats.json").read_bytes()) == { 125 | "done": 8, 126 | "total": 8, 127 | "partialZim": False, 128 | } 129 | 130 | 131 | @pytest.mark.parametrize( 132 | "filename", 133 | [ 134 | pytest.param("/output/stats_sizesoftlimit.json", id="sizesoftlimit"), 135 | pytest.param("/output/stats_timesoftlimit.json", id="timesoftlimit"), 136 | ], 137 | ) 138 | def test_stats_output_softlimit(filename): 139 | file = Path(filename) 140 | assert file.exists 141 | content = json.loads(file.read_bytes()) 142 | assert "done" in content 143 | assert "total" in content 144 | assert "partialZim" in content 145 | assert content["partialZim"] 146 | -------------------------------------------------------------------------------- /tests/test_dummy.py: -------------------------------------------------------------------------------- 1 | from zimit.zimit import NORMAL_WARC2ZIM_EXIT_CODE 2 | 3 | 4 | # dummy test, just to have coverage report done 5 | def test_something_exists(): 6 | assert NORMAL_WARC2ZIM_EXIT_CODE 7 | --------------------------------------------------------------------------------