Files
crawl4ai/.github/workflows/docker-release.yml
unclecode 7c0cc3ed88 fix: batch merge of community PRs (#1622, #1786, #1796, #1795, #1798, #1734, #1290, #1668)
Bug fixes:
- Verify redirect targets are alive before returning from URL seeder (#1622)
- Wire mean_delay/max_range from CrawlerRunConfig into dispatcher rate limiter (#1786)
- Use DOMParser instead of innerHTML in process_iframes to prevent XSS (#1796)

Security/Docker:
- Require api_token for /token endpoint when configured (#1795)
- Deep-crawl streaming now mirrors Python library behavior via arun() (#1798)

CI:
- Bump GitHub Actions to latest versions - checkout v6, setup-python v6,
  build-push-action v6, setup-buildx v4, login v4 (#1734)

Features:
- Support type-list pipeline in JsonCssExtractionStrategy for chained
  extraction like ["attribute", "regex"] (#1290)
- Add --json-ensure-ascii CLI flag and JSON_ENSURE_ASCII config setting
  for Unicode preservation in JSON output (#1668)
2026-03-07 08:45:11 +00:00

101 lines
3.6 KiB
YAML

name: Docker Release
on:
release:
types: [published]
push:
tags:
- 'docker-rebuild-v*' # Allow manual Docker rebuilds via tags
jobs:
docker:
runs-on: ubuntu-latest
steps:
- name: Free up disk space
run: |
echo "=== Disk space before cleanup ==="
df -h
# Remove unnecessary tools and libraries (frees ~25GB)
sudo rm -rf /usr/share/dotnet
sudo rm -rf /usr/local/lib/android
sudo rm -rf /opt/ghc
sudo rm -rf /opt/hostedtoolcache/CodeQL
sudo rm -rf /usr/local/share/boost
sudo rm -rf /usr/share/swift
# Clean apt cache
sudo apt-get clean
echo "=== Disk space after cleanup ==="
df -h
- name: Checkout code
uses: actions/checkout@v6
- name: Extract version from release or tag
id: get_version
run: |
if [ "${{ github.event_name }}" == "release" ]; then
# Triggered by release event
VERSION="${{ github.event.release.tag_name }}"
VERSION=${VERSION#v} # Remove 'v' prefix
else
# Triggered by docker-rebuild-v* tag
VERSION=${GITHUB_REF#refs/tags/docker-rebuild-v}
fi
echo "VERSION=$VERSION" >> $GITHUB_OUTPUT
echo "Building Docker images for version: $VERSION"
- name: Extract major and minor versions
id: versions
run: |
VERSION=${{ steps.get_version.outputs.VERSION }}
MAJOR=$(echo $VERSION | cut -d. -f1)
MINOR=$(echo $VERSION | cut -d. -f1-2)
echo "MAJOR=$MAJOR" >> $GITHUB_OUTPUT
echo "MINOR=$MINOR" >> $GITHUB_OUTPUT
echo "Semantic versions - Major: $MAJOR, Minor: $MINOR"
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v4
- name: Log in to Docker Hub
uses: docker/login-action@v4
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_TOKEN }}
- name: Build and push Docker images
uses: docker/build-push-action@v6
with:
context: .
push: true
tags: |
unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}
unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}
unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}
unclecode/crawl4ai:latest
platforms: linux/amd64,linux/arm64
cache-from: type=gha
cache-to: type=gha,mode=max
- name: Summary
run: |
echo "## 🐳 Docker Release Complete!" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Published Images" >> $GITHUB_STEP_SUMMARY
echo "- \`unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}\`" >> $GITHUB_STEP_SUMMARY
echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MINOR }}\`" >> $GITHUB_STEP_SUMMARY
echo "- \`unclecode/crawl4ai:${{ steps.versions.outputs.MAJOR }}\`" >> $GITHUB_STEP_SUMMARY
echo "- \`unclecode/crawl4ai:latest\`" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### Platforms" >> $GITHUB_STEP_SUMMARY
echo "- linux/amd64" >> $GITHUB_STEP_SUMMARY
echo "- linux/arm64" >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "### 🚀 Pull Command" >> $GITHUB_STEP_SUMMARY
echo "\`\`\`bash" >> $GITHUB_STEP_SUMMARY
echo "docker pull unclecode/crawl4ai:${{ steps.get_version.outputs.VERSION }}" >> $GITHUB_STEP_SUMMARY
echo "\`\`\`" >> $GITHUB_STEP_SUMMARY