Scrape #5673
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: "Scrape" | |
| on: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: "0 3,6,9,12,15,18,21 * * *" | |
| - cron: "0 0 * * *" | |
| jobs: | |
| scrape: | |
| name: Scrape | |
| runs-on: ubuntu-latest | |
| env: | |
| FETCH_NUM_MONTHS: "${{ github.event.schedule == '0 0 * * *' && '12' || '3' }}" | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v3 | |
| with: | |
| fetch-depth: 0 | |
| - name: Setup Python | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: '3.9' | |
| cache: 'pip' | |
| - name: Install Python dependencies | |
| run: pip install -r requirements.txt | |
| - name: Install VPN | |
| run: wget --quiet --content-disposition https://github.com/mullvad/mullvadvpn-app/releases/download/2025.2/MullvadVPN-2025.2_amd64.deb && sudo apt install -y ./MullvadVPN-2025.2_amd64.deb | |
| - name: Connect to VPN | |
| run: |- | |
| mullvad account login ${{ secrets.MULLVAD_ACCOUNT_NUMBER }} | |
| mullvad relay set location us | |
| mullvad connect --wait | |
| - name: Fetch | |
| run: python scripts/00-fetch.py --overwrite --expand --num-months $FETCH_NUM_MONTHS | |
| - name: Log out of VPN | |
| if: always() | |
| run: |- | |
| mullvad disconnect | |
| mullvad account logout | |
| - name: Config git | |
| run: git config --global user.email "[email protected]" && git config --global user.name "Automated" | |
| - name: Commit changes | |
| run: git add data/fetched && (git diff --cached --quiet || git commit -m "Refresh last $FETCH_NUM_MONTHS months of data") | |
| - name: Get discovery dates | |
| run: python scripts/01-get-discovery-dates.py --num-months $FETCH_NUM_MONTHS | |
| - name: Create filtered datasets | |
| run: python scripts/02-filter.py | |
| - name: Write RSS | |
| run: python scripts/03-generate-rss.py | |
| - name: Commit changes | |
| run: git add data/processed && (git diff --cached --quiet || git commit -m "Generate discovery dates and RSS") | |
| - name: Push changes | |
| run: git push |