altstack-data/.github/workflows/scrape-data.yml

name: Scrape GitHub Data

on:
  schedule:
    - cron: '0 0 * * *' # Every day at midnight UTC
  workflow_dispatch: # Allow manual trigger

jobs:
  scrape:
    runs-on: ubuntu-latest
    permissions:
      contents: write
    
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.10'

      - name: Install dependencies
        run: |
          if [ -f scraper/requirements.txt ]; then
            pip install -r scraper/requirements.txt
          fi

      - name: Run scraper
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: python scraper/scraper.py

      - name: Create Pull Request
        uses: peter-evans/create-pull-request@v6
        with:
          token: ${{ secrets.GITHUB_TOKEN }}
          commit-message: 'chore: nightly data enrichment [skip ci]'
          title: 'chore: nightly GitHub data enrichment'
          body: |
            Automated nightly update of GitHub metadata for open-source tools.
            - Stars, last commit, language, and license fields refreshed.
          branch: chore/nightly-enrichment
          delete-branch: true
          labels: automated