scrape.yml

name: scrape

on:
  workflow_dispatch:
  push:
  schedule:
    - cron: '0 0 * * *'

permissions:
  contents: write

jobs:
  run:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4
        with:
          persist-credentials: true

      - name: Setup Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.11'

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt

      - name: Run scraper
        env:
          PYTHONUNBUFFERED: '1'
        run: python scrape_ollama.py

      - name: Commit and push changes
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          # Configure git user
          git config user.name "github-actions"
          git config user.email "github-actions@github.com"

          # Ensure remote uses GITHUB_TOKEN
          git remote set-url origin https://x-access-token:${GITHUB_TOKEN}@github.com/${{ github.repository }}.git

          # Stage changes
          git add -A

          # Commit and push if there are changes
          if ! git diff --cached --quiet; then
            git commit -m "✨ Data update at $(date -u '+%Y-%m-%d')"
            git push origin HEAD:${{ github.ref_name }}
          else
            echo "No changes to commit"
          fi