scrape.yml

name: scrape
on:
  workflow_dispatch:
  schedule:
    - cron: '0 21 * * *'
jobs:
  scrape:
    runs-on: ubuntu-latest
    permissions:
      contents: write
    steps:
      - name: Check out this repo
        uses: actions/checkout@v4
        with:
          ref: main
      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.10'
      - name: Installed package list
        run: apt list --installed
      - name: Remove Chrome
        run: sudo apt purge google-chrome-stable
      - name: Remove default Chromium
        run: sudo apt purge chromium-browser
      - name: Install a new Chromium
        run: sudo apt install -y chromium-browser
      - name: Install all necessary packages
        run: pip install requests beautifulsoup4 pandas webdriver-manager selenium
      - name: Run the scraping script
        run: cd docs/games/grand_archive_gabrary_spoilers;python scraper.py;cd ../../..
      - name: Auto-Commit
        uses: stefanzweifel/git-auto-commit-action@v5
        with:
          branch: main
          file_pattern: docs/games/grand_archive_gabrary_spoilers/sets/
          commit_message: Update docs/games/grand_archive_gabrary_spoilers/sets/gabrary_spoilers.json