run_scraper.yaml

name: Run scraper on a schedule and push all changed and new files to the repository

on:
  # Run periodically.
  schedule:
    - cron: '43 */8 * * *'  # every eight hours on the 43rd minute

  # Also run on push. Fortunately GitHub Actions doesn't trigger this
  # from the push that this action itself pushes!
  push:
jobs:
  run_scraper_and_push:
    name: Run scraper and push all changed and new files
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v2
      - run: |
          pip install -r requirements.txt
      - run: |
          scrapy runspider scraper.py --loglevel=ERROR
      - run: |
          git status
          git diff
      - run: |
          python test.py
      - name: git add && git commit && git push
        run: |
          git add -A archive
          if ! git diff-index --quiet --cached HEAD --; then # https://stackoverflow.com/a/2659808
            git config --global user.name 'GitHub Action run_scraper'
            git config --global user.email 'unitedstates@users.noreply.github.com'
            git commit -am "Scraper run by GitHub Action"
            git push
          else
            echo Nothing scraped so nothing to commit and push.
          fi