scrape.yml

# This workflow scrapes the latest show episodes and commits the new episode and data
# files to the repo.

name: Scrape and commit
on:
  schedule:
    - cron:  '0 0,12 * * *'  # At midnight & noon UTC
  workflow_dispatch:   # Allows you to run this workflow manually from the Actions tab

jobs:
  scrape:
    runs-on: ubuntu-latest
    steps:
    - name: 'Checkout jupiterbroadcasting.com'
      uses: actions/checkout@v3
      with:
        ref: main
        path: ./jbsite

    - name: 'Checkout show-scraper'
      uses: actions/checkout@v3
      with:
        repository: JupiterBroadcasting/show-scraper
        ref: main
        path: ./show-scraper

    - name: 'Setup Python'
      uses: actions/setup-python@v3
      with:
        python-version: '3.10'
        architecture: 'x64'
        cache: "pipenv"
    
    - name: 'Install Python deps'
      run: pip install pipenv && cd ./show-scraper && pipenv sync --bare

    - name: 'Scrape'
      run: |
        cd ./show-scraper
        DATA_DIR=../jbsite LATEST_ONLY=true pipenv run ./scraper.py

    - name: 'Commit'
      uses: stefanzweifel/git-auto-commit-action@v4
      with:
        commit_message: 'Automatically scraped and committed via a GitHub Action.'
        repository: ./jbsite