cron.yml

name: Cron

on:
  schedule:
    # Set any time that you'd like scrapers to run (in UTC)
    - cron: "1 6 * * *"
  workflow_dispatch:

env:
  CI: true
  PIPENV_VENV_IN_PROJECT: true
  SCRAPY_SETTINGS_MODULE: city_scrapers.settings.prod
  WAYBACK_ENABLED: true
  AUTOTHROTTLE_MAX_DELAY: 30.0
  AUTOTHROTTLE_START_DELAY: 1.5
  AUTOTHROTTLE_TARGET_CONCURRENCY: 3.0
  # Add secrets for the platform you're using and uncomment here
  # AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
  # AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
  # S3_BUCKET: ${{ secrets.S3_BUCKET }}
  # AZURE_ACCOUNT_KEY: ${{ secrets.AZURE_ACCOUNT_KEY }}
  # AZURE_ACCOUNT_NAME: ${{ secrets.AZURE_ACCOUNT_NAME }}
  # AZURE_CONTAINER: ${{ secrets.AZURE_CONTAINER }}
  # GOOGLE_APPLICATION_CREDENTIALS = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")
  # GCS_BUCKET = os.getenv("GCS_BUCKET")
  # Setup Sentry, add the DSN to secrets and uncomment here
  # SENTRY_DSN: ${{ secrets.SENTRY_DSN }}

jobs:
  crawl:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v2

      - name: Set up Python 3.8
        uses: actions/setup-python@v1
        with:
          python-version: 3.8

      - name: Install Pipenv
        uses: dschep/install-pipenv-action@v1

      - name: Cache Python dependencies
        uses: actions/cache@v1
        with:
          path: .venv
          key: pip-3.8-${{ hashFiles('**/Pipfile.lock') }}
          restore-keys: |
            pip-3.8-
            pip-

      - name: Install dependencies
        run: pipenv sync
        env:
          PIPENV_DEFAULT_PYTHON_VERSION: 3.8

      - name: Run scrapers
        run: |
          export PYTHONPATH=$(pwd):$PYTHONPATH
          ./.deploy.sh

      - name: Combine output feeds
        run: |
          export PYTHONPATH=$(pwd):$PYTHONPATH
          pipenv run scrapy combinefeeds -s LOG_ENABLED=False