cron.yml

name: Cron

on:
  schedule:
    - cron: "1 6 * * *"
  workflow_dispatch:

env:
  CI: true
  PYTHON_VERSION: 3.11
  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
  AZURE_ACCOUNT_KEY: ${{ secrets.AZURE_ACCOUNT_KEY }}
  AZURE_ACCOUNT_NAME: ${{ secrets.AZURE_ACCOUNT_NAME }}
  AZURE_CONTAINER: ${{ secrets.AZURE_CONTAINER }}
  AZURE_STATUS_CONTAINER: ${{ secrets.AZURE_STATUS_CONTAINER }}
  SENTRY_DSN: ${{ secrets.SENTRY_DSN }}

jobs:
  crawl:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Set up Python ${{ env.PYTHON_VERSION }}
        uses: actions/setup-python@v5
        with:
          python-version: ${{ env.PYTHON_VERSION }}

      - name: Install Pipenv
        run: pip install --user pipenv

      - name: Cache Python dependencies
        uses: actions/cache@v4
        with:
          path: .venv
          key: ${{ env.PYTHON_VERSION }}-${{ hashFiles('**/Pipfile.lock') }}
          restore-keys: |
            ${{ env.PYTHON_VERSION }}-
            pip-

      - name: Install dependencies
        run: pipenv sync
        env:
          PIPENV_DEFAULT_PYTHON_VERSION: ${{ env.PYTHON_VERSION }}

      - 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

      - name: Prevent workflow deactivation
        uses: gautamkrishnar/keepalive-workflow@v1
        with:
          committer_username: "citybureau-bot"
          committer_email: "documenters@citybureau.org"