archive.yml

name: Archive

on:
  schedule:
    - cron: "7 11 * * *"
  workflow_dispatch:

env:
  CI: true
  PYTHON_VERSION: 3.9
  PIPENV_VENV_IN_PROJECT: true
  SCRAPY_SETTINGS_MODULE: city_scrapers.settings.archive
  AUTOTHROTTLE_MAX_DELAY: 30.0
  AUTOTHROTTLE_START_DELAY: 1.5
  AUTOTHROTTLE_TARGET_CONCURRENCY: 3.0

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