.github/workflows/get-availability.yml #675

	on:
	# Run only once per day – it takes a long time to execute due to rate
	# limiting, and GitHub Actions only affords ~60 minutes per day in free
	# processing time!
	schedule:
	- cron: "0 0 * * *"
	# Although if we really need to, we can manually trigger a run
	workflow_dispatch:

	jobs:
	get-availability:
	runs-on: ubuntu-latest
	steps:
	- name: Install required HTML parsing libraries
	run: sudo apt-get install -y libxml2-dev libxslt-dev python3-dev
	- uses: actions/checkout@v4
	- name: Install Poetry
	run: pipx install poetry
	- uses: actions/setup-python@v4
	with:
	python-version: 3.9
	cache: "poetry"
	- name: Install Python dependencies
	run: poetry install
	- name: Run scraper
	run: poetry run data/get_availability.py
	- name: Configure AWS credentials
	uses: aws-actions/configure-aws-credentials@v4
	with:
	aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
	aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
	aws-region: us-east-1
	# GitHub Actions runners have the AWS CLI pre-installed
	- name: Upload output to S3
	# Apply a one-hour cache to the JSON file
	run: aws s3 cp data/availability.json s3://${{ secrets.AWS_BUCKET }}/availability.json --acl public-read --cache-control "public, max-age=3600, immutable"

Provide feedback