Scrape and publish #39

	name: Scrapes all defined sites and publishes to pp-data repository.
	on:
	schedule:
	- cron: "* 12 * * 1-5"
	workflow_dispatch:

	jobs:
	generate:
	runs-on: ubuntu-latest

	steps:
	- uses: actions/checkout@v4
	- name: Checkout pp-data repo
	uses: actions/checkout@v4
	with:
	repository: havasd/pp-data
	path: pp-data
	- uses: getsentry/[email protected]
	id: venv
	with:
	python-version: 3.11
	cache-dependency-path: \|
	requirements.txt
	requirements-frozen.txt
	install-cmd: pip install -r requirements.txt -c requirements-frozen.txt
	- name: Scrape historical prices
	run: \|
	cd price_scraper
	scrapy crawl aranykor -a base_dir=../pp-data
	scrapy crawl mak -a base_dir=../pp-data
	scrapy crawl bamosz -a base_dir=../pp-data
	scrapy crawl otp_nyugdij -a base_dir=../pp-data
	- name: Push historical prices to pp-data
	uses: cpina/github-action-push-to-another-repository@main
	env:
	SSH_DEPLOY_KEY: ${{ secrets.SSH_DEPLOY_KEY }}
	API_TOKEN_GITHUB: ${{ secrets.API_TOKEN_GITHUB }}
	with:
	source-directory: 'pp-data'
	commit-message: 'Update pricing data from ORIGIN_COMMIT'
	destination-github-username: 'havasd'
	destination-repository-name: 'pp-data'
	user-email: [email protected]
	target-branch: main

Provide feedback