Refresh Volumes #40

	name: Dataset Refresh

	on:
	#schedule:
	# - cron: '0 0 * * 0' # Runs every Sunday at midnight UTC. You can customize the schedule using cron syntax.
	workflow_dispatch: # This allows manual triggering from the GitHub Actions UI.

	jobs:
	build:
	runs-on: ubuntu-latest

	steps:
	- name: Checkout code
	uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4

	- uses: pnpm/action-setup@v3
	with:
	version: 8

	- name: Install dependencies
	run: \|
	cd web-scraper
	pnpm install

	- name: Refresh datasets
	run: \|
	cd web-scraper
	pnpm start

	- name: Commit and push changes
	run: \|
	git config --global user.name "Adam Setch"
	git config --global user.email "[email protected]@example.com"
	git checkout -b weekly-build
	git add .
	git diff --quiet --exit-code \|\| git commit -m "Automated dataset refresh - $(date +'%Y-%m-%d')"
	git push --set-upstream origin weekly-build

	pull-request:
	runs-on: ubuntu-latest
	needs: build
	steps:
	- name: Create Pull Request
	uses: peter-evans/create-pull-request@v6
	with:
	token: ${{ secrets.GITHUB_TOKEN }}
	branch: weekly-build # Change this to the branch name where you want to raise the PR.
	commit-message: "Automated dataset refresh - $(date +'%Y-%m-%d')"
	title: "Automated dataset refresh - $(date +'%Y-%m-%d')"
	body: 'Automated dataset refresh'

Provide feedback