Refresh xkcd data #146

	name: Refresh xkcd data

	on:
	schedule:
	- cron: '0 0 * * *'
	workflow_dispatch:

	jobs:
	build:
	runs-on: ubuntu-latest

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

	- name: Setup Node.js
	uses: actions/setup-node@v3
	with:
	node-version-file: '.nvmrc'
	cache: yarn
	cache-dependency-path: yarn.lock

	- name: Install dependencies
	run: yarn install --frozen-lockfile

	- name: Download xkcd cache
	uses: dawidd6/action-download-artifact@v2
	with:
	name: xkcd-cache
	search_artifacts: true
	workflow_conclusion: ""
	if_no_artifact_found: warn

	- name: Uncompress xkcd cache
	run: \|
	tar_file="xkcd-cache.tar.gz" && \
	[ -f "$tar_file" ] && \
	tar -xzvf "$tar_file" -C data/raw && \
	rm xkcd-cache.tar.gz
	exit 0

	- name: Run script
	env:
	TYPESENSE_HOST: ${{ vars.TYPESENSE_HOST }}
	TYPESENSE_PORT: ${{ vars.TYPESENSE_PORT }}
	TYPESENSE_PROTOCOL: ${{ vars.TYPESENSE_PROTOCOL }}
	TYPESENSE_ADMIN_API_KEY: ${{ secrets.TYPESENSE_ADMIN_API_KEY }}
	run: \|
	find data/raw -name "*.html" -type f -exec grep -l "explanation may be incomplete" {} + \| xargs -r rm
	yarn fetchData
	find data/raw -name "*.html" -type f -exec grep -l "server is temporarily unable" {} + \| xargs -r rm
	find data/raw -name "*.json" -type f -exec grep -l "<html>" {} + \| xargs -r rm
	yarn refreshData

	- name: Compress xkcd cache
	if: success() \|\| failure()
	run: \|
	tar -czvf xkcd-cache.tar.gz -C data/raw .

	- name: Save xkcd cache
	uses: actions/upload-artifact@v3
	if: always()
	with:
	name: xkcd-cache
	path: xkcd-cache.tar.gz
	if-no-files-found: warn
	retention-days: 7

Provide feedback