Scrape latest data #755

	name: Scrape latest data

	on:
	push:
	workflow_dispatch:
	schedule:
	- cron: '21 11 * * *'

	jobs:
	scheduled:
	runs-on: ubuntu-latest
	steps:
	- name: Check out this repo
	uses: actions/checkout@v3
	with:
	fetch-depth: 0
	- name: Set up Python
	uses: actions/setup-python@v4.3.0
	with:
	python-version: 3.8
	- name: Install Python dependencies
	# Install csv-diff with https://github.com/simonw/csv-diff/pull/19
	run: python3 -m pip install git+https://github.com/mikecoop83/csv-diff@c3d32f758343a2ba3737d612e6e906fd9d77322b
	- name: Fetch latest data
	run: \|-
	cp doaj.csv doaj-old.csv
	curl -o doaj.csv -L https://doaj.org/csv
	# Generate commit message using csv-diff
	csv-diff doaj-old.csv doaj.csv --key "URL in DOAJ" --encoding "utf-8" --singular=journal --plural=journals \| head -n 1 > message.txt
	- name: Commit and push if it changed
	run: \|-
	git config user.name "Automated"
	git config user.email "actions@users.noreply.github.com"
	git add doaj.csv
	timestamp=$(date -u)
	git commit -F message.txt \|\| exit 0
	git push

Provide feedback