statistics - Generate datasources for statistics #1

	name: statistics - Generate datasources for statistics
	on:
	workflow_dispatch:
	schedule:
	- cron: '0 0 1 * *'
	permissions: read-all
	jobs:
	build:
	runs-on: ubuntu-latest
	permissions:
	contents: write
	steps:
	- uses: actions/checkout@v6
	- name: Set up Python
	uses: actions/setup-python@v6
	with:
	python-version: "3.12"
	- name: Install dependencies
	run: \|
	cd subprojects/statistics
	python -m pip install --upgrade pip
	if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
	- name: Generate the input CSV file from a fresh Majestic CSV file
	run: \|
	cd subprojects/statistics
	wget http://downloads.majestic.com/majestic_million.csv
	cat majestic_million.csv \| awk -F "," 'NR>1 {print $1 "," $3}' > data/input.csv
	rm majestic_million.csv
	- name: Run data gathering script
	run: \|
	cd subprojects/statistics
	cd scripts
	python gather_data.py
	ls -l --block-size=M ../data/data.db
	- name: Set up Git user
	run: git config --global user.email "gha@github.com"; git config --global user.name "GHActionBot"
	- name: Commit update
	run: git commit -am "Sync statistics data DB and corresponding input CSV file"; git push

Provide feedback