Scrape Songs Data #47

	name: Scrape Songs Data

	on:
	schedule:
	- cron: '0 0 /2 *'
	workflow_dispatch:

	jobs:
	scrape-songs:
	runs-on: ubuntu-latest
	permissions:
	contents: write

	steps:
	- name: Checkout repository
	uses: actions/checkout@v4
	with:
	ref: main

	- name: Set up Python
	uses: actions/setup-python@v5
	with:
	python-version: '3.11'

	- name: Install dependencies
	run: \|
	python -m pip install --upgrade pip
	pip install requests beautifulsoup4 lxml

	- name: Run scraper
	run: python scripts/scrape_fumen_database.py

	- name: Check for changes
	id: check-diff
	run: \|
	if git diff --quiet songs.json; then
	echo "has_changes=false" >> $GITHUB_OUTPUT
	else
	echo "has_changes=true" >> $GITHUB_OUTPUT
	fi

	- name: Commit and push changes
	if: steps.check-diff.outputs.has_changes == 'true'
	run: \|
	git config --local user.email "41898282+github-actions[bot]@users.noreply.github.com"
	git config --local user.name "github-actions[bot]"
	git add songs.json songs_raw.json history/*
	git commit -m "chore: scrape songs data"
	git push origin main

Navigation Menu