Generate CDSE Documentation Search Index #46

	name: Generate CDSE Documentation Search Index
	on:
	schedule:
	- cron: '0 0 * * *' # Every midnight
	workflow_dispatch:
	inputs:
	start_url:
	description: 'Starting URL for crawling (default: https://documentation.dataspace.copernicus.eu/)'
	required: false
	default: 'https://documentation.dataspace.copernicus.eu/'
	max_minutes:
	description: 'Maximum crawling time in minutes (default: 15)'
	required: false
	default: '15'
	concurrency: generate-search-index
	jobs:
	generate-index:
	runs-on: ubuntu-latest
	steps:
	- name: Check out repository
	uses: actions/checkout@v3
	- name: Set Git config
	run: \|
	git config --local user.email "actions@github.com"
	git config --local user.name "Github Actions"
	- name: Create git subtree
	run: git subtree add --prefix search_index origin docportal-search-index
	- name: Set up Python
	uses: actions/setup-python@v4
	with:
	python-version: '3.14'
	cache: 'pip'
	- name: Install dependencies
	run: pip install -r .github/scripts/requirements.txt
	- name: Generate search index
	env:
	START_URL: ${{ github.event.inputs.start_url \|\| 'https://documentation.dataspace.copernicus.eu/' }}
	MAX_MINUTES: ${{ github.event.inputs.max_minutes \|\| '15' }}
	run: \|
	python .github/scripts/run.py scrape --start-url "$START_URL" --max-minutes "$MAX_MINUTES"
	- name: Commit
	run: \|
	git add search_index
	if git diff --cached --quiet; then
	echo "No changes in search_index to commit"
	else
	git commit -m "search - update of index"
	git subtree push --prefix search_index origin docportal-search-index
	fi

Provide feedback