bb #406

	name: bb

	on:
	workflow_dispatch:
	inputs:
	start_date:
	description: 'Start date'
	end_date:
	description: 'End date'
	legislative_term:
	description: 'Legislative term'
	document_type:
	description: 'Document type'
	schedule:
	- cron: "0 3 * * *"

	jobs:
	scrape:
	runs-on: ubuntu-latest
	container: ghcr.io/okfde/dokukratie:main
	defaults:
	run:
	working-directory: /opt/dokukratie
	services:
	redis:
	image: redis:alpine
	options: >-
	--health-cmd "redis-cli ping"
	--health-interval 10s
	--health-timeout 5s
	--health-retries 5
	ports:
	- 6379:6379
	env:
	ARCHIVE_BUCKET: ${{ secrets.ARCHIVE_BUCKET }}
	ARCHIVE_ENDPOINT_URL: ${{ secrets.ARCHIVE_ENDPOINT_URL }}
	DATA_BUCKET: ${{ secrets.DATA_BUCKET }}
	AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
	AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
	steps:
	- name: Pull crawler runtime data
	run: make bb.pull
	- name: Run crawler
	env:
	START_DATE: ${{ github.event.inputs.start_date }}
	END_DATE: ${{ github.event.inputs.end_date }}
	LEGISLATIVE_TERMS: ${{ github.event.inputs.legislative_term }}
	DOCUMENT_TYPES: ${{ github.event.inputs.document_type }}
	run: make bb.run_prod
	- name: Generate mmmeta
	if: always()
	run: make bb.mmmeta
	- name: Upload data
	if: always()
	run: make bb.upload

Provide feedback