Scheduled ETL: Consolidate extracts #2138
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: "Scheduled ETL: Consolidate extracts" | |
| on: | |
| schedule: | |
| - cron: '0 */8 * * *' | |
| workflow_dispatch: | |
| concurrency: | |
| group: extract-consolidate | |
| cancel-in-progress: true | |
| jobs: | |
| consolidate-extracts: | |
| name: Consolidate extracts | |
| runs-on: ubuntu-latest | |
| steps: | |
| - id: checkout | |
| name: Checkout | |
| uses: actions/checkout@v4 | |
| - id: install | |
| name: Install | |
| uses: ./.github/actions/install | |
| - id: consolidate-extracts | |
| name: Consolidate extracts | |
| run: pipenv run python -m newshomepages.extract consolidate -o _extracts; | |
| shell: bash | |
| - id: save | |
| name: Save artifact | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: extracts | |
| path: _extracts | |
| if-no-files-found: error | |
| - id: upload-to-internet-archive | |
| name: Upload files to archive.org | |
| uses: palewire/internet-archive-upload@v1 | |
| with: | |
| access-key: ${{ secrets.IA_ACCESS_KEY }} | |
| secret-key: ${{ secrets.IA_SECRET_KEY }} | |
| identifier: news-homepages-extracts | |
| files: ./_extracts/ | |
| - id: publish-to-bln | |
| name: Publish files to biglocalnews.org | |
| uses: biglocalnews/upload-files@v2 | |
| with: | |
| api-key: ${{ secrets.BLN_API_TOKEN }} | |
| project-id: ${{ secrets.BLN_PROJECT_ID }} | |
| path: ./_extracts/ |