Scheduled ETL: Extract robots.txt sample #499
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: Extract robots.txt sample" | |
| on: | |
| schedule: | |
| - cron: '30 0 * * *' | |
| workflow_dispatch: | |
| concurrency: | |
| group: extract-robotstxt | |
| cancel-in-progress: true | |
| jobs: | |
| download: | |
| name: Download robots.txt files | |
| runs-on: ubuntu-latest | |
| steps: | |
| - id: checkout | |
| name: Checkout | |
| uses: actions/checkout@v4 | |
| - id: install | |
| name: Install | |
| uses: ./.github/actions/install | |
| - id: download-robotstxt | |
| name: Download robots.txt files | |
| run: pipenv run newshomepages-extract robotstxt --latest --no-cache --verbose --output-path=./robotstxt-sample.csv; | |
| shell: bash | |
| - 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: robotstxt-sample.csv |