first draft of actions crawling #1
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
| extends: .github/workflows/setup.yml | |
| jobs: | |
| crawl: | |
| needs: setup | |
| runs-on: ubuntu-latest | |
| services: | |
| selenium: | |
| image: selenium/standalone-chrome | |
| ports: | |
| - 4444/tcp | |
| steps: | |
| - uses: actions/checkout@v2 | |
| - name: Run Selenium crawler script | |
| run: | | |
| pip install -r requirements.txt | |
| mkdir data | |
| # date -d "2 days ago" +"%Y-%m-%d" | |
| python scripts/crawl_concurrently.py --path ./data --season $CURRENT_SEASON --server http://selenium:4444 | |
| python scripts/insert_data.py -db $DB_FILENAME --data ./data/*.json | |
| - name: Upload database as artifact | |
| uses: actions/upload-artifact@v2 | |
| with: | |
| name: $DB_FILENAME | |
| path: artifacts |