Scrape Maersk daily #399
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
| # This workflows starts scraping Routescanner and MSC each day at 06:00 UTC, | |
| # using the v1 scrapers, and opens a PR to merge the gathered data. | |
| name: Scrape Maersk daily | |
| on: | |
| # Disabled because Routescanner v1 is broken, and MSC v1 is redundant (replaced by v2) | |
| schedule: | |
| - cron: '0 6 * * *' | |
| push: | |
| paths: | |
| - ".github/workflows/daily_run.yml" | |
| #- "webscrapers/routescanner_automated.py" | |
| #- "webscrapers/msc_automated.py" | |
| - "webscrapers/maersk.py" | |
| workflow_dispatch: | |
| jobs: | |
| maersk: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - uses: actions/setup-python@v4 | |
| with: | |
| python-version: "3.11" | |
| - run: pip install -U pip wheel setuptools | |
| - run: pip install -U selenium beautifulsoup4 pandas numpy packaging webdriver-manager | |
| - run: python maersk.py | |
| working-directory: ./webscrapers | |
| - uses: stefanzweifel/git-auto-commit-action@v4 | |
| with: | |
| branch: "data_staging" | |
| commit_options: '--signoff' | |
| commit_message: "Add Maersk data" |