FaunaDB scrapping #8375
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
| # produce yaml file cron job | |
| name: FaunaDB scrapping | |
| on: | |
| push: | |
| branches: | |
| - 'main' | |
| - "feature/*" | |
| paths-ignore: | |
| - ".github/workflows/*.yml" | |
| schedule: | |
| # * is a special character in YAML so you have to quote this string | |
| - cron: '10 1-23/2 * * 1-5' | |
| env: | |
| FAUNA_SECRET: ${{ secrets.FAUNA_AI_ACCESS_TOKEN }} | |
| DISCORD_WEBHOOK: ${{ secrets.DISCORD_DAILY_REVIEW_WEBHOOK }} | |
| DISCORD_CRITICAL_WEBHOOK: ${{ secrets.DISCORD_CRITICAL_WEBHOOK }} | |
| # Add cron job to ensure external webpages + apis have no changed | |
| jobs: | |
| scrap_data: | |
| runs-on: ubuntu-latest | |
| name: get_data | |
| steps: | |
| - uses: actions/checkout@v2 | |
| - uses: actions/setup-python@v3 | |
| with: | |
| python-version: '3.9' # Version range or exact version of a Python version to use, using SemVer's version range syntax | |
| architecture: 'x64' | |
| - name: Install Dependencies | |
| run: | | |
| python3 -m pip install -r requirements.txt | |
| python3 -m spacy download en_core_web_sm | |
| - name: Crawl | |
| run: | | |
| python3 recommend_news.py | |
| - name: Commit files | |
| run: | | |
| if [[ -z $(git status -s) ]] | |
| then | |
| echo "tree is clean" | |
| else | |
| git add .txt .csv || true | |
| git add . | |
| git config --local user.email "action@github.com" | |
| git config --local user.name "GitHub Action" | |
| echo "tree is dirty, please commit changes before running this" | |
| echo "PUSH_FILES=true" >> $GITHUB_ENV | |
| git config pull.rebase false || true | |
| git commit -m "Add changes" -a | |
| git merge -Xours main || true | |
| git pull origin main --strategy=ours || true | |
| git pull origin main || true | |
| fi | |
| - name: Test | |
| run: echo ${{ env.PUSH_FILES }} | |
| - name: Push changes | |
| if: ${{ env.PUSH_FILES == 'true' }} | |
| uses: ad-m/github-push-action@master | |
| with: | |
| github_token: ${{ secrets.GITHUB_TOKEN }} | |
| branch: ${{ github.ref }} |