scraperv3 #100
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: scraperv3 | |
| on: | |
| schedule: | |
| - cron: '0 4 * * 2' # in the midnight Monday to Tuesday UTC-4 (Tuesday at 04.00 AM UTC) | |
| - cron: '0 4 * * 4' # Thursday | |
| - cron: '0 4 * * 6' # Saturday | |
| jobs: | |
| scraping: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout repo | |
| uses: actions/checkout@v3 | |
| - name: Setup python | |
| uses: actions/setup-python@v4 | |
| with: | |
| python-version: '3.8' | |
| - name: Install python module | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install playwright | |
| playwright install --with-deps firefox | |
| - name: Run scraper | |
| run: python scraper.py | |
| - name: Commit result | |
| run: | | |
| git config user.name "github-actions[bot]" | |
| git config user.email "github-actions[bot]@users.noreply.github.com" | |
| git add history/*.json | |
| timestamp=$(TZ='America/New_York' date +'%a, %F at %H:%M %Z') | |
| git commit -m "Scraping updated: ${timestamp}" || exit 0 | |
| git push | |
| forwarding: | |
| runs-on: ubuntu-latest | |
| needs: scraping | |
| steps: | |
| - name: Checkout repo | |
| uses: actions/checkout@v3 | |
| - name: Setup R | |
| uses: r-lib/actions/setup-r@v2 | |
| with: | |
| r-version: '4.1.1' | |
| - name: Install R library | |
| run: | | |
| sudo apt-get install libcurl4-openssl-dev | |
| Rscript -e 'install.packages(c("dplyr", "googlesheets4", "jsonlite"))' | |
| - name: Run wrangler | |
| run: Rscript wrangler.R | |
| - name: Run forwarder | |
| env: | |
| CRED_PATH: ${{ secrets.CRED_PATH }} | |
| SECRET_TOKEN: ${{ secrets.SECRET_TOKEN }} | |
| SHEETS_FORECLOSE: ${{ secrets.SHEETS_FORECLOSE }} | |
| SHEETS_TAXDEED: ${{ secrets.SHEETS_TAXDEED }} | |
| SHEETS_TEST: ${{ secrets.SHEETS_TEST }} | |
| run: | | |
| echo $SECRET_TOKEN >> $CRED_PATH | |
| Rscript foreclose.R | |
| Rscript taxdeed.R | |
| rm $CRED_PATH | |
| - name: Commit data | |
| run: | | |
| git config user.name "github-actions[bot]" | |
| git config user.email "github-actions[bot]@users.noreply.github.com" | |
| git pull | |
| git add *.rds history/foreclose/*.csv history/taxdeed/*.csv | |
| timestamp=$(TZ='America/New_York' date +'%a, %F at %H:%M %Z') | |
| git commit -m "Data updated: ${timestamp}" || exit 0 | |
| git push | |