Get latest data #1267
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: Get latest data | |
| on: | |
| push: | |
| workflow_dispatch: | |
| schedule: | |
| - cron: '5 * * * *' | |
| jobs: | |
| scheduled: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Check out this repo | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - name: Fetch latest data | |
| run: |- | |
| # Get all of the files | |
| cat urls.txt | |
| while IFS= read -r url; do | |
| echo "domaining" | |
| domain=$(echo "$url" | sed -e 's|^[^/]*//||' -e 's|/.*$||' -e 's|.*\.\([^.]*\.[^.]*\)$|\1|' -e 's|\.gov||') | |
| filename="${domain}.json" | |
| echo $filename | |
| wget -qO- "$url" --user-agent="Mozilla/5.0 (Macintosh; Intel Mac OS X 10\_15\_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36" | python -m json.tool --sort-keys > "$filename" | |
| done < urls.txt | |
| - name: Commit and push if it changed | |
| run: |- | |
| git config user.name "Automated" | |
| git config user.email "[email protected]" | |
| git add *.json | |
| timestamp=$(date -u) | |
| git commit -m "Updated data: ${timestamp}" || exit 0 | |
| git push |