Scheduled Scrape #270
This file contains hidden or 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: Scheduled Scrape | |
| on: | |
| schedule: | |
| # Run every 6 hours | |
| - cron: '0 */6 * * *' | |
| workflow_dispatch: | |
| inputs: | |
| routes: | |
| description: 'Comma-separated routes (e.g., JFK-LAX,IST-JFK)' | |
| required: false | |
| default: '' | |
| jobs: | |
| scrape: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.8' | |
| - name: Install dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install -e . | |
| - name: Initialize database | |
| run: | | |
| flight-cli db init | |
| - name: Run scheduled routes | |
| run: | | |
| # Popular routes to scrape | |
| ROUTES=${ROUTES:-"JFK-LAX,JFK-IST,JFK-CDG,SFO-TYO,LAX-LHR"} | |
| for route in $(echo "$ROUTES" | tr ',' ' '); do | |
| origin=$(echo "$route" | cut -d'-' -f1) | |
| dest=$(echo "$route" | cut -d'-' -f2) | |
| date=$(date -v+7d +%Y-%m-%d 2>/dev/null || date -d "+7 days" +%Y-%m-%d) | |
| echo "Scraping $origin -> $dest for $date" | |
| flight-cli scrape "$origin" "$dest" -d "$date" || true | |
| done | |
| - name: Report results | |
| run: | | |
| echo "Scrape completed" | |
| flight-cli db info | |
| flight-cli db history --days 1 || echo "No history yet" |