Scrape Catalog (printers/filaments) #11
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: Scrape Catalog (printers/filaments) | |
| on: | |
| schedule: | |
| - cron: "0 6 * * 1" # weekly Monday 06:00 UTC | |
| workflow_dispatch: | |
| jobs: | |
| scrape: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Checkout | |
| uses: actions/checkout@v4 | |
| - name: Setup Node | |
| uses: actions/setup-node@v4 | |
| with: | |
| node-version: 20 | |
| cache: "pnpm" | |
| - name: Setup pnpm | |
| uses: pnpm/action-setup@v4 | |
| with: | |
| run_install: false | |
| - name: Install JS deps | |
| run: pnpm install --frozen-lockfile | |
| - name: Setup Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: "3.11" | |
| - name: Cache pip | |
| uses: actions/cache@v4 | |
| with: | |
| path: ~/.cache/pip | |
| key: pip-${{ runner.os }}-3.11-${{ hashFiles('scripts/*.py') }} | |
| restore-keys: | | |
| pip-${{ runner.os }}-3.11- | |
| - name: Install Python deps (scrapers) | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install requests beautifulsoup4 lxml tqdm | |
| - name: Run printer scraper | |
| run: | | |
| python scripts/scrape-printers.py \ | |
| --json packages/api-gateway/data/printers.json \ | |
| --api-json packages/api-gateway/data/printers.json \ | |
| --sqlite packages/api-gateway/data/printers.sqlite \ | |
| --sql scripts/seed-printers.sql | |
| - name: Build filaments sqlite | |
| run: | | |
| python scripts/build-filaments-sqlite.py \ | |
| --json packages/api-gateway/data/filaments.json \ | |
| --sqlite packages/api-gateway/data/filaments.sqlite | |
| - name: List artifacts | |
| run: ls -lh packages/api-gateway/data | |
| - name: Upload scraped artifacts | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: scraped-catalog | |
| path: | | |
| packages/api-gateway/data/printers.json | |
| packages/api-gateway/data/printers.sqlite | |
| packages/api-gateway/data/filaments.json | |
| packages/api-gateway/data/filaments.sqlite | |
| scripts/seed-printers.sql | |