How to Build a Product Database from Multiple Suppliers with OpenClaw
Build a Product Database from Multiple Suppliers with OpenClaw and ToolRouter. Automate recurring multi-supplier catalogue extractions and keep your product database current.
Tool
OpenClaw automates recurring multi-supplier catalogue extractions on a schedule — keeping your product database current by re-scraping supplier catalogues weekly or monthly and applying the same normalization logic each time. This is the right approach when supplier inventories change regularly and manual updates are not sustainable.
Connect ToolRouter to OpenClaw
1Install the CLI
npm install -g toolrouter-mcp2Call tools directly from OpenClaw
toolrouter-mcp call web-search search --query "AI tools"
toolrouter-mcp toolsSteps
Once connected (see setup above), use the Catalogue Scraper tool:
- Define the supplier URLs, target schema, and normalization rules for category names and price formats.
- Run `catalogue-scraper` with `scrape_catalogue` for all suppliers and normalize results to the shared schema.
- Diff the new extraction against the current database state to identify new, updated, and removed products.
- Schedule monthly runs and push changes to the database automatically.
Example Prompt
Try this with OpenClaw using the Catalogue Scraper tool
Use catalogue-scraper to scrape these supplier catalogues monthly: https://supplier-a.com/products, https://supplier-b.com/catalogue, https://supplier-c.com/items. Normalize all results to the schema: {name, price_gbp, category, description, supplier, sku}. Return the merged dataset in a stable schema so I can diff against the current database to find new and changed products.
Tips
- Use `sku` as the primary key for database diffs — product names are too unstable for reliable matching.
- Apply the same normalization rules consistently across every run so the database diff stays clean.
- Schedule extractions to coincide with supplier price list update cycles — typically monthly for wholesale.