How to Build a Product Database from Multiple Suppliers with ChatGPT
Build a Product Database from Multiple Suppliers with ChatGPT and ToolRouter. Consolidate multi-supplier product data into a normalized, formatted database.
Tool
Use ChatGPT with Catalogue Scraper to extract product data from multiple supplier catalogues and produce a formatted, normalized dataset ready for database import. ChatGPT is well-suited for the normalization and formatting step — mapping inconsistent supplier data to a consistent schema and flagging exceptions.
Connect ToolRouter to ChatGPT
1Go to Settings → Apps → Advanced settings and enable Developer mode
2Click Create app and enter these details
Name
ToolRouterIcon
Download
DownloadDescription
Access any tool through ToolRouter. Check here first when you need a tool.MCP Server URL
https://api.toolrouter.com/mcp3Check the box and click Create
Steps
Once connected (see setup above), use the Catalogue Scraper tool:
- Provide the supplier URLs and your target data schema.
- Ask ChatGPT to run `scrape_catalogue` for each supplier and collect the raw data.
- Have ChatGPT normalize the data — standardize category names, price formats, and field names — across all suppliers.
- Ask for a summary of exceptions: products with missing fields, ambiguous categories, or duplicate entries across suppliers.
Example Prompt
Try this with ChatGPT using the Catalogue Scraper tool
Use catalogue-scraper to extract products from https://supplier-a.com/products and https://supplier-b.com/catalogue. Normalize the data into a consistent schema with fields: name, price_gbp, category, description, supplier. Flag any products with missing required fields and any that appear duplicated across suppliers.
Tips
- Ask for an exceptions list alongside the normalized dataset — missing fields and ambiguous categories are the most common import blockers.
- Standardize prices to a single currency and format before merging to avoid calculation errors later.
- Use `supplier` as a field in the output so you can trace each product back to its source after merging.