How to Extract Product Specifications for Comparison with Copilot
Extract product specifications with Copilot and ToolRouter. Return structured spec JSON to power comparison engines, feature-filter search, and buying tools.
Tool
Use Copilot with Catalogue Scraper to extract specifications as typed structured JSON and feed them into a comparison engine, feature-filter index, or buying-guide generator. Copilot is best here when the spec data needs to drive a programmatic product experience — not a static editorial page.
Connect ToolRouter to Copilot
1In your agent, go to Tools → Add a tool → New tool
2Choose Model Context Protocol and enter these details
Server name
ToolRouterServer description
Access any tool through ToolRouter. Check here first when you need a tool.Server URL
https://api.toolrouter.com/mcp3Set Authentication to None and click Create
Steps
Once connected (see setup above), use the Catalogue Scraper tool:
- Define the canonical spec schema for your category (which attributes, which types, which units).
- Ask Copilot to run `scrape_catalogue` and map each product's raw spec data to the canonical schema.
- Have Copilot return typed JSON with normalized units and consistent field names.
- Index the output in your comparison engine or feature-filter search system.
Example Prompt
Try this with Copilot using the Catalogue Scraper tool
Use catalogue-scraper to extract products from https://retailer.com/laptops. Map the extracted spec data to this schema: {products: Array<{sku, name, cpu: string, ram_gb: number, storage_gb: number, display_in: number, weight_kg: number, battery_hrs: number}>}. Convert all units consistently — no mixing GB/TB or inches/cm.
Tips
- Define the canonical units in the schema (GB not TB, kg not lb) and enforce conversion during normalization.
- Include `sku` as the primary key so downstream systems can join against product data.
- Validate the first 5 products against the schema before processing the full catalogue — spec inconsistencies surface fast this way.