How to Extract Product Specifications for Comparison with OpenClaw
Extract product specifications with OpenClaw and ToolRouter. Run recurring spec extractions to keep comparison databases and buying guides current.
Tool
OpenClaw automates recurring spec extraction — keeping a comparison database current by re-scraping catalogues on a schedule and refreshing the normalized spec dataset. This is the right approach for publishers and retailers whose comparison pages need to reflect current product specs as manufacturers release new models.
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 catalogue URLs, the canonical spec schema, and the normalization rules.
- Run `catalogue-scraper` with `scrape_catalogue` against each catalogue on a monthly schedule.
- Normalize the extracted specs to the canonical schema and update the comparison database.
- Flag any products where the spec structure changed — usually a signal of a manufacturer refresh or new model generation.
Example Prompt
Try this with OpenClaw using the Catalogue Scraper tool
Use catalogue-scraper to scrape https://retailer.com/laptops monthly. Normalize specs to our canonical laptop schema and update the comparison database. Flag products where the spec structure changed since last month — those are either new models or refreshed listings that need editorial review.
Tips
- Run monthly for specs — unlike prices, specs change on product refresh cycles, not continuously.
- Flag structural spec changes (new fields appearing, old fields dropping) as editorial review items, not silent updates.
- Archive historical spec snapshots so comparison pages can show 'new this generation' changes credibly.