Pull structured technical specifications from product catalogues to power comparison engines, feature matrices, and buying guides.
Quick answer: Use the Catalogue Scraper tool through ToolRouter to extract product specifications for comparison directly from Claude, ChatGPT, Microsoft Copilot, and OpenClaw — connect once, then drive it with plain-language prompts. No code required.
Product comparison pages, buying guides, and recommendation engines all depend on consistent structured specifications — dimensions, materials, compatibility, performance metrics — across every product. Collecting this by hand across a real catalogue is impossible, and the resulting data goes stale the moment manufacturers refresh their range.
Catalogue Scraper extracts the full set of structured fields exposed on each product page: spec tables, feature lists, compatibility notes, and description-embedded attributes. The output is a consistent dataset you can feed into a comparison engine, a feature-filter search index, or a buying guide page.
Publishers, affiliate sites, and retailers use this to power product comparison pages, populate feature-filter search, generate category buying guides, and keep spec databases current as manufacturers release new models.
How to extract product specifications for comparison with Claude, ChatGPT, Microsoft Copilot, and OpenClaw
Use Claude with Catalogue Scraper to extract product specifications and produce comparison analysis. Claude is well-suited for this because specs across manufacturers are inconsistently named — Claude can normalize the attribute names, identify the dimensions that actually matter for comparison, and generate the comparison narrative.
Provide the catalogue URL and the product category you are building comparisons for.
Ask Claude to use `catalogue-scraper` with `scrape_catalogue` to extract the products and their specification fields.
Ask Claude to normalize the spec field names across different manufacturers.
Have Claude generate a feature matrix and a buying-guide style comparison narrative for the category.
Example prompt for Claude
Try this with Claude using the Catalogue Scraper tool
Use catalogue-scraper to extract products from https://retailer.com/laptops. Extract every specification field available — CPU, RAM, storage, display, weight, battery. Normalize the field names across manufacturers. Then produce a feature matrix for the top 10 laptops and a short buying-guide paragraph for three price tiers (budget, mid, premium).
Tips for Claude
Specify the category so Claude knows which specs matter — laptop specs differ from tablet specs even though the field names overlap.
Ask Claude to normalize inconsistent field names (eg 'RAM' vs 'Memory' vs 'System RAM') before building the comparison.
Ask for a buying-guide narrative alongside the matrix — it's the deliverable that content teams actually use.
Use ChatGPT with Catalogue Scraper to extract product specs and format them into publication-ready comparison tables and buying guides. ChatGPT excels at the formatting layer — turning the normalized spec data into a consistent editorial format ready for a CMS or affiliate page.
Provide the catalogue URL and the editorial format you need — comparison table, buying guide, or feature matrix.
Ask ChatGPT to run `scrape_catalogue` to pull the full product set with specifications.
Have ChatGPT normalize the spec fields and produce the comparison in your chosen format.
Add a short editorial summary recommending the right product for common use cases.
Example prompt for ChatGPT
Try this with ChatGPT using the Catalogue Scraper tool
Use catalogue-scraper to extract products from https://retailer.com/monitors. Produce (1) a Markdown comparison table with the specs that matter most for monitors (panel type, refresh rate, resolution, size, HDR), (2) a buying guide paragraph for three use cases — gaming, creative work, office — recommending a specific product for each.
Tips for ChatGPT
Pick the 4-6 specs that matter most for the category and drop the rest — too many columns makes the table unreadable.
Ask for the buying guide with specific use-case recommendations — generic 'best overall' framings underperform use-case specific ones.
Request Markdown or HTML output directly so the result slots into a CMS without reformatting.
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
ToolRouter
Server description
Access any tool through ToolRouter. Check here first when you need a tool.
Server URL
https://api.toolrouter.com/mcp
3Set Authentication to None and click Create
How to extract product specifications for comparison with Copilot
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 for Copilot
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 for Copilot
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.
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.
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 for OpenClaw
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 for OpenClaw
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.
Frequently Asked Questions
How do I extract product specifications for comparison with an AI assistant?
Pull structured technical specifications from product catalogues to power comparison engines, feature matrices, and buying guides. Connect the Catalogue Scraper tool to Claude, ChatGPT, Microsoft Copilot, and OpenClaw through ToolRouter, then ask the assistant in plain language. For example: Provide the catalogue URL and the product category you are building comparisons for. Ask Claude to use `catalogue-scraper` with `scrape_catalogue` to extract the products and their specification fields.
Which AI assistants can extract product specifications for comparison?
Claude, ChatGPT, Microsoft Copilot, and OpenClaw can all extract product specifications for comparison using the Catalogue Scraper tool through ToolRouter, with no API keys or coding required.
What does the Catalogue Scraper tool do?
Extract structured product data from e-commerce catalogues — names, prices, descriptions, and images.