Catalogue Scraper
Extract products from any website into your file space
On it. Running Catalogue Scraper now and I'll bring the results straight back here.
Try asking
About
Catalogue Scraper turns any e-commerce website into a structured product database in minutes. Point it at a homepage or catalogue URL and it discovers every product page, extracts the data, and saves a file for each item to your file space.
It works on any site structure — no custom integration required. The tool uses AI-powered extraction to find products even when they're buried in nested navigation or dynamically loaded pages. Each product file includes images, pricing, categories, and variants.
What you can do
- scrape_catalogue — crawl any public e-commerce site and extract all products into your file space, with images, pricing, categories, and variants
Who it's for
Retailers, brand managers, and agencies who need to audit competitor catalogues, migrate product data, or build databases without writing a custom scraper. Also useful for anyone building a price-comparison workflow or doing market research.
How to use it
- Use scrape_catalogue and pass the website's homepage or catalogue page URL
- Optionally set max_products to limit scope during testing, or pass include_paths to focus on specific URL patterns
- When the job completes, the response includes a products_url — click it to browse your extracted catalogue, grouped by category
Discover and extract all products from any e-commerce website. Identifies product pages, extracts structured data, generates spec sheets, and saves each product to your file space. Runs asynchronously — returns a job_id, poll with get_job_result.
- Use Firecrawl v2 JSON extraction per product page, preserving each source URL and provider-credit costs.
- Initial release: scrape any website to discover and catalogue all products with images, pricing, categories, and variants