Crawl entire websites and extract content from multiple pages. Perfect for building datasets, analyzing site structure, or bulk content extraction.
How many levels deep to crawl (1-10)
Maximum number of pages to crawl
Comma-separated paths to include (e.g., /blog, /docs)
Comma-separated paths to exclude (e.g., /admin, /private)
Clean, structured content
Original HTML content
Visual capture of pages
Use AI to extract specific information from each crawled page