burch ai
It's all about the prompt!
Title Extractor
Site Title/Heading Crawler
Crawl a Site and Extract Titles and Headings
Start URL (must be HTTPS)
Max pages
Max depth (0 = only the start page)
?
Depth is how many link clicks away from the start URL the crawler will go. Depth 0 = just the start page; depth 1 = pages linked from the start; depth 2 = links found on those pages; and so on.
Concurrency
?
The number of pages fetched at the same time. Higher values are faster but can stress servers or trigger blocks. 2–6 is usually a safe range.
Delay between requests (ms)
Use CORS proxy (recommended)
Stay within starting path only
?
Limits the crawl to the same host AND to the starting directory. Examples: - Start: https://example.com/blog/post-1 Crawls: https://example.com/blog/... (any page whose path begins with /blog/) Skips: https://example.com/shop/... and https://blog.example.com/ (different subdomain) - Start: https://example.com/docs/ Crawls: https://example.com/docs/... only - Start: https://example.com/ Effect: same as whole site on this host (path is "/"). Tip: Start at the section root (e.g., https://example.com/docs/) to limit the crawl to that section.
Ignore tracking params (utm_*, gclid, fbclid)
Crawl Site
Stop
Results (text)
Results (clickable links)
Copy
Save
Clear
Notes: - Many sites block direct browser fetches. Keep “Use CORS proxy” on. - Be considerate: set reasonable limits. Some sites have thousands of pages. - This stays on your device. No server stores your data.
Saved Extractions
Export All
Clear All Saved
Burch Ai
www.burchai.com