Responsible website extraction

Scrape structured data with citations.

Checking API
Checking session
Session Sign in required
Scope preview Ready
Boundary
Same-domain public crawl
Limits
10 pages, depth 1, 2000 ms delay
Rendering
Static HTML extraction
Waiting for crawl input.
Status Idle
Pages crawled 0
Blocked 0
Failed 0

Pages

Start a crawl to populate results.

0 pages
URL HTTP Words Title
No crawl results yet.

Search

Find extracted facts inside this project.

No search submitted.

Page detail

Select a page row to inspect citations.

No page selected Extracted fields, contacts, and SEO findings will appear here.

Data quality

Machine-generated output requires review.

Source URLs Each field keeps the crawl URL and section.
Confidence Fields and findings include a confidence score.
Contact care Likely personal contacts are excluded from default exports.