Start from one URL, limit depth, preserve parent-child structure, and inspect cleaned content page by page.
New Job
Overview
Runs a BFS crawl, keeps accepted pages in scope, and stores the page tree.
Renders each page, captures the main content, and preserves the raw markdown for review.
Scores blocks generically by page type, position, density, and repetition across the crawl.
Recent Jobs
| Job | Status | URL | Discovered | Succeeded | Created |
|---|---|---|---|---|---|
| No jobs yet. | |||||