fetch_website_nested
Crawl nested URLs from a starting webpage, fetch content, and convert it into structured markdown. Control depth, page limits, domain scope, and URL inclusion/exclusion for precise content extraction.
Instructions
Fetch website content with nested URL crawling and convert to clean markdown
Input Schema
Name | Required | Description | Default |
---|---|---|---|
excludePatterns | No | Regex patterns for URLs to exclude | |
includePatterns | No | Regex patterns for URLs to include (if specified, only matching URLs will be processed) | |
maxDepth | No | Maximum depth to crawl (default: 2) | |
maxPages | No | Maximum number of pages to fetch (default: 50) | |
sameDomainOnly | No | Only crawl URLs from the same domain (default: true) | |
timeout | No | Request timeout in milliseconds (default: 10000) | |
url | Yes | The starting URL to fetch and crawl |