工具 API

tavily_crawl

Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

search1 积分

调用信息

url必填

The root URL to begin the crawl

max_depth

Max depth of the crawl. Defines how far from the base URL the crawler can explore.

max_breadth

Max number of links to follow per level of the tree (i.e., per page)

limit

Total number of links the crawler will process before stopping

instructions

Natural language instructions for the crawler. Instructions specify which types of pages the crawler should return.

select_paths

Regex patterns to select only URLs with specific path patterns (e.g., /docs/.*, /api/v1.*)

select_domains

Regex patterns to restrict crawling to specific domains or subdomains (e.g., ^docs\.example\.com$)

allow_external

Whether to return external links in the final response

extract_depth

Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency

format

The format of the extracted web page content. markdown returns content in markdown format. text returns plain text and may increase latency.

include_favicon

Whether to include the favicon URL for each result