← capabilities

Web Article-extract

Extract the main article/content body from one bounded public static HTML page as clean text and conservative Markdown. Forest deterministically selects article-like content, strips common navigation/footer/form/aside/consent chrome and returns bounded metadata. No JavaScript rendering, link following, authentication or model inference.

Forest exposes this capability as a deterministic machine-readable API for software agents. Discovery is free; execution uses the canonical paid endpoint below. The live x402 challenge is the source of truth for payment terms.

$0.003 / callPOST /web/article-extractx402 · Base

Typical agent tasks

This capability is intended for bounded machine decisions such as:

What Forest guarantees

Boundaries

Machine contract

The request and response schemas are published in the canonical OpenAPI document. This page shows a representative input from the same production manifest.

Input example

{ "url": "https://http--forest-gas-station-mainnet--lcjl27p8lmjs.code.run/fixtures/page" }

Canonical paid endpoint

https://http--forest-gas-station-mainnet--lcjl27p8lmjs.code.run/web/article-extract

OpenAPI contract →

Related capabilities