kloakt_extract
Extract clean markdown content from web pages using a headless browser with full JavaScript rendering. Automatically strips navigation, headers, and footers for focused reading.
Instructions
Extract clean markdown content from a web page using a headless browser with full JavaScript rendering. Strips nav/header/footer by default. Returns structured data: title, URL, markdown content, meta tags, timing. Use this instead of WebFetch when you need JS-rendered content or clean markdown.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL to extract content from | |
| delay | No | Extra milliseconds to wait after load for async content (default: 0) | |
| format | No | Output format (default: markdown) | markdown |
| schema | No | Optional. Extract structured fields instead of markdown. An object mapping field name -> CSS selector. Suffix a selector with [] to return all matches as a list, and with @attr to return an attribute instead of text. e.g. {"title":"h1","prices":".price[]","links":"a[]@href"}. When given, returns {url, data:{...}, elapsed_ms}. | |
| stealth | No | Enable anti-detection mode | |
| selector | No | CSS selector to wait for before extracting | |
| main_only | No | Strip nav/header/footer/sidebar (default: true) | |
| max_chars | No | Truncate content to N characters (0 = unlimited, default: 0) | |
| wait_until | No | When to consider page loaded (default: load) | load |