> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# CaptureKit

> CaptureKit captures webpage screenshots, extracts structured web content, crawls pages, and analyzes websites with AI.

![CaptureKit logo](https://mintcdn.com/composio-preview/PudKL42NVsy5O-ND/images/toolkits/capturekit.svg?fit=max\&auto=format\&n=PudKL42NVsy5O-ND\&q=85\&s=f2374fdd28bef234ab1a6faedced475d)

* **Category:** developer tools
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 5
* **Triggers:** 0
* **Slug:** `CAPTUREKIT`
* **Version:** 20261030\_00

## Tools

> [accordion] Analyze Webpage
>
> **Slug:** `CAPTUREKIT_ANALYZE_WEBPAGE`
>
> Analyze a webpage with AI to identify its summary, value proposition, features, categories, use cases, audience, and optional custom fields.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Absolute HTTP or HTTPS URL of the webpage to analyze.
>
> **custom\_fields** `object`
>
> Map of custom output field names to instructions for generating each value.
>
> **custom\_prompt** `string`
>
> Additional instructions that guide the webpage analysis.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Capture Webpage
>
> **Slug:** `CAPTUREKIT_CAPTURE_WEBPAGE`
>
> Capture a webpage as an image or PDF and return a downloadable file reference.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Absolute HTTP or HTTPS URL of the webpage to capture.
>
> **delay** `number`
>
> Seconds to wait before taking the capture.
>
> **device** `string ("galaxy_fold4" | "galaxy_s23" | "galaxy_s23_ultra" | "galaxy_s8" | "huawei_mate_50_pro" | "huawei_p60_pro" | "ipad" | "iphone_12" | "iphone_13_mini" | "iphone_13_pro_max" | "iphone_14_pro" | "iphone_14_pro_max" | "iphone_x" | "pixel_5" | "pixel_6a" | "pixel_7_pro" | "redmi_note_11" | "redmi_note_12_pro")`
>
> Optional mobile or tablet device profile to emulate.
>
> **format** `string ("png" | "jpeg" | "jpg" | "webp" | "pdf")`
>
> Output file format.
>
> **selector** `string`
>
> CSS selector of a single page element to capture.
>
> **full\_page** `boolean`
>
> Capture the full scrollable page instead of only the viewport.
>
> **remove\_ads** `boolean`
>
> Attempt to remove ads before capture.
>
> **wait\_until** `array`
>
> Page readiness events to await before taking the capture.
>
> **viewport\_width** `integer`
>
> Viewport width in pixels when no device profile supplies it.
>
> **viewport\_height** `integer`
>
> Viewport height in pixels when no device profile supplies it.
>
> **remove\_selectors** `array`
>
> CSS selectors to hide before capture. They are sent to CaptureKit as one comma-separated query value.
>
> **wait\_for\_selector** `string`
>
> CSS selector that must appear before capture.
>
> **remove\_cookie\_banners** `boolean`
>
> Attempt to remove cookie banners before capture.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Extract Webpage Content
>
> **Slug:** `CAPTUREKIT_EXTRACT_WEBPAGE_CONTENT`
>
> Extract webpage metadata and links, optionally including rendered HTML, Markdown, sitemap data, or cleaned main content.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Absolute HTTP or HTTPS URL of the webpage to extract.
>
> **delay** `number`
>
> Seconds to wait before extracting content.
>
> **remove\_ads** `boolean`
>
> Attempt to remove ads before extraction.
>
> **wait\_until** `array`
>
> Page readiness events to await. Each event is sent as a repeated wait\_until query parameter.
>
> **include\_html** `boolean`
>
> Include rendered page HTML in the result.
>
> **use\_defuddle** `boolean`
>
> Reduce the page to primary content by removing navigation and other non-essential elements.
>
> **include\_sitemap** `boolean`
>
> Include discovered sitemap data.
>
> **include\_markdown** `boolean`
>
> Include page content converted to Markdown.
>
> **remove\_selectors** `array`
>
> CSS selectors to hide before extraction. They are sent to CaptureKit as one comma-separated query value.
>
> **wait\_for\_selector** `string`
>
> CSS selector that must appear before extraction.
>
> **remove\_cookie\_banners** `boolean`
>
> Attempt to remove cookie banners before extraction.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Fetch Page HTML
>
> **Slug:** `CAPTUREKIT_FETCH_PAGE_HTML`
>
> Fetch a webpage's raw HTML without browser rendering for fast scraping, audits, or monitoring.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> Absolute HTTP or HTTPS URL of the webpage to fetch.
>
> **allow\_redirects** `boolean`
>
> Whether CaptureKit may follow HTTP redirects.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Usage
>
> **Slug:** `CAPTUREKIT_GET_USAGE`
>
> Return the connected workspace's current CaptureKit allowance, usage, API-key status, quotas, and effective rate limits.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
