---
canonical_url: "https://docs.composio.dev/toolkits/capturekit"
markdown_url: "https://docs.composio.dev/toolkits/capturekit.md"
product: "platform"
version: null
last_updated: null
---

# CaptureKit

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

- **Category:** developer tools
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 5
- **Triggers:** 0
- **Slug:** `CAPTUREKIT`
- **Version:** 00000000_00

## Tools

### 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | Yes | Absolute HTTP or HTTPS URL of the webpage to analyze. |
| `custom_fields` | object | No | Map of custom output field names to instructions for generating each value. |
| `custom_prompt` | string | No | Additional instructions that guide the webpage analysis. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Capture Webpage

**Slug:** `CAPTUREKIT_CAPTURE_WEBPAGE`

Capture a webpage as an image or PDF and return a downloadable file reference.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | Yes | Absolute HTTP or HTTPS URL of the webpage to capture. |
| `delay` | number | No | 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") | No | Optional mobile or tablet device profile to emulate. |
| `format` | string ("png" | "jpeg" | "jpg" | "webp" | "pdf") | No | Output file format. |
| `selector` | string | No | CSS selector of a single page element to capture. |
| `full_page` | boolean | No | Capture the full scrollable page instead of only the viewport. |
| `remove_ads` | boolean | No | Attempt to remove ads before capture. |
| `wait_until` | array | No | Page readiness events to await before taking the capture. |
| `viewport_width` | integer | No | Viewport width in pixels when no device profile supplies it. |
| `viewport_height` | integer | No | Viewport height in pixels when no device profile supplies it. |
| `remove_selectors` | array | No | CSS selectors to hide before capture. They are sent to CaptureKit as one comma-separated query value. |
| `wait_for_selector` | string | No | CSS selector that must appear before capture. |
| `remove_cookie_banners` | boolean | No | Attempt to remove cookie banners before capture. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | Yes | Absolute HTTP or HTTPS URL of the webpage to extract. |
| `delay` | number | No | Seconds to wait before extracting content. |
| `remove_ads` | boolean | No | Attempt to remove ads before extraction. |
| `wait_until` | array | No | Page readiness events to await. Each event is sent as a repeated wait_until query parameter. |
| `include_html` | boolean | No | Include rendered page HTML in the result. |
| `use_defuddle` | boolean | No | Reduce the page to primary content by removing navigation and other non-essential elements. |
| `include_sitemap` | boolean | No | Include discovered sitemap data. |
| `include_markdown` | boolean | No | Include page content converted to Markdown. |
| `remove_selectors` | array | No | CSS selectors to hide before extraction. They are sent to CaptureKit as one comma-separated query value. |
| `wait_for_selector` | string | No | CSS selector that must appear before extraction. |
| `remove_cookie_banners` | boolean | No | Attempt to remove cookie banners before extraction. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `url` | string | Yes | Absolute HTTP or HTTPS URL of the webpage to fetch. |
| `allow_redirects` | boolean | No | Whether CaptureKit may follow HTTP redirects. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Usage

**Slug:** `CAPTUREKIT_GET_USAGE`

Return the connected workspace's current CaptureKit allowance, usage, API-key status, quotas, and effective rate limits.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |