Extract image links from a web page

Give your Agent one page URL to collect image source links, available alternative text and source-element labels. Choose visual deduplication or extra browser wait when the task needs them.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use scrape-images-context-dev through my existing Toolmu connection; follow https://toolmu.com/SKILL.md if setup is needed. Stay within my existing authorization and budget. Supply one full URL in queryParams.url, and apply my native dedupe, maxAgeMs and waitForMs preferences. Keep timeoutMS below the Tool request timeout. Return image references with available original alt, type and element values, plus loading and cache context. Organize records using their reported fields; keep missing text rather than inventing vision captions. Distinguish reference delivery from image-file downloads, and avoid claiming complete coverage, current accessibility or reuse permission.

Task:
Find pictures on [full webpage link, e.g. https://example.com/gallery] and list their links and any description text available on the page.

Paste into your connected AI's conversation.

Connection guide

Up to 0.00108 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

Context.dev

Extract image links from a web page

Give your Agent one page URL to collect image source links, available alternative text and source-element labels. Choose visual deduplication or extra browser wait when the task needs them.

You receive

Receive a list of image references with source links, reported alternative text, reference kind and page-element labels. Loading state and cache context help explain the capture, and your Agent can organize the returned records for review.

Start with your task

Find pictures on [full webpage link, e.g. https://example.com/gallery] and list their links and any description text available on the page.

What to know

This is a one-page reference list, not a file download or ZIP archive. It does not establish complete site, gallery or CSS-image coverage. Page-provided text is not an AI caption; source links do not guarantee current availability or reuse permission.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Image extraction request`queryParams`	`object`	Required	Required request containing one full page URL and optional deduplication, cache-age, timeout and browser-wait preferences. Required fields `url`
Page URL`queryParams.url`	`string`	Required	Required full URL including http:// or https://. The request targets one page rather than crawling all pages on its domain. Format `uri`
Visual deduplication`queryParams.dedupe`	`boolean`	Optional	Optional boolean, false by default. Requests loading images for perceptual-hash comparison and retaining the highest-resolution member within each detected duplicate group.
Maximum cache age`queryParams.maxAgeMs`	`integer`	Optional	Integer from 0 to 2,592,000,000 milliseconds (30 days). The native description states a one-day default; 0 requests fresh retrieval. Inspect returned cache context. Minimum `0` Maximum `2592000000`
Supplier timeout`queryParams.timeoutMS`	`integer`	Optional	Optional integer from 1,000 to 300,000 milliseconds. Keep it below the Tool request timeout. Minimum `1000` Maximum `300000`
Extra browser wait`queryParams.waitForMs`	`integer`	Optional	Optional wait of 0–30,000 milliseconds after page load before capture. It can help delayed content without scrolling or guaranteeing every image is captured. Minimum `0` Maximum `30000`

View raw JSON

{
  "type": "object",
  "required": [
    "queryParams"
  ],
  "properties": {
    "queryParams": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "url"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "description": "Full URL to fetch, including the http:// or https:// scheme."
        },
        "dedupe": {
          "type": "boolean",
          "description": "Remove visually duplicate images: every image is loaded and perceptually hashed and only the highest-resolution copy of each duplicate group is kept. Default false."
        },
        "maxAgeMs": {
          "type": "integer",
          "maximum": 2592000000,
          "minimum": 0,
          "description": "Reuse a cached result younger than this many milliseconds. Default 86400000 (1 day), max 2592000000 (30 days). Set 0 to always fetch fresh."
        },
        "timeoutMS": {
          "type": "integer",
          "maximum": 300000,
          "minimum": 1000,
          "description": "Upstream timeout in milliseconds (max 300000). Context.dev aborts the call with a 408 when exceeded. Keep it below the endpoint's requestTimeoutMs so the provider answers before the platform's own budget expires."
        },
        "waitForMs": {
          "type": "integer",
          "maximum": 30000,
          "minimum": 0,
          "description": "Extra browser wait in milliseconds after page load before the content is captured (0-30000). Useful for JavaScript-heavy pages."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

No fixed output contract is available. Field types reflect saved result evidence; individual responses can differ.

Result schema
Field / Path	Type	Meaning
Image-reference result`result`	`object`	Image references from the requested page with available capture and cache context.
Reported page URL`result.url`	`string`	Page URL reported for this capture.
Image references`result.images`	`array`	List of captured image-source records. Each record can contain src, alt, type and element; references can include content images and link-element icons.
Image source reference`result.images[].src`	`string`	Returned source URL or reference. It is not image-file bytes or proof of current retrieval availability.
Reported alternative text`result.images[].alt`	`string \| null`	Alternative text reported from the page when available; it can be null and is not a generated image caption.
Reference kind`result.images[].type`	`string`	Reported reference kind, such as url; this is distinct from the image’s subject or file format.
Source element`result.images[].element`	`string`	Reported page-element label, such as img or link, rather than an image-content classification.
Capture success`result.success`	`boolean`	Supplier-reported capture success, not a guarantee of complete image coverage or current file availability.
Page loading state`result.finalDOMState`	`string`	Supplier-reported loading state at capture. loaded does not establish that all lazy images or later interaction states were captured.
Cache context`result.cache_metadata`	`object`	Supplier-reported cache status and age for the reference result.
Cache status`result.cache_metadata.status`	`string`	Reported cache state, such as hit or miss, for this capture.
Cache age`result.cache_metadata.age_ms`	`number`	Reported cached-result age in milliseconds, rather than a retention period or a current check of every linked image.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

The result delivers source references and reported labels, rather than image-file bytes or an archive. A returned URL can later change, require access or fail, so retrieval and reuse permissions need separate checks.

Extract image links from a web page

Extract image links from a web page

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Enter a webpage link

Choose the page you want

Check the pictures found

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Enter a webpage link

Choose the page you want

Check the pictures found

Questions about this tool.

Will I receive image files or a ZIP download?

Are all returned records page photos or product images?

What does missing alternative text mean?

How does visual deduplication work?

How can I capture delayed images or request a fresh result?