Webpage Image Extractor
Pricing
from $0.02 / 1,000 image records
Go to Apify Store
Webpage Image Extractor
Extract image URLs and metadata from public pages for SEO audits, ecommerce checks, asset migration, and AI image dataset workflows.
Webpage Image Extractor
Pricing
from $0.02 / 1,000 image records
Extract image URLs and metadata from public pages for SEO audits, ecommerce checks, asset migration, and AI image dataset workflows.
You can access the Webpage Image Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "bSnOcf5EhPQqwPHlP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fetch_cat~webpage-image-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fetch_cat-webpage-image-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fetch_cat~webpage-image-extractor/runs": { "post": { "operationId": "runs-sync-fetch_cat-webpage-image-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fetch_cat~webpage-image-extractor/run-sync": { "post": { "operationId": "run-sync-fetch_cat-webpage-image-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Public webpage URLs or direct image URLs to inspect.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "Public webpage or direct image URL." } } } }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of pages to fetch across all start URLs.", "default": 3 }, "maxImages": { "title": "Maximum image records", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of image records to save to the dataset.", "default": 200 }, "includeSrcset": { "title": "Include srcset images", "type": "boolean", "description": "Extract responsive image candidates from srcset attributes.", "default": true }, "includeCssBackgrounds": { "title": "Include CSS background images", "type": "boolean", "description": "Extract image URLs from inline style attributes and page style blocks.", "default": false }, "checkImageStatus": { "title": "Check image status and size", "type": "boolean", "description": "Send a lightweight request to each image URL to collect status code, MIME type, and byte size when available.", "default": true }, "crawlSameDomain": { "title": "Crawl same-domain links", "type": "boolean", "description": "Follow links on the same domain until Maximum pages is reached.", "default": false }, "downloadImages": { "title": "Download images to key-value store", "type": "boolean", "description": "Download supported raster image files to the run key-value store when their declared and streamed size is at most 15 MB. Disabled by default to keep runs cheap.", "default": false }, "connection": { "title": "Connection", "enum": [ "direct", "automatic" ], "type": "string", "description": "Direct (default) makes public-page and image requests without a proxy and never switches to a paid route. Automatic uses the existing Apify-managed proxy strategy from the first request, with no direct-first fallback or route switching. Proxy traffic can add costs. Explicit saved/API proxyConfiguration settings always take precedence, including customer proxy pools and disabled proxies.", "default": "direct" }, "proxyConfiguration": { "title": "Existing or custom proxy settings", "type": "object", "description": "Optional advanced settings. When supplied, these override Connection, even its default or prefill. Existing managed groups, country selection, customer proxy URLs and explicit useApifyProxy:false remain supported. No substitute route is used if the selected proxy is unavailable. Omit this object to use Connection." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Webpage Image Extractor from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: