{
"openapi": "3.0.1",
"info": {
"title": "Website Image Scraper",
"description": "Extract every image URL from a website. Crawls the start page (and optionally internal links up to a configurable depth), parses `![]()
` tags, ``/``, `srcset` candidates, and CSS `background-image` declarations. HTTP-only, no proxy or browser needed.",
"version": "0.1",
"x-build-id": "5lafNCefriCSMGxiM"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/crawlerbros~website-image-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-crawlerbros-website-image-scraper",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/crawlerbros~website-image-scraper/runs": {
"post": {
"operationId": "runs-sync-crawlerbros-website-image-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/crawlerbros~website-image-scraper/run-sync": {
"post": {
"operationId": "run-sync-crawlerbros-website-image-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"startUrl"
],
"properties": {
"startUrl": {
"title": "Start URL",
"type": "string",
"description": "The page to start crawling from (e.g. 'https://example.com'). The actor extracts images from this page and, if `maxCrawlDepth >= 1`, follows internal links to additional pages on the same host."
},
"maxCrawlDepth": {
"title": "Maximum crawl depth",
"minimum": 0,
"maximum": 5,
"type": "integer",
"description": "0 = only the start URL. 1 = also follow links found on the start URL (same host only). Higher values widen the crawl but cost more time.",
"default": 1
},
"maxImagesPerPage": {
"title": "Maximum images per page",
"minimum": 1,
"maximum": 5000,
"type": "integer",
"description": "Cap on how many images are extracted from a single page. Pathological gallery pages can list hundreds of duplicates; this keeps runs bounded.",
"default": 200
},
"maxTotalImages": {
"title": "Maximum images per run",
"minimum": 1,
"maximum": 50000,
"type": "integer",
"description": "Hard cap on the total number of image records pushed across all crawled pages. The crawl stops once this many images are emitted.",
"default": 1000
},
"imageExtensions": {
"title": "Image extensions to accept",
"type": "array",
"description": "Only image URLs whose path ends in one of these extensions are kept. Drop entries to filter to a subset (e.g. only ['svg']) or extend with custom formats.",
"default": [
"jpg",
"jpeg",
"png",
"gif",
"webp",
"svg",
"avif",
"bmp",
"ico"
],
"items": {
"type": "string"
}
},
"includeBackgroundImages": {
"title": "Include CSS background-images",
"type": "boolean",
"description": "Also extract images referenced via inline `style=\"background-image: url(...)\"` attributes. Disable to only collect `![]()
`-sourced images.",
"default": true
},
"userAgent": {
"title": "Custom User-Agent (optional)",
"type": "string",
"description": "Override the default Chrome User-Agent string. Most sites accept the default; only set this if a target server filters by UA."
}
}
},
"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
}
}
},
"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
}
}
}
}
}
}
}
}
}
}