{
"openapi": "3.0.1",
"info": {
"title": "Bulk Image Scraper — Real Dimension & File Size Filter",
"description": "Crawl a website (or list of URLs) and collect every image, filtered by the REAL decoded pixel width/height and file size — not just the declared HTML attribute. Detects true format via magic bytes and dedupes by content hash. Optional full download to the key-value store.",
"version": "0.1",
"x-build-id": "lkrPYWeG5CdlcmZZR"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/codeclouds~bulk-image-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-codeclouds-bulk-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/codeclouds~bulk-image-scraper/runs": {
"post": {
"operationId": "runs-sync-codeclouds-bulk-image-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/codeclouds~bulk-image-scraper/run-sync": {
"post": {
"operationId": "run-sync-codeclouds-bulk-image-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"startUrls"
],
"properties": {
"startUrls": {
"title": "Start URLs",
"type": "array",
"description": "One or more web pages to scan for images. Example: https://example.com/gallery",
"default": [
"https://example.com"
],
"items": {
"type": "string"
}
},
"maxCrawlDepth": {
"title": "Max crawl depth",
"minimum": 0,
"maximum": 5,
"type": "integer",
"description": "How many link-hops to follow from each start URL. 0 = only scan the start URL itself, no link-following. Example: 1",
"default": 1
},
"sameHostOnly": {
"title": "Same host only",
"type": "boolean",
"description": "Only follow links that stay on the same hostname as the start URL. Turn off to allow crawling across subdomains/hosts.",
"default": true
},
"imageExtensions": {
"title": "Image extensions to include",
"type": "array",
"description": "Only collect images whose URL ends with one of these extensions. Example: jpg, png, webp",
"items": {
"type": "string",
"enum": [
"jpg",
"jpeg",
"png",
"gif",
"webp",
"svg",
"avif",
"bmp",
"ico"
]
},
"default": [
"jpg",
"jpeg",
"png",
"gif",
"webp",
"svg",
"avif",
"bmp",
"ico"
]
},
"minWidth": {
"title": "Minimum width (px)",
"minimum": 0,
"type": "integer",
"description": "Skip images narrower than this, based on the REAL decoded pixel width (not the HTML width attribute). Leave empty for no minimum. Example: 400"
},
"minHeight": {
"title": "Minimum height (px)",
"minimum": 0,
"type": "integer",
"description": "Skip images shorter than this, based on the REAL decoded pixel height. Leave empty for no minimum. Example: 300"
},
"maxWidth": {
"title": "Maximum width (px)",
"minimum": 0,
"type": "integer",
"description": "Skip images wider than this, based on the REAL decoded pixel width. Leave empty for no maximum. Example: 4000"
},
"maxHeight": {
"title": "Maximum height (px)",
"minimum": 0,
"type": "integer",
"description": "Skip images taller than this, based on the REAL decoded pixel height. Leave empty for no maximum. Example: 4000"
},
"minFileSizeKb": {
"title": "Minimum file size (KB)",
"minimum": 0,
"type": "integer",
"description": "Skip images smaller than this file size in kilobytes. Leave empty for no minimum. Example: 10"
},
"maxFileSizeKb": {
"title": "Maximum file size (KB)",
"minimum": 0,
"type": "integer",
"description": "Skip images larger than this file size in kilobytes. Leave empty for no maximum. Example: 5000"
},
"includeBackgroundImages": {
"title": "Include CSS background images",
"type": "boolean",
"description": "Also collect images referenced via a CSS \"background-image: url(...)\" inline style, not just ![]()
/ tags.",
"default": false
},
"includeSrcset": {
"title": "Include srcset variants",
"type": "boolean",
"description": "Also collect every image URL listed in an ![]()
/ \"srcset\" attribute (responsive images), not just the main \"src\".",
"default": true
},
"downloadFiles": {
"title": "Download full image files",
"type": "boolean",
"description": "Download the complete image bytes into the run's key-value store (not only metadata). Increases run time/cost. When off, only metadata is collected and file size/dimensions are read from response headers where possible.",
"default": false
},
"maxImagesPerPage": {
"title": "Max images per page",
"minimum": 1,
"maximum": 2000,
"type": "integer",
"description": "Stop collecting candidate images on a single page after this many are found (safety cap for very large galleries). Example: 200",
"default": 200
},
"maxTotalImages": {
"title": "Max total images",
"minimum": 1,
"maximum": 50000,
"type": "integer",
"description": "Stop the whole run after this many images have been returned across all pages combined. Example: 1000",
"default": 1000
}
}
},
"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
}
}
}
}
}
}
}
}
}
}