{ "openapi": "3.0.1", "info": { "title": "Web Images Scraper", "description": "Extract image URLs from public webpages, domains, and direct image links. Get source pages, discovery methods, metadata, and optional saved files or ZIP archives.", "version": "0.0", "x-build-id": "d2Px0NuT1ScdmRCZx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maximedupre~web-images-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maximedupre-web-images-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maximedupre~web-images-scraper/runs": { "post": { "operationId": "runs-sync-maximedupre-web-images-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maximedupre~web-images-scraper/run-sync": { "post": { "operationId": "run-sync-maximedupre-web-images-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Webpage or image URLs", "minItems": 1, "maxItems": 100, "type": "array", "description": "Add public webpages, domains, or direct image URLs. Domains like example.com are accepted and normalized to HTTPS.", "items": { "type": "object", "properties": { "url": { "title": "URL", "type": "string", "description": "Public webpage, bare domain, or direct image URL.", "minLength": 1 } }, "required": [ "url" ] } }, "maxImagesPerPage": { "title": "Max images per page", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum accepted images to save from each webpage before moving to the next page.", "default": 100 }, "maxPagesPerStartUrl": { "title": "Max pages per input", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum webpages to open for each input URL when crawling is enabled.", "default": 1 }, "crawlDepth": { "title": "Crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many same-domain link levels to follow from each input page. Use 0 to extract images only from the submitted page.", "default": 0 }, "includeSrcset": { "title": "Include responsive 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 styles and linked stylesheets.", "default": true }, "includeMetadataImages": { "title": "Include page metadata images", "type": "boolean", "description": "Extract Open Graph, Twitter Card, and icon image URLs from page metadata.", "default": true }, "downloadImages": { "title": "Save image files to Apify storage", "type": "boolean", "description": "Download each accepted image and add Apify storage links to the output.", "default": false }, "zipDownloads": { "title": "Create ZIP files", "type": "boolean", "description": "When image saving is enabled, also create one ZIP archive per input URL and link it from each image.", "default": false }, "minImageBytes": { "title": "Minimum image size", "minimum": 0, "maximum": 100000000, "type": "integer", "description": "Skip images with a known byte size below this value. Images without known size are kept.", "default": 1024 }, "allowedExtensions": { "title": "Allowed extensions", "type": "array", "description": "Image file extensions to keep. Leave the default list for broad webpage image extraction, or narrow it to formats like png and webp.", "items": { "type": "string" }, "default": [ "jpg", "jpeg", "png", "gif", "webp", "svg", "bmp", "ico", "avif" ] }, "includeUrlPatterns": { "title": "Only include URLs containing", "type": "array", "description": "Optional text filters. When set, an image URL must contain at least one value.", "items": { "type": "string" }, "default": [] }, "excludeUrlPatterns": { "title": "Exclude URLs containing", "type": "array", "description": "Optional text filters for image URLs to skip.", "items": { "type": "string" }, "default": [] }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings used to load webpages and images. Keep the default unless the target site needs a specific proxy setup.", "default": { "useApifyProxy": true, "apifyProxyCountry": "US" } } } }, "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 } } } } } } } } } }