{ "openapi": "3.0.1", "info": { "title": "Bulk Image Downloader", "description": "Download every image from a list of public web pages or direct image URLs, with size and type filters, optional ZIP output and per-image links in the dataset.", "version": "1.0", "x-build-id": "NtyPBY3gN1kQVPKRM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/busy_courtyard~bulk-image-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-busy_courtyard-bulk-image-downloader", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/busy_courtyard~bulk-image-downloader/runs": { "post": { "operationId": "runs-sync-busy_courtyard-bulk-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/busy_courtyard~bulk-image-downloader/run-sync": { "post": { "operationId": "run-sync-busy_courtyard-bulk-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Pages or image URLs", "type": "array", "description": "Web pages to collect images from, or direct links to image files. Pages are not crawled further: only the images on each listed page are downloaded.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxImagesPerPage": { "title": "Max images per page", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Stop after this many images from one page (filtered-out images don't count).", "default": 100 }, "maxTotalImages": { "title": "Max images in total", "minimum": 1, "maximum": 100000, "type": "integer", "description": "A hard cap for the whole run, so cost stays predictable.", "default": 1000 }, "minWidth": { "title": "Min width (px)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Skip smaller images such as icons and tracking pixels. Skipped images are not charged.", "default": 50 }, "minHeight": { "title": "Min height (px)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Skip images shorter than this.", "default": 50 }, "imageTypes": { "title": "Image types", "type": "array", "description": "Which formats to keep. The type is detected from the file contents, not just the extension.", "items": { "type": "string", "enum": [ "jpeg", "png", "gif", "webp", "avif", "svg", "bmp", "ico" ], "enumTitles": [ "JPEG", "PNG", "GIF", "WebP", "AVIF", "SVG", "BMP", "ICO" ] }, "default": [ "jpeg", "png", "gif", "webp", "avif", "svg", "bmp", "ico" ] }, "maxImageMb": { "title": "Max size per image (MB)", "minimum": 0.1, "maximum": 200, "type": "number", "description": "Larger files are skipped mid-download.", "default": 25 }, "includeSrcset": { "title": "Use the largest srcset version", "type": "boolean", "description": "For responsive images (srcset and picture), download the largest version offered.", "default": true }, "includeBackgroundImages": { "title": "Include CSS background images", "type": "boolean", "description": "Images in inline style attributes and style blocks. External CSS files are not fetched.", "default": true }, "includeMetaImages": { "title": "Include social preview images", "type": "boolean", "description": "og:image, twitter:image and touch icons.", "default": true }, "includeLinksToImages": { "title": "Follow links to image files", "type": "boolean", "description": "Also download links that point straight at an image file. Galleries often link thumbnails to the full-size file this way. Off by default, because many sites (wikis, for example) link to HTML pages whose URLs end in .jpg.", "default": false }, "sameDomainOnly": { "title": "Same site only", "type": "boolean", "description": "Only keep images hosted on the same site as the page.", "default": false }, "urlIncludeRegex": { "title": "Only image URLs matching (regex)", "type": "string", "description": "Optional, case-insensitive. Example: upload\\.wikimedia\\.org" }, "urlExcludeRegex": { "title": "Skip image URLs matching (regex)", "type": "string", "description": "Optional, case-insensitive. Example: logo|sprite|icon" }, "createZip": { "title": "Create images.zip", "type": "boolean", "description": "Bundle all saved images into one ZIP in the key-value store. Its link is in the OUTPUT record.", "default": true }, "maxZipMb": { "title": "Max ZIP size (MB)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Images beyond this stay in the key-value store but are left out of the ZIP. Raise the run memory if you increase it.", "default": 100 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages and images that the site's robots.txt disallows. Turn it off only for sites you own or have permission to download from.", "default": true }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of images downloaded at the same time.", "default": 5 }, "minDelayBetweenRequestsSecs": { "title": "Min delay per site (s)", "minimum": 0, "maximum": 60, "type": "number", "description": "Minimum time between two requests to the same host. A robots.txt Crawl-delay overrides it if it is longer.", "default": 0.25 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Maximum time for one download.", "default": 30 }, "maxRetries": { "title": "Retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for timeouts, 429 and 5xx errors. Retries use exponential backoff.", "default": 2 }, "selfTest": { "title": "Self-test mode", "type": "boolean", "description": "Ignore the other fields (startUrls is still required by the form, any URL will do) and download 2 images from a Wikipedia page, then fail the run if no image was saved or key fields are empty. Meant for a daily health-check schedule.", "default": false } } }, "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 } } } } } } } } } }