{ "openapi": "3.0.1", "info": { "title": "Bulk Image Downloader API: Save Page Images with Sizes", "description": "Download the images of any web pages, or direct image links, into a key-value store with width, height, format, size and a download link per file. Tracking pixels are skipped, robots.txt obeyed, pay only for images saved.", "version": "1.0", "x-build-id": "SP5boGcqXBugZ5cSD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rowcraft~bulk-image-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rowcraft-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rowcraft~bulk-image-downloader/runs": { "post": { "operationId": "runs-sync-rowcraft-bulk-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rowcraft~bulk-image-downloader/run-sync": { "post": { "operationId": "run-sync-rowcraft-bulk-image-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "urls": { "title": "Page URLs", "type": "array", "description": "Web pages to collect the images of, one address per line (https://example.com/product/1). The images shown on each page are found in its HTML: img tags, srcset, picture, and the og:image preview. Duplicates and invalid entries are skipped and never charged.", "items": { "type": "string" } }, "imageUrls": { "title": "Direct image URLs (optional)", "type": "array", "description": "Links that point straight at an image file (https://example.com/photo.jpg), one per line. They go through the same checks and filters as the images found on pages, and are listed with the source `direct`.", "items": { "type": "string" } }, "minWidth": { "title": "Minimum width (px)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Images narrower than this are not saved and not charged: tracking pixels, spacers and icons. 0 = no limit.", "default": 100 }, "minHeight": { "title": "Minimum height (px)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Images lower than this are not saved and not charged. 0 = no limit.", "default": 100 }, "formats": { "title": "Formats", "type": "array", "description": "Save only these image formats. Empty = every format. The format is read from the file itself; when a picture lists several versions in different formats, the versions that announce another format are not downloaded.", "items": { "type": "string", "enum": [ "jpeg", "png", "gif", "webp", "avif", "svg", "bmp", "ico", "tiff" ], "enumTitles": [ "JPEG", "PNG", "GIF", "WebP", "AVIF", "SVG", "BMP", "ICO", "TIFF" ] } }, "maxImagesPerPage": { "title": "Maximum images per page", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Stop reading a page after this many images were saved from it. The rest are listed as not read in COVERAGE.", "default": 100 }, "maxItems": { "title": "Maximum images saved", "minimum": 0, "type": "integer", "description": "Stop after this many images are saved in the whole run. 0 = no limit.", "default": 500 }, "allSizes": { "title": "Save every listed size of a picture", "type": "boolean", "description": "Off (default): one file per picture, its largest listed version (the biggest srcset width), so a product photo is not saved three times at three sizes. On: every size and every format a picture lists is downloaded.", "default": false }, "includeLinkedImages": { "title": "Also take links to image files", "type": "boolean", "description": "Add images that a page only links to (), such as the full-size versions behind gallery thumbnails. Only addresses that end in an image file extension are taken.", "default": false }, "includeBackgroundImages": { "title": "Also take inline CSS backgrounds", "type": "boolean", "description": "Add images set with background-image in the style attribute of a tag. Backgrounds defined in separate stylesheets are not read.", "default": false }, "dedupe": { "title": "Skip duplicates", "type": "boolean", "description": "On (default): an image address already handled, and a file with the same content (SHA-1) as one already saved in this run, is skipped and not charged. Off: every occurrence is saved.", "default": true }, "maxImageSizeMb": { "title": "Largest file (MB)", "minimum": 0.05, "maximum": 30, "type": "number", "description": "Files bigger than this are not saved and not charged; a file that announces its size is not even downloaded. Maximum 30.", "default": 15 }, "includeAltText": { "title": "Deliver the alt text", "type": "boolean", "description": "On (default): the alt attribute of the image is in the `alt` column, with e-mail addresses, phone numbers and contact names next to a cue removed. Off: the column stays empty. Turn it off if the pages show photos of people with their names in the alt text.", "default": true }, "onlyNew": { "title": "Only new rows since the last run", "type": "boolean", "description": "Remember the rows already delivered to you (in a key-value store in your Apify account) and deliver only rows that appeared since the last run with the same state key. The first run delivers everything that matches; later runs cost only the new rows. Ideal for schedules.", "default": false }, "stateName": { "title": "State name", "type": "string", "description": "Name of the memory used by \"Only new rows\". Use a different name for each schedule or search (for example `stockholm-python`) so they do not share one memory.", "default": "default" }, "notifyUrl": { "title": "Notify this URL when the run ends", "type": "string", "description": "A webhook address that receives one JSON POST with the number of new rows and links to the dataset: a Slack or Discord incoming webhook, a Make, n8n or Zapier catch hook, or your own endpoint. The message is also in the `text` (Slack) and `content` (Discord) fields." }, "notifyWhenEmpty": { "title": "Notify also when there are no new rows", "type": "boolean", "description": "By default the notification is sent only when at least one row was delivered.", "default": false }, "requestIntervalMs": { "title": "Delay between requests (ms)", "minimum": 250, "maximum": 10000, "type": "integer", "description": "Pause between two requests to the same host (a page and its image server are separate hosts). Default 1000 ms; minimum 250. A longer Crawl-delay in a site's robots.txt is applied instead, up to 10 s.", "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 }, "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 } } } } } } } } } }