{ "openapi": "3.0.1", "info": { "title": "Bulk File and Image Downloader: Download Images from Website", "description": "Download files in bulk from direct links, or every image, video, audio file, PDF, document or archive on a list of web pages. Each file is stored with a link you can open, plus its name, type, size, SHA-256 checksum, image width, height and alt text. Duplicates are found and not charged.", "version": "0.1", "x-build-id": "EkIeAH8F1oEssJ11W" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/v0iddo~bulk-file-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-v0iddo-bulk-file-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/v0iddo~bulk-file-downloader/runs": { "post": { "operationId": "runs-sync-v0iddo-bulk-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/v0iddo~bulk-file-downloader/run-sync": { "post": { "operationId": "run-sync-v0iddo-bulk-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "fileUrls": { "title": "File links", "type": "array", "description": "Direct links to files of any type (images, video, audio, PDF, documents, archives). Each one is downloaded whatever its type. A link that turns out to be a web page comes back as a row that says so: put it under Pages instead.", "items": { "type": "string" } }, "pageUrls": { "title": "Pages", "type": "array", "description": "Web pages to download files from: the images it shows (the largest size it offers), its video and audio, and the files it links to, filtered by File types. Pages are read as HTML without a browser, so files a page loads with JavaScript only are not found.", "items": { "type": "string" } }, "fileTypes": { "title": "File types", "type": "array", "description": "Which files to take from Pages. Direct file links are always downloaded.", "items": { "type": "string", "enum": [ "image", "video", "audio", "pdf", "document", "archive" ], "enumTitles": [ "Images", "Videos", "Audio", "PDF files", "Documents (Word, Excel, PowerPoint, OpenDocument, text, CSV, EPUB)", "Archives (ZIP, RAR, 7z, TAR, GZ)" ] }, "default": [ "image" ] }, "sameSiteOnly": { "title": "Only files from the page's own site", "type": "boolean", "description": "Take only files on the host of the page or its subdomains, leaving out files on other hosts (many sites keep their images on a separate CDN host, so this can drop them).", "default": false }, "maxFilesPerPage": { "title": "Maximum files per page", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Caps the files taken from one page, in the order they appear on it.", "default": 200 }, "minImageKB": { "title": "Skip images under (KB)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Images found on pages that are smaller than this are left out (icons, spacers, tracking pixels) and not charged; 0 keeps every image. Direct links are always kept.", "default": 5 }, "maxFileMB": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files come back as a row with the reason, at no charge. Above 100 MB give the run more memory: 1 GB for every 150 MB of this limit (a few files can be in memory at once).", "default": 100 }, "maxItems": { "title": "Maximum results", "minimum": 1, "maximum": 50000, "type": "integer", "description": "The run stops after this many result rows. It also caps what one run can cost.", "default": 1000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Leave as is: the run starts on the cheapest network the site accepts and switches to Apify Proxy automatically when the site blocks it. Pick proxy groups here only to force one specific network." } } }, "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 } } } } } } } } } }