{ "openapi": "3.0.1", "info": { "title": "Bulk File and Image Downloader: URLs to ZIP", "description": "Downloads every file or image URL you list, or the images and linked files on the pages you name, into ZIP files and direct download links, with size, type and SHA-256 for each file.", "version": "0.1", "x-build-id": "82DoGYHXBaCoW3feO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/examsens.ai~bulk-file-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-examsens.ai-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/examsens.ai~bulk-file-downloader/runs": { "post": { "operationId": "runs-sync-examsens.ai-bulk-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/examsens.ai~bulk-file-downloader/run-sync": { "post": { "operationId": "run-sync-examsens.ai-bulk-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 URLs", "type": "array", "description": "Direct links to files of any type: images, PDFs, documents, audio, video, archives. Each one is downloaded as it is.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "pageUrls": { "title": "Page URLs", "type": "array", "description": "Web pages to collect files from. Each page is read once (no crawling to other pages) and the images or linked files it shows are downloaded.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "findOnPages": { "title": "Find on pages", "enum": [ "images", "files", "both" ], "type": "string", "description": "What to collect from Page URLs. Images: img tags, lazy loaded image attributes, social share images, inline style background images and links to image files. Linked files: links whose file extension is in the list below. Both: both.", "default": "images" }, "fileExtensions": { "title": "Linked file extensions", "type": "array", "description": "Extensions of linked files to collect from pages when Find on pages is Linked files or both. Without a dot, such as pdf.", "default": [ "pdf", "doc", "docx", "xls", "xlsx", "ppt", "pptx", "csv", "txt", "zip", "mp3", "mp4" ], "items": { "type": "string" } }, "includeSrcset": { "title": "Include srcset images", "type": "boolean", "description": "Also collect every size listed in srcset attributes of img and picture tags. Off collects the main image source only.", "default": false }, "sameHostOnly": { "title": "Same host only", "type": "boolean", "description": "Collect only files on the same host as the page. Off also takes files from image CDNs and other hosts.", "default": false }, "maxFilesPerPage": { "title": "Maximum files per page", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop collecting from a page after this many files.", "default": 500 }, "output": { "title": "Output", "enum": [ "both", "zip", "files" ], "type": "string", "description": "ZIP and files: every file gets its own download link and is also packed into ZIP files. ZIP only: one ZIP download (split into parts when large). Files only: one download link per file, no ZIP.", "default": "both" }, "zipPartSizeMb": { "title": "ZIP part size (MB)", "minimum": 10, "maximum": 2000, "type": "integer", "description": "A new ZIP part starts when the current one would pass this size. Keep it under half the run memory.", "default": 200 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Files larger than this get an error row and are not charged.", "default": 100 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs the site's robots.txt disallows and wait the crawl delay it sets between requests to that host.", "default": true }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many files to download at the same time. Each host gets at most 2 at once whatever this is set to.", "default": 4 }, "timeoutSecs": { "title": "Timeout per request (seconds)", "minimum": 5, "maximum": 600, "type": "integer", "description": "How long to wait for a server before the request fails. Timeouts and busy answers are retried twice.", "default": 60 } } }, "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 } } } } } } } } } }