{ "openapi": "3.0.1", "info": { "title": "Bulk File Downloader: Download Files from URLs to Storage", "description": "Bulk download files from a URL list (PDF, ZIP, CSV, images, audio, video) to storage, each with a public link, real file type and SHA-256. $1 per 1,000 files.", "version": "0.1", "x-build-id": "gq0LGmT9NU4qLydhH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ataism~file-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ataism-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ataism~file-downloader/runs": { "post": { "operationId": "runs-sync-ataism-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/ataism~file-downloader/run-sync": { "post": { "operationId": "run-sync-ataism-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 http(s) links to files, one per line. Web pages are refused (free) unless you allow text/html below; nothing is crawled. Private, local and internal addresses are blocked, and so are social-media, video-platform and Google hosts. robots.txt of each host is checked. Through the API you can also pass objects like {\"url\": \"https://...\", \"fileName\": \"report.pdf\"}. At most 1,000 files per run.", "items": { "type": "string" } }, "fileNames": { "title": "File names (optional)", "type": "array", "description": "One name per URL, in the same order as the URLs; leave a line empty to use the name the server or the URL gives. A name you give is used as the key in the store (made safe: no folders or odd characters; a number is added if two files get the same key). Without a name, the key is the file name plus the first 8 characters of its SHA-256, so the same content always gets the same key.", "items": { "type": "string" } }, "allowedTypes": { "title": "Allowed types (optional)", "type": "array", "description": "Only keep files of these types; others are skipped for free. Use extensions (pdf, zip, csv) or MIME types (application/pdf, image/*). The check uses the file's real type from its first bytes, not just its name. Empty = every type except web pages. To download HTML pages on purpose, add text/html here.", "items": { "type": "string" } }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped with an error and not charged. Default 100, maximum 500. Files are streamed to the run's disk (about twice its memory), so with the default 512 MB of memory about 800 MB fit at once; the limit is lowered automatically if the disk is too small. Files above 5 MB add the large-file event (one per started 10 MB above the first 5 MB, see Pricing).", "default": 100 }, "dedupeBySha256": { "title": "Skip duplicate content", "type": "boolean", "description": "On: a file whose SHA-256 matches a file already saved in this run is not stored again and not charged (its row says status duplicate and points to the first copy). Off (default): every file is saved.", "default": false }, "outputStore": { "title": "Save files in this key-value store (optional)", "type": "string", "description": "Pick one of your own key-value stores to receive the files (the Actor then gets write access to that store only; it works with Limited permissions). Empty = the run's own default store. Files with the same key in a store you pick are overwritten." }, "allowSlowHosts": { "title": "Allow slow hosts", "type": "boolean", "description": "Off: files on a host whose robots.txt asks for a Crawl-delay above 1 second are skipped (free \"slow-host\" rows), because waiting between downloads is billed as run time and can exceed the file price. On: delays up to 2 seconds (1.62 seconds at 1,024 MB of memory) are honoured in full between every request to that host, so the run takes longer. Hosts that ask for more than that are always skipped. The delay is never shortened. Default off.", "default": false }, "downloadTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 10, "maximum": 600, "type": "integer", "description": "Per file, including redirects. Time spent waiting for a Crawl-delay is not counted. Every file also has a time limit set by its price, counted from the moment the request is sent (3.6 seconds for a file up to 5 MB at 512 MB; the wait for the server's first answer counts). A file that takes longer is dropped for free (see the README, Minimum speed).", "default": 300 }, "mode": { "title": "Mode", "type": "string", "description": "Internal: \"selfTest\" runs the maintainer health check and saves no files.", "default": "run" } } }, "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 } } } } } } } } } }