{ "openapi": "3.0.1", "info": { "title": "Bulk File Downloader: Download Files from URLs — Ferrywren", "description": "Bulk file downloader: download files from a list of URLs, or every PDF, Word, Excel, CSV and ZIP linked on web pages, into one ZIP or separate links. Type checked from the bytes, duplicates removed, a row per file with size and SHA-256. $1.50 per 1,000 files.", "version": "0.1", "x-build-id": "tsJyrCPNL30bBSM9q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cybermax~bulk-file-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cybermax-bulk-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/cybermax~bulk-file-downloader/runs": { "post": { "operationId": "runs-sync-cybermax-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/cybermax~bulk-file-downloader/run-sync": { "post": { "operationId": "run-sync-cybermax-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", "required": [ "urls" ], "properties": { "urls": { "title": "File links or web pages", "type": "array", "description": "One URL per line. A file link (…/report.pdf, a CSV export, an MP4) is downloaded as it is. A web page is searched for links to files (PDF, Word, Excel, PowerPoint, CSV, ZIP… or the types you pick below) and each one is downloaded. Mix both freely.", "items": { "type": "string" } }, "fileTypes": { "title": "File types to keep", "type": "array", "description": "Optional, e.g. pdf, docx, xlsx, csv, mp4, or a group: documents, images, video, audio, archives. Empty = keep every file you link directly, and look for documents and archives on pages. The type is checked from the file's own bytes, not just its name.", "items": { "type": "string" } }, "output": { "title": "Output", "enum": [ "zip", "zipPerPage", "files" ], "type": "string", "description": "ZIP parts are split at the size below. 'files' stores every file with its own public link (handy for Make, Zapier, n8n or a CMS import).", "default": "zip" }, "sameDomainOnly": { "title": "Only files on the page's own domain", "type": "boolean", "description": "Skip file links on a page that point to other sites (CDNs of the same company count as other sites).", "default": false }, "urlPattern": { "title": "Only file URLs matching (regex)", "type": "string", "description": "e.g. annual|2026" }, "excludeUrlPattern": { "title": "Skip file URLs matching (regex)", "type": "string", "description": "e.g. draft|thumbnail" }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 3800, "type": "integer", "description": "Bigger files are skipped (free). For large videos raise the run's memory too: more memory = more disk.", "default": 500 }, "minFileSizeKb": { "title": "Min file size (KB)", "minimum": 0, "type": "integer", "description": "Skip tiny files (placeholders, error stubs).", "default": 0 }, "maxFilesPerPage": { "title": "Max files per page", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Cap on file links followed from one page (the first ones on the page are kept).", "default": 200 }, "maxFilesTotal": { "title": "Max files in total", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "A hard cap on files delivered (and charged) in this run.", "default": 10000 }, "dedupe": { "title": "Remove duplicates", "type": "boolean", "description": "The same file (by content) is delivered once, even from different URLs. Duplicates are free.", "default": true }, "fileNaming": { "title": "File names", "enum": [ "original", "index", "hash" ], "type": "string", "description": "How files are named inside the ZIP or store.", "default": "original" }, "monitor": { "title": "Monitor mode (only new files)", "type": "boolean", "description": "For scheduled runs over the same pages: return (and charge) only files never delivered before for this watchlist, e.g. new reports, new price lists, new filings.", "default": false }, "monitorKey": { "title": "Watchlist name", "type": "string", "description": "Optional name for this watchlist's saved state, so you can edit the URL list without starting over." }, "includeUntypedDownloads": { "title": "Also follow links without an extension", "type": "boolean", "description": "Links marked with the HTML download attribute are files even when the URL has no extension (e.g. /export?id=7).", "default": true }, "zipPartSizeMb": { "title": "ZIP part size (MB)", "minimum": 10, "maximum": 3900, "type": "integer", "description": "Big jobs are split into several ZIP parts of at most this size.", "default": 1000 }, "concurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 20, "type": "integer", "description": "Files downloaded at the same time.", "default": 4 }, "timeoutSecs": { "title": "Timeout per download (seconds)", "minimum": 5, "maximum": 900, "type": "integer", "description": "Per download. Raise it for very large files on slow servers.", "default": 120 }, "retryWithProxy": { "title": "Retry blocked downloads through Apify Proxy", "type": "boolean", "description": "When a site answers 401/403/429, retry once through Apify Proxy (datacenter).", "default": true }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Residential proxies help with sites that block datacenter IPs (billed by Apify to your account)." } } }, "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 } } } } } } } } } }