{ "openapi": "3.0.1", "info": { "title": "Bulk File Downloader — URL List to Storage or ZIP", "description": "Download any files in bulk from URL lists or the file links on a web page: PDF, ZIP, CSV, XLSX, DOCX, MP3, MP4 and more. Public download links, real type from the bytes, size, SHA-256, type/glob filters, dedupe, size caps, optional ZIP. $2 per 1,000 files + $0.001 per 10 MB.", "version": "0.1", "x-build-id": "23vv4nCHqYUEKgliN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actor-forge~bulk-file-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actor-forge-bulk-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/actor-forge~bulk-file-downloader/runs": { "post": { "operationId": "runs-sync-actor-forge-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/actor-forge~bulk-file-downloader/run-sync": { "post": { "operationId": "run-sync-actor-forge-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": { "mode": { "title": "What to download", "enum": [ "images", "files" ], "type": "string", "description": "Any files (default): every file type from a URL list or page links. Images only: scans pages for every image (img, srcset, lazy, CSS backgrounds) and is billed per image — see Pricing.", "default": "files" }, "urls": { "title": "File or page URLs", "type": "array", "description": "Direct file URLs (any type) and/or web pages whose file links should be downloaded — mix freely. A page's static HTML is scanned for links, media sources and embeds. Links added by JavaScript aren't found.", "items": { "type": "string" } }, "fileTypes": { "title": "File types", "type": "array", "description": "Only keep files of these types, e.g. pdf, zip, csv, docx, mp3. Matched against the type detected from the file bytes and against the URL extension. On pages, links with these extensions are followed. Empty = every type (page links: common document, archive, data and media extensions).", "default": [], "items": { "type": "string" } }, "urlGlobs": { "title": "Link URL globs", "type": "array", "description": "On pages, also follow links matching these globs, e.g. *.pdf, /reports/**, https://cdn.example.com/files/*. Use for download links without an extension (/download?id=…). * stays inside one folder, ** crosses folders.", "default": [], "items": { "type": "string" } }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 0.1, "maximum": 500, "type": "number", "description": "Skip files larger than this (up to 500 MB). Oversized downloads are aborted early and never charged.", "default": 100 }, "maxTotalSizeMb": { "title": "Total size cap (MB)", "minimum": 0, "type": "number", "description": "Stop downloading once the files saved add up to this many MB (0 = no cap). Keeps transfer charges predictable.", "default": 2048 }, "minFileSizeKb": { "title": "Minimum file size (KB)", "minimum": 0, "type": "number", "description": "Skip files smaller than this. Skipped files are not charged.", "default": 0 }, "maxFiles": { "title": "Max files", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after saving this many files in total.", "default": 1000 }, "skipDuplicates": { "title": "Skip duplicate files", "type": "boolean", "description": "Skip files whose content (SHA-256) is identical to one already downloaded, even from different URLs. Duplicates are not charged.", "default": true }, "createZip": { "title": "Also create a ZIP", "type": "boolean", "description": "Bundle everything into ZIP file(s) of up to 200 MB each. Links are in the run's OUTPUT record. No extra charge.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that the site's robots.txt disallows for crawlers (direct file URLs you list are always fetched).", "default": true } } }, "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 } } } } } } } } } }