{ "openapi": "3.0.1", "info": { "title": "Bulk File Downloader - URLs to Files and ZIP", "description": "Download files from a list of URLs, web pages or another Actor's dataset: images, PDFs, video, audio. Fast and resumable, with SHA-256, image size, duplicates removed and optional ZIP. You pay only for files stored.", "version": "0.1", "x-build-id": "eCbBEeGrspIHYdCUO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pshivam~bulk-file-downloader-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pshivam-bulk-file-downloader-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pshivam~bulk-file-downloader-scraper/runs": { "post": { "operationId": "runs-sync-pshivam-bulk-file-downloader-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pshivam~bulk-file-downloader-scraper/run-sync": { "post": { "operationId": "run-sync-pshivam-bulk-file-downloader-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "File URLs", "type": "array", "description": "Direct links to the files to download (images, PDFs, video, audio, archives). Add them one by one, paste a list (one per line) or load a text file. Repeated addresses are downloaded once.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "pageUrls": { "title": "Or web pages to scan for files", "type": "array", "description": "Web pages whose images, videos, audio, documents and archives you want. Each page is read once (no further crawling); pages that load their images with JavaScript need a browser scraper first.", "items": { "type": "string" } }, "datasetId": { "title": "Or a dataset of another Actor", "type": "string", "description": "The id of an Apify dataset (from another Actor's run). Every file link in its rows is downloaded: image, video, pdf and similar fields are found on their own." }, "urlFields": { "title": "Dataset fields with the links", "type": "array", "description": "Only for a dataset: the fields that hold file links (imageUrl, images, media.main). Empty: find them on their own.", "items": { "type": "string" } }, "fileTypes": { "title": "Only these kinds of files", "type": "array", "description": "Keep only these kinds. For web pages, only matching links are taken. A file of another kind is skipped and not charged. Empty: every kind.", "items": { "type": "string", "enum": [ "any", "image", "document", "video", "audio", "archive", "other" ], "enumTitles": [ "Any", "Images", "Documents", "Video", "Audio", "Archives", "Other" ] } }, "sameHostOnly": { "title": "Only files from the same site as the page", "type": "boolean", "description": "For web pages: skip files hosted elsewhere (CDNs, other sites).", "default": false }, "maxFilesPerPage": { "title": "Maximum files per page", "minimum": 0, "type": "integer", "description": "For web pages: take at most this many files from each page. 0 means all.", "default": 0 }, "saveFiles": { "title": "Store each file", "type": "boolean", "description": "Save every file as a record in the key-value store. Turn off to get only the ZIP (fewer API calls, faster).", "default": true }, "zip": { "title": "Pack into ZIP", "enum": [ "none", "single", "byHost" ], "type": "string", "description": "Also pack the files into ZIP parts in the key-value store (files-part-001.zip, ...).", "default": "none" }, "zipPartMb": { "title": "ZIP part size (MB)", "minimum": 10, "maximum": 1000, "type": "integer", "description": "A ZIP part is closed and uploaded when it reaches this size.", "default": 200 }, "fileNameTemplate": { "title": "File name template", "type": "string", "description": "The record key of each file. Placeholders: {filename} {name} {ext} {host} {urlhash} {sha} {type} {index}. Example: {type}_{host}_{filename}", "default": "{filename}" }, "uniqueFileNames": { "title": "Make file names unique", "type": "boolean", "description": "Put a short code of the address in front of each key, so two files with the same name never overwrite each other.", "default": true }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Larger files are skipped and not charged. The size is checked before the download when the server says it.", "default": 100 }, "maxRetries": { "title": "Retries per file", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries after a timeout, a dropped connection, HTTP 429 or a server error. A broken download continues where it stopped when the server allows.", "default": 3 }, "timeoutSeconds": { "title": "Timeout (seconds)", "minimum": 5, "maximum": 600, "type": "integer", "description": "How long to wait for the server's next bytes.", "default": 60 }, "maxPerHost": { "title": "Connections per site", "minimum": 1, "maximum": 50, "type": "integer", "description": "Downloads at the same time from one site. Lower it for sites that block fast downloads.", "default": 8 }, "headers": { "title": "Extra request headers", "type": "object", "description": "Headers sent with every request, e.g. {\"Authorization\": \"Bearer ...\", \"Cookie\": \"...\"} for files you are allowed to download." }, "userAgent": { "title": "User agent", "type": "string", "description": "Overrides the User-Agent header." }, "referer": { "title": "Referer", "type": "string", "description": "Sent as the Referer header. Files found on a page get that page as the Referer on their own." }, "acceptHtml": { "title": "Accept web pages as files", "type": "boolean", "description": "By default an address that returns a web page is a failure (an expired link often shows a page). Turn on to save pages as files.", "default": false }, "keyValueStoreName": { "title": "Key-value store name", "type": "string", "description": "Save into this named key-value store instead of the run's own one. Named stores do not expire." }, "onlyNew": { "title": "Only new files", "type": "boolean", "description": "Skip addresses that earlier runs of this same input already returned, so you never pay twice. The first run works as usual and remembers what it returned, in your key-value store 'bulk-file-downloader-scraper-only-new'.", "default": false }, "maxItems": { "title": "Maximum files", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many stored files. You are charged per stored file; failed downloads are free and do not count.", "default": 100 }, "maxConcurrency": { "title": "Max parallel downloads", "minimum": 1, "maximum": 100, "type": "integer", "description": "Files downloaded at the same time.", "default": 20 } } }, "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 } } } } } } } } } }