{ "openapi": "3.0.1", "info": { "title": "Bulk File Downloader — Links or a Dataset to Files and a ZIP", "description": "Bulk download files from a list of URLs or from a field of another run's dataset (images, PDFs, videos, documents): each file stored with a public link, size, type and SHA-256, duplicates skipped, plus one ZIP of everything. A bulk image downloader you can also call via API.", "version": "1.0", "x-build-id": "r4iOiEleBbB8oaiK1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/steadyscrape~bulk-file-downloader/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-steadyscrape-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/steadyscrape~bulk-file-downloader/runs": { "post": { "operationId": "runs-sync-steadyscrape-bulk-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/steadyscrape~bulk-file-downloader/run-sync": { "post": { "operationId": "run-sync-steadyscrape-bulk-file-downloader", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "File links", "type": "array", "description": "Direct links to files: images, PDFs, videos, audio, documents, archives. One per line. A link that opens a web page is not a file and comes back as a free row that says so.", "items": { "type": "string" } }, "datasetId": { "title": "Or take the links from a dataset", "type": "string", "description": "Pick the dataset of another run (a scraper's results, an import) and this Actor downloads the files its items link to: product photos, listing pictures, attachments, PDFs. Only the dataset you pick here can be read." }, "datasetFields": { "title": "Dataset fields with the links", "type": "array", "description": "The fields of each dataset item that hold file links, as dotted paths; arrays are walked through, so images.url takes the url of every element of images. Leave empty to take every link in a field named like media (image, photo, thumbnail, video, file, pdf…) or ending in a file extension.", "items": { "type": "string" } }, "fileTypes": { "title": "Kinds of files to keep", "type": "array", "description": "Keep only these kinds; the rest come back as free skipped rows, read no further than their headers. Empty keeps every kind of file. Web pages are never stored.", "items": { "type": "string", "enum": [ "images", "videos", "audio", "documents", "archives", "other" ], "enumTitles": [ "Images", "Videos", "Audio", "Documents (PDF, Office, text, CSV, JSON)", "Archives (ZIP, 7z, RAR, tar, gz)", "Anything else" ] }, "default": [] }, "maxFiles": { "title": "Most files", "minimum": 1, "maximum": 100000, "type": "integer", "description": "The run stops starting downloads once this many files are stored.", "default": 1000 }, "maxTotalMegabytes": { "title": "Most megabytes in total", "minimum": 1, "type": "integer", "description": "The run never stores more than this. A file that would pass it is not stored and not charged, and the run stops there.", "default": 5000 }, "maxFileMegabytes": { "title": "Most megabytes per file", "minimum": 1, "maximum": 2048, "type": "integer", "description": "A bigger file is a free too_large row. A file waits on the run's disk until it is stored, and a run has twice its memory in disk: for files over 500 MB, give the run more memory.", "default": 500 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "On: a link a site's robots.txt disallows for this Actor (or for every robot) is a free row, and so is every link of a site whose robots.txt cannot be read. Off: you take responsibility for having the right to download those files.", "default": true }, "skipDuplicates": { "title": "Skip duplicate files", "type": "boolean", "description": "A file with the same bytes (SHA-256) as one already stored in this run is not stored again and not charged; its row points to the first.", "default": true }, "maxConcurrency": { "title": "Downloads at once", "minimum": 1, "maximum": 16, "type": "integer", "description": "Files downloaded at the same time, never more than two from one host.", "default": 4 } } }, "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 } } } } } } } } } }