{ "openapi": "3.0.1", "info": { "title": "Multi-Cloud Dataset Exporter — S3, R2, B2 & Wasabi", "description": "Send Apify datasets to AWS S3, Cloudflare R2, Backblaze B2, Wasabi or an S3-compatible bucket. Partitioned JSONL/CSV, gzip, manifest, and optional incremental export.", "version": "0.1", "x-build-id": "gNbjUBcJUWMELlk22" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/optirefine~multicloud-dataset-exporter/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-optirefine-multicloud-dataset-exporter", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/optirefine~multicloud-dataset-exporter/runs": { "post": { "operationId": "runs-sync-optirefine-multicloud-dataset-exporter", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/optirefine~multicloud-dataset-exporter/run-sync": { "post": { "operationId": "run-sync-optirefine-multicloud-dataset-exporter", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "provider": { "title": "Cloud Storage Provider", "enum": [ "aws", "r2", "backblaze", "wasabi", "custom" ], "type": "string", "description": "Select the cloud storage provider for your export.", "default": "r2" }, "bucket": { "title": "Destination Bucket", "type": "string", "description": "Cloud storage bucket name. Required for a real upload; optional for dry-run previews." }, "region": { "title": "Cloud Region", "type": "string", "description": "Cloud storage region, such as us-east-1.", "default": "us-east-1" }, "endpoint": { "title": "Custom S3 Endpoint", "type": "string", "description": "Optional S3-compatible endpoint URL. Confirm the runtime supports this field name." }, "accessKeyId": { "title": "Access Key ID", "type": "string", "description": "Cloud storage access key identifier. Stored as encrypted input." }, "secretAccessKey": { "title": "Secret Access Key", "type": "string", "description": "Cloud storage secret access key. Stored as encrypted input." }, "sessionToken": { "title": "Session Token", "type": "string", "description": "Optional temporary cloud authentication token. Stored as encrypted input." }, "datasetId": { "title": "Source Apify Dataset", "type": "string", "description": "Select an Apify dataset to export. Required for incremental dataset processing." }, "runId": { "title": "Source Apify Run ID", "type": "string", "description": "Optional source Actor run ID. Use only if supported by the exporter's runtime." }, "sampleItems": { "title": "Sample Data", "type": "array", "description": "Sample records for a dry-run preview. Do not combine with incremental processing." }, "format": { "title": "Export Format", "type": "string", "description": "Output format supported by the exporter, such as jsonl.", "default": "jsonl" }, "keyPrefix": { "title": "Object Key Prefix", "type": "string", "description": "Prefix used when creating destination object keys.", "default": "apify-exports" }, "maxItems": { "title": "Maximum Records", "minimum": 1, "type": "integer", "description": "Maximum number of source records to process during this run.", "default": 1 }, "maxRowsPerPart": { "title": "Maximum Rows Per File", "minimum": 1, "type": "integer", "description": "Maximum number of records in each exported file.", "default": 1000 }, "maxBytesPerPart": { "title": "Maximum Bytes Per File", "minimum": 1, "type": "integer", "description": "Maximum target size of each export part in bytes.", "default": 5242880 }, "compressGzip": { "title": "Enable GZIP Compression", "type": "boolean", "description": "Compress exported data using GZIP.", "default": false }, "forcePathStyle": { "title": "Force Path-Style S3 Requests", "type": "boolean", "description": "Use path-style bucket addressing for compatible S3 endpoints.", "default": true }, "incremental": { "title": "Enable Incremental Export", "type": "boolean", "description": "Process new dataset records using saved export progress. Requires a real source dataset or run.", "default": false }, "cursorStoreName": { "title": "Cursor Store Name", "type": "string", "description": "Persistent cursor storage identifier used for incremental export tracking.", "default": "multicloud-exporter-cursor" }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Generate an export preview without uploading files to cloud storage.", "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 } } } } } } } } } }