{ "openapi": "3.0.1", "info": { "title": "Data Cleaning & Deduplication", "description": "Clean, normalize, deduplicate, and profile messy datasets using only the records you provide. Standardize fields, remove duplicates, flag invalid records, handle empty values, and generate an auditable data-quality summary—with no scraping or proxies required.", "version": "0.0", "x-build-id": "iPs0YK6JkMCpGmPuj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/moving_beacon-owner1~data-cleaning-deduplication/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-moving_beacon-owner1-data-cleaning-deduplication", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/moving_beacon-owner1~data-cleaning-deduplication/runs": { "post": { "operationId": "runs-sync-moving_beacon-owner1-data-cleaning-deduplication", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/moving_beacon-owner1~data-cleaning-deduplication/run-sync": { "post": { "operationId": "run-sync-moving_beacon-owner1-data-cleaning-deduplication", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "records": { "title": "Records (inline JSON)", "type": "array", "description": "Inline JSON array of record objects to clean. Alternatively use csv/json/datasetId/datasetUrl." }, "csv": { "title": "CSV text", "type": "string", "description": "CSV data (first row is the header). Used if 'records' is empty." }, "json": { "title": "JSON text", "type": "string", "description": "A JSON array as text. Used if 'records' and 'csv' are empty." }, "datasetId": { "title": "Apify dataset ID", "type": "string", "description": "Load records from an existing Apify dataset by id or name." }, "datasetUrl": { "title": "Dataset URL", "type": "string", "description": "Public URL returning a JSON array of records." }, "dedupeStrategy": { "title": "Deduplication strategy", "enum": [ "business", "product", "none" ], "type": "string", "description": "Key used to detect duplicates.", "default": "business" }, "fuzzyDedupe": { "title": "Fuzzy deduplication", "type": "boolean", "description": "Use fuzzy name similarity instead of exact keys.", "default": false }, "fuzzyThreshold": { "title": "Fuzzy threshold", "minimum": 0, "maximum": 1, "type": "number", "description": "Similarity (0-1) above which two records are duplicates when fuzzyDedupe is on.", "default": 0.9 }, "normalizeFields": { "title": "Field normalization map", "type": "object", "description": "Map of fieldName -> type in {email, phone, company, product, address, url}. Invalid emails/phones/urls flag the record as invalid.", "default": {} }, "dropEmptyColumns": { "title": "Drop empty columns", "type": "boolean", "description": "Remove columns that are empty across every cleaned record.", "default": false }, "includeRemoved": { "title": "Include removed rows", "type": "boolean", "description": "Also output removed duplicates and invalid rows (tagged by recordType).", "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 } } }, "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 } } } } } } } } } }