{ "openapi": "3.0.1", "info": { "title": "Data Cleaner & Normalizer API — JSON/CSV Dedupe & Clean", "description": "Data Cleaner API for JSON/CSV normalization, deduplication and CRM cleanup. Trim or collapse whitespace, lowercase emails, normalize phones and ISO dates, remove empty fields or rows, deduplicate by key and process nested objects with bounded batch limits.", "version": "0.2", "x-build-id": "6GPacDqza8P7Yivnq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zenomastro~data-cleaner-normalizer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zenomastro-data-cleaner-normalizer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zenomastro~data-cleaner-normalizer/runs": { "post": { "operationId": "runs-sync-zenomastro-data-cleaner-normalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zenomastro~data-cleaner-normalizer/run-sync": { "post": { "operationId": "run-sync-zenomastro-data-cleaner-normalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "items" ], "properties": { "items": { "title": "Items (JSON array)", "maxItems": 10000, "type": "array", "description": "The records to clean — a JSON array of objects (maximum 10,000 per run)." }, "trimWhitespace": { "title": "Trim whitespace", "type": "boolean", "description": "Trim leading/trailing spaces from all string values.", "default": true }, "collapseSpaces": { "title": "Collapse inner spaces", "type": "boolean", "description": "Collapse runs of inner whitespace into a single space.", "default": true }, "lowercaseEmails": { "title": "Lowercase emails", "type": "boolean", "description": "Detect email-looking values and lowercase them.", "default": true }, "cleanPhones": { "title": "Clean phone numbers", "type": "boolean", "description": "Strip spaces, dashes and brackets from phone-looking values (keeps a leading +).", "default": true }, "normalizeDates": { "title": "Normalize dates to ISO", "type": "boolean", "description": "Best-effort convert date-looking values to ISO format (YYYY-MM-DD).", "default": false }, "removeEmptyValues": { "title": "Remove empty fields", "type": "boolean", "description": "Drop keys whose value is null or an empty string.", "default": false }, "dropEmptyRows": { "title": "Drop empty rows", "type": "boolean", "description": "Skip records that have no remaining fields after cleaning.", "default": true }, "dedupeKey": { "title": "Deduplicate by field", "type": "string", "description": "Optional field name. If set, keeps only the first record for each non-empty unique value of this field (e.g. \"email\")." }, "recursive": { "title": "Clean nested values", "type": "boolean", "description": "Apply the same string cleaning rules recursively inside nested objects and arrays.", "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 } } } } } } } } } }