{ "openapi": "3.0.1", "info": { "title": "JSON Dataset Cleaner and Deduplicator", "description": "Clean JSON datasets, remove empty rows, deduplicate by any field, validate emails, and prepare scraper output for CRMs, analysis, or AI workflows.", "version": "1.0", "x-build-id": "U1Eavdcwc19Fcwhtd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rodrgds~dataset-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rodrgds-dataset-cleaner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rodrgds~dataset-cleaner/runs": { "post": { "operationId": "runs-sync-rodrgds-dataset-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rodrgds~dataset-cleaner/run-sync": { "post": { "operationId": "run-sync-rodrgds-dataset-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "data" ], "properties": { "data": { "title": "Data", "type": "array", "description": "Array of JSON objects to clean. Each object is treated as one row.", "items": { "type": "object" } }, "textColumns": { "title": "Text columns", "type": "array", "description": "String fields to clean. Leave empty to clean all string fields.", "items": { "type": "string" }, "default": [] }, "trimWhitespace": { "title": "Trim whitespace", "type": "boolean", "description": "Remove leading and trailing whitespace from selected text fields.", "default": true }, "collapseWhitespace": { "title": "Collapse whitespace", "type": "boolean", "description": "Replace repeated whitespace inside text fields with a single space.", "default": true }, "removeControlCharacters": { "title": "Remove control characters", "type": "boolean", "description": "Remove non-printing control characters from text fields.", "default": true }, "emailColumns": { "title": "Email columns", "type": "array", "description": "Email fields to normalize and validate. Leave empty to auto-detect fields containing email.", "items": { "type": "string" }, "default": [] }, "normalizeEmails": { "title": "Normalize emails", "type": "boolean", "description": "Trim and lowercase email addresses, then validate their shape.", "default": true }, "requireValidEmail": { "title": "Require valid email", "type": "boolean", "description": "Reject rows with invalid email values instead of keeping them with warnings.", "default": false }, "phoneColumns": { "title": "Phone columns", "type": "array", "description": "Phone fields to normalize and validate. Leave empty to auto-detect phone, mobile, and tel fields.", "items": { "type": "string" }, "default": [] }, "defaultPhoneCountry": { "title": "Default phone country", "type": "string", "description": "ISO-2 country code used when phone numbers do not include a country prefix.", "default": "US" }, "normalizePhones": { "title": "Normalize phones", "type": "boolean", "description": "Parse phone numbers, output E.164, and add national format, country, and type metadata when available.", "default": true }, "requireValidPhone": { "title": "Require valid phone", "type": "boolean", "description": "Reject rows with invalid phone values instead of keeping them with warnings.", "default": false }, "urlColumns": { "title": "URL columns", "type": "array", "description": "URL, website, or domain fields to normalize. Leave empty to auto-detect url, website, and domain fields.", "items": { "type": "string" }, "default": [] }, "normalizeUrls": { "title": "Normalize URLs", "type": "boolean", "description": "Trim URLs, add https:// when missing, lowercase hostnames, and normalize domain-only fields to hostnames.", "default": true }, "dateColumns": { "title": "Date columns", "type": "array", "description": "Date fields to normalize to YYYY-MM-DD when the date is unambiguous.", "items": { "type": "string" }, "default": [] }, "numberColumns": { "title": "Number columns", "type": "array", "description": "Number fields to normalize by removing common currency symbols and thousands separators when safe.", "items": { "type": "string" }, "default": [] }, "dedupKeys": { "title": "Deduplication keys", "type": "array", "description": "Fields used together as the deduplication key after normalization.", "items": { "type": "string" }, "default": [] }, "removeEmpty": { "title": "Remove empty rows", "type": "boolean", "description": "Reject rows where all fields are blank, null, or missing.", "default": true }, "outputRejectedRows": { "title": "Output rejected rows", "type": "boolean", "description": "Write rejected rows to the dataset with errors and original row data.", "default": true }, "includeCleaningMetadata": { "title": "Include cleaning metadata", "type": "boolean", "description": "Add __changes and __warnings to cleaned rows.", "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 } } } } } } } } } }