{ "openapi": "3.0.1", "info": { "title": "CSV Data Cleaner & Profiler", "description": "Clean and profile your own CSV/JSON: normalize emails, phones, dates and amounts, remove duplicates, flag bad rows, and get a quality report plus an XLSX file.", "version": "0.0", "x-build-id": "9WpgKgFyUixeNf3c9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cleancellco~csv-data-cleaner-profiler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cleancellco-csv-data-cleaner-profiler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/cleancellco~csv-data-cleaner-profiler/runs": { "post": { "operationId": "runs-sync-cleancellco-csv-data-cleaner-profiler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/cleancellco~csv-data-cleaner-profiler/run-sync": { "post": { "operationId": "run-sync-cleancellco-csv-data-cleaner-profiler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "csvText": { "title": "CSV text", "type": "string", "description": "Paste your CSV (header row required)." }, "csvUrl": { "title": "CSV URL", "type": "string", "description": "Direct public http(s) link to your own file (max 50 MB). Private/local addresses blocked. Single download, no crawling." }, "rows": { "title": "JSON rows", "type": "array", "description": "Alternative: array of objects." }, "delimiter": { "title": "Delimiter", "type": "string", "description": "Auto-detected if empty." }, "dedupeKeys": { "title": "Dedupe key columns", "type": "array", "description": "Empty = whole-row duplicates.", "items": { "type": "string" } }, "requiredColumns": { "title": "Required columns", "type": "array", "description": "Column names that must be present and non-empty; rows missing them are rejected.", "items": { "type": "string" } }, "normalizeColumns": { "title": "Columns to normalize", "type": "array", "description": "Empty = all columns (kinds auto-detected).", "items": { "type": "string" } }, "columnTypes": { "title": "Force column kinds", "type": "object", "description": "e.g. {\"Phone\":\"phone\",\"Joined\":\"date\"}; kinds: email, phone, date, currency." }, "dateFormat": { "title": "Output date format", "type": "string", "description": "Output format for normalized dates (e.g. ISO YYYY-MM-DD).", "default": "%Y-%m-%d" }, "dropEmptyColumns": { "title": "Drop empty columns", "type": "boolean", "description": "Remove columns that are empty in every row.", "default": false }, "xlsxOutput": { "title": "Also save XLSX", "type": "boolean", "description": "Also save the cleaned data as an XLSX file.", "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 } } } } } } } } } }