{ "openapi": "3.0.1", "info": { "title": "Scraped Data Cleaner & Converter (No-Code CSV/JSON Tool) - PPE", "description": "Clean and organize scraped .json or .csv data โ€” no coding required. Remove duplicates, empty rows, unwanted columns, and sort by any field. Cleaned results are stored in Apify's Key-Value Store. Perfect for marketers, researchers, and no-code workflows.", "version": "0.0", "x-build-id": "8gUvEQeJVUfxmj0GQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/m3web~scraped-data-cleaner-ppe/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-m3web-scraped-data-cleaner-ppe", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/m3web~scraped-data-cleaner-ppe/runs": { "post": { "operationId": "runs-sync-m3web-scraped-data-cleaner-ppe", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/m3web~scraped-data-cleaner-ppe/run-sync": { "post": { "operationId": "run-sync-m3web-scraped-data-cleaner-ppe", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "uploadedDataFile": { "title": "1.1 ๐Ÿ“ Uploaded Data File", "type": "string", "description": "Upload a CSV or JSON file, or paste a full Apify URL for a stored record. The file must contain structured rows of data with fields you want to clean or filter." }, "deduplicateBy": { "title": "1.2 ๐Ÿง  Deduplicate By Field", "type": "string", "description": "Enter the name of a field (e.g. 'email', 'product_id') to remove duplicate rows. Only the first row with each unique value will be kept.", "default": "" }, "removeEmpty": { "title": "1.3 ๐Ÿงน Remove Empty Rows", "type": "boolean", "description": "Removes rows that contain no meaningful data. Works for both CSV and JSON files.", "default": true }, "requiredFields": { "title": "2.1.1 ๐Ÿ”Ž Must-Have Fields", "type": "array", "description": "Specify one or more field names (e.g. 'email', 'phone'). Rows missing required data in these fields will be removed.", "items": { "type": "string" } }, "requireAllFields": { "title": "2.1.2 ๐Ÿ”Ž Match All Required Fields", "type": "boolean", "description": "If checked, rows must contain data in ALL required fields. If unchecked, rows with data in ANY one required field will be kept.", "default": false }, "requiredFieldKey": { "title": "2.2.1 ๐ŸŽฏ Filter by Field", "type": "string", "description": "Keep only rows where this field matches a specific value. Enter the field name (e.g. 'member', 'status').", "default": "" }, "requiredFieldValue": { "title": "2.2.2 ๐ŸŽฏ Match Specific Value", "type": "string", "description": "Value to match for the field above (e.g. 'pro', 'active'). Only exact matches will be kept.", "default": "" }, "removeColumns": { "title": "3.1 ๐Ÿช“ Remove Fields", "type": "array", "description": "List of field names to remove from each row (e.g. 'email', 'internal_notes'). Applies to both CSV and JSON.", "items": { "type": "string" } }, "sortBy": { "title": "4.1 ๐Ÿ“Œ Sort By Field(s)", "type": "array", "description": "Fields to sort by, in order of priority (e.g. 'status', 'created_at'). Applies to both CSV and JSON.", "items": { "type": "string" } }, "sortDescending": { "title": "4.2 ๐Ÿ”„ Sort in Descending Order", "type": "boolean", "description": "Enable to sort rows from Zโ€“A or high-to-low for numeric/date values.", "default": false } } }, "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 } } } } } } } } } }