{ "openapi": "3.0.1", "info": { "title": "Data Cleaner: Normalize Phone, URL, Price & Date Fields", "description": "Data cleaner from $0.50 per 1,000 rows ($0.80 on the Free plan): normalizes 6 field types in datasets, CSV, JSON or Excel: phone to E.164, email, URL, price and currency, date to ISO, company names. Works on nested fields and flags new, changed and removed rows since the last run.", "version": "0.1", "x-build-id": "GHK1PGv3AO45j6dO2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tamatama~data-normalizer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tamatama-data-normalizer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tamatama~data-normalizer/runs": { "post": { "operationId": "runs-sync-tamatama-data-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/tamatama~data-normalizer/run-sync": { "post": { "operationId": "run-sync-tamatama-data-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", "properties": { "data": { "title": "Rows (JSON array)", "type": "array", "description": "The rows to clean, as a JSON array of objects. Nested objects are fine (e.g. contact.phone). Use this, or a dataset ID, or a file URL below." }, "datasetId": { "title": "Apify dataset ID", "type": "string", "description": "Clean the items of an Apify dataset, e.g. the output of a scraper run. Overrides the rows above." }, "fileUrl": { "title": "File URL (CSV, JSON, JSON Lines or XLSX)", "type": "string", "description": "A public URL of a CSV, JSON, JSON Lines or Excel (.xlsx, first sheet) file, up to 50 MB. Overrides the rows above." }, "fields": { "title": "Fields and their types", "type": "object", "description": "Which fields to clean and how: {\"field name\": \"type\"}. Types: phone, email, url, price, date, company. Use dots for nested fields, e.g. {\"contact.tel\": \"phone\", \"cost\": \"price\"}. Leave empty to detect by field name." }, "autoDetect": { "title": "Detect fields by name", "type": "boolean", "description": "Also clean fields whose names say what they are (phone, tel, email, url, website, price, cost, salary, date, createdAt, company, employer...). Fields you name above win.", "default": true }, "defaultCountry": { "title": "Country for phone numbers without +", "type": "string", "description": "Two-letter country code used for numbers written without a country code, e.g. US, GB, DE, JP. Numbers starting with + are read as written.", "default": "US" }, "dateOrder": { "title": "Order of numeric dates", "enum": [ "MDY", "DMY", "YMD" ], "type": "string", "description": "How to read dates like 03/04/2026: MDY = March 4 (US), DMY = 3 April (UK, EU), YMD. Values where day and month could be swapped get a note in _issues.", "default": "MDY" }, "defaultCurrency": { "title": "Currency for $, ¥, kr and plain numbers", "type": "string", "description": "Three-letter code used when the symbol is shared by several currencies ($, ¥, kr) or missing, e.g. USD, CAD, JPY, CNY. Empty = leave the currency null and note it in _issues.", "default": "USD" }, "decimalSeparator": { "title": "Decimal separator in prices", "enum": [ "", ".", "," ], "type": "string", "description": "Leave on auto unless your prices are all written one way: \".\" (1,299.50) or \",\" (1.299,50).", "default": "" }, "removeTrackingParams": { "title": "Remove tracking parameters from URLs", "type": "boolean", "description": "Drop utm_*, gclid, fbclid and similar parameters.", "default": true }, "removeWww": { "title": "Remove www. from URLs", "type": "boolean", "description": "Treat www.example.com and example.com as the same site.", "default": true }, "companyMatchThreshold": { "title": "Company name match (0-100)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Company names whose cleaned keys are at least this similar get the same _group (e.g. \"Acme Corp.\" and \"ACME Corporation\"). 100 = exact keys only, 0 = off.", "default": 90 }, "keyField": { "title": "Key field to compare with the last run", "type": "string", "description": "A field that identifies a row (e.g. id, sku, url). Each row then gets _change: new, changed or unchanged against the last run with the same compare name, and rows that are gone are added with _change: removed (not charged)." }, "compareName": { "title": "Compare name", "type": "string", "description": "Separate comparisons by name, e.g. one per supplier feed. Runs with the same name are compared.", "default": "default" }, "onlyChanges": { "title": "Output only new and changed rows", "type": "boolean", "description": "With a key field: leave out unchanged rows (they are not charged).", "default": false }, "maxRows": { "title": "Max rows", "minimum": 0, "type": "integer", "description": "Stop after this many rows. 0 = all (up to 100,000 per run).", "default": 0 } } }, "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 } } } } } } } } } }