{ "openapi": "3.0.1", "info": { "title": "Data Cleaning & Transformation Toolkit", "description": "A powerful, multi-mode Apify actor that transforms messy, unstructured data into clean, structured JSON — ready for APIs, databases, or downstream processing.", "version": "0.0", "x-build-id": "U3HDOIjThX89PE5Db" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/moving_beacon-owner1~my-actor-66/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-moving_beacon-owner1-my-actor-66", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/moving_beacon-owner1~my-actor-66/runs": { "post": { "operationId": "runs-sync-moving_beacon-owner1-my-actor-66", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/moving_beacon-owner1~my-actor-66/run-sync": { "post": { "operationId": "run-sync-moving_beacon-owner1-my-actor-66", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Transformation Mode", "enum": [ "messy_text", "excel_csv", "html_scrape", "key_value", "url_fetch" ], "type": "string", "description": "Select the type of data transformation to perform.", "default": "messy_text" }, "inputText": { "title": "Input Text / Raw Data", "type": "string", "description": "Paste your messy text, key-value config, or raw HTML here. Not needed if uploading a file or fetching a URL.", "default": "Name: John Doe | Age: 29 | City: New York | Active: yes\nName: Jane Smith | Age: 32 | City: Los Angeles | Active: true\nName: Bob Johnson | Age: 45 | City: Chicago | Active: no" }, "fileUrl": { "title": "File URL (Excel / CSV / HTML)", "type": "string", "description": "Direct URL to an .xlsx, .csv, or .html file to download and process.", "default": "" }, "urls": { "title": "URLs to Scrape", "type": "array", "description": "List of web page URLs to fetch and extract data from (for url_fetch and html_scrape modes).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "The web page URL to fetch and process." } } }, "default": [ { "url": "https://books.toscrape.com/" } ] }, "textParseStrategy": { "title": "Text Parsing Strategy", "enum": [ "auto", "delimited", "key_value", "block" ], "type": "string", "description": "How to parse the messy text. 'auto' detects the format automatically.", "default": "auto" }, "kvFormat": { "title": "Key-Value Format", "enum": [ "auto", "env", "ini", "log", "yaml" ], "type": "string", "description": "Format of the key-value input. 'auto' detects automatically.", "default": "auto" }, "htmlExtractMode": { "title": "HTML Extraction Mode", "enum": [ "tables", "elements", "links", "text", "auto" ], "type": "string", "description": "What to extract from the HTML content.", "default": "tables" }, "cssSelector": { "title": "CSS Container Selector", "type": "string", "description": "CSS selector for repeating items (e.g., 'div.product-card', 'li.item'). Used in 'elements' HTML mode.", "default": "article.product_pod" }, "fieldMap": { "title": "Field Mapping (JSON)", "type": "string", "description": "JSON object mapping output field names to CSS selectors within each container. Example: {\"title\": \"h3 a\", \"price\": \".price_color\"}", "default": "{\n \"title\": \"h3 a\",\n \"price\": \".price_color\",\n \"availability\": \".availability\",\n \"rating\": \"p.star-rating\"\n}" }, "sheetName": { "title": "Sheet Name", "type": "string", "description": "Specific Excel sheet to read. Leave empty to read all sheets.", "default": "" }, "skipEmptyRows": { "title": "Skip Empty Rows", "type": "boolean", "description": "Remove rows that are entirely blank from the output.", "default": true }, "forwardFillColumns": { "title": "Forward-Fill Columns", "type": "string", "description": "Comma-separated list of column names to forward-fill (for merged cells in Excel). Leave empty to skip.", "default": "" }, "pageSize": { "title": "Page Size (Pagination)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Number of records per page in the output. Set to 0 for no pagination.", "default": 0 }, "outputFormat": { "title": "Output Format", "enum": [ "records", "wrapped", "flat" ], "type": "string", "description": "How to structure the final output in the dataset.", "default": "records" }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for fetching URLs. Uses Apify Proxy by default.", "default": { "useApifyProxy": true } }, "maxRequestRetries": { "title": "Max Request Retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum number of retries for failed HTTP requests.", "default": 3 } } }, "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 } } } } } } } } } }