{ "openapi": "3.0.1", "info": { "title": "Dataset Transform: JSON to CSV, Flatten, Filter, Rename", "description": "Turn any Apify dataset (or pasted JSON) into clean tables: flatten nested JSON, pick and rename columns, convert types, filter, sort, then export CSV, JSON or JSONL with a link. Empty input = free demo. $0.50 per 1,000 output rows.", "version": "0.1", "x-build-id": "iae86baevgl1zTovb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ucchiii~dataset-transform/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ucchiii-dataset-transform", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ucchiii~dataset-transform/runs": { "post": { "operationId": "runs-sync-ucchiii-dataset-transform", "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/ucchiii~dataset-transform/run-sync": { "post": { "operationId": "run-sync-ucchiii-dataset-transform", "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": { "datasetIds": { "title": "Datasets", "type": "array", "description": "Dataset IDs (the 'defaultDatasetId' of a finished run of any Actor, e.g. 'WkzbQMuFYuamGv3YF'). Rows are read in the order given. You can paste a dataset URL from Apify Console or the API too. Leave this AND 'items' empty to run a free demo on sample data (not charged)." }, "items": { "title": "Or paste rows (JSON)", "type": "array", "description": "Rows to transform, as a JSON array of objects, e.g. [{\"name\":\"A\",\"price\":\"$1,200\"}]. Used after the datasets (if any). Up to 50,000 rows; use a dataset for more." }, "select": { "title": "Keep only these columns", "type": "array", "description": "Columns to output, in this order. Use the flattened name, e.g. 'address.city'. A parent name such as 'address' keeps all columns under it ('address.city', 'address.zip'). Empty = all columns.", "items": { "type": "string" } }, "omit": { "title": "Remove these columns", "type": "array", "description": "Columns to drop from the output. A parent name such as 'meta' removes everything under it ('meta.id', 'meta.tags.0'). Applied after 'Keep only these columns'.", "items": { "type": "string" } }, "rename": { "title": "Rename columns", "type": "object", "description": "Map of current column name to new name, e.g. {\"address.city\": \"city\", \"price\": \"price_usd\"}. Use names as they are after flattening. Two columns cannot share a new name." }, "maxDepth": { "title": "Flatten depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many levels of nested objects and arrays to flatten into dot-path columns (e.g. address.geo.lat). 0 = do not flatten (nested values stay as JSON). Anything deeper than this limit stays as a JSON value. Default 10, maximum 20.", "default": 10 }, "arrayMode": { "title": "Arrays", "enum": [ "json", "join", "index", "first", "count" ], "type": "string", "description": "How arrays are turned into columns. 'join' only joins numbers/text; arrays of objects stay as a JSON string. 'index' creates columns like 'lines.0.sku'. Default: json.", "default": "json" }, "arrayJoinSeparator": { "title": "Join separator", "type": "string", "description": "Text placed between values when Arrays = join. Default '; ' (semicolon and space). Max 20 characters.", "default": "; " }, "maxArrayItems": { "title": "Max items per array (index mode)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "With Arrays = index, only the first N items of each array get columns (protects against thousands of columns). Rows that were cut are counted in the run statistics. Default 100, maximum 1000.", "default": 100 }, "flattenSeparator": { "title": "Path separator", "type": "string", "description": "Character(s) that join nested names in flattened columns, e.g. '.' gives 'address.city' and '_' gives 'address_city'. Column names in other settings must use the same separator. Max 5 characters.", "default": "." }, "coerce": { "title": "Convert column types", "type": "object", "description": "Map of column name to type: string, number, integer, boolean or date. Example: {\"price\": \"number\", \"inStock\": \"boolean\", \"createdAt\": \"date\"}. Numbers accept '$1,234.50' and '(12)'; dates become ISO 8601 UTC. Values that cannot be converted become empty and are counted in the run statistics. Runs before filters and sorting." }, "decimalSeparator": { "title": "Decimal separator in numbers", "enum": [ ".", "," ], "type": "string", "description": "How to read numbers written as text when converting to number or integer. Default: dot.", "default": "." }, "trimStrings": { "title": "Trim spaces in text", "type": "boolean", "description": "Remove leading and trailing spaces from all text values.", "default": false }, "emptyStringsAsNull": { "title": "Treat empty text as empty value", "type": "boolean", "description": "Turn empty or whitespace-only text into null (an empty cell in CSV).", "default": false }, "filters": { "title": "Filter rows", "type": "array", "description": "Keep only rows that match. A JSON list of conditions: {\"field\": \"price\", \"op\": \"gt\", \"value\": 10}. Operators: eq, ne, gt, gte, lt, lte, contains, notContains, startsWith, endsWith, in, notIn (value is a list), exists, notExists. Up to 50 conditions. Field names are the flattened names, before renaming." }, "filterMode": { "title": "Combine conditions with", "enum": [ "all", "any" ], "type": "string", "description": "Whether a row must match all filter conditions or just one.", "default": "all" }, "filterIgnoreCase": { "title": "Ignore letter case in filters", "type": "boolean", "description": "Compare text without regard to upper/lower case in eq, ne, in, contains and similar operators.", "default": true }, "sortBy": { "title": "Sort by column", "type": "string", "description": "Flattened column name to sort by, e.g. 'price'. Numbers sort before text; empty values always go last. Sorting holds the matching rows in memory (max 500,000 rows). Empty = keep the original order." }, "sortOrder": { "title": "Sort order", "enum": [ "asc", "desc" ], "type": "string", "description": "Ascending or descending. Only used when 'Sort by column' is set.", "default": "asc" }, "offset": { "title": "Skip first rows", "minimum": 0, "type": "integer", "description": "Skip this many rows of the final result (after filtering and sorting). Skipped rows are not charged. Default 0.", "default": 0 }, "limit": { "title": "Max output rows", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many output rows. Leave empty for no limit (hard cap 1,000,000 rows per run). Billing is per output row, so this also caps cost." }, "maxCellChars": { "title": "Max characters per text cell", "minimum": 0, "maximum": 10000000, "type": "integer", "description": "Longer text is cut to this length (32,000 fits Excel's cell limit of 32,767). Cut cells are counted in the run statistics. 0 = no limit. Default 32000.", "default": 32000 }, "exportFormat": { "title": "Also save a file", "enum": [ "csv", "jsonl", "json", "none" ], "type": "string", "description": "Besides the output dataset, save all output rows as a file in the run's key-value store and return a link in the run statistics (record STATS, field fileUrl). The file is capped at 150 MB. Default: csv.", "default": "csv" }, "fileName": { "title": "File name", "type": "string", "description": "File name without extension. Only letters, digits, dot, dash and underscore are kept. The extension (.csv, .jsonl or .json) is added automatically.", "default": "export" }, "csvDelimiter": { "title": "CSV delimiter", "enum": [ ",", ";", "tab", "|" ], "type": "string", "description": "Column separator for CSV files. Default: comma.", "default": "," }, "csvBom": { "title": "CSV: add UTF-8 BOM for Excel", "type": "boolean", "description": "Adds a byte-order mark so Excel opens non-English text correctly. Leave off for pandas, databases and most code.", "default": false }, "csvEscapeFormulas": { "title": "CSV: neutralize spreadsheet formulas", "type": "boolean", "description": "Prefix text cells starting with =, +, @ (or - followed by text) with an apostrophe so Excel or Sheets never run them as formulas. Recommended when the CSV will be opened in a spreadsheet and the data comes from untrusted sources.", "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 }, "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 } } } } } } } } } }