{ "openapi": "3.0.1", "info": { "title": "Dataset Splitter: CSV, XLSX, JSON by rows or column", "description": "Split an Apify dataset or a CSV/JSON/NDJSON file into parts by row count, number of parts, column value or file size, or draw a random sample. Saves CSV/JSON/NDJSON/XLSX files and datasets. Empty input = free demo. $0.10 per 1,000 rows.", "version": "0.1", "x-build-id": "MJ5RCXDWUFEkf5oCr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ucchiii~dataset-splitter/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ucchiii-dataset-splitter", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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-splitter/runs": { "post": { "operationId": "runs-sync-ucchiii-dataset-splitter", "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-splitter/run-sync": { "post": { "operationId": "run-sync-ucchiii-dataset-splitter", "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": { "datasetId": { "title": "Apify dataset", "type": "string", "description": "Dataset to split (the 'defaultDatasetId' of a finished run). You can paste a dataset URL from Apify Console too. Up to 2,000,000 rows. Use this OR a file URL. Leave both empty to run a free demo." }, "fileUrl": { "title": "File URL", "type": "string", "description": "Public http(s) link to a CSV, TSV, JSON or NDJSON file (up to 200 MB). Links to internal networks are blocked. Use this OR an Apify dataset. Leave both empty to run a free demo on a built-in sample (not charged)." }, "splitMode": { "title": "Split mode", "enum": [ "rows", "parts", "column", "size", "sample" ], "type": "string", "description": "How to cut the data. rows: 'Rows per part'. parts: 'Number of parts'. column: 'Column'. size: 'Target size'. sample: 'Sample rows' or 'Sample percent'. Default: rows.", "default": "rows" }, "rowsPerPart": { "title": "Rows per part", "minimum": 1, "maximum": 2000000, "type": "integer", "description": "Mode 'rows': maximum rows in each part (the last part may be smaller). Example 10000 for CRM imports. A run makes at most 500 parts. Default when empty: 10,000." }, "partCount": { "title": "Number of parts", "minimum": 1, "maximum": 500, "type": "integer", "description": "Mode 'parts': how many parts of nearly equal size to make (up to 500). With fewer rows than parts you get one row per part. Default when empty: 2." }, "column": { "title": "Column", "type": "string", "description": "Mode 'column': name of the column whose values define the parts (matched case-insensitively if needed). Rows with an empty value go to a part named 'empty'. For dataset items only top-level fields are columns." }, "maxParts": { "title": "Max parts (split by column)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Mode 'column': if the column has more different values than this, the run fails before anything is written or charged. Hard limit 500. Default: 500.", "default": 500 }, "targetSizeMb": { "title": "Target size per part (MB)", "minimum": 0.01, "maximum": 1000, "type": "number", "description": "Mode 'size': approximate size of each part in MB, estimated from the output format (XLSX is estimated at about 40% of the CSV size). Real files can differ by some percent. Default: 5.", "default": 5 }, "sampleRows": { "title": "Sample rows", "minimum": 1, "maximum": 2000000, "type": "integer", "description": "Mode 'sample': number of rows to draw at random. Takes precedence over 'Sample percent'. Rows keep their original order." }, "samplePercent": { "title": "Sample percent", "minimum": 0.0001, "maximum": 100, "type": "number", "description": "Mode 'sample': share of rows to draw, for example 10 for 10 percent (at least one row). Used when 'Sample rows' is empty." }, "seed": { "title": "Random seed", "minimum": 0, "maximum": 2147483647, "type": "integer", "description": "Mode 'sample': the same seed and the same data always give the same sample. Empty = a random seed, which is reported in the output (field seed) so you can repeat the sample." }, "outputFormat": { "title": "Output format", "enum": [ "csv", "json", "ndjson", "xlsx" ], "type": "string", "description": "Format of the part files saved to the key-value store. Default: csv.", "default": "csv" }, "saveToKeyValueStore": { "title": "Save part files", "type": "boolean", "description": "Save every part as a file in the key-value store, with a public download link. Turn off to write only datasets. Default: on.", "default": true }, "saveToDatasets": { "title": "Also save parts as new datasets", "type": "boolean", "description": "Write every part into its own new named dataset (prefix-001, prefix-002, ...). Named datasets stay until you delete them. The run fails before writing if one of them already has items. Default: off.", "default": false }, "datasetNamePrefix": { "title": "Dataset name prefix", "type": "string", "description": "Prefix for the new datasets: lowercase letters, digits and dashes (max 40). Empty = 'split-' plus the run ID, which is always new." }, "inputFormat": { "title": "Input format", "enum": [ "auto", "csv", "tsv", "json", "ndjson" ], "type": "string", "description": "Format of the source file. 'auto' uses the file extension, the content type and the content. Ignored for Apify datasets. Default: auto.", "default": "auto" }, "encoding": { "title": "Input text encoding", "enum": [ "auto", "utf-8", "utf-8-sig", "cp1252", "shift_jis" ], "type": "string", "description": "Character encoding of the source file. Output is always UTF-8. Default: auto (UTF-8, then Shift_JIS if kana are found, then Windows-1252).", "default": "auto" }, "detectNumbers": { "title": "Detect numbers in CSV", "type": "boolean", "description": "Turn plain numbers in a CSV into real numbers (useful for XLSX and JSON output). Values with leading zeros, more than 15 digits or exponents stay text. Default: off, values are kept exactly as in the file.", "default": false }, "csvBom": { "title": "CSV: add UTF-8 BOM for Excel", "type": "boolean", "description": "Add a byte-order mark to CSV parts so Excel opens non-English text (for example Japanese) correctly. Leave off for databases and most code.", "default": false }, "fileName": { "title": "File name", "type": "string", "description": "Start of every part file name, for example 'leads' gives leads-part-001.csv. Only letters, digits, dot, dash and underscore are kept. Empty = taken from the source." } } }, "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 } } } } } } } } } }