{ "openapi": "3.0.1", "info": { "title": "Dataset Deduplicator & Cleaner", "description": "Remove duplicate rows from an Apify Dataset or inline JSON. Deduplicate by selected fields, trim strings, and write the cleaned rows to a new Dataset.", "version": "0.1", "x-build-id": "ez1JVk1itozls72LC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/starshaped_bullsnake~dataset-deduplicator-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-starshaped_bullsnake-dataset-deduplicator-cleaner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/starshaped_bullsnake~dataset-deduplicator-cleaner/runs": { "post": { "operationId": "runs-sync-starshaped_bullsnake-dataset-deduplicator-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/starshaped_bullsnake~dataset-deduplicator-cleaner/run-sync": { "post": { "operationId": "run-sync-starshaped_bullsnake-dataset-deduplicator-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sourceDatasetId": { "title": "Source Dataset", "type": "string", "description": "Optional Apify Dataset to clean. If empty, the inline sample rows below are used." }, "rows": { "title": "Inline rows", "type": "array", "description": "JSON rows to clean when no Source Dataset is selected. The defaults intentionally contain one duplicate for a quick smoke test.", "items": { "type": "object" }, "default": [ { "id": "A001", "name": " Alpha ", "score": 10 }, { "id": "A002", "name": "Beta", "score": 20 }, { "id": "A001", "name": "Alpha duplicate", "score": 99 } ] }, "keyFields": { "title": "Deduplication key fields", "type": "array", "description": "Rows with the same values in these fields are treated as duplicates. Leave empty to compare the whole row.", "items": { "type": "string" }, "default": [ "id" ] }, "keep": { "title": "Which duplicate to keep", "enum": [ "first", "last" ], "type": "string", "description": "Choose whether the first or last row wins when duplicate keys are found.", "default": "first" }, "trimStrings": { "title": "Trim text values", "type": "boolean", "description": "Remove leading and trailing whitespace from top-level string fields before deduplication and output.", "default": true }, "caseInsensitiveKeys": { "title": "Case-insensitive text keys", "type": "boolean", "description": "When enabled, text values used in deduplication keys are compared without letter-case differences.", "default": false }, "maxItems": { "title": "Maximum source rows", "minimum": 1, "maximum": 250000, "type": "integer", "description": "Safety limit for rows read and processed in one run.", "default": 10000 } } }, "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 } } } } } } } } } }