{ "openapi": "3.0.1", "info": { "title": "Dataset Merge, Dedup & Transform – Clean Data", "description": "Merge several Apify datasets, remove duplicates by any field, filter, rename, pick or flatten columns, and write one clean dataset. Limited permissions.", "version": "1.0", "x-build-id": "9gK69Z03pdDCKwfdl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/innovative_cookie~dataset-merge-dedup/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-innovative_cookie-dataset-merge-dedup", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/innovative_cookie~dataset-merge-dedup/runs": { "post": { "operationId": "runs-sync-innovative_cookie-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/innovative_cookie~dataset-merge-dedup/run-sync": { "post": { "operationId": "run-sync-innovative_cookie-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 to merge", "type": "array", "description": "Pick one or more datasets (for example the results of several scraper runs). The Actor only gets READ access to the datasets you pick. Items are read in this order." }, "items": { "title": "Items (JSON)", "type": "array", "description": "Optional items pasted as a JSON array. They are processed before the datasets. Handy for a quick test or for small lists.", "default": [] }, "dedupFields": { "title": "Deduplicate by fields", "type": "array", "description": "Items with the same values in all these fields are duplicates. Use dot paths for nested fields (address.city). Leave empty to keep everything.", "items": { "type": "string" }, "default": [] }, "dedupWholeItem": { "title": "Deduplicate identical items", "type": "boolean", "description": "When no field is given above, remove items that are exactly identical (all fields).", "default": false }, "keep": { "title": "Which duplicate to keep", "enum": [ "first", "last", "merge" ], "type": "string", "description": "first = keep the first item seen (streaming, low memory). last = keep the most recent one. merge = keep the first and fill its empty fields from the duplicates.", "default": "first" }, "caseInsensitive": { "title": "Ignore letter case when comparing", "type": "boolean", "description": "Treat 'Example.com' and 'example.com' as the same value.", "default": false }, "trimValues": { "title": "Ignore extra spaces when comparing", "type": "boolean", "description": "Trim and collapse whitespace in text values before comparing.", "default": true }, "filters": { "title": "Filters (JSON)", "type": "array", "description": "Keep only items matching ALL conditions. Each condition is {\"field\": \"price\", \"op\": \"lt\", \"value\": 20}. Ops: eq, neq, contains, notContains, startsWith, endsWith, regex, gt, gte, lt, lte (numbers or dates), exists, notExists, empty, notEmpty, in, notIn (value = array).", "default": [] }, "pickFields": { "title": "Keep only these fields", "type": "array", "description": "Output only these fields, in this order (dot paths allowed). Leave empty to keep all fields.", "items": { "type": "string" }, "default": [] }, "omitFields": { "title": "Remove these fields", "type": "array", "description": "Fields to drop from the output (dot paths allowed).", "items": { "type": "string" }, "default": [] }, "renameFields": { "title": "Rename fields", "type": "object", "description": "Map old name to new name, applied last. Example: {\"title\": \"name\", \"stock.count\": \"stock_count\"}", "default": {} }, "flattenNested": { "title": "Flatten nested objects", "type": "boolean", "description": "Turn {\"stock\": {\"count\": 2}} into {\"stock.count\": 2}. Useful for CSV and Google Sheets.", "default": false }, "flattenArrays": { "title": "Flatten arrays too", "type": "boolean", "description": "With flattening on, also turn arrays into numbered keys (images.0, images.1...).", "default": false }, "skipHiddenFields": { "title": "Skip hidden fields", "type": "boolean", "description": "Drop fields starting with # (debug data) when reading datasets.", "default": false }, "addSourceField": { "title": "Add the source dataset ID", "type": "boolean", "description": "Add a _source field with the dataset ID each item came from (or 'inline').", "default": false }, "maxOutputItems": { "title": "Max items to write", "minimum": 0, "type": "integer", "description": "Stop after writing this many items. 0 = no limit.", "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 } } } } } } } } } }