{ "openapi": "3.0.1", "info": { "title": "Dataset Merge & Dedup", "description": "Merge any number of Apify datasets into one and remove duplicates by the fields you choose (e.g. url, placeId, email). Case/whitespace/URL normalization, keep first or last, pick or omit fields. $0.50 per 1,000 output items.", "version": "0.1", "x-build-id": "AiLZAbxmE9uSTh4wH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ucchiii~dataset-dedup-merge/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ucchiii-dataset-dedup-merge", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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-dedup-merge/runs": { "post": { "operationId": "runs-sync-ucchiii-dataset-dedup-merge", "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-dedup-merge/run-sync": { "post": { "operationId": "run-sync-ucchiii-dataset-dedup-merge", "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 the source Actor, e.g. 'WkzbQMuFYuamGv3YF'). Dataset IDs or names to merge, in order. Items are read in this order (this matters for 'keep first/last'). Leave empty to run a free demo on sample data (not charged). You can also paste the dataset URL from Apify Console or the API (the ID is taken from it)." }, "dedupFields": { "title": "Deduplicate by fields", "type": "array", "description": "Items with the same values in ALL these fields are duplicates. Use dots for nested fields (e.g. ['url'] or ['address.city']). Empty = compare whole items.", "items": { "type": "string" } }, "keep": { "title": "Which duplicate to keep", "enum": [ "first", "last" ], "type": "string", "description": "When duplicates are found, keep the 'first' or the 'last' occurrence (datasets are read in the order given). Default: first.", "default": "first" }, "output": { "title": "Output", "enum": [ "unique", "duplicatesOnly" ], "type": "string", "description": "'unique' returns the deduplicated items (default). 'duplicatesOnly' returns only the duplicates that were removed (for auditing).", "default": "unique" }, "caseInsensitive": { "title": "Ignore letter case", "type": "boolean", "description": "Treat 'Acme' and 'acme' as the same value.", "default": true }, "trimWhitespace": { "title": "Ignore extra whitespace", "type": "boolean", "description": "Treat ' Acme Inc ' and 'Acme Inc' as the same value.", "default": true }, "normalizeUrls": { "title": "Normalize URLs", "type": "boolean", "description": "Treat http/https, www and a trailing slash as the same URL.", "default": false }, "dedupEmptyKeys": { "title": "Deduplicate items with empty key fields", "type": "boolean", "description": "By default, items whose dedup fields are all empty are kept (never treated as duplicates).", "default": false }, "fields": { "title": "Keep only these fields", "type": "array", "description": "Top-level fields to output. Empty = all fields.", "items": { "type": "string" } }, "omitFields": { "title": "Remove these fields", "type": "array", "description": "Top-level fields to remove from the output.", "items": { "type": "string" } }, "addSourceField": { "title": "Add source dataset ID", "type": "boolean", "description": "Adds '_sourceDatasetId' to each output item.", "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 } } } } } } } } } }