{ "openapi": "3.0.1", "info": { "title": "Merge Datasets & Remove Duplicates [$0.20/1K 💰]", "description": "💰 $0.20 per 1,000 unique rows; duplicates free, no start fee. Merge Apify datasets and remove duplicate rows by any fields (URL, name, phone, place ID) with smart matching that ignores case, spaces and URL variations. Cheaper than saliga's merge-dedupe ($0.50/1K). New rows only on schedules.", "version": "0.1", "x-build-id": "nMDa6L4PFtXmFlVbn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cybermax~merge-dedupe-datasets/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cybermax-merge-dedupe-datasets", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/cybermax~merge-dedupe-datasets/runs": { "post": { "operationId": "runs-sync-cybermax-merge-dedupe-datasets", "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/cybermax~merge-dedupe-datasets/run-sync": { "post": { "operationId": "run-sync-cybermax-merge-dedupe-datasets", "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 the datasets (for example the results of several runs). Through the API, pass dataset IDs, e.g. a previous run's defaultDatasetId. Leave empty for a free demo on sample data." }, "dedupeFields": { "title": "Duplicate when these fields match", "type": "array", "description": "Fields that identify a row, e.g. url, or name + address, or placeId. Nested fields with dots: location.city. Empty = rows must be identical in every field.", "items": { "type": "string" } }, "smartMatching": { "title": "Smart matching", "type": "boolean", "description": "Ignore case and extra spaces; treat https://www.site.com/ and site.com as the same; compare phone numbers by digits only.", "default": true }, "keep": { "title": "When duplicates are found, keep", "enum": [ "first", "last" ], "type": "string", "description": "Which copy of a duplicate stays in the output.", "default": "first" }, "fillBlanks": { "title": "Fill blanks from duplicates", "type": "boolean", "description": "When the kept row has an empty field (no phone, no email) and a duplicate has it, copy it over. Holds rows in memory: about 75,000 unique rows at the default 512 MB; give the run more memory for more.", "default": false }, "excludeDatasetIds": { "title": "Drop rows found in these datasets", "type": "array", "description": "Optional. Rows whose key appears in these datasets are left out, e.g. leads you already have." }, "outputFields": { "title": "Keep only these fields", "type": "array", "description": "Optional. Empty = all fields.", "items": { "type": "string" } }, "addSourceDataset": { "title": "Add source dataset ID", "type": "boolean", "description": "Adds sourceDatasetId to each row.", "default": false }, "keepItemsWithoutKey": { "title": "Keep rows with empty key fields", "type": "boolean", "description": "Rows where every dedupe field is empty can't be matched; keep them (on) or drop them (off).", "default": true }, "maxItems": { "title": "Max unique rows", "minimum": 1, "type": "integer", "description": "Optional cap on rows written." }, "monitor": { "title": "Monitor mode: only rows never sent before", "type": "boolean", "description": "Remembers every row key this watchlist has written; later runs write only new rows. Rows sent before are not charged.", "default": false }, "monitorKey": { "title": "Watchlist name", "type": "string", "description": "Optional name for this watchlist's saved state (use one per workflow)." } } }, "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 } } } } } } } } } }