{ "openapi": "3.0.1", "info": { "title": "Remove Duplicates & Merge Datasets: Dedup, Only New", "description": "Dedup and merge Apify datasets: removes duplicate items by any fields, or by the whole item, and returns the unique items (or only the duplicates) with their original fields. Can skip items seen in earlier runs, for daily new results. Works with limited permissions. $0.02 per 1,000 items.", "version": "1.0", "x-build-id": "afje5Cta43u0AA8iz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brasspage~dataset-dedup-merge/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brasspage-dataset-dedup-merge", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/brasspage~dataset-dedup-merge/runs": { "post": { "operationId": "runs-sync-brasspage-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/brasspage~dataset-dedup-merge/run-sync": { "post": { "operationId": "run-sync-brasspage-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 to merge", "type": "array", "description": "One or more Apify datasets, read in this order. Pick them from Storage > Datasets. In an integration, use {{resource.defaultDatasetId}}. The Actor gets read access only to the datasets you pick here." }, "items": { "title": "JSON items", "type": "array", "description": "Optional items to add after the datasets, as a JSON array of objects. Useful for a quick test or a small list." }, "dedupFields": { "title": "Dedup by fields", "type": "array", "description": "Items with the same values in all of these fields count as duplicates. Use dots for nested fields, for example \"address.city\". Leave empty to compare whole items. Items where every field is empty are kept.", "items": { "type": "string" } }, "normalize": { "title": "Ignore case and extra spaces", "type": "boolean", "description": "Compare text without case and extra spaces, so \"HI@x.com \" equals \"hi@x.com\". The output keeps the original values.", "default": false }, "output": { "title": "Output", "enum": [ "unique", "duplicates" ], "type": "string", "description": "What goes into this run's dataset.", "default": "unique" }, "onlyNew": { "title": "Only items not seen in earlier runs", "type": "boolean", "description": "Remember the keys of every item across runs and skip items an earlier run already saw. Use it on a scheduled scraper to get only the new results each day.", "default": false }, "memoryKey": { "title": "Memory name", "type": "string", "description": "Runs with the same memory name share one memory. Use a different name for each scraper or task. Stored in your account as the key-value store dedup-memory-; delete it to start fresh.", "default": "default" }, "maxItems": { "title": "Max items to read", "minimum": 1, "type": "integer", "description": "Stop after this many items. Leave empty for no limit (the Apify free plan reads up to 10,000 items per run)." } } }, "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 } } } } } } } } } }