{ "openapi": "3.0.1", "info": { "title": "Only New Items | Cross-Run Dedupe Ledger for Any Dataset", "description": "Run your scraper on a schedule and get back only what you have never seen before. Name the field that identifies an item, pipe any dataset in, and this actor holds back everything already delivered. Records pass through untouched. The ledger is yours, not a database you rent.", "version": "0.1", "x-build-id": "jEkfm7fPHUHPKbkCZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/broomwagon~only-new-items/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-broomwagon-only-new-items", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/broomwagon~only-new-items/runs": { "post": { "operationId": "runs-sync-broomwagon-only-new-items", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/broomwagon~only-new-items/run-sync": { "post": { "operationId": "run-sync-broomwagon-only-new-items", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetId": { "title": "Dataset to filter", "type": "string", "description": "This run's scraper output. Pipe any actor's dataset straight in; a picked dataset always wins over the sample records below." }, "items": { "title": "Inline records", "type": "array", "description": "Records provided inline as a JSON array, for trying the actor out before wiring a scraper up. Ignored when a dataset is picked above." }, "fileUrl": { "title": "File URL", "type": "string", "description": "URL of a JSON or NDJSON file of records." }, "keyFields": { "title": "Key fields", "type": "array", "description": "The fields that identify an item, e.g. [\"url\"] or [\"jobId\"]. Matching is exact after trimming: no case folding, no fuzzy matching. Leave empty to key on the whole record, which makes any changed field a new item." }, "ledgerCapacity": { "title": "Ledger capacity", "minimum": 1000, "type": "integer", "description": "How many distinct items the ledger is sized for. It stays a few kilobytes either way; going far past this raises the rate at which a new item is mistaken for an old one. The run report always tells you where you stand.", "default": 100000 }, "memory": { "title": "Previous memory", "type": "object", "description": "An object beginning with \"memoryVersion\", copied from the MEMORY record in your last run's key-value store (not your records, those go in the fields above). It holds the ledger of everything already delivered." }, "memoryStoreId": { "title": "Memory key-value store", "type": "string", "description": "Optional: a key-value store in YOUR account. The actor reads the ledger from it before running and writes the update back after, so scheduled runs chain automatically with nothing to copy by hand." } } }, "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 } } } } } } } } } }