{ "openapi": "3.0.1", "info": { "title": "Lead List Cleaner", "description": "Turn any scraper's raw dataset into a clean, scored lead list — dedupe rows, kill dead emails and dead domains, rank the rest by hotness. Runs standalone or as an Integration bolted onto Google Maps / lead scrapers.", "version": "0.1", "x-build-id": "fKDhJXowD6hssRGe0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zinin~lead-list-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zinin-lead-list-cleaner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zinin~lead-list-cleaner/runs": { "post": { "operationId": "runs-sync-zinin-lead-list-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zinin~lead-list-cleaner/run-sync": { "post": { "operationId": "run-sync-zinin-lead-list-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 ID", "type": "string", "description": "Pick another Actor's dataset to clean (e.g. a Google Maps or lead-scraper run). Ignored when 'items' is set. Picking it here — not just pasting the ID — is what grants this run's token READ access to that dataset. When this Actor is added as an Integration on another Actor, this field is filled in automatically from the triggering run." }, "datasetUrl": { "title": "Dataset URL", "type": "string", "description": "Public URL returning a JSON array of lead rows. Used only when both 'items' and 'datasetId' are empty." }, "items": { "title": "Items", "type": "array", "description": "Raw lead rows to clean directly, one object per lead — any shape works (Google Maps scraper export, CSV turned into JSON, anything with an email/website/phone somewhere in it). Takes priority over 'datasetId' and 'datasetUrl'.", "items": { "type": "object" } }, "checks": { "title": "Checks to run", "type": "array", "description": "Pipeline stages to run, in order. 'dedupe' collapses rows sharing the same domain/email. 'email' verifies syntax + MX. 'domain' verifies the domain is alive. 'score' computes the hotness score used for the 'minScore' cutoff.", "items": { "type": "string", "enum": [ "dedupe", "email", "domain", "score" ], "enumTitles": [ "Dedupe", "Email verify (syntax + MX)", "Domain alive check", "Hotness score" ] }, "default": [ "dedupe", "email", "domain", "score" ] }, "minScore": { "title": "Minimum score", "minimum": 0, "maximum": 100, "type": "integer", "description": "Drop leads scoring below this threshold (0-100) from the clean, billed output. They still show up as free rejected rows with a reason.", "default": 0 }, "maxRows": { "title": "Max rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Safety cap on how many input rows this run will process, regardless of source.", "default": 1000 } } }, "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 } } } } } } } } } }