{ "openapi": "3.0.1", "info": { "title": "Email Scraper & Validator", "description": "Crawl websites, extract email addresses, validate each with a third-party validation API, and output clean, scored results.", "version": "0.1", "x-build-id": "hEc85Nn9tlImqaXQC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/akash9078~email-scraper-validator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-akash9078-email-scraper-validator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/akash9078~email-scraper-validator/runs": { "post": { "operationId": "runs-sync-akash9078-email-scraper-validator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/akash9078~email-scraper-validator/run-sync": { "post": { "operationId": "run-sync-akash9078-email-scraper-validator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more website URLs to crawl for email addresses.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "emails": { "title": "Emails to validate", "type": "array", "description": "Validate-only mode: provide email addresses directly without crawling. Leave empty to crawl startUrls.", "items": { "type": "string" } }, "maxPagesPerDomain": { "title": "Max pages per domain", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of pages crawled per domain before stopping.", "default": 10 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many link levels deep to crawl from each start URL.", "default": 2 }, "prioritizeContactPages": { "title": "Prioritize contact pages", "type": "boolean", "description": "Prefer URLs and links containing contact, about, team, support, impact, reach, imprint, kontakt, legal.", "default": true }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Only follow links on the same domain as the start URL.", "default": true }, "validateEmails": { "title": "Validate emails", "type": "boolean", "description": "Validate extracted emails with the validation API.", "default": true }, "validationApiUrl": { "title": "Validation API URL", "type": "string", "description": "Base URL of the email validation API.", "default": "https://email.lifestep.io" }, "validationBatchSize": { "title": "Validation batch size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of emails per validation API request.", "default": 25 }, "minScore": { "title": "Minimum score", "minimum": 0, "maximum": 100, "type": "integer", "description": "Filter out emails with a validation score below this value (0-100).", "default": 0 }, "excludeDisposable": { "title": "Exclude disposable", "type": "boolean", "description": "Exclude disposable and temporary email addresses.", "default": true }, "excludeRoleAccounts": { "title": "Exclude role accounts", "type": "boolean", "description": "Exclude role accounts such as info@, support@, admin@.", "default": false }, "excludeFreeProviders": { "title": "Exclude free providers", "type": "boolean", "description": "Exclude emails from free providers such as Gmail, Yahoo, Outlook.", "default": false }, "maxResults": { "title": "Max results", "minimum": 0, "type": "integer", "description": "Maximum number of email rows to output (0 = unlimited).", "default": 0 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum concurrent crawler requests.", "default": 10 } } }, "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 } } } } } } } } } }