{ "openapi": "3.0.1", "info": { "title": "Cheapest Website Data & Email Scraper - Enrichment & Validator", "description": "Extract emails, phone numbers, and social media profiles from any website. Validate email deliverability, detect digital platform accounts, and gather domain intelligence (tech stack, SSL, WHOIS, server location). The complete data enrichment toolkit for B2B lead generation.", "version": "2.0", "x-build-id": "razfcb4nzLahvhhDa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/expanditumarca~website-data-email-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-expanditumarca-website-data-email-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/expanditumarca~website-data-email-scraper/runs": { "post": { "operationId": "runs-sync-expanditumarca-website-data-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/expanditumarca~website-data-email-scraper/run-sync": { "post": { "operationId": "run-sync-expanditumarca-website-data-email-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "websiteUrls" ], "properties": { "websiteUrls": { "title": "Website URLs", "type": "array", "description": "List of website URLs to scrape for B2B contact data.", "items": { "type": "string" } }, "maxInternalPages": { "title": "Internal Pages to Scan", "enum": [ "0", "5", "10", "15", "20" ], "type": "string", "description": "Number of internal pages to visit per website (beyond homepage). More pages = more contacts found, higher cost. Each internal page scraped is charged separately.", "default": "0" }, "enableDepth2Nav": { "title": "Deep Site Crawl", "type": "boolean", "description": "Also visit sub-pages discovered within internal pages (e.g. individual blog posts, portfolio items). Each page counts toward the Internal Pages limit and is charged at the same rate. Only active when Internal Pages > 0.", "default": false }, "enableEmailVerification": { "title": "Email Domain Validation", "type": "boolean", "description": "Validates each email by checking its shape and whether its domain has active mail records. Mailbox-level probing does not run on this platform (outbound port 25 is blocked), so `smtpStatus` always comes back `unknown` and `mxValid` carries the verdict.", "default": false }, "enableHolehe": { "title": "Platform Account Detection", "type": "boolean", "description": "For each PERSONAL email found on the site (Gmail, Yahoo, Outlook, ISP mailboxes...), checks whether it has accounts on other platforms. Corporate addresses are not checked: behind them there is a company, not a person. Each address comes back with `inUse` — true (accounts found), false (checked, none found), or null (the question could not be asked). A null is NEVER 'no accounts', and only answered addresses are charged.", "default": false }, "networkStrategy": { "title": "Outbound route for account detection", "enum": [ "auto", "direct", "standard", "extended" ], "type": "string", "description": "How account detection reaches each source. Auto starts on the cheapest route and moves up only for the sources measured to need it, one at a time — forcing a higher route for all of them spends without buying answers.", "default": "auto" }, "enableDomainIntel": { "title": "Domain Intelligence", "type": "boolean", "description": "Gather technical intelligence per domain: detected services (Google Workspace, HubSpot, Shopify, etc.), domain registration age, SSL certificate validity, and server geo-location.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional proxy for scraping. Residential proxies improve access to bot-protected websites." } } }, "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 } } } } } } } } } }