{ "openapi": "3.0.1", "info": { "title": "Website Contact Extractor — AI Contacts, Emails, Phones", "description": "Extract structured contacts (name, position, email, phone, LinkedIn) plus emails, phones, socials and address from any company website. AI-powered — Gemini / Groq / OpenRouter (bring your own key). Pay-per-result.", "version": "2.1", "x-build-id": "tWBHcmdWMgYr6Waj1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/santamaria-automations~website-contact-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-santamaria-automations-website-contact-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/santamaria-automations~website-contact-extractor/runs": { "post": { "operationId": "runs-sync-santamaria-automations-website-contact-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/santamaria-automations~website-contact-extractor/run-sync": { "post": { "operationId": "run-sync-santamaria-automations-website-contact-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "URLs or Domains", "type": "array", "description": "List of website URLs or domains to extract contact details from. Bare domains (example.com) and full URLs (https://www.example.com) are both accepted.", "items": { "type": "string" } }, "companies": { "title": "Companies (with company_id passthrough)", "type": "array", "description": "Alternative to `urls`. Each entry carries a company_id (echoed on output row for join-back) plus optional company_name (used as an identity anchor in the LLM prompt so testimonials and third-party references are not misattributed).", "items": { "type": "object", "required": [ "website_url" ], "properties": { "company_id": { "title": "Company ID", "type": "string", "description": "Your internal identifier — echoed on the output row so you can join enrichment results back to your source data." }, "company_name": { "title": "Company Name", "type": "string", "description": "Company name — used in the LLM prompt to filter out testimonials and third-party references." }, "website_url": { "title": "Website URL", "type": "string", "description": "The company website URL to crawl." }, "team_page_url": { "title": "Team Page URL (optional)", "type": "string", "description": "Pre-discovered team page URL — added as priority when set." } } } }, "maxPagesPerUrl": { "title": "Max Pages Per URL", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum pages to crawl per website. Contact, about, impressum and team pages are prioritised. Higher values improve recall but cost more crawl time.", "default": 15 }, "llmProvider": { "title": "LLM Provider", "enum": [ "gemini", "groq", "openrouter" ], "type": "string", "description": "Primary AI provider for structured contact extraction. Gemini Flash is fastest and has a generous free tier.", "default": "gemini" }, "fallbackProvider": { "title": "Fallback LLM Provider", "enum": [ "gemini", "groq", "openrouter" ], "type": "string", "description": "Second-level fallback if primary provider fails (rate limit, auth error, etc)." }, "fallback2Provider": { "title": "Third-Level Fallback", "enum": [ "gemini", "groq", "openrouter" ], "type": "string", "description": "Third-level fallback if both primary and first fallback fail." }, "llmModel": { "title": "LLM Model (optional override)", "type": "string", "description": "Override default model. Defaults: Gemini → gemini-2.0-flash, Groq → llama-3.3-70b-versatile, OpenRouter → google/gemini-2.0-flash-001. If your OpenRouter key does not have access to the paid Gemini model (returns 404), set this to a free model like meta-llama/llama-3.1-8b-instruct." }, "geminiApiKey": { "title": "Gemini API Key (recommended)", "type": "string", "description": "Google Gemini Flash — best quality/cost ratio, generous free tier. Get a key at https://aistudio.google.com/app/apikey" }, "groqApiKey": { "title": "Groq API Key (optional)", "type": "string", "description": "Groq — ultra-fast inference. Get a key at https://console.groq.com/keys" }, "openrouterApiKey": { "title": "OpenRouter API Key (optional)", "type": "string", "description": "OpenRouter — access to 100+ models. Get a key at https://openrouter.ai/keys" }, "outputLanguage": { "title": "Output Language", "enum": [ "en", "de", "fr", "it", "es", "pt", "nl", "auto" ], "type": "string", "description": "Language for AI-extracted text fields (industry, description, positions, departments). 'auto' = match website language.", "default": "en" }, "enablePlaywrightFallback": { "title": "Browser Fallback for JS Sites", "type": "boolean", "description": "Auto-chain to the browser variant for sites flagged as JavaScript-rendered. Adds cost but recovers ~25% of otherwise-empty sites.", "default": false }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings. Apify proxy works for most sites.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }