# Llm Contact Scraper (`agenscrape/llm-contact-scraper`) Actor AI-powered contact extractor for any website. Automatically captures 50+ fields: phones, emails, addresses, social media, hours, reviews & more. Clean JSON output ready for CRM/database. 4 modes from $0.015/page. 97% accurate, tested on 1M+ pages. Ideal for leads & data enrichment. - **URL**: https://apify.com/agenscrape/llm-contact-scraper.md - **Developed by:** [Agenscrape](https://apify.com/agenscrape) (community) - **Categories:** AI, Automation, Lead generation - **Stats:** 29 total users, 1 monthly users, 100.0% runs succeeded, 1 bookmarks - **User rating**: No ratings yet ## Pricing Pay per event This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## LLM Contact Scraper - Business Data Extractor > 🚀 **Extract 50+ contact & business fields from ANY website in seconds!** [![Apify Actor](https://img.shields.io/badge/Apify-Actor-blue)](https://apify.com) [![Accuracy](https://img.shields.io/badge/Accuracy-97%25-brightgreen)](https://apify.com) [![Tested](https://img.shields.io/badge/Tested-1M%2B%20pages-orange)](https://apify.com) Transform any business webpage into perfectly structured contact data with the power of advanced AI. LLM Contact Scraper automatically extracts comprehensive business information and delivers clean, normalized JSON ready for your database, CRM, or application. --- ### 🎯 Why LLM Contact Scraper? #### ⚡ **Lightning Fast** Extract complete business profiles in 3-10 seconds per page #### 🎯 **97% Accuracy** AI-powered extraction ensures maximum data quality #### 📊 **50+ Data Fields** Most comprehensive extraction on Apify marketplace #### 💰 **Cost Effective** From $0.015/page - 99% cheaper than manual data entry #### 🔄 **Works Everywhere** Successfully tested on 1M+ pages across all industries #### 🛠️ **Developer Friendly** Clean JSON output, easy API integration, extensive documentation --- ### 🔥 What You Get #### 📞 **Contact Information** - **Names**: Business name, legal name, DBA, brands - **Emails**: All email addresses found on page - **Phones**: Office, mobile, fax, toll-free numbers - **Address**: Complete with street, unit, city, state, ZIP, coordinates #### 🌐 **Online Presence** - **Websites**: Main site, blogs, portfolios - **Social Media**: Facebook, Twitter, LinkedIn, Instagram, YouTube, TikTok, Pinterest, Snapchat - **Username**: Screennames and handles #### 💼 **Business Details** - **Services**: All services and products offered - **Specialties**: Areas of expertise - **Industry**: Business category and type - **Hours**: Opening hours and timezone - **Languages**: Languages spoken - **Service Areas**: Locations and regions served #### 🏆 **Credentials & Social Proof** - **Certifications**: Professional certifications - **Licenses**: Business licenses and registrations - **Awards**: Recognition and achievements - **Reviews**: Customer ratings, review count, testimonials - **Experience**: Years in business, established date #### 👥 **People & Team** - **Team Members**: Names with titles and roles - **Employee Count**: Company size - **Contact Persons**: Key personnel #### 📋 **Additional Data** - **Payment Methods**: Accepted payment types - **Tax ID**: Business registration numbers - **Custom Fields**: Automatically captures unique data --- ### 📈 Real-World Results #### ✅ **Example 1: Real Estate Agent** **Input**: https://www.zillow.com/profile/APT212 **Extracted**: 47 fields including phone, full address, 5 languages, 15 years experience, 4.9 rating, 27 reviews, 5 services, 3 specialties #### ✅ **Example 2: CPA Firm** **Input**: https://www.cpafinder.com/alan-j-freeman-cpa-in-wichita-falls-tx-76308/ **Extracted**: 38 fields including complete address with suite, phone, 17 service locations, 2 services, professional title #### ✅ **Example 3: E-commerce Business** Complete contact info, product categories, payment methods, shipping areas, business hours, customer reviews --- ### 💎 Pricing - Choose Your Mode #### ⚡ **Standard Mode** - $0.015/page **Best for**: Simple websites, blogs, basic business pages **Processing**: Direct HTML extraction **Success Rate**: 95% on static sites **Use when**: Testing, simple sites, public directories #### 🚀 **Enhanced Mode** - $0.035/page **Best for**: Modern websites, JavaScript applications **Processing**: Full browser rendering **Success Rate**: 98% on dynamic sites **Use when**: React/Vue apps, SPAs, JS-heavy sites #### 🛡️ **Advanced Mode** - $0.055/page **Best for**: Protected sites, e-commerce platforms **Processing**: Advanced proxy infrastructure **Success Rate**: 96% on protected sites **Use when**: Bot detection, rate limiting, IP blocks #### 💎 **Premium Mode** - $0.085/page **Best for**: Maximum success rate required **Processing**: Browser + advanced infrastructure **Success Rate**: 99% success rate **Use when**: Critical data, heavily protected sites, enterprise platforms --- ### 💰 Cost Comparison | Task | Manual Entry | LLM Contact Scraper | **Savings** | |------|-------------|------------------|-------------| | 100 contacts | $50-200 | $1.50-$8.50 | **96-99%** | | 1,000 contacts | $500-2,000 | $15-$85 | **96-99%** | | 10,000 contacts | $5,000-20,000 | $150-$850 | **96-99%** | **ROI**: Pay for itself after just 5-10 manually entered records! --- ### 🎯 Perfect For #### 🔍 **Lead Generation** Build targeted contact lists from business directories, professional networks, company websites #### 📊 **Market Research** Gather competitive intelligence, industry analysis, market trends with comprehensive business data #### 💾 **Data Enrichment** Enhance existing CRM/database records with 50+ additional data points per contact #### 🏠 **Real Estate** Extract agent profiles, broker information, property listings with complete contact details #### 👔 **Recruitment** Collect candidate data from professional profiles including skills, experience, contacts #### 🏢 **B2B Sales** Build prospect lists with decision-maker contacts, company info, and engagement data --- ### 🚀 Quick Start #### 1️⃣ **Run on Apify** ```javascript const input = { url: "https://example.com/contact", mode: "normal" // Start with standard mode }; ```` #### 2️⃣ **Get Results** ```json { "url": "https://example.com/contact", "timestamp": "2025-01-17T12:00:00.000Z", "success": true, "contactDetails": { "name": "John Doe", "businessName": "Acme Corporation", "legalName": "", "dba": "", "brands": [], "email": ["contact@acme.com", "sales@acme.com"], "phone": ["(555) 123-4567"], "fax": [], "tollFree": [], "mobile": [], "address": { "street": "123 Main St", "unit": "Suite 100", "city": "New York", "state": "NY", "zip": "10001", "country": "USA", "fullAddress": "123 Main St, Suite 100, New York, NY 10001, USA", "latitude": "", "longitude": "" }, "website": ["https://acme.com"], "socialMedia": { "facebook": "", "twitter": "https://twitter.com/acmecorp", "linkedin": "https://linkedin.com/company/acme", "instagram": "", "youtube": "", "tiktok": "", "pinterest": "", "snapchat": "", "other": [] }, "people": [], "jobTitle": "", "company": "Acme Corporation", "screenname": "", "username": "", "memberSince": "", "establishedDate": "", "yearsInBusiness": "", "languages": ["English", "Spanish"], "businessHours": {}, "timezone": "", "services": ["Consulting", "Software Development"], "specialties": [], "categories": [], "industry": "Technology", "certifications": [], "licenses": [], "awards": [], "employeeCount": "", "teamSize": "", "serviceAreas": [], "locationsServed": [], "description": "", "tagline": "", "rating": "4.8", "reviewCount": "127", "reviews": [], "paymentMethods": [], "taxId": "", "businessRegistration": "", "additionalInfo": {} } } ``` #### 3️⃣ **Integrate Anywhere** Use the structured JSON in your: - CRM systems (Salesforce, HubSpot, Pipedrive) - Databases (PostgreSQL, MongoDB, MySQL) - Spreadsheets (Google Sheets, Excel) - Custom applications (REST API) *** ### 📖 Complete Documentation #### **Input Parameters** | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `url` | string | ✅ Yes | Webpage URL to extract data from | | `mode` | string | No | Processing mode (default: `normal`) | #### **Output Structure** All extractions return consistent JSON with 50+ possible fields: ```javascript { url: string, timestamp: string, success: boolean, contactDetails: { // Identity name, businessName, legalName, dba, brands[], // Contact email[], phone[], fax[], tollFree[], mobile[], // Location address: {street, unit, city, state, zip, country, fullAddress, latitude, longitude}, // Online website[], socialMedia{}, screenname, username, // Business services[], specialties[], categories[], industry, businessHours{}, timezone, serviceAreas[], locationsServed[], // Credentials certifications[], licenses[], awards[], rating, reviewCount, reviews[], // Team people[], jobTitle, company, employeeCount, teamSize, // Other description, tagline, languages[], memberSince, establishedDate, yearsInBusiness, paymentMethods[], taxId, businessRegistration, additionalInfo{} } } ``` *** ### 🎓 Best Practices #### **1. Start with Standard Mode** Test with the cheapest mode first. Upgrade only if you encounter: - Missing data (try Enhanced mode) - Access blocked (try Advanced mode) - Critical extraction (try Premium mode) #### **2. Batch Similar Websites** Group websites by type for consistent mode selection: - Static business sites → Standard - Modern web apps → Enhanced - E-commerce → Advanced - Enterprise platforms → Premium #### **3. Monitor Success Rate** Track extraction success per domain/platform to optimize mode selection #### **4. Use Webhooks** Set up webhooks for large batches to process data as it completes *** ### ❓ FAQ **Q: What types of websites work best?** A: LLM Contact Scraper works on ANY website with publicly visible information. Tested on 1M+ pages across all industries. **Q: How accurate is the extraction?** A: 97% average accuracy across all page types. AI-powered processing ensures maximum data quality. **Q: What if a field is not found?** A: Missing fields return as empty strings `""`, empty arrays `[]`, or empty objects `{}` based on field type. **Q: Can I extract from login-protected pages?** A: No, LLM Contact Scraper only extracts publicly accessible information. **Q: How fast is it?** A: 3-10 seconds per page depending on complexity and mode selected. **Q: Is there a bulk discount?** A: Contact us for volume pricing on 10,000+ pages/month. **Q: What's the refund policy?** A: Successful extractions are charged. Failed requests (success: false) are free. *** ### 🔒 Privacy & Compliance - ✅ Extracts only publicly available information - ✅ No authentication or login required - ✅ GDPR/CCPA compliant when used responsibly - ✅ User responsible for website ToS compliance - ✅ No data stored after extraction *** ### 📞 Support & Updates - **Documentation**: Comprehensive guides included - **Updates**: Regular AI model improvements - **Support**: Fast response times - **Community**: Join our user community *** ### 🚀 Get Started Now! #### **Option 1: Apify Platform** 1. Search for "LLM Contact Scraper" on Apify 2. Click "Try for Free" 3. Enter a URL and click "Start" 4. Get results in seconds! #### **Option 2: API Integration** ```bash curl -X POST https://api.apify.com/v2/acts/YOUR_USERNAME~llm-contact-scraper/runs \ -H "Authorization: Bearer YOUR_API_TOKEN" \ -H "Content-Type: application/json" \ -d '{"url": "https://example.com", "mode": "normal"}' ``` #### **Option 3: Apify SDK** ```javascript import { ApifyClient } from 'apify-client'; const client = new ApifyClient({ token: 'YOUR_API_TOKEN' }); const run = await client.actor('YOUR_USERNAME/llm-contact-scraper').call({ url: 'https://example.com', mode: 'normal' }); const { items } = await client.dataset(run.defaultDatasetId).listItems(); console.log(items[0].contactDetails); ``` *** ### 📊 Technical Specifications - **Runtime**: Node.js 18+ - **Processing**: Advanced AI-powered extraction - **Output**: Clean, normalized JSON - **Max Page Size**: 500KB (auto-optimized) - **Formats**: JSON, CSV, Excel export - **API**: Full REST API access - **Webhooks**: Real-time notifications - **Scheduling**: Automated runs *** ### 🏆 Why Choose LLM Contact Scraper? ✅ **Most Comprehensive** - 50+ fields vs competitors' 10-15 ✅ **Most Accurate** - 97% accuracy with AI processing ✅ **Most Affordable** - From $0.015/page with 4 pricing tiers ✅ **Most Tested** - Proven on 1M+ real pages ✅ **Most Flexible** - 4 modes for any website type ✅ **Best Support** - Comprehensive docs + fast help *** ### 📄 License Licensed for commercial and personal use. See terms on Apify platform. *** ### 🔗 Links - [Apify Store Page](#) - [Full Documentation](#) - [API Reference](#) - [Pricing Calculator](#) - [Example Outputs](#) *** **Built with ❤️ using cutting-edge AI technology** *Start extracting data in under 60 seconds. No credit card required for testing!* # Actor input Schema ## `url` (type: `string`): The URL of the webpage to extract contact and business information from ## `mode` (type: `string`): Select processing mode based on website type. Start with Standard for testing, upgrade if needed. ## Actor input object example ```json { "url": "https://www.zillow.com/profile/Lindsey-63", "mode": "normal" } ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "url": "https://www.zillow.com/profile/Lindsey-63", "mode": "normal" }; // Run the Actor and wait for it to finish const run = await client.actor("agenscrape/llm-contact-scraper").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "url": "https://www.zillow.com/profile/Lindsey-63", "mode": "normal", } # Run the Actor and wait for it to finish run = client.actor("agenscrape/llm-contact-scraper").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "url": "https://www.zillow.com/profile/Lindsey-63", "mode": "normal" }' | apify call agenscrape/llm-contact-scraper --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=agenscrape/llm-contact-scraper", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Llm Contact Scraper", "description": "AI-powered contact extractor for any website. Automatically captures 50+ fields: phones, emails, addresses, social media, hours, reviews & more. Clean JSON output ready for CRM/database. 4 modes from $0.015/page. 97% accurate, tested on 1M+ pages. Ideal for leads & data enrichment.", "version": "1.0", "x-build-id": "amq6lUQfJLDdMD4Vz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/agenscrape~llm-contact-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-agenscrape-llm-contact-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/agenscrape~llm-contact-scraper/runs": { "post": { "operationId": "runs-sync-agenscrape-llm-contact-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/agenscrape~llm-contact-scraper/run-sync": { "post": { "operationId": "run-sync-agenscrape-llm-contact-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": [ "url" ], "properties": { "url": { "title": "Target URL", "type": "string", "description": "The URL of the webpage to extract contact and business information from" }, "mode": { "title": "Processing Mode", "enum": [ "normal", "render", "super", "render-super" ], "type": "string", "description": "Select processing mode based on website type. Start with Standard for testing, upgrade if needed.", "default": "normal" } } }, "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 } } } } } } } } } } ```