🤖 AI Lead Extractor - Dual Mode Extract any information from websites OR analyze any data using intelligent AI A powerful Apify actor that combines traditional web scraping with advanced AI capabilities. Extract contact information, generate summaries, analyze data, or create custom structured outputs from any website or raw data. --- ## 📋 Table of Contents - Features - Two Operating Modes - Quick Start - Input Configuration - Output Structure - Pricing & Billing - Use Cases - API Usage - Advanced Configuration - Troubleshooting - FAQ - Support --- ## ✨ Features ### 🎯 Dual Extraction Modes - Normal Mode: Web scraping with browser automation - Standby Mode: Direct data analysis (no browser needed) ### 🤖 AI-Powered Intelligence - Free Tier: Basic extraction + AI via OpenRouter (pay-per-use) - Paid Tier: Advanced AI included + superior accuracy - Natural Language Instructions: Tell AI what you want in plain English - Flexible Output: JSON, CSV, markdown, or any format you specify ### ⚡ Performance & Reliability - Full Browser Rendering: Handles JavaScript-heavy websites - Screenshot Capture: Automatic page screenshots for reference - Smart Retry Logic: Automatic recovery from failures - Token Management: Automatic overflow protection (30K token limit) - Graceful Fallback: Falls back to basic extraction if AI fails ### 💰 Transparent Billing - Memory-Based Pricing: Predictable costs based on allocated memory - Word-Based AI Billing: Pay only for words processed (input/output) - Usage Tracking: Detailed breakdown of all charges - Tier-Based Discounts: Lower rates for paid subscribers --- ## 🎭 Two Operating Modes ### 1️⃣ Normal Mode - Web Scraping When to use: Extract data from websites How it works: - Launches browser (Playwright) - Navigates to URLs - Extracts content with AI or basic methods - Captures screenshots - Returns structured data Example: json { "startUrls": [{"url": "https://apify.com/about"}], "useAI": true, "aiInstructions": "Extract company description and contact info" } ### 2️⃣ Standby Mode - Data Analysis When to use: Analyze any data without web scraping How it works: - No browser needed - Accepts any data format (JSON, CSV, text, etc.) - AI analyzes and transforms data - Fast response times - Cost-effective for data processing Example HTTP Request: bash curl -X POST "https://dz-omar--ai-lead-extractor.apify.actor?token=YOUR_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "data": "name,email\nAlice,alice@example.com\nBob,bob@example.com", "aiInstructions": "Extract emails as JSON array" }' --- ## 🚀 Quick Start ### Method 1: Apify Console (Easiest) 1. Sign up: Create free Apify account 2. Find Actor: Search for "AI Lead Extractor" or visit directly 3. Configure Input: Add URLs and instructions 4. Run: Click "Start" button 5. Download Results: Export as JSON, CSV, or Excel ### Method 2: API Call bash curl -X POST "https://api.apify.com/v2/acts/IeZZMR1Uv6J9h7pdS/runs?token=$API_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "startUrls": [{"url": "https://example.com"}], "useAI": true, "aiInstructions": "Extract contact information" }' ### Method 3: Standby Mode (Always-On) bash # Enable Standby Mode in Actor settings, then: curl -X POST "https://dz-omar--ai-lead-extractor.apify.actor?token=YOUR_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "data": "Your data here", "aiInstructions": "What to do with it" }' --- ## 📥 Input Configuration ### Basic Extraction (No AI) json { "startUrls": [ {"url": "https://example.com/contact"}, {"url": "https://example.com/about"} ], "useAI": false } What you get: Emails, phones, social links ### AI Extraction (Free Users - Pay Per Use) json { "startUrls": [{"url": "https://apify.com/about"}], "useAI": true, "aiInstructions": "Summarize this page in 3 bullet points" } Billing: Charged to your Apify account per request via OpenRouter ### Premium AI (Paid Subscribers - Included) json { "startUrls": [{"url": "https://apify.com/about"}], "useAI": true, "aiInstructions": "Extract CEO name, support email, and company mission" } Billing: Included in subscription, no per-request charges ### Standby Mode - Data Analysis json { "data": "Any data: JSON, CSV, text, XML, etc.", "aiInstructions": "Transform to JSON with name and email fields" } Note: No startUrls needed for data analysis ### Input Parameters | Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | startUrls | array | Yes | [] | List of URLs to scrape (not needed in Standby data analysis mode) | | useAI | boolean | No | false | Enable AI-powered extraction | | aiInstructions | string | No | See below | Natural language instructions for AI (max 75 words/500 chars) | | data | string | No | null | Data to analyze (Standby Mode only) | Default AI Instructions: "Extract all useful information: emails, phones, social links, descriptions, etc." --- ## 📤 Output Structure ### Free Tier - Basic Only json { "url": "https://example.com", "title": "Example Company", "basicExtraction": { "emails": ["info@example.com"], "phones": ["+1-555-0100"], "socialLinks": ["https://twitter.com/example"], "extractionMethod": "regex" }, "screenshot": { "available": true, "url": "https://api.apify.com/v2/key-value-stores/.../records/ss-123456" }, "extractionTier": "FREE", "extractionMethod": "Basic Only", "scrapedAt": "2025-12-17T12:00:00.000Z" } ### With AI Extraction json { "url": "https://apify.com/about", "title": "About · Apify", "aiExtraction": { "ceo_name": "Jan Čurn", "support_email": "support@apify.com", "company_mission": "Make the web more programmable" }, "basicExtraction": { "emails": ["support@apify.com"], "phones": ["+420-123-456-789"], "socialLinks": ["https://linkedin.com/company/apify"] }, "aiCost": { "inputWords": 2836, "outputWords": 2606, "totalWords": 5442, "cost": "$0.015981", "breakdown": "Processed 2,836 input words, generated 2,606 output words" }, "screenshot": { "available": true, "url": "https://..." }, "extractionTier": "PAID", "extractionMethod": "AI-Powered + Basic", "userTier": "GOLD", "scrapedAt": "2025-12-17T12:00:00.000Z" } ### Output Field Reference | Field | Description | |-------|-------------| | url | Scraped website URL | | title | Page title from HTML | | aiExtraction | AI-extracted data (structure varies by instructions) | | basicExtraction | Contact info (emails, phones, social links) | | aiCost | AI usage breakdown (words, cost) | | screenshot | Screenshot URL for visual reference | | extractionMethod | Method used (Basic, AI-Powered, etc.) | | extractionTier | User tier (FREE, PAID) | | userTier | Subscription level (FREE, BRONZE, SILVER, GOLD) | | scrapedAt | ISO timestamp | --- ## 💰 Pricing & Billing ### Billing Components (Normal Mode vs Standby Mode) #### 1. Memory-Based Billing (Normal Mode ONLY) Memory-based billing applies only when using Normal Mode. - Charged every 30 seconds based on allocated memory | Memory | Events/30s | FREE Tier | GOLD Tier | |--------|-----------|-----------|-----------| | 128 MB | 1 | $0.0008 | $0.0002 | | 256 MB | 2 | $0.0016 | $0.0004 | | 512 MB | 4 | $0.0032 | $0.0008 | | 1024 MB | 8 | $0.0064 | $0.0016 | Formula: Events = Memory (MB) / 128 #### Standby Mode Billing (No Memory Charges) Standby Mode runs as an API-style actor and follows Apify’s special Standby pricing rules: - ❌ No memory-based billing to the DEVELOPER - ✅ User pays: - Platform usage costs - PPE (event) costs - ✅ DEVELOPER is not responsible for platform usage costs #### 2. AI Word-Based Billing Charged per 1,000 words processed (when AI is enabled) | Type | FREE | BRONZE | SILVER | GOLD | |------|------|--------|--------|------| | Input Words (per 1K) | $0.0015 | $0.0012 | $0.0010 | $0.0008 | | Output Words (per 1K)| $0.0045 | $0.0036 | $0.0030 | $0.0024 | Conversion: 1 token ≈ 0.75 words ### Cost Examples #### Example 1: Basic Extraction (No AI) - Memory: 256 MB for 2 minutes - Memory Cost: 4 intervals × 2 events × $0.0016 = $0.0128 - AI Cost: $0 (AI disabled) - Total: $0.0128 #### Example 2: AI Extraction (Free Tier) - Memory: 256 MB for 2 minutes = $0.0128 - AI Input: 2,836 words = $0.0015 × 2.836 = $0.00425 - AI Output: 2,606 words = $0.0045 × 2.606 = $0.01173 - Total: $0.0288 #### Example 3: AI Extraction (GOLD Tier) - Memory: 256 MB for 2 minutes = $0.0032 - AI Input: 2,836 words = $0.0008 × 2.836 = $0.00227 - AI Output: 2,606 words = $0.0024 × 2.606 = $0.00625 - Total: $0.0117 (60% savings vs FREE) ### Upgrade Benefits | Feature | Free | Paid Tiers | |---------|------|-----------| | Basic Extraction | ✅ | ✅ | | AI Model | Simple | Advanced | | AI Billing | Pay-per-use | Tier discounts | | Memory Rates | Standard | Up to 75% off | | AI Accuracy | Good | Superior | | Complex Tasks | Limited | Excellent | --- ## 🎯 Use Cases ### 🏢 Lead Generation & Sales - Extract contact info from company websites - Build prospect databases - Enrich existing CRM data - Personalize outreach campaigns Example Instructions: - "Extract CEO name, company email, and phone number" - "Find all team members with their LinkedIn profiles" - "Get pricing plans and contact information" ### 📊 Market Research - Analyze competitor offerings - Track pricing changes - Monitor industry trends - Compare vendor capabilities Example Instructions: - "Compare features across all pricing tiers" - "Summarize company's value proposition" - "List all products with their descriptions" ### 🤖 Data Processing - Transform unstructured data to JSON - Clean and normalize datasets - Extract specific fields from documents - Generate summaries and reports Example Instructions: - "Convert this CSV to JSON with name and email fields" - "Extract all dates and amounts from this invoice" - "Summarize key findings in 5 bullet points" ### 📝 Content Creation - Research and fact-checking - Citation management - Content repurposing - Automated summaries Example Instructions: - "Extract main topics covered on this page" - "Generate a 2-sentence company description" - "List all statistics and their sources" --- ## 🔌 API Usage ### 1. Run Actor via API bash curl -X POST "https://api.apify.com/v2/acts/IeZZMR1Uv6J9h7pdS/runs?token=$API_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "startUrls": [{"url": "https://apify.com/about"}], "useAI": true, "aiInstructions": "Extract company info" }' Response: json { "data": { "id": "run_abc123", "status": "RUNNING", "defaultDatasetId": "dataset_xyz" } } ### 2. Standby Mode (Real-Time) bash # Web Scraping curl -X POST "https://dz-omar--ai-lead-extractor.apify.actor?token=YOUR_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "url": "https://example.com", "useAI": true, "aiInstructions": "Extract contacts" }' # Data Analysis curl -X POST "https://dz-omar--ai-lead-extractor.apify.actor?token=YOUR_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "data": "your data here", "aiInstructions": "analyze and transform" }' ### SDK Integration (Node.js) javascript import { ApifyClient } from 'apify-client'; const client = new ApifyClient({ token: 'YOUR_TOKEN' }); // Run the actor const run = await client.actor('dz_omar/ai-lead-extractor').call({ startUrls: [{ url: 'https://apify.com/about' }], useAI: true, aiInstructions: 'Extract CEO name and contact info' }); // Get results const { items } = await client.dataset(run.defaultDatasetId).listItems(); console.log(items); --- ## ❓ FAQ ### General Questions Q: What's the difference between Normal Mode and Standby Mode? A: Normal Mode is designed strictly for web scraping using a browser and requires URLs (startUrls). Standby Mode works like an API: it can analyze user-provided data directly and can optionally use Playwright if a URL is provided. --- Q: Can I use AI on the free tier? A: Yes! Free tier has access to AI via OpenRouter (charges your Apify account per request). Paid tiers include advanced AI with better accuracy and lower rates. --- Q: How much does AI cost on the free tier? A: Around $0.002–$0.005 per page depending on content size. Check the aiCost field in results for the exact breakdown. --- Q: When should I upgrade to a paid tier? A: Upgrade if you: * Use AI regularly (more cost-effective) * Need higher accuracy for complex tasks * Want predictable costs * Process large volumes of data --- ### Technical Questions Q: Can I analyze my own data instead of scraping a website? A: * ❌ No in Normal Mode — it only processes content extracted from URLs * ✅ Yes in Standby Mode — it accepts any data format (JSON, CSV, text, etc.) --- Q: Does Standby Mode always use Playwright? A: No. * If data is provided → no browser is used * If a url is provided → Playwright is used * If both are provided → data takes priority This allows Standby Mode to act as a data analysis API, a lightweight scraper, or a hybrid processor. --- Q: Can I process multiple URLs? A: Yes. In Normal Mode, you can provide an array of URLs in startUrls and process thousands of pages in one run. --- Q: What data formats are supported in Standby Mode? A: Any text-based format: JSON, CSV, XML, HTML, plain text, markdown, etc. The AI automatically detects the format. --- ### Billing Questions Q: How is memory billed? A: Memory is billed every 30 seconds based on allocated memory 📌 Only when using Normal Mode Standby Mode does not incur memory-based billing for the actor creator. --- Q: Who pays the costs in Standby Mode? A: When a Standby Actor is monetized with PPE: * The user pays platform usage and PPE costs * The creator does not pay execution costs * The creator still receives 80% of PPE revenue --- Q: What if I run out of credits? A: The actor stops gracefully. Add credits to your Apify account and resume. --- Q: Can I set a budget limit? A: Yes. Set spending limits in Apify Console → Account Settings → Limits. --- md Standby Mode supports both Playwright-based browsing and direct data analysis, while Normal Mode is limited to scraping content from URLs only. --- ## 📞 Support ### Get Help - 🌐 Website: flowextractapi.com - 📧 Email: flowextractapi@outlook.com - 🙋 Apify Profile: dz_omar - 💬 GitHub Issues: FlowExtractAPI ### Social Media - 💼 LinkedIn: flowextract-api - 🐦 Twitter: @FlowExtractAPI - 📱 Facebook: flowextractapi ### Documentation - 📚 Apify Docs: docs.apify.com - 🔧 API Reference: docs.apify.com/api/v2 - 🎓 Tutorials: Check our blog for guides and examples --- ## 🌟 Related Actors by DZ_OMAR ### 🎬 Video & Media - YouTube Transcript Extractor - Extract transcripts with timestamps - YouTube Scraper Pro - Complete channel and playlist extraction - Zoom Scraper - Download recordings and transcripts - Loom Scraper - Loom video and transcript extraction ### 🏠 Real Estate - Idealista Scraper API - Spanish property data with API - Idealista Scraper - Real estate listings extractor ### 🛠️ Developer Tools - Screenshot - Fast webpage screenshots - Ultimate Screenshot - Advanced screenshot tool - Network Security Scanner - Security vulnerability scanner ### 📱 Social Media - Facebook Ads Scraper Pro - Extract Facebook ads data --- ## 📄 License This actor is provided as-is for use on the Apify platform. Use responsibly and in accordance with applicable laws and website terms of service. --- ## ⚖️ Legal & Compliance This actor extracts publicly available information from websites. Ensure your use complies with: - ✅ Website Terms of Service - ✅ Copyright laws - ✅ Data protection regulations (GDPR, CCPA) - ✅ Robots.txt directives - ✅ Your jurisdiction's laws You are responsible for how you use extracted data. Use ethically and legally. --- ## 🚀 Ready to Start? 1. Sign up for Apify (free tier available) 2. Try AI Lead Extractor 3. Configure your first extraction 4. Get results in seconds Have questions? Contact us at flowextractapi@outlook.com ---