Llm Contact Scraper

by agenscrape

An AI-powered scraper that automatically extracts 50+ contact fields from any website. Get clean, accurate data for lead generation and CRM enrichment starting at $0.015/page.

190 runs

19 users

Try This Actor

Opens on Apify.com

About Llm Contact Scraper

Tired of manually hunting for contact details across websites? The Llm Contact Scraper is what I use to automate that entire process. It’s an AI-driven actor that intelligently scans any site you give it and pulls out over 50 different data points. I’m talking about the obvious stuff like phone numbers and email addresses, but it also reliably finds physical addresses, social media profiles, business hours, and even customer reviews. What I appreciate is how it structures everything into clean, ready-to-use JSON. You can pipe that output directly into your CRM, a spreadsheet, or a custom database without any messy cleanup. It’s built for practical lead generation and data enrichment projects. You can choose from four different pricing modes depending on your volume, starting at just $0.015 per page, which makes it super scalable. The accuracy is legit—they’ve hit a 97% success rate across more than a million test pages, so you’re not getting a bunch of junk data. If you need to build a targeted contact list or enrich your existing records with fresh info, this actor handles the heavy lifting.

What does this actor do?

Llm Contact Scraper is a web scraping and automation tool available on the Apify platform. It's designed to help you extract data and automate tasks efficiently in the cloud.

Key Features

Cloud-based execution - no local setup required
Scalable infrastructure for large-scale operations
API access for integration with your applications
Built-in proxy rotation and anti-blocking measures
Scheduled runs and webhooks for automation

How to Use

Click "Try This Actor" to open it on Apify
Create a free Apify account if you don't have one
Configure the input parameters as needed
Run the actor and download your results

Documentation

LLM Contact Scraper

Extract structured business and contact data from any website using AI. This Apify actor processes webpages and returns clean, normalized JSON containing 50+ fields like contact details, business information, and online presence. It's designed for lead generation, data enrichment, and CRM integration.

Key Features

AI-Powered Extraction: Uses advanced LLMs to accurately identify and extract relevant data from diverse webpage layouts.
Comprehensive Data: Captures over 50 structured fields across multiple categories.
High Accuracy: Claims ~97% accuracy, tested on over 1 million pages.
Multiple Processing Modes: Choose a mode based on website complexity and your budget.
Developer-Friendly: Outputs clean JSON, integrates easily via API, and includes detailed documentation.

Extracted Data Categories

Contact Info: Business name, emails, phone numbers, full physical address.
Online Presence: Website URLs, social media profiles (Facebook, LinkedIn, etc.), usernames.
Business Details: Services, specialties, industry, hours, languages, service areas.
Credentials: Certifications, licenses, awards, reviews, years in business.
Team: Team member names/roles, employee count, key contacts.
Additional: Payment methods, tax IDs, custom fields.

How to Use

Run the actor via the Apify API, console, or schedule it. Provide a list of website URLs as input.

Input Configuration

The main input is a list of URLs. You can configure the run using these key options:

startUrls: (Required) An array of URLs to scrape. [{ "url": "https://example.com/business" }]
mode: Choose the processing method and price tier.
- standard ($0.015/page): Direct HTML parsing. Best for simple, static sites.
- enhanced ($0.035/page): Full browser rendering. For JavaScript-heavy sites (React, Vue, SPAs).
- advanced ($0.055/page): Adds proxy rotation. For sites with basic bot protection.
- premium ($0.085/page): Maximum success rate for heavily protected sites (e.g., e-commerce).
maxPagesPerStartUrl: Limit the number of pages crawled per seed URL (default: 1).
extractionModel: Specify the LLM model for data extraction (default is optimized for accuracy/cost).
proxyConfiguration: Use custom proxies, required for advanced and premium modes.

Example Input (JSON)

{
  "startUrls": [
    { "url": "https://www.example-business.com/contact" }
  ],
  "mode": "enhanced",
  "maxPagesPerStartUrl": 1
}

Output

The actor outputs a dataset of items, where each item corresponds to a successfully scraped page. Each item is a structured JSON object containing the extracted fields.

Example Output (Simplified)

{
  "url": "https://www.example-business.com/contact",
  "businessName": "Example Corp",
  "emails": ["contact@example.com"],
  "phones": ["+1-555-123-4567"],
  "address": {
    "street": "123 Main St",
    "city": "San Francisco",
    "state": "CA",
    "zipCode": "94105"
  },
  "services": ["Web Development", "Consulting"],
  "socialMedia": {
    "linkedin": "https://linkedin.com/company/example-corp"
  }
}

The dataset is available in JSON, CSV, XML, and other formats via the Apify API for direct integration into your database, CRM, or application.