Business Profile Enricher

Extract structured business data from any website using AI. Get emails, phone numbers, owner/staff names, services, social media links, certifications, and more — all from a business website URL.

Unlike CSS-based scrapers that only grab data from one platform, this enricher reads the actual website content using AI, so it works on any business site regardless of how it's built.

What data do you get?

For each business URL, you get:

Field	Example
Business Name	The Smith Law Firm, LLC
Description	Family law firm serving the St. Louis area since 1998
Emails	neil@smithlawfirm.com
Phones	(314) 725-4400
People	Neil Smith — Attorney
Services	Dissolution of Marriage, Child Custody, Paternity, ...
Social Links	Facebook, Instagram, Twitter, LinkedIn, YouTube, TikTok, Yelp
Year Established	1998
Address	231 S. Bemiston Ave., Suite 800, St. Louis, MO 63105
Service Area	St. Louis, St. Charles
Certifications	Licenses, bar admissions, BBB ratings
Hours	Mon-Fri 9am-5pm
Languages	English, Spanish
Payment Methods	Credit card, financing, insurance accepted

The enricher automatically crawls key subpages (About, Contact, Team, Services) for each business to maximize data coverage.

How to use it

Option 1: Provide URLs directly

Paste a list of business website URLs. Works with any website.

{
    "mode": "urls",
    "urls": [
        "https://www.smithlawfirm.com",
        "https://www.abrahamwatkins.com",
        "https://www.benfranklinplumbing.com"
    ]
}

Option 2: Enrich a Google Maps Scraper dataset

Already scraped businesses with the Google Maps Scraper? Pass the dataset ID and we'll enrich every business that has a website.

{
    "mode": "dataset",
    "datasetId": "AXu06pVFRUYhGQ9Su"
}

How it works

1. Fetches the homepage of each business website
2. Discovers subpages — automatically finds and fetches About, Contact, Team/Staff, and Services pages
3. AI extraction — sends the combined page content to an AI model that reads the site like a human and extracts structured data
4. Returns clean JSON — every business gets a consistent profile with all available fields

Why use AI extraction instead of CSS scraping?

Traditional scrapers break when a website changes its layout. They also can't handle the massive variety of small business websites — every plumber, lawyer, and dentist has a different site structure.

AI extraction reads the page content and understands what it means, regardless of how the HTML is structured. This means:

• Works on any website — WordPress, Squarespace, Wix, custom builds
• Never breaks — no selectors to maintain
• Extracts meaning — finds "John Smith, Managing Partner" on an About page, not just raw text

Output format

Each result in the dataset includes both flat fields (for easy CSV export) and a nested enrichmentData object (for programmatic access).

Integrations

Works with Apify's full integration ecosystem: Zapier, Make, Google Sheets, webhooks, REST API, and more.