Extract Contacts from Any Website — Emails, Phones, and Decision-Makers via LLM

Feed in a list of company websites and get back structured contact data: emails, phone numbers, and decision-maker names. Our 2-phase crawler first discovers contact and team pages, then uses an LLM chain (Gemini, Groq, OpenRouter) to extract and structure the information. Automatic browser fallback for JS-heavy sites.

Open on Apify → Try it now
Runtime
Node.js
RAM
~256MB
Proxy
Datacenter
Coverage
Any website
Pricing
$0.01/company
AI Engine
LLM chain (Gemini/Groq)

What You Can Scrape

Primary Use Cases

API Example

# Start a run via the Apify API
curl -X POST "https://api.apify.com/v2/acts/santamaria-automations~website-contact-extractor/runs?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "urls": ["https://example.com", "https://another-company.de"],
    "maxPagesPerDomain": 5
  }'

# Or use with AI agents via MCP:
# https://mcp.apify.com?tools=santamaria-automations/website-contact-extractor

Integrations

How It Compares

FeatureNanoScrapeManual / Hunter.io
Cost per company$0.01$0.03 - $0.10
Decision-makersLLM-extractedDatabase lookup only
Phone numbersYesUsually email-only
Works on any siteYes (2-phase crawl)Limited to indexed sites
Browser fallbackAutomatic for JS sitesN/A
API accessFull Apify APISeparate subscription

Output Fields

FieldTypeExample
domainstringexample.com
emailsstring[]["[email protected]", "[email protected]"]
phonesstring[]["+49 89 123456", "+49 89 123457"]
contactsobject[][{"name": "Max Mustermann", "role": "CEO"}]
addressstringMusterstr. 1, 80331 Munich
social_linksobject{"linkedin": "...", "twitter": "..."}
pages_crawlednumber4
Open on Apify → Try it now — free tier available