Website Contact Extractor (Browser)

Extract contacts from JavaScript-rendered company websites (React, Vue, Angular SPAs) using AI + Playwright.

This is the browser-based companion to the Website Contact Extractor (HTTP-only). Use this actor when the HTTP version flags companies with js_rendering_suspected status.

When to use this actor

• Team/contact/about pages built with React, Vue, Angular, or other JS frameworks
• Pages that return empty/skeleton HTML without JavaScript execution
• Companies flagged by the HTTP actor's JS-rendering detection
• Auto-chained via enablePlaywrightFallback on the HTTP actor

How it works

1. Link discovery from homepage (HTTP, fast)
2. Phase 1: Playwright renders main pages (team, contact, about, impressum)
3. Phase 2: Playwright renders team member detail pages
4. LLM extraction using Gemini Flash / Groq / OpenRouter
5. Anti-hallucination validation against source HTML
6. Cross-company dedup to catch LLM-invented names

Same extraction pipeline as the HTTP actor — same output format, same quality.

Input

Same input format as the HTTP actor:

{
  "companies": [
    {
      "company_id": "abc-123",
      "company_name": "TechCorp AG",
      "website_url": "https://techcorp.ch"
    }
  ],
  "llmProvider": "gemini",
  "geminiApiKey": "YOUR_KEY"
}

Output

Each company result includes browser_extraction: true:

{
  "company_id": "abc-123",
  "company_name": "TechCorp AG",
  "contacts": [
    {
      "name": "Max Mustermann",
      "position": "CTO",
      "email": "max@techcorp.ch",
      "confidence": 0.92
    }
  ],
  "status": "success",
  "browser_extraction": true
}

Memory requirements

• Minimum: 1024 MB (Playwright + Chrome)
• Recommended: 2048 MB for 5+ companies
• Maximum: 4096 MB

Pricing

Browser-based extraction costs ~2x the HTTP actor:

Event	Cost
browser-company-enriched	$0.02/company
browser-contact-result	$0.010/contact

Auto-chaining

The HTTP actor can automatically trigger this browser actor:

1. Run the HTTP actor with enablePlaywrightFallback: true
2. Companies with js_rendering_suspected status are collected
3. A browser actor run starts automatically (fire-and-forget)
4. The browser run ID is saved in the key-value store

LLM fallback chain

Like the HTTP actor, this actor supports automatic provider fallback. Just provide API keys for the providers you want to use:

{
  "geminiApiKey": "YOUR_GEMINI_KEY",
  "llmApiKey": "YOUR_GROQ_KEY",
  "openrouterApiKey": "YOUR_OPENROUTER_KEY"
}

The system auto-discovers available providers and builds a fallback chain (e.g. Gemini → Groq → OpenRouter). If one provider's quota runs out, it instantly falls back to the next.

End-to-end pipeline

This actor is part of a 5-actor enrichment suite:

Actor	Purpose	Memory	Link
Google Maps Scraper	Find companies by location	~80MB	View
Website Contact Extractor	Extract contacts (HTTP)	~256MB	View
Website Contact Extractor (Browser)	Extract contacts from JS pages	~1-4GB	This actor
Website Job Extractor	Extract jobs (HTTP)	~128MB	View
Website Job Extractor (Browser)	Extract jobs from JS pages	~1-4GB	View

Limitations

• Higher memory usage (~1GB vs ~256MB for HTTP)
• Slower execution (page rendering + wait times)
• Higher cost per result (2x HTTP rates)
• Use the HTTP actor first — only fall back to browser when needed