import { shouldBlockCrawler, extractUserAgent } from 'crawl-me-not';
import { NextRequest, NextResponse } from 'next/server';

export function middleware(request: NextRequest) {
  const userAgent = extractUserAgent(request.headers);
  const result = shouldBlockCrawler(userAgent, {
    blockAI: true,
    blockSEO: false,
    customBlocked: [/scrapy/i, /curl/i], // Block additional patterns
    debug: true
  });

  if (result.isBlocked) {
    console.log(`Blocked ${result.crawlerType} crawler: ${result.userAgent}`);
    
    return NextResponse.json(
      { 
        error: 'Access denied',
        reason: `${result.crawlerType} crawler detected`,
        userAgent: result.userAgent
      },
      { 
        status: 403,
        headers: {
          'X-Blocked-Reason': 'Automated traffic detected'
        }
      }
    );
  }

  return NextResponse.next();
}

// Configure which paths to run middleware on
export const config = {
  matcher: [
    /*
     * Match all request paths except for the ones starting with:
     * - api (API routes)
     * - _next/static (static files)
     * - _next/image (image optimization files)
     * - favicon.ico (favicon file)
     */
    '/((?!api|_next/static|_next/image|favicon.ico).*)',
  ],
};