Vercel / Netlify Middleware

import { NextRequest, NextResponse } from 'next/server';

const AI_BOT_PATTERNS = [
  // OpenAI — citations & training
  'OAI-SearchBot', 'ChatGPT-User', 'GPTBot',
  // Anthropic / Claude — citations & training
  'Claude-Web', 'Claude-User', 'ClaudeBot', 'anthropic-ai',
  // Perplexity
  'PerplexityBot', 'Perplexity-User',
  // Google / Gemini — citations & training
  'Googlebot', 'Google-Extended', 'Google-Gemini',
  // Microsoft / Bing
  'bingbot', 'BingPreview',
  // Meta
  'Meta-ExternalAgent', 'FacebookBot',
  // Others
  'Bytespider', 'cohere-ai', 'CCBot',
  // Traditional search
  'YouBot', 'DuckDuckBot', 'Baiduspider',
];

const LOG_ENDPOINT = '<TRAFFIC_INGEST_SERVICE_URL>/log/vercel';
const ORGANIZATION_ID = '<YOUR_ORGANIZATION_ID>';

export function middleware(request: NextRequest) {
  const ua = request.headers.get('user-agent') ?? '';
  const isBot = AI_BOT_PATTERNS.some((p) =>
    ua.toLowerCase().includes(p.toLowerCase())
  );

  if (isBot) {
    const payload = {
      timestamp: new Date().toISOString(),
      bot_ua: ua,
      url: request.url,
      method: request.method,
      ip: request.headers.get('x-forwarded-for') ?? request.headers.get('x-real-ip'),
      country: request.headers.get('x-vercel-ip-country'),
      city: request.headers.get('x-vercel-ip-city'),
    };

    // Fire-and-forget — never awaited, does not block the response
    fetch(LOG_ENDPOINT, {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        Authorization: `Bearer ${ORGANIZATION_ID}`,
      },
      body: JSON.stringify(payload),
    }).catch(() => {});
  }

  return NextResponse.next();
}

export const config = {
  // Run on all routes except Next.js internals and static files
  matcher: ['/((?!_next/static|_next/image|favicon.ico).*)'],
};

// SvelteKit: place in src/hooks.server.js
// Nuxt: place in server/middleware/bot-tracker.js
// Astro: place in src/middleware.js

const AI_BOT_PATTERNS = [
  // OpenAI — citations & training
  'OAI-SearchBot', 'ChatGPT-User', 'GPTBot',
  // Anthropic / Claude — citations & training
  'Claude-Web', 'Claude-User', 'ClaudeBot', 'anthropic-ai',
  // Perplexity
  'PerplexityBot', 'Perplexity-User',
  // Google / Gemini — citations & training
  'Googlebot', 'Google-Extended', 'Google-Gemini',
  // Microsoft / Bing
  'bingbot', 'BingPreview',
  // Meta
  'Meta-ExternalAgent', 'FacebookBot',
  // Others
  'Bytespider', 'cohere-ai', 'CCBot',
  // Traditional search
  'YouBot', 'DuckDuckBot', 'Baiduspider',
];

const LOG_ENDPOINT = '<TRAFFIC_INGEST_SERVICE_URL>/log/vercel';
const ORGANIZATION_ID = '<YOUR_ORGANIZATION_ID>';

export async function handle({ event, resolve }) {
  const ua = event.request.headers.get('user-agent') ?? '';
  const isBot = AI_BOT_PATTERNS.some((p) =>
    ua.toLowerCase().includes(p.toLowerCase())
  );

  if (isBot) {
    const payload = {
      timestamp: new Date().toISOString(),
      bot_ua: ua,
      url: event.request.url,
      method: event.request.method,
      ip: event.request.headers.get('x-forwarded-for'),
      country: event.request.headers.get('x-vercel-ip-country'),
      city: event.request.headers.get('x-vercel-ip-city'),
    };

    fetch(LOG_ENDPOINT, {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        Authorization: `Bearer ${ORGANIZATION_ID}`,
      },
      body: JSON.stringify(payload),
    }).catch(() => {});
  }

  return resolve(event);
}