# https://www.robotstxt.org/robotstxt.html
User-agent: *
Allow: /

# Disallow 404 error page from search index
Disallow: /404

# Disallow common hack / exploit probes
Disallow: /bkx/
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /*.php$
Disallow: /*.env$
Disallow: /cgi-bin/
Disallow: /admin/
Disallow: /backup/
Disallow: /config/
Disallow: /temp/

# Disallow build / cache artifacts
Disallow: /assets/*.map$

# Disallow common aggressive scrapers & data harvesting bots
User-agent: Bytespider
User-agent: PetalBot
User-agent: SemrushBot
User-agent: AhrefsBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: Rogerbot
User-agent: MegaIndex
User-agent: AspiegelBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: CCBot
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Amazonbot
Disallow: /

# Crawl delay for other polite crawlers
Crawl-delay: 5

# Host
Host: https://airtek.com.pk

# Sitemap Location
Sitemap: https://airtek.com.pk/sitemap.xml