# =====================================================================
# robots.txt - Khushbindu Technologies (KIT)
# https://khushbindutechnologies.com
# =====================================================================

# --- Default: allow everything except internal dirs ---
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /content/
Disallow: /scripts/
Disallow: /css/*.map$
Disallow: /js/*.map$

# --- Googlebot: full access, no crawl-delay ---
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /img/
Allow: /blogs/

# --- Bingbot ---
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# --- Block AI training scrapers that don't respect noindex ---
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: FacebookExternalHit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Twitterbot
Allow: /

# --- Sitemaps ---
Sitemap: https://khushbindutechnologies.com/sitemap.xml

# --- Host (Yandex) ---
Host: https://khushbindutechnologies.com