# Robots.txt - CodeZen SEO Configuration
# Defines crawling rules for search engines and bots

# ── Default rules for all user agents ──────────────────────────────────────
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /_next/
Disallow: /*.json$
Disallow: /secure-form/
Disallow: /dashboard/
Disallow: /login
Disallow: /register
Disallow: /reset-password
Disallow: /auth/
Disallow: /settings/
Disallow: /profile/
Disallow: /?*
Disallow: /*?*sort=
Disallow: /*?*filter=
Disallow: /*?*page=
Allow: /?token=

# ── Crawl delay and rate limiting ──────────────────────────────────────────
# Conservative limits to prevent overload
Crawl-delay: 1
Request-rate: 30/60s

# ── GoogleBot specific rules ───────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/
Disallow: /login
Crawl-delay: 0

# ── BingBot specific rules ────────────────────────────────────────────────
User-agent: Bingbot
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/
Crawl-delay: 1

# ── Block bad bots ────────────────────────────────────────────────────────
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12Bot
Disallow: /

User-agent: Magnet
Disallow: /

User-agent: Grapeshot
Disallow: /

# ── Sitemap ───────────────────────────────────────────────────────────────
Sitemap: https://codezen.ai/sitemap.xml

# ── CDN and static assets (images, stylesheets, scripts) ──────────────────
User-agent: *
Allow: /*.css$
Allow: /*.js$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.gif$
Allow: /*.svg$
Allow: /*.webp$
Allow: /*.avif$
Allow: /*.woff$
Allow: /*.woff2$
Allow: /*.ttf$

# ── Social media crawlers (enabled for rich previews) ─────────────────────
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Slurp
Allow: /