# Robots.txt for zenocloud.io
# Last updated: 2026-02-04

# Default rules for all crawlers
User-agent: *
Allow: /
Crawl-delay: 1

# Sitemap location
Sitemap: https://zenocloud.io/sitemap-index.xml

# Disallow admin, internal, and non-content paths
Disallow: /admin/
Disallow: /api/
Disallow: /_astro/
Disallow: /*.json$
Disallow: /*?*
Disallow: /cdn-cgi/
Disallow: /search?

# Block parameter URLs to prevent duplicate content
Disallow: /*?sort=
Disallow: /*?filter=
Disallow: /*?page=
Disallow: /*?ref=
Disallow: /*?utm_

# Allow specific bots with full access
User-agent: Googlebot
Allow: /
Crawl-delay: 0

User-agent: Googlebot-Image
Allow: /

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

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: facebot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# AI Search & Discovery Bots (Allowed for AEO - AI Engine Optimization)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Block aggressive content scrapers (not search/discovery)
User-agent: CCBot
Disallow: /

# Block aggressive/malicious bots
User-agent: AhrefsBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Host directive
Host: https://zenocloud.io