# Middlehost Robots.txt
# https://middlehost.com

# Allow all crawlers
User-agent: *
Allow: /

# Block internal/utility paths
Disallow: /api/
Disallow: /libs/
Disallow: /js/
Disallow: /*.css$
Disallow: /*.js$

# Block duplicate pagination beyond page 3 (keep initial pages for discoverability)
Disallow: /blog/page/4/
Disallow: /blog/page/5/
Disallow: /en-PK/blog/page/4/
Disallow: /en-PK/blog/page/5/
Disallow: /en-AE/blog/page/4/
Disallow: /en-AE/blog/page/5/



# Sitemaps and AI resources
Sitemap: https://middlehost.com/sitemap.xml
# AI/LLM-friendly: https://middlehost.com/ai.txt https://middlehost.com/llms.txt

# GPTBot (OpenAI)
User-agent: GPTBot
Allow: /

# Google-Extended (Bard/Gemini training)
User-agent: Google-Extended
Allow: /

# CCBot (Common Crawl)
User-agent: CCBot
Allow: /

# Anthropic Claude
User-agent: anthropic-ai
Allow: /
User-agent: Claude-Web
Allow: /