# robots.txt for Fundación Energisa de Honduras
# https://fundacionenergisa.org/robots.txt

User-agent: *
Allow: /

# Allow all search engines to crawl the entire site
Allow: /css/
Allow: /js/
Allow: /Images/
Allow: /icons/

# Disallow crawling of sensitive or unnecessary files
Disallow: /admin/
Disallow: /private/
Disallow: /.git/
Disallow: /node_modules/
Disallow: /*.log$
Disallow: /temp/
Disallow: /cache/

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Crawl-delay: 1

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

User-agent: Slurp
Allow: /
Crawl-delay: 2

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# AI Search Engine Crawlers (2025)
# Allow AI crawlers for LLM indexing and AI search engines
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: cohere-ai
Allow: /

# Block aggressive crawlers
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SemrushBot
Disallow: /

# Sitemap location
Sitemap: https://fundacionenergisa.org/sitemap.xml

# Host directive (for some search engines)
Host: https://fundacionenergisa.org