# robots.txt for greektranscoder.org
# Academic website - allow indexing, block AI training crawlers

# Block AI training crawlers
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

# Allow all other crawlers (standard search engines)
User-agent: *
Allow: /
Disallow: /_test_/

# Sitemap location
Sitemap: https://www.greektranscoder.org/sitemap_index.xml