# robots.txt for https://www.gllm.ac.uk

Sitemap: https://www.gllm.ac.uk/sitemap.xml

# --- Block AI training / scraping bots ---

#User-agent: GPTBot
#Disallow: /

#User-agent: ChatGPT-User
#Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

# --- Default rules ---

User-agent: *
Disallow: /cpresources/
Disallow: /vendor/
Disallow: /.env
Disallow: /craft/
Disallow: /secretadmin
Disallow: /marketing
Disallow: /_temp
Disallow: /jobs/apply
Disallow: /cy/jobs/apply
Disallow: /jobs/internal
Disallow: /cy/jobs/internal
Disallow: /staff-induction
Disallow: /cy/staff-induction
Disallow: /tours
Disallow: /marketing-request