# dr-hughes.uk
# I'm happy for my materials to be used, but please don't scrape this site:
# I pay for it personally. Downloads are for humans. See https://dr-hughes.uk/llms/

# AI training and bulk-collection crawlers: please stay out entirely.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: CCBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: PerplexityBot
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Diffbot
User-agent: Omgilibot
User-agent: ImagesiftBot
User-agent: Timpibot
User-agent: AI2Bot
User-agent: PetalBot
Disallow: /

# Everyone else (search engines, and assistants fetching a page because a person
# asked): pages are fine, but not the slide decks, the apps' assets or the API.
User-agent: *
Content-Signal: search=yes, ai-train=no
Disallow: /slides/
Disallow: /teaching/pyodle/assets/
Disallow: /teaching/quizzle/assets/
Disallow: /api/
Allow: /