58 lines
1.1 KiB
Text
58 lines
1.1 KiB
Text
# No AI companies please
|
|
User-agent: GPTBot
|
|
Disallow: /
|
|
|
|
User-agent: ChatGPT-User
|
|
Disallow: /
|
|
|
|
User-agent: ClaudeBot
|
|
Disallow: /
|
|
|
|
User-agent: Google-Extended
|
|
Disallow: /
|
|
|
|
User-agent: CCBot
|
|
Disallow: /
|
|
|
|
User-agent: PerplexityBot
|
|
Disallow: /
|
|
|
|
User-agent: Diffbot
|
|
Disallow: /
|
|
|
|
# Facebook https://developers.facebook.com/docs/sharing/webmasters/web-crawlers
|
|
|
|
User-agent: meta-externalfetcher
|
|
Disallow: /
|
|
|
|
# Apple doesn't distinguish a crawler specifically for their LLM if they ever make one and I don't care abou Siri results
|
|
User-agent: Applebot
|
|
Disallow: /
|
|
|
|
# Other fun things I wanna block which I found from https://www.cyberciti.biz/web-developer/block-openai-bard-bing-ai-crawler-bots-using-robots-txt-file/
|
|
|
|
User-agent: Omgilibot
|
|
Disallow: /
|
|
|
|
User-agent: Omgili
|
|
Disallow: /
|
|
|
|
# Will probably be ignored but might as well
|
|
User-agent: Bytespider
|
|
Disallow: /
|
|
|
|
User-agent: Amazonbot
|
|
Disallow: /
|
|
|
|
User-agent: ImagesiftBot
|
|
Disallow: /
|
|
|
|
User-agent: YouBot
|
|
Disallow: /
|
|
|
|
# https://marginalia-search.com/ it's a search engine so it's fine
|
|
User-Agent: search.marginalia.nu
|
|
Allow: /
|
|
# generic allowance for search engines and what not
|
|
User-Agent: *
|
|
Allow: /
|