2024-06-14 03:55:38 +00:00
|
|
|
# Google AI
|
|
|
|
|
User-agent: Google-Extended
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# Google
|
2024-06-28 13:58:49 +00:00
|
|
|
#User-agent: Googlebot
|
|
|
|
|
#Disallow: /
|
2024-06-14 03:55:38 +00:00
|
|
|
|
|
|
|
|
User-agent: GoogleOther
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Googlebot-Image
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: AdsBot-Google
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# Bing
|
2024-06-28 13:58:49 +00:00
|
|
|
#User-agent: bingbot
|
|
|
|
|
#Disallow: /
|
2024-06-14 03:55:38 +00:00
|
|
|
|
|
|
|
|
# Common Crawl
|
|
|
|
|
User-agent: CCBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# OpenAI
|
|
|
|
|
User-agent: ChatGPT-User
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: ChatGPT
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: GPTBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# Omgili
|
|
|
|
|
User-agent: Omgilibot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Omgili
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# Facebook AI
|
|
|
|
|
User-agent: FacebookBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Claude-Web
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: ClaudeBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# Other AI training known or suspected
|
|
|
|
|
User-agent: anthropic-ai
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: PerplexityBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Bytespider
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: The Knowledge AI
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: aiHitBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: cohere-ai
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Diffbot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: YouBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: ImagesiftBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# Siri and Alexa yuck
|
|
|
|
|
User-agent: Amazonbot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Applebot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
# Miscellaneous
|
|
|
|
|
User-agent: TurnitinBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: NPBot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: SlySearch
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: 360Spider
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: netEstate NE Crawler
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
User-agent: Pinterestbot
|
|
|
|
|
Disallow: /
|
|
|
|
|
|
|
|
|
|
Sitemap: https://www.thepaperpilot.org/sitemap.xml
|
