# Search engines are welcome. Crawlers that exist to feed model training are
# not, and are refused below by name. See /LICENSE.txt
#
# This file is a request, not a fence. Well-behaved crawlers honour it;
# anything that ignores robots.txt will ignore this too.

User-agent: *
Allow: /

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Google -- Search still indexes; this is the training/Gemini opt-out
User-agent: Google-Extended
Disallow: /

# Apple -- Search still indexes; this is the training opt-out
User-agent: Applebot-Extended
Disallow: /

# Meta
User-agent: meta-externalagent
Disallow: /

User-agent: FacebookBot
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

# Common Crawl -- the corpus much of the rest is trained from
User-agent: CCBot
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

# ByteDance
User-agent: Bytespider
Disallow: /

# Allen Institute
User-agent: AI2Bot
Disallow: /

User-agent: Ai2Bot-Dolma
Disallow: /

# Others
User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

Sitemap: https://cat.flairr.com/sitemap.xml