Block AI crawlers

robots.txt файл

# I know this can just be _totally_ ignored by crawlers
# But let's hope they behave well :)
# Code: https://github.com/ellie/notes
# Source: https://darkvisitors.com/
# OpenAI, ChatGPT
# https://platform.openai.com/docs/gptbot
User-agent: GPTBot
Disallow: /
# Google AI (Bard, etc)
# https://developers.google.com/search/docs/crawling-indexing/overview-google-crawlers
User-agent: Google-Extended
Disallow: /
# Block common crawl
# I have mixed feelings on this one, but many models are trained on this data
# It is also used to bootstrap new search indices though
# https://commoncrawl.org/ccbot
User-agent: CCBot
Disallow: /
# Facebook
# https://developers.facebook.com/docs/sharing/bot/
User-agent: FacebookBot
Disallow: /
# Cohere.ai
# https://darkvisitors.com/agents/cohere-ai
User-agent: cohere-ai
Disallow: /
# Perplexity
# https://docs.perplexity.ai/docs/perplexitybot
User-agent: PerplexityBot
Disallow: /
# Anthropic
# https://darkvisitors.com/agents/anthropic-ai
User-agent: anthropic-ai
Disallow: /
# ...also anthropic
# https://darkvisitors.com/agents/claudebot
User-agent: ClaudeBot
Disallow: /

источник

Sitemap: https://coryd.dev/sitemap.xml

User-agent: *
Disallow:

User-agent: AdsBot-Google
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot
User-agent: AwarioRssBot
User-agent: AwarioSmartBot
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: cohere-ai
User-agent: DataForSeoBot
User-agent: Diffbot
User-agent: FacebookBot
User-agent: FriendlyCrawler
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: GPTBot
User-agent: img2dataset
User-agent: ImagesiftBot
User-agent: magpie-crawler
User-agent: Meltwater
User-agent: omgili
User-agent: omgilibot
User-agent: peer39_crawler
User-agent: peer39_crawler/1.0
User-agent: PerplexityBot
User-agent: PiplBot
User-agent: scoop.it
User-agent: Seekr
User-agent: YouBot
Disallow: /