stephan.hadan.de/docs/robots.txt

38 lines
No EOL
928 B
Text

# Humans and normal search engines are allowed to read/index
User-agent: *
Disallow: /cv/
# But we don't feed into the AI/ML hype here. Stop wasting the planet's resources.
User-agent: CCbot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: FacebookBot
User-agent: Meta-ExternalFetcher
User-agent: Meta-ExternalAgent
User-agent: Google-Extended
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: PiplBot
User-agent: PerplexityBot
User-agent: Omgilibot
User-Agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Bytespider
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: Omgili
User-agent: YouBot
User-agent: Ai2Bot
User-agent: Ai2Bot-Dolma
User-agent: FriendlyCrawler
User-agent: Scrapy
User-agent: Timpibot
User-agent: PetalBot
User-agent: img2dataset
User-agent: AhrefsBot
Disallow: /
Sitemap: https://stephan.hadan.de/sitemap.xml