# Globale Einstellungen für reguläre Crawler
User-agent: *
Allow: /

User-agent: *
Disallow: /*.pdf$

# https://github.com/ai-robots-txt/ai.robots.txt/blob/main/robots.txt

# KI und ML Crawler Blocking
# Große KI-Modelle
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: cohere-ai
User-agent: PerplexityBot
Disallow: /

# Suchmaschinen-KI und erweiterte Crawler
User-agent: GoogleOther
User-agent: Google-Extended
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Webzio-Extended
Disallow: /

# KI Training und Datenssammlung
User-agent: AI2Bot
User-agent: Ai2Bot-Dolma
User-agent: CCBot
User-agent: Diffbot
User-agent: img2dataset
User-agent: ImagesiftBot
Disallow: /

# Social Media und Marketing Bots
User-agent: FacebookBot
User-agent: facebookexternalhit
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Bytespider
Disallow: /

# Weitere spezialisierte Crawler
User-agent: Scrapy
User-agent: PetalBot
User-agent: omgili
User-agent: omgilibot
User-agent: YouBot
User-agent: ICC-Crawler
User-agent: ISSCyberRiskCrawler
User-agent: Sidetrade
User-agent: Timpibot
User-agent: VelenPublicWebCrawler
User-agent: Kangaroo
Disallow: /

# Amazon Crawler
User-agent: Amazonbot
Disallow: /

# Sitemap Definition
Sitemap: https://phlow.de/sitemap.xml