# robots.txt for AegisSight UG — wird am Tag X als robots.txt aktiv geschaltet
# Allgemein: Crawling erlaubt, außer API-Endpunkte und interne Pfade

User-agent: *
Allow: /
Disallow: /api/
Disallow: /_archiv/
Disallow: /vorschau/

# Sitemap
Sitemap: https://aegis-sight.de/sitemap.xml

# AI-Crawler explizit blocken — keine Trainingsdaten-Verwendung
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Archiv-Bots blocken
User-agent: ia_archiver
Disallow: /

User-agent: Wayback Machine
Disallow: /

User-agent: archive.org_bot
Disallow: /

# SEO-/Spam-Crawler blocken
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: SEOkicks-Robot
Disallow: /

User-agent: MauiBot
Disallow: /

User-agent: Majestic-12
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SerendeputyBot
Disallow: /

# Download-Manager blocken
User-agent: HTTrack
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebCopier
Disallow: /
