# tresorrari.de crawler policy
# Default: Disallow. Allow: grosse Suchmaschinen, grosse AI, Link-Vorschau.
# TDM reserved (§ 44b UrhG / DSM Art. 4). Policy: /nutzung#tdm
# Wir drosseln Google nicht. Der Host hat Kapazitaet.
# Liste: server/lib/crawler-policy.js

# --- Suchmaschinen ---
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: Googlebot-Video
User-agent: Storebot-Google
User-agent: Google-InspectionTool
User-agent: GoogleOther
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: Mediapartners-Google
User-agent: Bingbot
User-agent: AdIdxBot
User-agent: MicrosoftPreview
User-agent: BingPreview
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: YandexBot
User-agent: YandexImages
Allow: /
Disallow: /hackend
Disallow: /assets/brand/
Disallow: /api/
Disallow: /__trap

# --- Grosse AI-Systeme ---
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Google-CloudVertexBot
User-agent: Applebot-Extended
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Amazonbot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: YouBot
User-agent: GrokBot
User-agent: xAI-Grok
Allow: /
Disallow: /hackend
Disallow: /assets/brand/
Disallow: /api/
Disallow: /__trap

# --- Link-Vorschau (OG-Karten, kein Index) ---
User-agent: facebookexternalhit
User-agent: Facebot
User-agent: Twitterbot
User-agent: LinkedInBot
User-agent: Slackbot
User-agent: TelegramBot
User-agent: WhatsApp
User-agent: Discordbot
Allow: /
Disallow: /hackend
Disallow: /assets/brand/
Disallow: /api/
Disallow: /__trap

# --- Bekannte Scraper, explizit ---
User-agent: AhrefsBot
User-agent: AhrefsSiteAudit
User-agent: SemrushBot
User-agent: SplitSignalBot
User-agent: MJ12bot
User-agent: DotBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: PetalBot
User-agent: Bytespider
User-agent: CCBot
User-agent: ia_archiver
User-agent: magpie-crawler
User-agent: MegaIndex
User-agent: BUbiNG
User-agent: ZoominfoBot
User-agent: SeekportBot
User-agent: Seobility
User-agent: sistrix
User-agent: HTTrack
User-agent: Baiduspider
User-agent: Sogou
User-agent: YisouSpider
User-agent: MegaIndex.ru
Disallow: /

# --- Alle anderen ---
User-agent: *
Disallow: /

Sitemap: https://tresorrari.de/sitemap.xml