# robots.txt – hausarztpraxen-retten.de
# Ziel: maximale Sichtbarkeit für klassische Suchmaschinen (SEO)
# und für KI-/Answer-Engines (GEO). Standard-WordPress-Schutz für Backend.

# ----------------------------------------------------------------------
# Alle Crawler: Inhalte freigeben, nur Backend/Systempfade ausschließen
# ----------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /xmlrpc.php
Disallow: /?s=
Disallow: /search/
Disallow: /*?replytocom=

# ----------------------------------------------------------------------
# KI- / Answer-Engine-Crawler (GEO) – ausdrücklich erlaubt
# ----------------------------------------------------------------------

# OpenAI (ChatGPT / SearchGPT)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google (Gemini / AI Overviews – Opt-in über Google-Extended)
User-agent: Google-Extended
Allow: /

# Microsoft Bing / Copilot
User-agent: Bingbot
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (Trainingsdaten vieler KI-Modelle)
User-agent: CCBot
Allow: /

# Meta AI
User-agent: meta-externalagent
Allow: /

# ----------------------------------------------------------------------
# Sitemap & maschinenlesbare Inhaltsübersicht
# ----------------------------------------------------------------------
Sitemap: https://www.hausarztpraxen-retten.de/sitemap.xml