#
# robots.txt – Shop-Buster.de
#
# Basis: Drupal Standard, erweitert um KI-Crawler-Opt-Out
#

User-agent: *
Crawl-delay: 10
# CSS, JS, Images (Erlaubnis für korrekte Darstellung)
Allow: /misc/*.css$
Allow: /misc/*.css?
Allow: /misc/*.js$
Allow: /misc/*.js?
Allow: /misc/*.gif
Allow: /misc/*.jpg
Allow: /misc/*.jpeg
Allow: /misc/*.png
Allow: /modules/*.css$
Allow: /modules/*.css?
Allow: /modules/*.js$
Allow: /modules/*.js?
Allow: /modules/*.gif
Allow: /modules/*.jpg
Allow: /modules/*.jpeg
Allow: /modules/*.png
Allow: /profiles/*.css$
Allow: /profiles/*.css?
Allow: /profiles/*.js$
Allow: /profiles/*.js?
Allow: /profiles/*.gif
Allow: /profiles/*.jpg
Allow: /profiles/*.jpeg
Allow: /profiles/*.png
Allow: /themes/*.css$
Allow: /themes/*.css?
Allow: /themes/*.js$
Allow: /themes/*.js?
Allow: /themes/*.gif
Allow: /themes/*.jpg
Allow: /themes/*.jpeg
Allow: /themes/*.png

# Geschützte Drupal-Verzeichnisse
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/

# Geschützte Dateien
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php

# Geschützte Pfade (Clean URLs)
Disallow: /admin/
Disallow: /comment/reply/
Disallow: /filter/tips/
Disallow: /node/add/
Disallow: /search/
Disallow: /user/register/
Disallow: /user/password/
Disallow: /user/login/
Disallow: /user/logout/

# Geschützte Pfade (No clean URLs)
Disallow: /?q=admin/
Disallow: /?q=comment/reply/
Disallow: /?q=filter/tips/
Disallow: /?q=node/add/
Disallow: /?q=search/
Disallow: /?q=user/password/
Disallow: /?q=user/register/
Disallow: /?q=user/login/
Disallow: /?q=user/logout/

# --- KI-Crawler blockieren (Opt-Out Training) ---
# OpenAI
User-agent: GPTBot
Disallow: /
User-agent: OAI-SearchBot
Disallow: /
User-agent: ChatGPT-User
Disallow: /

# Google AI (Gemini)
User-agent: Google-Extended
Disallow: /

# Anthropic (Claude)
User-agent: ClaudeBot
Disallow: /
User-agent: Claude-User
Disallow: /
User-agent: Claude-SearchBot
Disallow: /

# Apple AI
User-agent: Applebot-Extended
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /
User-agent: Perplexity-User
Disallow: /

# Common Crawl (oft für Trainingsdaten)
User-agent: CCBot
Disallow: /

# ByteDance/TikTok
User-agent: Bytespider
Disallow: /

# Empfehlung: Schonung Server
Crawl-delay: 1