# Stand: 2026-09-25
#
# ==============================================================================
# CONTENT SIGNALS & EU DSM DIRECTIVE (URHEBERRECHTLICHER NUTZUNGSVORBEHALT)
#
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.
# ==============================================================================

# ==============================================================================
# 1. Allgemeine Suchmaschinen (Google, Bing etc.)
# ==============================================================================
User-agent: *
Content-signal: search=yes, ai-train=no, ai-input=no, use=reference
Allow: /

# Diese Einträge prüfen/löschen, falls der Shop live indexiert werden soll:
Disallow: /anzeigen-upload-pdf
Disallow: /shop/*

# Obility-Software & Skripte
Disallow: /cgi-bin/

# Generische Maskenaufrufe & interne Rewrite-Pfade
Disallow: /html_aufruf/
Disallow: /ops42_*
Disallow: /shop_*

# Consent-Management (Klaro) nicht crawlen
Disallow: /klaro.js
Disallow: /klaro.tdp.css
Disallow: /klaro.tdp.js

# PDF-Dateien (z. B. Widerrufsformulare) ausschließen
Disallow: /*.pdf$

# Sensible Kundenbilder / Uploads (Schutz vor Indexierung)
Disallow: /r50/obility/bilder/firma417/kunden/

# ==============================================================================
# 2. KI-Scraper & LLM-Crawler blockieren (Data Scraping & Model Training)
# ==============================================================================
User-agent: Amazonbot
User-agent: anthropic-ai
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: CCBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Cohere-ai
User-agent: Diffbot
User-agent: FacebookBot
User-agent: Google-Extended
User-agent: GPTBot
User-agent: meta-externalagent
User-agent: Omegabot
User-agent: PerplexityBot
Disallow: /

# ==============================================================================
# 3. Aggressive SEO- & Backlink-Crawler blockieren (Serverlast minimieren)
# ==============================================================================
User-agent: AhrefsBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: DotBot
User-agent: MegaIndex
User-agent: MJ12bot
User-agent: PetalBot
User-agent: Rogerbot
User-agent: SemrushBot
Disallow: /

# ==============================================================================
# 4. Content-Harvester / Scraper
# ==============================================================================
User-agent: LinkpadBot
User-agent: SeekportBot
User-agent: spbot
User-agent: ZoominfoBot
Disallow: /

# ==============================================================================
# XML-Sitemap
# ==============================================================================
Sitemap: https://www.trauerdruckportal.de/sitemap.xml