# Robots.txt for https://www.via-health.de/
# Webflow Website - Health Services
# Last updated: November 2025

# Allow all legitimate search engine bots by default
User-agent: *
Allow: /

# Block specific privacy software page
Disallow: /datenschutz-software

# Block Webflow-specific system pages
Disallow: /401
Disallow: /404
Disallow: /401.html
Disallow: /404.html
Disallow: /password
Disallow: /search

# Block form submission endpoints
Disallow: /form-success

# Block utility pages that might exist
Disallow: /unsubscribe
Disallow: /email-preferences
Disallow: /api/

# Block search and filter parameters to avoid duplicate content
Disallow: /*?category=
Disallow: /*?filter=
Disallow: /*?sort=
Disallow: /*?page=
Disallow: /*?ref=
Disallow: /*?utm

# Block any test or staging subdirectories
Disallow: /test/
Disallow: /staging/
Disallow: /draft/
Disallow: /temp/

# Prevent indexing of documents (if we host any directly)
Disallow: /*.pdf$
Disallow: /*.doc$
Disallow: /*.docx$
Disallow: /*.xls$
Disallow: /*.xlsx$

# Specific rules for major search engines
User-agent: Googlebot
Allow: /
Allow: /*.css
Allow: /*.js
Crawl-delay: 0

User-agent: Bingbot
Allow: /
Allow: /*.css
Allow: /*.js
Crawl-delay: 0

# Block aggressive SEO bots
User-agent: AhrefsBot
Disallow: /

User-agent: SEMrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: Rogerbot
Disallow: /

# Sitemap location (Webflow auto-generates this)
Sitemap: https://www.via-health.de/sitemap.xml

Sitemap: https://www.via-health.de/sitemap.xml