# Heloix Robots.txt - Generated on 2025-11-24T19:10:19.958Z
# Website: https://heloix.com
# 
# This file tells search engine crawlers which URLs they can access on this site.
# For more information about robots.txt, visit: https://www.robotstxt.org/

# Global rules for all user agents
User-agent: *

# Allow crawling of main content areas
Allow: /
Allow: /shop
Allow: /product/
Allow: /category/
Allow: /blog/
Allow: /bundles
Allow: /compare
Allow: /about
Allow: /contact
Allow: /support
Allow: /careers
Allow: /press
Allow: /security
Allow: /compare-alternatives
Allow: /resources
Allow: /webinars
Allow: /consultation
Allow: /sustainability
Allow: /investor-relations
Allow: /roadmap
Allow: /academy
Allow: /community
Allow: /case-studies
Allow: /request-quote
Allow: /roi-calculator
Allow: /reseller-program
Allow: /affiliate-program
Allow: /privacy-policy

# Disallow admin and dashboard areas
Disallow: /admin/
Disallow: /dashboard/
Disallow: /api/
Disallow: /_next/
Disallow: /onboarding/

# Disallow user-specific pages
Disallow: /cart
Disallow: /checkout
Disallow: /wishlist
Disallow: /addons
Disallow: /order-confirmation
Disallow: /auth/

# Disallow utility and maintenance pages
Disallow: /500
Disallow: /maintenance

# Disallow search and dynamic pages with parameters
Disallow: /search?*
Disallow: /*?utm_*
Disallow: /*?ref=*
Disallow: /*?source=*
Disallow: /*?campaign=*

# Disallow file types that shouldn't be indexed
Disallow: /*.json$
Disallow: /*.xml$
Disallow: /*.txt$
Disallow: /*.log$
Disallow: /*.env$
Disallow: /*.config$

# Allow CSS and JS for better rendering in search results
Allow: /css/
Allow: /js/
Allow: /_next/static/
Allow: /images/
Allow: /uploads/

# Specific rules for different bots
User-agent: Googlebot
Allow: /

User-agent: Bingbot  
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# Block known bad bots and scrapers
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# Block AI training bots (optional - you may want to allow these)
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Crawl delay for respectful crawling (in seconds)
Crawl-delay: 1

# Sitemap locations
Sitemap: https://heloix.com/sitemap.xml

# Host directive (helps with canonicalization)
Host: https://heloix.com

# Additional notes:
# - This robots.txt follows best practices for SaaS/e-commerce platforms
# - Admin and user-specific areas are blocked to protect privacy
# - Static assets are allowed for better search result rendering  
# - Known scraping bots are blocked to preserve server resources
# - Crawl delay is set to be respectful to server resources
# - Multiple sitemaps can be added as the site grows

# Last updated: 2025-11-24T19:10:19.958Z