# The Samosa Shop Robots.txt
# Last updated: 2025-11-20

# Main directives for all search engine bots
User-agent: *
Allow: /

# Disallow admin and system directories
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/

# Disallow query parameters
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# Noindex for llms.txt (for search engines only, AI crawlers should still access it)
Disallow: /llms.txt

# AI Bot specific directives
# AI crawlers CAN access llms.txt and all content
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Google-Extended
User-agent: GoogleOther
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: PerplexityBot
User-agent: Omgilibot
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Google Ads Bot
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# Bing Ads Bot
User-agent: adidxbot
Allow: /

# Sitemap location
Sitemap: https://www.thesamosashop.online/sitemap.xml

# Crawl delay for heavy bots
User-agent: Baiduspider
Crawl-delay: 10

User-agent: Yandex
Crawl-delay: 5

# Block aggressive crawlers
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: dotbot
Disallow: /