# robots.txt — Indian Spice Route | Indian & Hakka Chinese Cuisine
# 5026 Centre St, Niagara Falls, ON L2G 3N7
# https://indianspicerouteniagara.com/

# ------------------------------------------------------------------
# All crawlers
# ------------------------------------------------------------------
User-agent: *
Allow: /

# Keep rendering resources crawlable — blocking these breaks how
# Google sees the page (header/footer are injected by components.js).
Allow: /assets/
Allow: /components/
Allow: /*.css$
Allow: /*.js$
Allow: /*.webp$
Allow: /*.svg$

# Never useful in an index: tracking / preview query strings
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=
Disallow: /*?*preview=
Disallow: /*?*replace-state=

# llms.txt is written for AI agents, not for search results.
# It stays crawlable; it just should not be indexed as a page.
Noindex: /llms.txt

# ------------------------------------------------------------------
# AI assistants & answer engines — welcome to read the whole site
# so answers about our menu, hours and delivery areas are accurate.
# ------------------------------------------------------------------
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: CCBot
User-agent: cohere-ai
User-agent: YouBot
Allow: /
Allow: /llms.txt

# Boilerplate legal text adds nothing to an AI answer
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ------------------------------------------------------------------
# Ad crawlers — must reach landing pages for quality scoring
# ------------------------------------------------------------------
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ------------------------------------------------------------------
# Heavy / low-value crawlers — throttled
# ------------------------------------------------------------------
User-agent: Baiduspider
Crawl-delay: 10

User-agent: Bytespider
Crawl-delay: 10

# ------------------------------------------------------------------
# Sitemap
# ------------------------------------------------------------------
Sitemap: https://indianspicerouteniagara.com/sitemap.xml