# Foodies Calgary - robots.txt
# Halal Pakistani & Indian (Desi) Restaurant
# 7 Westwinds Crescent NE, Calgary, AB T3J 5H2
# https://foodiescalgary.ca

# ==========================================
# Default directives for all crawlers
# ==========================================
User-agent: *
Allow: /
Allow: /tags/
Allow: /tags/dishes/
Allow: /tags/places/
Allow: /assets/

# Non-content / infrastructure paths
Disallow: /components/
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Disallow: /cgi-bin/

# Parameterised & duplicate URLs
Disallow: /*?*author=
Disallow: /*?*tag=
Disallow: /*?*month=
Disallow: /*?*view=
Disallow: /*?*format=
Disallow: /*?*replytocom=
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=

# Machine-readable site summary: crawlable by AI agents, not for search results.
# Google no longer honours the non-standard `Noindex:` directive in robots.txt —
# for a static site, complement this with `X-Robots-Tag: noindex` at the CDN /
# host layer (e.g. Netlify `_headers`, Cloudflare Pages `_headers`, or Apache
# `.htaccess`) for `/llms.txt`.
Noindex: /llms.txt

# ==========================================
# AI / LLM crawlers - full content access
# ==========================================
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Bytespider
User-agent: CCBot
User-agent: cohere-ai
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
Allow: /
Allow: /llms.txt
Disallow: /components/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ==========================================
# Ads crawlers - required for landing page quality
# ==========================================
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ==========================================
# Image crawlers - dish & gallery photography
# ==========================================
User-agent: Googlebot-Image
Allow: /assets/

# ==========================================
# Crawl-rate limits for aggressive bots
# ==========================================
User-agent: Baiduspider
Crawl-delay: 10

User-agent: YandexBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: AhrefsBot
Crawl-delay: 10

# ==========================================
# Sitemap
# ==========================================
Sitemap: https://foodiescalgary.ca/sitemap.xml