# Mar's Sisig – Filipino Restaurant, Winnipeg MB – robots.txt
# Site: https://www.mars-sisig.ca/
# Last Updated: 2026-08-25

# ---- Default rules for all crawlers ----
# llms.txt is intentionally NOT blocked here so AI agents and other
# well-behaved bots can read it.
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /config/
Disallow: /search/
Disallow: /api/
Disallow: /static/
Disallow: /logs/
Disallow: /*?*
Disallow: /*&*
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Disallow: /Store%20Information.txt
Disallow: /Store*Information.txt
Disallow: /ReadMe.txt
Disallow: /update-menu.js
Disallow: /*.md$

# ---- Search engines: keep llms.txt out of the search index ----
# llms.txt is intended for LLM/AI agents only and must not appear in
# Google/Bing search results. Disallow blocks crawling; the Noindex line
# below is advisory (Bing honours it, Google no longer does). For full
# noindex enforcement, also set an "X-Robots-Tag: noindex" response header
# for /llms.txt at the hosting layer — this affects search engines only,
# AI agents fetching llms.txt directly are unaffected.
#
# Example (Netlify _headers):   /llms.txt
#                                 X-Robots-Tag: noindex
# Example (Apache .htaccess):   <Files "llms.txt">
#                                 Header set X-Robots-Tag "noindex"
#                               </Files>
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
Allow: /
Disallow: /admin/
Disallow: /config/
Disallow: /search/
Disallow: /api/
Disallow: /static/
Disallow: /logs/
Disallow: /*?*
Disallow: /*&*
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Disallow: /Store%20Information.txt
Disallow: /Store*Information.txt
Disallow: /ReadMe.txt
Disallow: /update-menu.js
Disallow: /*.md$
Disallow: /llms.txt
Noindex: /llms.txt

# ---- AI / LLM training & crawler bots: full access including llms.txt ----
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: cohere-ai
User-agent: FacebookBot
User-agent: meta-externalagent
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Amazonbot
User-agent: MistralAI-User
User-agent: DuckAssistBot
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html
Disallow: /Store%20Information.txt
Disallow: /Store*Information.txt
Disallow: /ReadMe.txt

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

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

User-agent: Yandex
Crawl-delay: 10

# ---- Sitemap ----
Sitemap: https://www.mars-sisig.ca/sitemap.xml