# Hi-Ball Restaurant | robots.txt
# 421 Academy Rd, Winnipeg, MB R3N 0C1 | https://www.Hi-BallRestaurant.ca/

# ---------------------------------------------------------------
# All crawlers
# ---------------------------------------------------------------
User-agent: *
Allow: /
Allow: /tags/
Allow: /assets/
Allow: /llms.txt

# Static site - no app directories to crawl, but block stray
# query-string variants so duplicate URLs are not indexed.
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*
Disallow: /*?*utm_*

# llms.txt is meant to be read by AI agents, not listed in search
# results. Crawling stays allowed above; indexing is refused here.
# (Pair with an "X-Robots-Tag: noindex" response header on /llms.txt
# at the server or CDN for full coverage.)
Noindex: /llms.txt

# ---------------------------------------------------------------
# AI / LLM crawlers - welcome to read the site and llms.txt
# ---------------------------------------------------------------
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: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: cohere-ai
User-agent: Bytespider
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: FacebookBot
Allow: /
Allow: /llms.txt
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ---------------------------------------------------------------
# Google Ads
# ---------------------------------------------------------------
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: YandexBot
Crawl-delay: 10

# ---------------------------------------------------------------
# Sitemap
# ---------------------------------------------------------------
Sitemap: https://www.Hi-BallRestaurant.ca/sitemap.xml