# robots.txt — 5 O’clock Cafe And Lounge
# Site: https://5oclockcafe.ca
# Updated: 2026-07-28
#
# NOTE ON /llms.txt
#   /llms.txt is intentionally CRAWLABLE by everyone, including Googlebot and
#   Bingbot. It is kept OUT of search results with an HTTP response header
#   (X-Robots-Tag: noindex) rather than with a Disallow rule here — see the
#   _headers file in this repo.
#
#   This is deliberate: "Disallow" blocks crawling, it does NOT mean noindex.
#   A blocked URL can still be indexed (URL-only) if something links to it, and
#   a crawler that is blocked can never read the noindex header. Allowing the
#   fetch is what lets Google and Bing see the noindex and honour it, while AI
#   agents — which do not act on X-Robots-Tag — can still read the file.
#
#   The old "Noindex:" robots.txt directive is NOT used here: Google stopped
#   supporting it in September 2019 and it was never part of the standard.

# ---------------------------------------------
# Default policy — all crawlers
# ---------------------------------------------
User-agent: *
Allow: /

# Internal files that should not be surfaced to crawlers.
# ("Store Information.txt" is percent-encoded — robots.txt paths cannot
#  contain literal spaces.)
Disallow: /Store%20Information.txt
Disallow: /update-menu.js

# Deliberately NOT disallowed, because blocking these would break rendering:
#   /components/   header & footer fragments fetched at runtime by components.js
#   /menu.js       menu data required to render the menu page
#   /script.js  /components.js  /style.css  /global.css  /assets/

# ---------------------------------------------
# AI / LLM crawlers
# Full access, including /llms.txt. Legal pages are withheld.
# ---------------------------------------------
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-Web
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: CCBot
User-agent: cohere-ai
User-agent: FacebookBot
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: Bytespider
User-agent: Amazonbot
User-agent: DuckAssistBot
User-agent: MistralAI-User
Allow: /
Allow: /llms.txt
Disallow: /Store%20Information.txt
Disallow: /update-menu.js
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# ---------------------------------------------
# Google Ads crawlers — must reach landing pages
# ---------------------------------------------
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# ---------------------------------------------
# Rate limiting for heavy / low-value crawlers
# (Googlebot and Bingbot ignore Crawl-delay; manage those in Search Console
#  and Bing Webmaster Tools instead.)
# ---------------------------------------------
User-agent: Baiduspider
Crawl-delay: 10

User-agent: YandexBot
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 10

User-agent: AhrefsBot
Crawl-delay: 10

User-agent: MJ12bot
Crawl-delay: 10

# ---------------------------------------------
# FALLBACK ONLY — leave commented out.
# If the host cannot send an X-Robots-Tag header, uncomment this block to keep
# /llms.txt out of Google and Bing by blocking the crawl instead. Less correct
# than the header (see note at top), and it must not be used together with it.
# ---------------------------------------------
# User-agent: Googlebot
# Allow: /
# Disallow: /llms.txt
# Disallow: /Store%20Information.txt
# Disallow: /update-menu.js
#
# User-agent: Bingbot
# Allow: /
# Disallow: /llms.txt
# Disallow: /Store%20Information.txt
# Disallow: /update-menu.js

# ---------------------------------------------
# Sitemap
# ---------------------------------------------
Sitemap: https://5oclockcafe.ca/sitemap.xml