# Seven Sisters Motel & Restaurant — robots.txt
# https://www.sevensistersmb.ca/
# 63004 Manitoba 307, Seven Sisters Falls, MB R0E 1Y0

# ---------- All crawlers ----------
User-agent: *
Allow: /
Disallow: /components/
Disallow: /assets/favicon/
Disallow: /.github/
Disallow: /.vscode/
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=
Disallow: /*?*author=
Disallow: /*?*tag=
Disallow: /*?*month=
Disallow: /*?*view=
Disallow: /*?*format=
Disallow: /*?*replytocom=

# ---------- AI / LLM crawlers ----------
# Content is open to AI agents; only the legal boilerplate is withheld.
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: Claude-Web
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: Bytespider
User-agent: CCBot
User-agent: cohere-ai
User-agent: Amazonbot
User-agent: DuckAssistBot
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

# ---------- Indexing directives ----------
# llms.txt is an agent-readable summary, not a page for search results.
# It stays crawlable on purpose (AI agents must be able to fetch it),
# but it should not appear in search results.
Noindex: /llms.txt

# NOTE: `Noindex` in robots.txt is a non-standard directive and is no
# longer honoured by Google. The reliable way to keep /llms.txt out of
# the index is an HTTP response header from the web server, e.g.
#
#   Apache (.htaccess):
#     <Files "llms.txt">
#       Header set X-Robots-Tag "noindex"
#     </Files>
#
#   Nginx:
#     location = /llms.txt { add_header X-Robots-Tag "noindex"; }
#
#   Netlify (netlify.toml):
#     [[headers]]
#       for = "/llms.txt"
#       [headers.values]
#         X-Robots-Tag = "noindex"

# ---------- Sitemap ----------
Sitemap: https://www.sevensistersmb.ca/sitemap.xml