# Dancing Noodle Winnipeg — robots.txt
# https://dancingnoodle.ca

# ── General directives for all crawlers ──────────────────────────────────────
User-agent: *
Allow: /

# llms.txt is publicly readable by AI agents but should NOT be indexed
# as a search result. The noindex directive is applied via X-Robots-Tag
# in .htaccess (Apache) or equivalent server config.
Allow: /llms.txt

# Block legal pages from indexing (still accessible to users via footer links)
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Block URL parameters that don't produce unique content
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# ── AI crawlers — full access including llms.txt ──────────────────────────────
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: PerplexityBot
Allow: /

# ── Google Ads bots ───────────────────────────────────────────────────────────
User-agent: AdsBot-Google
Allow: /

User-agent: AdsBot-Google-Mobile
Allow: /

# ── Slow down aggressive crawlers ────────────────────────────────────────────
User-agent: Baiduspider
Crawl-delay: 10

User-agent: SemrushBot
Crawl-delay: 5

User-agent: AhrefsBot
Crawl-delay: 5

# ── Sitemap ───────────────────────────────────────────────────────────────────
Sitemap: https://dancingnoodle.ca/sitemap.xml