# Cafe Gulzar - robots.txt
# Pakistani cafe at 9332 34 Avenue NW, Edmonton, AB T6E 5T5

# Main directives for all bots
User-agent: *
Allow: /
Disallow: /components/
Disallow: /.github/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# AI crawlers (llms.txt is readable but should not be indexed in search results)
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: PerplexityBot
User-agent: Google-Extended
User-agent: CCBot
User-agent: cohere-ai
Allow: /
Allow: /llms.txt
Disallow: /components/
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

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

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

# Keep llms.txt out of search engine indexes (honoured by crawlers that support Noindex;
# for full enforcement also send an "X-Robots-Tag: noindex" header for /llms.txt on the host)
User-agent: *
Noindex: /llms.txt

# Sitemap location
Sitemap: https://www.cafegulzaryeg.ca/sitemap.xml