# NOTICE: The collection of content and other data on this
# site through automated means, including any device, tool,
# or process designed to data mine or scrape content, is
# prohibited except (1) for the purpose of search engine indexing or
# artificial intelligence retrieval augmented generation or (2) with express
# written permission from this site’s operator.

# To request permission to license our intellectual
# property and/or other materials, please contact this
# site’s operator directly.

# BEGIN Cloudflare Managed content

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

User-agent: *
Allow: /

# Allow all pages except API routes and internal Next.js files
Disallow: /api/
Disallow: /_next/
Disallow: /admin/
Disallow: /*.json$

# Allow specific important paths
Allow: /kalender-jawa/
Allow: /sitemap*.xml

# Sitemap index for comprehensive discovery
Sitemap: https://www.jawaku.id/sitemap-index.xml

# Additional sitemaps for specific content
Sitemap: https://www.jawaku.id/sitemap-static.xml
Sitemap: https://www.jawaku.id/sitemap-weton.xml
Sitemap: https://www.jawaku.id/sitemap-neptu.xml
Sitemap: https://www.jawaku.id/sitemap-weton-dates.xml

# Crawl-delay for respectful crawling
Crawl-delay: 1

# Host directive (helps with canonical domain)
Host: www.jawaku.id