User-agent: *
Allow: /

# High-value content (canonical URLs without .html)
Allow: /verse/
Allow: /chapter/
Allow: /questions/
Allow: /gita-verses-about/
Allow: /blog/

# Block .html versions (redirect to clean URLs)
# These are handled by Vercel cleanUrls but explicitly block for crawlers
Disallow: /*.html$
Disallow: /verse/*.html
Disallow: /chapter/*.html
Disallow: /questions/*.html
Disallow: /blog/*.html
Disallow: /gita-verses-about/*.html
Disallow: /aeo/*.html
Disallow: /aeo-batch2/*.html

# Block deprecated URL patterns (redirected in vercel.json)
Disallow: /topics/
Disallow: /verses/
Disallow: /chapters$
Disallow: /chapters.html

# Prevent indexing of admin/test files
Disallow: /reports/
Disallow: /scripts/
Disallow: /*.md$
Disallow: /*.json$
Disallow: /ab-tests-config.json
Disallow: /audit-report*.json
Disallow: /minimal-deploy/
Disallow: /backups/
Disallow: /node_modules/
Disallow: /backup/
Disallow: /*-backup*
Disallow: /data/

# Sitemaps
Sitemap: https://www.srimadgita.com/sitemap.xml
Sitemap: https://www.srimadgita.com/sitemap-index.xml
Sitemap: https://www.srimadgita.com/aeo-questions/aeo-sitemap.xml
Sitemap: https://www.srimadgita.com/aeo-batch2/aeo-batch2-sitemap.xml

# AI Crawler Directives — Allow full site access
User-agent: GPTBot
Allow: /
Crawl-delay: 1

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /