# Robots.txt for jamesdev.in
# Updated: 2025-01-28
# Purpose: Optimize search engine crawling and indexing

# Allow all search engines to crawl the entire site
User-agent: *
Allow: /

# Sitemap location for search engines
Sitemap: https://jamesdev.in/sitemap.xml

# Crawl delay to prevent server overload (optional)
Crawl-delay: 1

# Block access to sensitive or unnecessary files/directories
Disallow: /admin/
Disallow: /private/
Disallow: /temp/
Disallow: /cache/
Disallow: /.git/
Disallow: /.vscode/
Disallow: /node_modules/
Disallow: /backup/
Disallow: /logs/

# Block access to specific file types that shouldn't be indexed
Disallow: /*.log$
Disallow: /*.tmp$
Disallow: /*.bak$
Disallow: /*.old$
Disallow: /*.zip$
Disallow: /*.tar$
Disallow: /*.gz$

# Allow important static files
Allow: /images/
Allow: /uploads/
Allow: /css/
Allow: /js/
# Allow: /fonts/ (removed - using Google Fonts)
Allow: /*.css$
Allow: /*.js$
Allow: /*.png$
Allow: /*.jpg$
Allow: /*.jpeg$
Allow: /*.gif$
Allow: /*.svg$
Allow: /*.webp$
Allow: /*.ico$
Allow: /*.woff$
Allow: /*.woff2$
Allow: /*.ttf$
Allow: /*.eot$

# Special rules for specific bots (if needed)
# Google Bot - Allow everything (default behavior)
User-agent: Googlebot
Allow: /

# Bing Bot - Allow everything
User-agent: Bingbot
Allow: /

# Social Media Crawlers
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Block malicious or unwanted bots (optional)
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Host directive (helps with canonical URL)
Host: https://jamesdev.in