# robots.txt for InsideTheStar.com
# Last updated: September 2025

# Allow all major search engines
User-agent: *
Allow: /
Crawl-delay: 1

User-agent: *
Disallow: /*blackhole
Disallow: /?blackhole

# Specific rules for Googlebot
User-agent: Googlebot
Allow: /
Crawl-delay: 0

# Specific rules for Bingbot
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# Block bad bots and scrapers
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Protect sensitive directories
User-agent: *
Disallow: /admin/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-login.php
Disallow: /wp-config.php
Disallow: /private/
Disallow: /config/
Disallow: /tmp/
Disallow: /cache/

# Block access to specific file types
User-agent: *
Disallow: /*.sql$
Disallow: /*.log$
Disallow: /*.bak$
Disallow: /*.zip$
Disallow: /*.tar$
Disallow: /*.gz$

# Allow access to public JSON feeds
User-agent: *
Allow: /feed/json*
Allow: /feeds/*.json$
Allow: /api/*.json$

# Allow access to CSS and JS files for rendering
User-agent: *
Allow: /*.css$
Allow: /*.js$
Allow: /images/
Allow: /media/

# Prevent crawling of duplicate content
User-agent: *
Disallow: /tag/
Disallow: /category/
Disallow: /page/
Disallow: /*?*
Disallow: /*?print=
Disallow: /*&print=
Disallow: /search/
Disallow: /rss/
Disallow: /trackback/

# Sitemap location
Sitemap: https://insidethestar.com/wp-sitemap.xml
Sitemap: https://insidethestar.com/sitemap-news.xml