# Mbarara Environmental Reporting System - Robots.txt
# Last updated: <?php echo date('Y-m-d'); ?>

User-agent: *
Allow: /

# Disallow access to sensitive directories
Disallow: /cron/
Disallow: /config/
Disallow: /includes/
Disallow: /vendor/
Disallow: /node_modules/

# Disallow access to admin area (if you want to hide from search engines)
Disallow: /pages/admin/

# Disallow access to user area (if you want to hide from search engines)
Disallow: /pages/user/

# Disallow access to auth pages
Disallow: /pages/auth/

# Disallow access to API
Disallow: /api/

# Disallow access to temporary files
Disallow: /tmp/
Disallow: /temp/

# Disallow access to backup files
Disallow: /*.bak$
Disallow: /*.old$
Disallow: /*.backup$

# Sitemap location
Sitemap: <?php echo (isset($_SERVER['HTTPS']) && $_SERVER['HTTPS'] === 'on' ? "https" : "http") . "://$_SERVER[HTTP_HOST]"; ?>/sitemap.xml

# Crawl delay (requests per second)
Crawl-delay: 1

# Specific rules for search engines

# Google
User-agent: Googlebot
Allow: /
Disallow: /cron/
Disallow: /config/
Disallow: /includes/
Crawl-delay: 0.5

# Bing
User-agent: bingbot
Allow: /
Disallow: /cron/
Disallow: /config/
Disallow: /includes/
Crawl-delay: 1

# Yandex
User-agent: Yandex
Allow: /
Disallow: /cron/
Disallow: /config/
Disallow: /includes/
Crawl-delay: 1

# Baidu
User-agent: Baiduspider
Allow: /
Disallow: /cron/
Disallow: /config/
Disallow: /includes/
Crawl-delay: 2

# Bad bots - block completely
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: SEMrushBot
Disallow: /

User-agent: dotbot
Disallow: /

User-agent: megaindex.ru
Disallow: /

# Development/staging environments
<?php
if (strpos($_SERVER['HTTP_HOST'], 'dev.') !== false || 
    strpos($_SERVER['HTTP_HOST'], 'staging.') !== false || 
    strpos($_SERVER['HTTP_HOST'], 'test.') !== false) {
    echo "User-agent: *\n";
    echo "Disallow: /\n";
}
?>