User-agent: *
Allow: /

# Sitemap
Sitemap: https://semnatv.com/sitemap.xml

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

# Allow all major search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

# Block unwanted bots
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Allow social media crawlers
User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# Specific rules for SemnaTv
# Allow access to all educational content
Allow: /index.html
Allow: /archive.html
Allow: /css/
Allow: /js/
Allow: /images/

# Block sensitive files
Disallow: /update-system.php
Disallow: /*.log
Disallow: /youtube_videos.json
Disallow: /fetch_channel_data.py

# Cache policy
# Request crawlers to respect our content freshness
# Content is updated hourly