User-agent: *
Allow: /

# Allow crawling of all important content
Allow: /article/
Allow: /category/
Allow: /about
Allow: /contact
Allow: /privacy
Allow: /terms

# Block admin and sensitive areas
Disallow: /admin*
Disallow: /login
Disallow: /api*
Disallow: /*.json$
Disallow: /search?*
Disallow: /*?*utm_*
Disallow: /*?*fbclid=*
Disallow: /*?*gclid=*

# Block duplicate URLs with language parameters
Disallow: /*?lang=*&*

# Sitemap locations (both dynamic and static)
Sitemap: https://impaxnews.com/sitemap.xml
Sitemap: https://impaxnews.com/static/sitemap.xml

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

# Special rules for news crawlers (faster crawling for news content)
User-agent: Googlebot-News
Allow: /
Allow: /article/
Allow: /category/
Crawl-delay: 0

User-agent: Bingbot
Allow: /
Crawl-delay: 2

# Social media crawlers
User-agent: facebookexternalhit/*
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Telegrambot
Allow: /