# robots.txt for worldwebnewspapers.com
# Last updated: 2025-07-25
# Contact: admin@worldwebnewspapers.com

# Crawl-delay is ignored by Google but honoured by some bots
Crawl-delay: 1

# Sitemaps (update the dates when you regenerate)
Sitemap: https://worldwebnewspapers.com/sitemap_index.xml
Sitemap: https://worldwebnewspapers.com/news-sitemap.xml

# Main rule: allow everything except the disallowed list
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/cache/
Disallow: /wp-content/uploads/*/backup/
Disallow: /cgi-bin/
Disallow: /search/
Disallow: /?s=*
Disallow: /tag/
Disallow: /author/
Disallow: /date/
Disallow: /*?replytocom=*
Disallow: /*utm_source=*
Disallow: /*utm_medium=*
Disallow: /*utm_campaign=*

# Google News (and Googlebot-News) must see all article pages
User-agent: Googlebot-News
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/

# Bingbot (news vertical)
User-agent: Bingbot
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/