# robots.txt for https://newspaperspk.com
# This file is used to guide web crawlers on how to interact with the site.
# It allows crawlers to access certain resources and disallows others to ensure optimal indexing.

User-agent: *
# Allowing crawlers to access common web resources like JavaScript, CSS, and image files
Allow: /*.js*
Allow: /*.css*
Allow: /*.png*
Allow: /*.jpg*
Allow: /*.gif*

# Disallowing crawlers from accessing sensitive or backend directories
Disallow: /administrator/
Disallow: /api/
Disallow: /bin/
Disallow: /cache/
Disallow: /cli/
Disallow: /includes/
Disallow: /installation/
Disallow: /language/
Disallow: /layouts/
Disallow: /libraries/
Disallow: /logs/
Disallow: /tmp/

# Sitemap entries to guide crawlers to the correct sitemap locations for better indexing
Sitemap: https://newspaperspk.com/sitemap.xml
Sitemap: https://newspaperspk.com/sitemap_articles_pakistani_newspapers.xml
Sitemap: https://newspaperspk.com/sitemap_articles_indian_newspapers.xml
Sitemap: https://newspaperspk.com/sitemap_articles_world_newspapers.xml
Sitemap: https://newspaperspk.com/sitemap_images.xml