# robots.txt for Penguin Random House

User-agent: Twitterbot
Allow: /images

User-agent: *
Allow: /

# Directories
Disallow: /etc/clientlibs/prh

# Block references to old site image requests
Disallow: /content/dam/prh-consumer
Disallow: /content/dam/prh-corporate

# Paths (clean URLs)
Disallow: /README.md

# Paths (no clean URLs)
Disallow: /*?*
Disallow: /*?
Disallow: /*.js$
Disallow: /*.css$
Disallow: /*.php$
Disallow: /*?p=*&

# Block servlet calls
Disallow: /bin/

# Sitemap
Sitemap: https://www.penguin.co.uk/sitemap.xml