# robots.txt for http://www.cl.cam.ac.uk/
# $Header: /anfs/www/html/RCS/robots.txt,v 1.5 2006/10/24 15:54:25 maj1 Exp $

User-agent: *
Disallow: /research/hvg/FIV/
Disallow: /research/hvg/HOL/mail/
Disallow: /research/wip/
Disallow: /users/mjcg/no_robot/
Disallow: /~mjcg/no_robot/
Disallow: /wednesday/
Disallow: /m3doc/
Disallow: /netmaint/
Disallow: /newslist/
Disallow: /javadoc/
Disallow: /pythondoc/
Disallow: /texinfodoc/

User-agent: Ultraseek (webmaster@ucs.cam.ac.uk)  # local search engine
Disallow: /research/hvg/FIV/
Disallow: /research/hvg/HOL/mail/
Disallow: /research/wip/
Disallow: /users/mjcg/no_robot/
Disallow: /~mjcg/no_robot/
Disallow: /wednesday/
Disallow: /m3doc/
Disallow: /netmaint/
Disallow: /newslist/
Disallow: /javadoc/
Disallow: /pythondoc/
Disallow: /texinfodoc/
Disallow: /local/sys/
Disallow: /users/
Disallow: /~

User-agent: Ultraseek (internal search; webmaster@ucs.cam.ac.uk)  # local search engine
Disallow: /research/hvg/FIV/
Disallow: /research/hvg/HOL/mail/
Disallow: /research/wip/
Disallow: /users/mjcg/no_robot/
Disallow: /~mjcg/no_robot/
Disallow: /wednesday/
Disallow: /m3doc/
Disallow: /netmaint/
Disallow: /newslist/
Disallow: /javadoc/
Disallow: /pythondoc/
Disallow: /texinfodoc/
Disallow: /users/
Disallow: /~

User-agent: linkchecker