#
# robots.txt for http://www.w3.org/
#
# $Id: robots.txt,v 1.56 2009/05/28 19:30:02 ted Exp $
#

# For use by search.w3.org
User-agent: W3C-gsa
Disallow: /Out-Of-Date

User-agent: W3T_SE
Disallow: /Out-Of-Date

User-agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT; MS Search 4.0 Robot)
Disallow: /

# W3C Link checker
User-agent: W3C-checklink
Disallow:

# exclude some access-controlled areas
User-agent: *
Disallow: /2004/ontaria/basic
Disallow: /Team
Disallow: /Project
Disallow: /Web
Disallow: /Systems
Disallow: /History
Disallow: /Out-Of-Date
Disallow: /2002/02/mid
Disallow: /mid/
Disallow: /2005/06/blog/
Disallow: /2004/08/W3CTalks
Disallow: /2007/11/Talks/search
Disallow: /People/all/
Disallow: /RDF/Validator/ARPServlet
Disallow: /2003/03/Translations/byLanguage
Disallow: /2003/03/Translations/byTechnology
Disallow: /2005/11/Translations/Query
Disallow: /2003/glossary/subglossary/
#Disallow: /2001/07/pubrules-checker
#shouldnt get transparent proxies but will ml links of things like pubrules
Disallow: /2000/06/webdata/xslt
Disallow: /2000/09/webdata/xslt
Disallow: /2005/08/online_xslt/xslt
Disallow: /Bugs/
Disallow: /Search/Mail/Public/
Disallow: /2006/02/chartergen
Disallow: /2004/01/pp-impl
Disallow: /Consortium/supporters
Disallow: /2007/08/pyRdfa/