# ---------------------------------------------------------------------- DRUPAL # # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/wc/robots.html # # For syntax checking, see: # http://www.sxw.org.uk/computing/robots/check.html User-agent: * Crawl-delay: 10 # Directories Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /profiles/ Disallow: /scripts/ Disallow: /themes/ # Files Disallow: /CHANGELOG.txt Disallow: /cron.php Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /INSTALL.sqlite.txt Disallow: /install.php Disallow: /INSTALL.txt Disallow: /LICENSE.txt Disallow: /MAINTAINERS.txt Disallow: /update.php Disallow: /UPGRADE.txt Disallow: /xmlrpc.php # Paths (clean URLs) Disallow: /admin/ Disallow: /comment/reply/ Disallow: /filter/tips/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ Disallow: /user/logout/ # Paths (no clean URLs) Disallow: /?q=admin/ Disallow: /?q=comment/reply/ Disallow: /?q=filter/tips/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ Disallow: /?q=user/logout/ # ---------------------------------------------------- OLD WWW.LIBRARY.YALE.EDU User-Agent: * Disallow: /cgi-bin/ Disallow: /lmc/ Disallow: /journals/arl/ Disallow: /systems_steering/ Disallow: /libtech/ Disallow: /swish/ Disallow: /htdig/ Disallow: /analog/ Disallow: /~lso/ Disallow: /lso/workstation/archives/ Disallow: /lso/workstation/docs/linklint20/ Disallow: /lso/workstation/docs/listserv.htm Disallow: /ecollections/ Disallow: /~invoice/ Disallow: /~sinker/ Disallow: /~coleman/invoice/ Disallow: /scilib/ Disallow: /orbis2/private Disallow: /teagle/ Disallow: /orbis2/yale_only Disallow: /mtblog/ulibrarian/ Disallow: /sakai/ Disallow: /labs/ Disallow: /lec/ Disallow: /feed/ Disallow: /copyright/ Disallow: /BeinCatR/ Disallow: /CDC/ Disallow: /Internet/ Disallow: /NERL/ Disallow: /archives300/ Disallow: /ccl/ Disallow: /~fdstaff/ Disallow: /~prowns/ Disallow: /science/forms/ Disallow: /~mcolavol/ Disallow: /art/ Disallow: /ebooks/ Disallow: /digitalcollections/wwii/ Disallow: /wsg/archives Disallow: /projects User-Agent: htdog Disallow: /cgi-bin/ Disallow: /lmc/ Disallow: /journals/arl/ Disallow: /systems_steering/ Disallow: /libtech/ Disallow: /swish/ Disallow: /htdig/ Disallow: /~lso/workstation/archives/ Disallow: /ecollections/access/ Disallow: /ecollections/restricted/ Disallow: /ecollections/ovidyul_archive/ Disallow: /~invoice/ Disallow: /~sinker/ Disallow: /~coleman/invoice/ Disallow: /scilib/newbooks/ Disallow: /orbis2/private Disallow: /orbis2/yale_only User-Agent: Lhtdog Disallow: /cgi-bin/ Disallow: /lmc/ Disallow: /journals/arl/ Disallow: /systems_steering/ Disallow: /libtech/ Disallow: /swish/ Disallow: /htdig/ Disallow: /~lso/workstation/docs/linklint20/ Disallow: /ecollections/access/ Disallow: /ecollections/restricted/ Disallow: /~invoice/ Disallow: /~sinker/ Disallow: /~coleman/invoice/ Disallow: /scilib/newbooks/ Disallow: /orbis2/private Disallow: /orbis2/yale_onl