# robots.txt for http://www.gigascale.org # See http://info.webcrawler.com/mak/projects/robots/norobots.html ################################################################## # First, htdig's rules: # User-agent: htdig Disallow: robots.txt # Disallow: /bookshelf/overview/vlsicad.cs.ucla Disallow: /bookshelf/overview/www-agz.informatik.uni-kl.de Disallow: /bookshelf/overview/www.cs.berkeley.edu Disallow: /bookshelf/overview/www.ece.nwu.edu Disallow: /bookshelf/overview/www.ee.princeton.edu Disallow: /bookshelf/overview/www.ee.umn.edu Disallow: /bookshelf/overview/www.jimy.org Disallow: /bookshelf/Slots/cache # Disallow: /datamodel/overview/vlsicad.cs.ucla Disallow: /datamodel/overview/www-agz.informatik.uni-kl.de Disallow: /datamodel/overview/www.cs.berkeley.edu Disallow: /datamodel/overview/www.ece.nwu.edu Disallow: /datamodel/overview/www.ee.princeton.edu Disallow: /datamodel/overview/www.ee.umn.edu Disallow: /datamodel/overview/www.jimy.org # Disallow: /dopcenter/links.htm # Disallow: /gsrc/manuals Disallow: /gsrc/overview/vlsicad.cs.ucla Disallow: /gsrc/overview/www-agz.informatik.uni-kl.de Disallow: /gsrc/overview/www.cs.berkeley.edu Disallow: /gsrc/overview/www.ece.nwu.edu Disallow: /gsrc/overview/www.ee.princeton.edu Disallow: /gsrc/overview/www.ee.umn.edu Disallow: /gsrc/overview/www.jimy.org Disallow: /gtxdev/overview/vlsicad.cs.ucla Disallow: /gtxdev/overview/www-agz.informatik.uni-kl.de Disallow: /gtxdev/overview/www.cs.berkeley.edu Disallow: /gtxdev/overview/www.ece.nwu.edu Disallow: /gtxdev/overview/www.ee.princeton.edu Disallow: /gtxdev/overview/www.ee.umn.edu Disallow: /gtxdev/overview/www.jimy.org Disallow: /infrax/overview/vlsicad.cs.ucla Disallow: /infrax/overview/www-agz.informatik.uni-kl.de Disallow: /infrax/overview/www.cs.berkeley.edu Disallow: /infrax/overview/www.ece.nwu.edu Disallow: /infrax/overview/www.ee.princeton.edu Disallow: /infrax/overview/www.ee.umn.edu Disallow: /infrax/overview/www.jimy.org Disallow: /mailman/admin Disallow: /mailman/admin/ Disallow: /mailman/listinfo Disallow: /mailman/listinfo/ Disallow: /metropolis/src/ Disallow: /news Disallow: /news/ Disallow: /people/lists Disallow: /people/lists/ Disallow: /pipermail Disallow: /pipermail/ Disallow: /ptexternal/nightly Disallow: /ptexternal/rnightly/ Disallow: /ptolemy/nightly Disallow: /ptolemy/nightly/ Disallow: /ptolemy/reviews/template/index.htm Disallow: /ptolemy/src/ptII/adm/dists/ Disallow: /ptolemy/src/ptII/ptolemy/codegen/saveasjava/test/ Disallow: /ptolemy/src/ptII/ptolemy/copernicus/c/test Disallow: /ptolemy/src/ptII/doc/installJNLP.htm Disallow: /ptolemy/src/ptII/ptolemy/apps/webstart/ Disallow: /ptolemy/src/ptII/ptolemy/apps/webstart/README.html Disallow: /ptolemy/src/ptII/ptolemy/copernicus/c/test/testOutput Disallow: /ptolemy/src/ptII/vendors/ Disallow: /ptolemy/src/ptII/vendors Disallow: /ptolemy/src/ptII/vendors/ocp/OCP_B0.01/ Disallow: /ptolemy/src/ptII/vendors/soot/usage.html Disallow: /ptolemy/src/ptII/vendors/sun/commapi/PlatformSpecific.html # Disallow: /slip/overview/vlsicad.cs.ucla Disallow: /slip/overview/www-agz.informatik.uni-kl.de Disallow: /slip/overview/www.cs.berkeley.edu Disallow: /slip/overview/www.ece.nwu.edu Disallow: /slip/overview/www.ee.princeton.edu Disallow: /slip/overview/www.ee.umn.edu Disallow: /slip/overview/www.jimy.org Disallow: /testgroup/ Disallow: /?annotate=1/ Disallow: /?annotate=1?annotate=1/ # Don't search this because it could include links from logs in the # past that point to pages that do not exist. Disallow: /accesswatch/ Disallow: /infrax/sysadmin/accesswatch/ Disallow: /infrax/sysadmin/accesswatch/day/ Disallow: /infrax/sysadmin/accesswatch/week/ Disallow: /infrax/sysadmin/accesswatch/month/ Disallow: /infrax/sysadmin/accesswatch/year/ Disallow: /infrax/sysadmin/accesswatch/day/page.html Disallow: /infrax/sysadmin/accesswatch/week/page.html Disallow: /infrax/sysadmin/accesswatch/month/page.html Disallow: /infrax/sysadmin/accesswatch/year/page.html # texi2html is a program, not an html file Disallow: /gsrc/manuals/mysql/texi2html # Don't allow searching of the Php/Mysql tool Disallow: /mysql/ # A message about missing links was posted, which causes more # missing links Disallow: /diva/listinfo/diva/1999-October/000314.html # 3898 pages to be searched in this directory, so we skip # it so that the search engine finishes quickly Disallow: /diva/snapshot/api Disallow: /gsrc/manuals/java # ################################################################## # Now, everybody else's rules: # Lots of duplication to maintain here, but no other way to explicitly # allow htdig to search what others can't (/gsrc/manuals/). # That's because htdig doesn't support an "Allow:" rule. # User-agent: * Disallow: robots.txt # Disallow: /bookshelf/overview/vlsicad.cs.ucla Disallow: /bookshelf/overview/www-agz.informatik.uni-kl.de Disallow: /bookshelf/overview/www.cs.berkeley.edu Disallow: /bookshelf/overview/www.ece.nwu.edu Disallow: /bookshelf/overview/www.ee.princeton.edu Disallow: /bookshelf/overview/www.ee.umn.edu Disallow: /bookshelf/overview/www.jimy.org Disallow: /bookshelf/Slots/cache # Disallow: /datamodel/overview/vlsicad.cs.ucla Disallow: /datamodel/overview/www-agz.informatik.uni-kl.de Disallow: /datamodel/overview/www.cs.berkeley.edu Disallow: /datamodel/overview/www.ece.nwu.edu Disallow: /datamodel/overview/www.ee.princeton.edu Disallow: /datamodel/overview/www.ee.umn.edu Disallow: /datamodel/overview/www.jimy.org # Disallow: /dopcenter/links.htm # Disallow: /gsrc/manuals Disallow: /gsrc/overview/vlsicad.cs.ucla Disallow: /gsrc/overview/www-agz.informatik.uni-kl.de Disallow: /gsrc/overview/www.cs.berkeley.edu Disallow: /gsrc/overview/www.ece.nwu.edu Disallow: /gsrc/overview/www.ee.princeton.edu Disallow: /gsrc/overview/www.ee.umn.edu Disallow: /gsrc/overview/www.jimy.org Disallow: /gtxdev/overview/vlsicad.cs.ucla Disallow: /gtxdev/overview/www-agz.informatik.uni-kl.de Disallow: /gtxdev/overview/www.cs.berkeley.edu Disallow: /gtxdev/overview/www.ece.nwu.edu Disallow: /gtxdev/overview/www.ee.princeton.edu Disallow: /gtxdev/overview/www.ee.umn.edu Disallow: /gtxdev/overview/www.jimy.org Disallow: /infrax/overview/vlsicad.cs.ucla Disallow: /infrax/overview/www-agz.informatik.uni-kl.de Disallow: /infrax/overview/www.cs.berkeley.edu Disallow: /infrax/overview/www.ece.nwu.edu Disallow: /infrax/overview/www.ee.princeton.edu Disallow: /infrax/overview/www.ee.umn.edu Disallow: /infrax/overview/www.jimy.org Disallow: /login Disallow: /login/ Disallow: /mailman/admin Disallow: /mailman/admin/ Disallow: /mailman/listinfo Disallow: /mailman/listinfo/ Disallow: /metropolis/src/ Disallow: /people/lists Disallow: /people/lists/ Disallow: /pipermail Disallow: /pipermail/ Disallow: /ptexternal/nightly Disallow: /ptexternal/rnightly/ Disallow: /ptolemy/nightly Disallow: /ptolemy/nightly/ Disallow: /ptolemy/reviews/template/index.htm Disallow: /ptolemy/src/ptII/adm/dists/ Disallow: /ptolemy/src/ptII/ptolemy/codegen/saveasjava/test/ Disallow: /ptolemy/src/ptII/ptolemy/copernicus/c/test Disallow: /ptolemy/src/ptII/doc/installJNLP.htm Disallow: /ptolemy/src/ptII/ptolemy/apps/webstart/ Disallow: /ptolemy/src/ptII/ptolemy/apps/webstart/README.html Disallow: /ptolemy/src/ptII/ptolemy/copernicus/c/test/testOutput Disallow: /ptolemy/src/ptII/vendors/ Disallow: /ptolemy/src/ptII/vendors Disallow: /ptolemy/src/ptII/vendors/ocp/OCP_B0.01/ Disallow: /ptolemy/src/ptII/vendors/soot/usage.html Disallow: /ptolemy/src/ptII/vendors/sun/commapi/PlatformSpecific.html # Disallow: /slip/overview/vlsicad.cs.ucla Disallow: /slip/overview/www-agz.informatik.uni-kl.de Disallow: /slip/overview/www.cs.berkeley.edu Disallow: /slip/overview/www.ece.nwu.edu Disallow: /slip/overview/www.ee.princeton.edu Disallow: /slip/overview/www.ee.umn.edu Disallow: /slip/overview/www.jimy.org Disallow: /testgroup/ Disallow: /?annotate=1/ Disallow: /?annotate=1?annotate=1/ # Don't search this because it could include links from logs in the # past that point to pages that do not exist. Disallow: /accesswatch/ Disallow: /infrax/sysadmin/accesswatch/ Disallow: /infrax/sysadmin/accesswatch/day/ Disallow: /infrax/sysadmin/accesswatch/week/ Disallow: /infrax/sysadmin/accesswatch/month/ Disallow: /infrax/sysadmin/accesswatch/year/ Disallow: /infrax/sysadmin/accesswatch/day/page.html Disallow: /infrax/sysadmin/accesswatch/week/page.html Disallow: /infrax/sysadmin/accesswatch/month/page.html Disallow: /infrax/sysadmin/accesswatch/year/page.html # texi2html is a program, not an html file Disallow: /gsrc/manuals/mysql/texi2html # Don't allow searching of the Php/Mysql tool Disallow: /mysql/ # A message about missing links was posted, which causes more # missing links Disallow: /diva/listinfo/diva/1999-October/000314.html # 3898 pages to be searched in this directory, so we skip # it so that the search engine finishes quickly Disallow: /diva/snapshot/api Disallow: /gsrc/manuals/ Disallow: /pubs/satellites/