# robots.txt for http://liinwww.ira.uka.de/
#
# config file to control the access of web robots to our server
#
# see http://info.webcrawler.com/mak/projects/robots/norobots.html
# for an explanation of this file.
User-agent: hyperbot WIRE ExtractorPro emailsiphon DIIbot
Disallow: /

User-agent: teleport MSIECrawler htdig wget www.pl Microsoft_Site_Analyst DIIbot
Disallow: /cgi-bin
Disallow: /icons
Disallow: /searchbib
Disallow: /waisbib
Disallow: /mpsbib
Disallow: /csbib
Disallow: /bibliography
Disallow: /bibliography/searchbib

# Scripts and icons are off-limits 
User-agent: *
Disallow: /cgi-bin
Disallow: /icons
Disallow: /searchbib
Disallow: /waisbib
Disallow: /mpsbib
Disallow: /csbib
Disallow: /bibliography/rss
Disallow: /bibliography/tools
Disallow: /bibliography/searchbib

# rahn's program and data files 
# -> work in progress, browsable yes but robots tend to query old pages 
Disallow: ~rahn/src
Disallow: ~rahn/diplom/src/prog
Disallow: ~rahn/leader/src/prog
Disallow: ~rahn/loop/src/prog
Disallow: ~rahn/loop/src/data/proof.3.3
Disallow: ~rahn/loop/src/data/proof.3.4
Disallow: ~rahn/loop/src/data/proof.3.5
Disallow: ~rahn/loop/src/data/proof.4.3
Disallow: ~rahn/loop/src/data/proof.4.4
Disallow: ~rahn/rule110.dat