# $Id: robots.txt,v 1.15 2003/01/22 17:18:47 bolger Exp $
#
# This is a file retrieved by webwalkers a.k.a. spiders that
# conform to a defacto standard.
# See <URL:http://www.robotstxt.org/wc/exclusion.html#robotstxt>
#
# The webmaster for this site is <webmaster@i-marketing.nl>
#
# Format is:
#       User-agent: <name of spider>
#       Disallow: <nothing> | <path>
# Flag  Date      By      Reason
# $l1-  19950130  epc     finally understood what the file was for!
# $L2=  19960909  epc     fixed url since mak moved to Webcrawler...
# $L3=  19970811  epc     drop /Stretch
# $L4=  19991102  krusch  fixed User-agent capitalization and contact info
# $L5=  20010327  krusch  Updated disallow rules
# -----------------------------------------------------------------------------
User-agent: semanticdiscovery
Disallow: /

User-agent: Tutorial Crawler
Disallow: /

User-agent: TurnitinBot
Disallow: /

User-agent: NPBot
Disallow: /

User-agent: Web Downloader
Disallow: /
User-agent: Missigua Locator 1.9
Disallow: /
User-agent: Port Huron Labs
Disallow: /
User-agent: Wells Search II
Disallow: /
User-agent: Program Shareware 1.0.0
Disallow: /

User-agent: *
Disallow: /typo3conf
Allow: /fileadmin/sitemap.xml
Disallow: /fileadmin
Disallow: /media
Disallow: /tslib
Disallow: /typo3temp
Disallow: /t3lib
Disallow: /typo3
Disallow: /uploads
Disallow: /typo3_src
Disallow: /images