# Define access-restrictions for robots/spiders # http://www.robotstxt.org/wc/norobots.html # By default we allow robots to access all areas of our site # already accessible to anonymous users User-agent: * Disallow: /VirtualHostRoot Disallow: /rz/aktuellesadrz/a2005 Disallow: /rz/aktuellesadrz/a2006 Disallow: /rz/aktuellesadrz/2005 Disallow: /rz/aktuellesadrz/2006 Disallow: /rz/phone Disallow: /rz/test Disallow: /eit3_2/sonstiges/intranet # vgl. /etc/apache2/custom/skripte/proxy-dynamisch Disallow: /eit5/intern Disallow: /eit5/intern_en Disallow: /bauv5/lehre/skripte/skripte Disallow: /studber/intern Disallow: /zv # # ab hier Syntax-Erweiterungen, die nur bestimmte Bots verstehen # # Add Googlebot-specific syntax extension to exclude forms # that are repeated for each piece of content in the site # the wildcard is only supported by Googlebot # http://www.google.com/support/webmasters/bin/answer.py?answer=40367&ctx=sibling User-agent: Googlebot* User-agent: Slurp User-agent: Msnbot User-agent: Msnbot* Disallow: /*sendto_form$ Disallow: /*folder_factories$ Disallow: /*login_form$ Disallow: /VirtualHostRoot Disallow: /*--authorized/ Disallow: /*--rzintern/ Disallow: /*--internaluser/ Disallow: /rz/aktuellesadrz/a2005 Disallow: /rz/aktuellesadrz/a2006 Disallow: /rz/aktuellesadrz/2005 Disallow: /rz/aktuellesadrz/2006 Disallow: /rz/uniintern Disallow: /rz/test Disallow: /studber/intern Disallow: /zv # --------------------------------------------------------------------------- # Interne Suchmaschine # -------------------- # meldet sich mit folgendem Referer (Stand: August 2010): # Crawler-UniBwM (Enterprise; T1-CHJJUSJ5SEWAA; Stefan.Schwarz@unibw.de,Titus.Kristof-Crasnic@unibw.de) # Eigener Eintrag, um uni-internes fuer externe Crawler/Roboter zu sperren, # ohne eigene Suchmaschine zu behindern User-agent: T1-CHJJUSJ5SEWAA Disallow: /VirtualHostRoot Disallow: /rz/aktuellesadrz/a2005 Disallow: /rz/aktuellesadrz/a2006 Disallow: /rz/aktuellesadrz/2005 Disallow: /rz/aktuellesadrz/2006 Disallow: /rz/phone Disallow: /rz/test Disallow: /eit3_2/sonstiges/intranet Disallow: /eit5/intern Disallow: /eit5/intern_en Disallow: /bauv5/lehre/skripte/skripte Disallow: /*sendto_form$ Disallow: /*folder_factories$ Disallow: /*login_form$ Disallow: /*--authorized/ Disallow: /*--rzintern/ Disallow: /*/getFILE # ------------------------------------------------------- User-agent: Crawler-UniBw* Disallow: /rz Disallow: /VirtualHostRoot Disallow: /rz/aktuellesadrz/a2005 Disallow: /rz/aktuellesadrz/a2006 Disallow: /rz/aktuellesadrz/2005 Disallow: /rz/aktuellesadrz/2006 Disallow: /rz/phone Disallow: /rz/test Disallow: /eit3_2/sonstiges/intranet Disallow: /eit5/intern Disallow: /eit5/intern_en Disallow: /bauv5/lehre/skripte/skripte Disallow: /*sendto_form$ Disallow: /*folder_factories$ Disallow: /*login_form$ Disallow: /*--authorized/ Disallow: /*--rzintern/ Disallow: /*getFILE # Test # ab hier: nicht unser Crawler User-agent: t1-chjjusj5sewaa* Disallow: /praes User-agent: crawler-unibwm* Disallow: /rz