Infrastructure

#
# Robot exclusion file for K-State
#
# If you are a web publisher at K-State, and would like to have
# some of your documents not available to robots, please contact
# webservices@k-state.edu.
#
# For more information about robots and what they do, see
# http://www.robotstxt.org/ and http://en.wikipedia.org/wiki/Robots.txt

User-agent: *
Disallow: /KSU_resources/
Disallow: */ksu-resources/ou/
Disallow: /2025-archive
Disallow: /assessment/data-surveys/archive
Disallow: */dev/
Disallow: */test/
Disallow: /archive/
# Disallow the list of all updated files.
Disallow: /search/new/autonew.html
# Disallow anything that has a URL redirect to another location.
# They are indexed under their new name rather than the old.
Disallow: /Directories/ksudepts.html
Disallow: /its/development/
Disallow: /dept_links.html
Disallow: /gen_interest.html
Disallow: /mhk_area_info.html
Disallow: /courses/web-classes.html
Disallow: /creating-home-page.html
Disallow: /aboutuni/copyright.html
Disallow: /aboutuni/help.html
Disallow: /aboutuni/new
Disallow: /wp-query.html
Disallow: /mainemnu.html
Disallow: /welcome.html
Disallow: /admit/viewbook
#Disallow: /internet2
Disallow: /cns_info
#Disallow: /infotech
Disallow: /training
Disallow: /classes
Disallow: /course
Disallow: /ksufcu
Disallow: /sthlt
Disallow: /afact
Disallow: /audit
Disallow: /hrser
Disallow: /jl57
Disallow: /recc
Disallow: /isle
Disallow: /smf
Disallow: /cfc
Disallow: /reg/
Disallow: /blog-feeds/
Disallow: /univpub/
Disallow: /registrar/backup/ 
Disallow: /registrar/a_r/backup/ 
Disallow: /registrar/c_d/oldgrad/ 
Disallow: /registrar/dars/slideshow/backup/ 
Disallow: /registrar/enroll/backup/ 
Disallow: /registrar/faqs/backup/ 
Disallow: /registrar/ferpa/backup/ 
Disallow: /registrar/t_v/backup/ 
Disallow: /registrar/unpublished/ 
Disallow: /registrar/internal/ 
Disallow: /registrar/statistics/tabs/ 
Disallow: /safety-new/
# Data files that should never be retrieved
Disallow: /Directories/lsdcodes-save.html
Disallow: /Directories/qsearch.data
Disallow: /Directories/qsearch-save.data
Disallow: /cns/newsletter/
Disallow: /InfoTech/news/tuesday/archive/2001
Disallow: /InfoTech/news/tuesday/archive/2002
Disallow: /InfoTech/news/tuesday/archive/2003
Disallow: /cns/announce/199
Disallow: /cns/announce/2001
Disallow: /cns/announce/2002
Disallow: /cns/announce/2003
Disallow: /elp/univdept
Disallow: /courses/fall2020/
# Remove all eventview because it might be causing load problems and will soon
# be replaced.
Disallow: /cgi-bin/eventview
# No reason to index our Maven repository
Disallow: /repository/
Disallow: /maps2011/
# Somehow Bing started indexing using a path after the filename, e.g.:
# /media/k-statement/main.html/vol30/vol32/vol31/vol31/vol32/vol30/vol30/vol31/vol30/vol30/vol31/vol31/
Disallow: /media/k-statement/main.html/vol
Disallow: /media/k-statement/main.html/aboutus
# Google has gotten ahold of https://www.k-state.edu/uas
Disallow: /uas
# Lots of keywords in this data file:
Disallow: /admissions/js/majors.js
# Old PDF guides
Disallow: /admissions/guides/
# Parking instructions that apply to a small subset of people
Disallow: /admissions/cvparking/
# Archived department heads info that has confused people
Disallow: /dh/archive/
Disallow: /media/WEB
Disallow: /media/Web
Disallow: /ksis/intranet
Disallow: /campaign/
Disallow: /today/tipsheet/
Disallow: /today/tuesday/
Disallow: /challenges/development/
# No reason to index these data feed files
Disallow: /calendar/export/
Disallow: /behemoth/export/
# Old names -- content is available on a new URL.
Disallow: /isis/
#Disallow: /nonviolence/
# Mediasite administration, per Brandon, INC0298413
Disallow: /mediasite/admin/
# 2017 homepage preview
Disallow: /preview/
Disallow: *index-old*
Disallow: *old-template*
Disallow: /webservices/reports/
Disallow: /webservices/dev/
Disallow: /check2018
Disallow: /band/login/pride/
Disallow: */secure/
Disallow: /*.inc
Disallow: /home/index-dev/
Disallow: /access-opportunity/resources/committees/
Disallow: /access-opportunity/resources/support-request/
Disallow: /gender-equity/
# New sites
Disallow: /cardio-device/
Disallow: /hashemi-lab/
Disallow: /news/articles/*.xml$