# The FULL URL to the DSpace sitemaps
# The https://researchcommons.waikato.ac.nz will be auto-filled with the value in dspace.cfg
# XML sitemap is listed first as it is preferred by most search engines
Sitemap: https://researchcommons.waikato.ac.nz/sitemap
Sitemap: https://researchcommons.waikato.ac.nz/htmlmap

##########################
# Default Access Group
# (NOTE: blank lines are not allowable in a group record)
##########################
User-agent: *
# Disable access to Discovery search and filters
Disallow: /discover
Disallow: /*discover*
Disallow: /search-filter
Disallow: /*search-filter*
Disallow: /handle/*/browse*
#
# Optionally uncomment the following line ONLY if sitemaps are working
# and you have verified that your site is being indexed correctly.
# Disallow: /browse
#
# If you have configured DSpace (Solr-based) Statistics to be publicly 
# accessible, then you may not want this content to be indexed
Disallow: /statistics
#
# You also may wish to disallow access to the following paths, in order
# to stop web spiders from accessing user-based content
# Disallow: /contact
# Disallow: /feedback
# Disallow: /forgot
# Disallow: /login
# Disallow: /register
Disallow: /feed
Disallow: /dstats
Disallow: /stats
Disallow: /password-login
Disallow: /ldap-login
Disallow: /shibboleth-login
Disallow: /search
Disallow: /deposit
Disallow: /profile
Disallow: /mydspace
Disallow: /subscribe
Disallow: /metadata
Disallow: /simple-search
Disallow: /advanced-search
Disallow: /contact-us
Disallow: /dspace-oai
Disallow: /*stats*
Disallow: /*/*.pdf.txt*
Disallow: /*/license.txt*
Disallow: /citecounts
Disallow: /altmetrics
Disallow: /JSON
Disallow: /citation
#
Disallow: /handle/10289/9289*
Disallow: /bitstream/handle/10289/9289*
Disallow: /handle/10289/8715*
Disallow: /bitstream/handle/10289/8715*
Disallow: /handle/10289/8489*
Disallow: /bitstream/handle/10289/8489*

User-agent: Lucidworks-Anda/2.0
Disallow: /browse
Disallow: /discover
Disallow: /*discover*
Disallow: /search-filter
Disallow: /*search-filter*
Disallow: /handle/*/browse*
Disallow: /*browse*
Disallow: /feed
Disallow: /statistics
Disallow: /dstats
Disallow: /stats
Disallow: /forgot
Disallow: /login
Disallow: /password-login
Disallow: /ldap-login
Disallow: /shibboleth-login
Disallow: /register
Disallow: /search
Disallow: /deposit
Disallow: /profile
Disallow: /mydspace
Disallow: /subscribe
Disallow: /feedback
Disallow: /metadata
Disallow: /simple-search
Disallow: /advanced-search
Disallow: /contact-us
Disallow: /dspace-oai
Disallow: /*stats*
Disallow: /*/*.pdf.txt*
Disallow: /*/license.txt*
Disallow: /citecounts
Disallow: /altmetrics
Disallow: /JSON
Disallow: /citation
Disallow: /bitstream



User-agent: gsa-crawler
Disallow: /browse
Disallow: /discover
Disallow: /*discover*
Disallow: /search-filter
Disallow: /*search-filter*
Disallow: /handle/*/browse*
Disallow: /*browse*
Disallow: /feed
Disallow: /statistics
Disallow: /dstats
Disallow: /stats
Disallow: /forgot
Disallow: /login
Disallow: /password-login
Disallow: /ldap-login
Disallow: /shibboleth-login
Disallow: /register
Disallow: /search
Disallow: /deposit
Disallow: /profile
Disallow: /mydspace
Disallow: /subscribe
Disallow: /feedback
Disallow: /metadata
Disallow: /simple-search
Disallow: /advanced-search
Disallow: /contact-us
Disallow: /dspace-oai
Disallow: /*stats*
Disallow: /*/*.pdf.txt*
Disallow: /*/license.txt*
Disallow: /citecounts
Disallow: /altmetrics
Disallow: /JSON
Disallow: /citation
Disallow: /bitstream

##############################
# Section for misbehaving bots
# The following directives to block specific robots were borrowed from Wikipedia's robots.txt
##############################

# advertising-related bots:
User-agent: Mediapartners-Google*
Disallow: /

# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.
User-agent: UbiCrawler
Disallow: /

User-agent: DOC
Disallow: /

User-agent: Zao
Disallow: /

# Some bots are known to be trouble, particularly those designed to copy
# entire sites. Please obey robots.txt.
User-agent: sitecheck.internetseer.com
Disallow: /

User-agent: Zealbot
Disallow: /

User-agent: MSIECrawler
Disallow: /

User-agent: SiteSnagger
Disallow: /

User-agent: WebStripper
Disallow: /

User-agent: WebCopier
Disallow: /

User-agent: Fetch
Disallow: /

User-agent: Offline Explorer
Disallow: /

User-agent: Teleport
Disallow: /

User-agent: TeleportPro
Disallow: /

User-agent: WebZIP
Disallow: /

User-agent: linko
Disallow: /

User-agent: HTTrack
Disallow: /

User-agent: Microsoft.URL.Control
Disallow: /

User-agent: Xenu
Disallow: /

User-agent: larbin
Disallow: /

User-agent: libwww
Disallow: /

User-agent: ZyBORG
Disallow: /

User-agent: Download Ninja
Disallow: /

# Misbehaving: requests much too fast:
User-agent: fast
Disallow: /

#
# If your DSpace is going down because of someone using recursive wget, 
# you can activate the following rule.
#
# If your own faculty is bringing down your dspace with recursive wget,
# you can advise them to use the --wait option to set the delay between hits.
#
#User-agent: wget
#Disallow: /

#
# The 'grub' distributed client has been *very* poorly behaved.
#
User-agent: grub-client
Disallow: /

#
# Doesn't follow robots.txt anyway, but...
#
User-agent: k2spider
Disallow: /

#
# Hits many times per second, not acceptable
# http://www.nameprotect.com/botinfo.html
User-agent: NPBot
Disallow: /

# A capture bot, downloads gazillions of pages with no public benefit
# http://www.webreaper.net/
User-agent: WebReaper
Disallow: /

# ecommerce / pagerank bot
User-agent: dotbot
Disallow: /

# https://www.semrush.com/bot/
User-agent: SemrushBot
Disallow: / 

User-agent: SemrushBot-SA
Disallow: / 

User-agent: MauiBot
Disallow: /