# The FULL URL to the DSpace sitemaps
# XML sitemap is listed first as it is preferred by most search engines
# Make sure to replace "[dspace.url]" with the value of your 'dspace.url' setting in your dspace.cfg file.
Sitemap: https://researchspace.auckland.ac.nz/sitemap
Sitemap: https://researchspace.auckland.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*
Disallow: /*stats*
Disallow: /*/*.pdf.txt*
Disallow: /*/license.txt*
Disallow: /statistics

User-agent: *
Crawl-delay: 180
Disallow: /advanced-search
Disallow: /community-list
Disallow: /controlledvocabulary
Disallow: /dspace-oai
Disallow: /feedback
Disallow: /feed
Disallow: /forgot
Disallow: /internal-error
Disallow: /ldap-login
Disallow: /metadata
Disallow: /mydspace
Disallow: /openURL
Disallow: /password-login
Disallow: /profile
Disallow: /register
Disallow: /retrieve
Disallow: /search
Disallow: /simple-search
Disallow: /shibboleth-login
Disallow: /statistics
Disallow: /subscribe
Disallow: /subject-search
Disallow: /suggest
Disallow: /view-workspaceitem
Disallow: /workspace
Disallow: /xmlui
Disallow: /contact
Disallow: /login

User-agent: SemrushBot
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

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: /bitstream

User-agent: gsa-crawler
Disallow: /discover
Disallow: /*discover*
Disallow: /search-filter
Disallow: /*search-filter*
Disallow: /feed
Disallow: /statistics
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: /bitstream

##############################
# from Wikipedia's robots.txt
##############################

# Funnelback crawler at 225.168.15.103.squiz.net (103.15.168.225) 
User-agent: RPT-HTTPClient
Disallow: /

# 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: /

# recursive wget, 
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: /

# 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: /