# Sitemap
Sitemap: https://research.chalmers.se/sitemap_index/

# Default Access Group
User-agent: *

# Disable access to certatin paths that are not relevant for indexing
Disallow: /organisation
Disallow: /en/organization
Disallow: /rapporter
Disallow: /docs
Disallow: /publicationcreate
Disallow: /en/publicationcreate
Disallow: /projectupdate
Disallow: /en/projectupdate
Disallow: /organizationupdate
Disallow: /en/organizationupdate
Disallow: /admin
Disallow: /howtoregister
Disallow: /privacy
Disallow: /en/privacy

### Bots

# Added locally

# SEO-tools, very aggresive but should perhaps be enable anyway (if ne  eded)?
User-agent: SemrushBot
Crawl-delay: 120

User-agent: SemrushBot-SA
Crawl-delay: 120

User-agent: AhrefsBot
Crawl-delay: 120

# AmazonBot, used by Alexa (and other services?) but also very aggresive
# Don't respect Crawl-delay directives (240815)
User-agent: Amazonbot
Disallow: /

# Valid service, but also very aggresive and doesn't follow directives
User-agent: DataForSeoBot
Disallow: /

User-agent: ExaBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: GigaBot
Disallow: /

User-agent: ChinaClaw
Disallow: /

User-agent: RogerBot
Disallow: /

# Section for misbehaving bots
# Using https://en.wikipedia.org/robots.txt

User-agent: MJ12bot
Disallow: /

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

# Wikipedia work bots:
User-agent: IsraBot
Disallow: /

User-agent: Orthogaffe
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, please obey

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: /

# 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: /