#  _____ _               _____ _ _   _                 _____           _     
# /  ___| |             /  __ (_) | (_)               |_   _|         | |    
# \ `--.| |_ __ _ _ __  | /  \/_| |_ _ _______ _ __     | | ___   ___ | |___ 
#  `--. \ __/ _` | '__| | |   | | __| |_  / _ \ '_ \    | |/ _ \ / _ \| / __|
# /\__/ / || (_| | |    | \__/\ | |_| |/ /  __/ | | |   | | (_) | (_) | \__ \
# \____/ \__\__,_|_|     \____/_|\__|_/___\___|_| |_|   \_/\___/ \___/|_|___/
#                                                                           
# Are you a human? Maybe you want to help with the wiki? Contact us on Discord: https://discord.com/invite/XcKwqyD4sc
#
# robots.txt for Star Citizen Wiki
# based on version from Wikipedia in 2018-04-22
#
# Please note: There are a lot of pages on this site, and there are
# some misbehaved spiders out there that go _way_ too fast. If you're
# irresponsible, your access to the site may be blocked.
#
Sitemap: https://sitemap.starcitizen.tools/sitemap-index-starcitizentools.xml

# Observed spamming large amounts of https://en.wikipedia.org/?curid=NNNNNN
# and ignoring 429 ratelimit responses, claims to respect robots:
# http://mj12bot.com/
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, 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: /

#
# Sorry, wget in its recursive mode is a frequent problem.
# Please read the man page and use it properly; there is a
# --wait option you can use to set the delay between hits,
# for instance.
#
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: /

# Crawler list from runescape.wiki
# SEO bot
User-agent: AhrefsBot
Disallow: /

# SEO bot
User-agent: DotBot
Disallow: /

# Unknown
User-agent: Mauibot
Disallow: /

# Huawei's web crawler. Ignores Disallow and gets caught in loops accessing special pages. Produces the majority of uncachable requests.
User-agent: PetalBot
Disallow: /

# SEO bot
User-agent: SemrushBot
Disallow: /

# SEO bot
User-agent: DataForSeoBot
Disallow: /

# SEO bot
User-agent: Neevabot
Disallow: /

# SEO bot
User-agent: MegaIndex
Disallow: /

# SEO bot
User-agent: Seekport
Disallow: /

# SEO bot
User-agent: Barkrowler
Disallow: /

# Added rules from SCW
User-agent: *
Allow: /rest.php/wikiseo/v1/socialmediaimage
Disallow: /api.php
Disallow: /rest.php
Disallow: /ProjMGMT:
Disallow: /Mediawiki:
Disallow: /Mediawiki%3A
Disallow: /mediawiki:
Disallow: /*?title=Mediawiki:
Disallow: /*?title=Mediawiki%3A
Disallow: /*?*&title=Mediawiki:
Disallow: /*?*&title=Mediawiki%3A
Disallow: /Property:
Disallow: /Property%3A
Disallow: /property:
Disallow: /*?title=Property:
Disallow: /*?title=Property%3A
Disallow: /*?*&title=Property:
Disallow: /*?*&title=Property%3A
Disallow: /Special:
Disallow: /Special%3A
Disallow: /special:
Disallow: /*?title=Special:
Disallow: /*?title=Special%3A
Disallow: /*?*&title=Special:
Disallow: /*?*&title=Special%3A
Disallow: /Talk:
Disallow: /Talk%3A
Disallow: /talk:
Disallow: /*?title=Talk:
Disallow: /*?title=Talk%3A
Disallow: /*?*&title=Talk:
Disallow: /*?*&title=Talk%3A
Disallow: /*_talk:
Disallow: /*_talk%3A
Disallow: /*?title=*_talk:
Disallow: /*?title=*_talk%3A
Disallow: /*?*&title=*_talk:
Disallow: /*?*&title=*_talk%3A
Disallow: /Template:
Disallow: /Template%3A
Disallow: /template:
Disallow: /*?title=Template:
Disallow: /*?title=Template%3A
Disallow: /*?*&title=Template:
Disallow: /*?*&title=Template%3A
Disallow: /User:
Disallow: /User%3A
Disallow: /User:
Disallow: /*?title=User:
Disallow: /*?title=User%3A
Disallow: /*?*&title=User:
Disallow: /*?*&title=User%3A
Disallow: /*?action=
Disallow: /*?*&action=
Disallow: /*?feed=
Disallow: /*?*&feed=
Disallow: /*?from=
Disallow: /*?*&from=
Disallow: /*?oldid=
Disallow: /*?*&oldid=
Disallow: /*?printable=
Disallow: /*?*&printable=
Disallow: /*?redirect=
Disallow: /*?*&redirect=
Disallow: /*?uselang=
Disallow: /*?*&uselang=
Disallow: /*?useskin=
Disallow: /*?*&useskin=
Disallow: /*?veaction=
Disallow: /*?*&veaction=
Disallow: /*?filefrom=
Disallow: /*?*&filefrom=
Disallow: /*?fileuntil=
Disallow: /*?*&fileuntil=
Disallow: /*?navbox=
Disallow: /*?*&navbox=
Disallow: /*?pageuntil=
Disallow: /*?*&pageuntil=
Disallow: /*?pagefrom=
Disallow: /*?*&pagefrom=
Disallow: /*?diff=
Disallow: /*?*&diff=
Disallow: /*?curid=
Disallow: /*?*&curid=
Disallow: /*?search=
Disallow: /*?*&search=
Disallow: /*?section=
Disallow: /*?*&section=
crawl-delay: 5