Wikia.com

#
# 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.
#

# 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: /

User-agent: sitebot
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: /

#
# 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: /

User-agent: Googlebot
Disallow: /w/
Disallow: /trap/
Disallow: /dbdumps/
Disallow: /wikistats/
Disallow: /*feed=rss*
Disallow: /*action=history*
Disallow: /*action=delete*
Disallow: /*action=watch*
Noindex: /w/
Noindex: /trap/
Noindex: /dbdumps/
Noindex: /wikistats/
Noindex: /*printable=yes*
Noindex: /*feed=rss*
Noindex: /*action=edit*
Noindex: /*action=history*
Noindex: /*action=delete*
Noindex: /*action=watch*
# en
Allow: /Special:Sitemap*
Allow: /wiki/Special:Sitemap*
Allow: /Special:Sitemap*
Allow: /wiki/Special:Sitemap*
Disallow: /wiki/Special:*
Disallow: /Special:*
Disallow: /*title=Special:*
Disallow: /wiki/Special%3A*
Disallow: /*title=Special%3A*
# en
Noindex: /wiki/Special:*
Noindex: /Special:*
Noindex: /*title=Special:*
Noindex: /wiki/Special%3A*
Noindex: /Special%3A*
Noindex: /*title=Special%3A*

User-agent: *
Disallow: /w/
Disallow: /trap/
Disallow: /dbdumps/
Disallow: /wikistats/
Disallow: /*feed=rss*
Disallow: /*action=history*
Disallow: /*action=delete*
Disallow: /*action=watch*
# en
Allow: /Special:Sitemap*
Allow: /wiki/Special:Sitemap*
Allow: /Special:Sitemap*
Allow: /wiki/Special:Sitemap*
Disallow: /wiki/Special:*
Disallow: /Special:*
Disallow: /*title=Special:*
Disallow: /wiki/Special%3A*
Disallow: /Special%3A*
Disallow: /*title=Special%3A*

# sitemap
Sitemap: http://www.wikia.com/sitemap-index.xml