#
# robots.txt for http://www.fortwiki.com
# based on wikipedia.org's robots.txt
# and WikiHow.com robots.txt
#
# Crawlers that are kind enough to obey, but which we'd rather not have
# unless they're feeding search engines.
Sitemap: http://www.fortwiki.com/sitemap.xml
User-agent: Slurp
Crawl-delay: 3.0
User-agent: Gigabot
Crawl-delay: 10
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: /
#
# 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: /
# not sure what this bot's issue is
User-agent: HMSE_Robot
Disallow: /
#
# Friendly, low-speed bots are welcome viewing article pages, but not
# dynamically-generated pages please.
#
# Inktomi's "Slurp" can read a minimum delay between hits; if your
# bot supports such a thing using the 'Crawl-delay' or another
# instruction, please let us know.
#
User-agent: Googlebot
Disallow: /w/
Disallow: /Special:Search
Disallow: /Special:LSearch
Disallow: /Special:GoogSearch
Disallow: /Special:Articlestats
Disallow: /forum/
Disallow: /index.php
Disallow: /*feed=rss*
Disallow: /*action=edit*
Disallow: /*action=history*
Disallow: /*action=delete*
Disallow: /*action=watch*
Noindex: /w/
Noindex: /Special:Search
Noindex: /Special:LSearch
Noindex: /Special:GoogSearch
Noindex: /Special:Random
Noindex: /Special:Articlestats
Noindex: /forum/
Noindex: /index.php
Noindex: /*feed=rss*
Noindex: /*action=edit*
Noindex: /*action=history*
Noindex: /*action=delete*
Noindex: /*action=watch*
User-agent: Mediapartners-Google
Disallow: /w/
User-agent: *
Disallow: /w/
Disallow: /Special:Search
Disallow: /Special:LSearch
Disallow: /Special:GoogSearch
Disallow: /Special:Articlestats
Disallow: /forum/
Disallow: /index.php
Disallow: /*feed=rss*
Disallow: /*action=edit*
Disallow: /*action=history*
Disallow: /*action=delete*
Disallow: /*action=watch*