# robots.txt for http://www.wikipedia.org/ and friends

# 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: /

#
# 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: /

# Don't allow the wayback-maschine to index user-pages
#User-agent: ia_archiver
Disallow: /wiki/User
Disallow: /wiki/Benutzer

#
# 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: * # focusing on all spiders
Disallow: //page/
Disallow: /my/cgi-bin/
Disallow: /my/feed/
Disallow: /my/wp-content/
Disallow: /wp-includes/
Disallow: /wp-admin/
Disallow: /xmlrpc.php
Disallow: /wp-trackback.php
Disallow: /wp-settings.php
Disallow: /wp-rss2.php
Disallow: /wp-rss.php
Disallow: /wp-register.php
Disallow: /wp-rdf.php
Disallow: /wp-mail.php
Disallow: /wp-pass.php
Disallow: /wp-login.php
Disallow: /wp-links-opml.php
Disallow: /wp-feed.php
Disallow: /wp-config.php
Disallow: /wp-commentsrss2.php
Disallow: /wp-comments-post.php
Disallow: /wp-blog-header.php
Disallow: /wp-atom.php
Disallow: /wordpress/cgi-bin/
Disallow: /wordpress/feed/
Disallow: /wordpress/wp-content/
Disallow: /wordpress/wp-includes/
Disallow: /wordpress/wp-admin/
Disallow: /wordpress/xmlrpc.php
Disallow: /wordpress/wp-trackback.php
Disallow: /wordpress/wp-settings.php
Disallow: /wordpress/wp-rss2.php
Disallow: /wordpress/wp-rss.php
Disallow: /wordpress/wp-register.php
Disallow: /wordpress/wp-rdf.php
Disallow: /wordpress/wp-mail.php
Disallow: /wordpress/wp-pass.php
Disallow: /wordpress/wp-login.php
Disallow: /wordpress/wp-links-opml.php
Disallow: /wordpress/wp-feed.php
Disallow: /wordpress/wp-config.php
Disallow: /wordpress/wp-commentsrss2.php
Disallow: /wordpress/wp-comments-post.php
Disallow: /wordpress/wp-blog-header.php
Disallow: /wordpress/wp-atom.php
Disallow: /my/wordpress/cgi-bin/
Disallow: /my/wordpress/feed/
Disallow: /my/wordpress/wp-content/
Disallow: /my/wordpress/wp-includes/
Disallow: /my/wordpress/wp-admin/
Disallow: /my/wordpress/xmlrpc.php
Disallow: /my/wordpress/wp-trackback.php
Disallow: /my/wordpress/wp-settings.php
Disallow: /my/wordpress/wp-rss2.php
Disallow: /my/wordpress/wp-rss.php
Disallow: /my/wordpress/wp-register.php
Disallow: /my/wordpress/wp-rdf.php
Disallow: /my/wordpress/wp-mail.php
Disallow: /my/wordpress/wp-pass.php
Disallow: /my/wordpress/wp-login.php
Disallow: /my/wordpress/wp-links-opml.php
Disallow: /my/wordpress/wp-feed.php
Disallow: /my/wordpress/wp-config.php
Disallow: /my/wordpress/wp-commentsrss2.php
Disallow: /my/wordpress/wp-comments-post.php
Disallow: /my/wordpress/wp-blog-header.php
Disallow: /my/wordpress/wp-atom.php# BEGIN XML-SITEMAP-PLUGIN
Sitemap: http://www.bingeoncrackandtiramisu.co.uk/sitemap.xml.gz
# END XML-SITEMAP-PLUGIN