Sitemap: http://weaselhead.org/sitemap.xml

#
# robots.txt for Brent Johner's clients
# Irresponsible spiders are blocked from using this site.
#

# User-agent: *
# 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: /

# slow down Yahoo
User-agent: Slurp
Crawl-delay: 10


#
# 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 anything
User-agent: ia_archiver
Disallow: /

User-agent: *
Disallow:
Crawl-delay: 10
Disallow: /buttons/
Disallow: /calendar/
Disallow: /config_files/
Disallow: /error_pages/
Disallow: /images/
Disallow: /imagemanagement/
Disallow: /include/
Disallow: /javascript/
Disallow: /mailGroups
Disallow: /members/
Disallow: /members_old/
Disallow: /menus/
Disallow: /newsletter/
Disallow: /photographers
Disallow: /phpmailer/
Disallow: /phpmyadmin/
Disallow: /photos/
Disallow: /pool/
Disallow: /pool_old/
Disallow: /profile/profile_pic_frame.php
Disallow: /phpbb/admin/
Disallow: /phpbb/attach_mod/
Disallow: /phpbb/cache/
Disallow: /phpbb/db/
Disallow: /phpbb/docs/
Disallow: /phpbb/files/
Disallow: /phpbb/images/
Disallow: /phpbb/includes/
Disallow: /phpbb/language/
Disallow: /phpbb/templates/
Disallow: /phpbb/attach_rules.php
Disallow: /phpbb/common.php
Disallow: /phpbb/config.php
Disallow: /phpbb/download.php
Disallow: /phpbb/extension.inc
Disallow: /phpbb/faq.php
Disallow: /phpbb/groupcp.php
Disallow: /phpbb/login.php
Disallow: /phpbb/memberlist.php
Disallow: /phpbb/modcp.php
Disallow: /phpbb/posting.php
Disallow: /phpbb/privmsg.php
Disallow: /phpbb/attach_rules.php
Disallow: /phpbb/profile.php
Disallow: /phpbb/search.php
Disallow: /phpbb/uacp.php
Disallow: /scripts/
Disallow: /TAWUsers/
Disallow: /stats/
Disallow: /wildlifedb2/
Disallow: /weaselheadDBBackups/
Disallow: /zz/
Disallow: /*.asp$
Disallow: /learn/*.asp$