#
# robots.txt
#

# First, this is the
# robots.txt from http://www.wikipedia.org/ for "other" robots
# Thanks Wikipedians!
#
# 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.
#

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: /

# 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: /

User-agent: *
Sitemap: http://linuxchixperu.org/sitemap.xml
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wpi/
Disallow: /trackback/
Disallow: /*/*/*/*.xml
Disallow: /*/*/*/c/*


User-agent:  Googlebot
# No indexar directorios y archivos internos
Disallow: /cgi-bin/
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /*?jal_no_js=true&poll_id=*
 
# No indexar los archivos que terminan en extension
Disallow: /*.php$
Disallow: /*.js$
Disallow: /*.inc$
Disallow: /*.css$
Disallow: /*.gz$
Disallow: /*.cgi$
Disallow: /*.wmv$
Disallow: /*.cgi$
Disallow: /*.xhtml$
Disallow: /*.php*
Disallow: */trackback*
Disallow: /*?*
Allow: /wp-content/uploads/

# No indexar categorias, feeds y trackbacks.
Disallow: */trackback/
Disallow: */feed/
Disallow: /categoria/*
Disallow: /page/
Disallow: /comments/
Disallow: /2007/
Disallow: /2008/

# Google images que indexe todo
User-agent: Googlebot-Image
Allow: /*
Allow: /wp-content/uploads/

# Google Adsense que indexe todo
User-agent: Mediapartners-Google*
Allow: /*