# $Id: robots.txt,v 1.7.2.1 2007/03/23 18:57:07 drumm Exp $ # # robots.txt # # This file is to prevent the crawling and indexing of certain parts # of your site by web crawlers and spiders run by sites like Yahoo! # and Google. By telling these "robots" where not to go on your site, # you save bandwidth and server resources. # # This file will be ignored unless it is at the root of your host: # Used: http://example.com/robots.txt # Ignored: http://example.com/site/robots.txt # # For more information about the robots.txt standard, see: # http://www.robotstxt.org/wc/robots.html # # For syntax checking, see: # http://www.sxw.org.uk/computing/robots/check.html # Image Google crawler User-agent: Googlebot-Image Disallow: # Adsense crawler User-agent: Mediapartners-Google* Disallow: User-agent: noxtrumbot Crawl-delay: 400 User-agent: msnbot Crawl-delay: 10 User-agent: msnbot-media Crawl-delay: 30 User-agent: * # Directorios Disallow: /database/ Disallow: /includes/ Disallow: /misc/ Disallow: /modules/ Disallow: /sites/ Disallow: /themes/ Disallow: /scripts/ Disallow: /updates/ Disallow: /profiles/ # Archivos Disallow: /xmlrpc.php Disallow: /cron.php Disallow: /update.php Disallow: /install.php Disallow: /INSTALL.txt Disallow: /INSTALL.mysql.txt Disallow: /INSTALL.pgsql.txt Disallow: /CHANGELOG.txt Disallow: /MAINTAINERS.txt Disallow: /LICENSE.txt Disallow: /UPGRADE.txt # Paths (clean URLs) Disallow: /node/ Disallow: /privatemsg/ Disallow: /admin/ Disallow: /aggregator/ Disallow: /comment/reply/ Disallow: /comment/edit/ Disallow: /contact/ Disallow: /logout/ Disallow: /node/add/ Disallow: /search/ Disallow: /user/register/ Disallow: /user/password/ Disallow: /user/login/ Disallow: /taxonomy/ Disallow: /categorias/ Disallow: /imagen/ Disallow: /tagadelic/ # Paths (no clean URLs) Disallow: /?q=node/ Disallow: /?q=privatemsg/ Disallow: /?q=admin/ Disallow: /?q=aggregator/ Disallow: /?q=comment/reply/ Disallow: /?q=comment/edit/ Disallow: /?q=contact/ Disallow: /?q=logout/ Disallow: /?q=node/add/ Disallow: /?q=search/ Disallow: /?q=user/password/ Disallow: /?q=user/register/ Disallow: /?q=user/login/ Disallow: /?q=taxonomy/ Disallow: /?q=categorias/ Disallow: /?q=imagen/ Disallow: /?q=tagadelic/ Disallow: /?q=forum/ # Modifications from default Disallow: /node$ Disallow: /user$ Disallow: /search$ Disallow: /?q= Disallow: /*/track$ Disallow: /*/track?page= Disallow: /tracker? Disallow: /print/ Disallow: /book/ Disallow: /man/ Disallow: /forward/ Disallow: /frontpage$ Disallow: /usuario/register Disallow: /usuario/password Disallow: /usuario/login Disallow: /forum/ # Disallow robots from all but the main feed Disallow: /*/feed$ Disallow: /crss # This prevents duplicate content caused by some modules like the Forums and Views modules Disallow: /*sort= # Prevent duplicate content created by the Image module Disallow: /*size= # Directories that should be blocked on any site Disallow: /*.zip$ Disallow: /*.doc$ Disallow: /*.exe$ Disallow: /*.pdf$ # FullSite and bad bots User-agent: libwww Disallow: / User-agent: sitecheck.internetseer.com Disallow: / User-agent: TurnitinBot Disallow: / User-agent: EmailCollector Disallow: / User-agent: EmailWolf 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: WebReaper Disallow: / #bad bots User-agent: VoilaBot Disallow: / User-agent: ichiro Disallow: / User-agent: Speedy Disallow: / User-agent: KeegyBot Disallow: / User-agent: studybot Disallow: / User-agent: omgilibot Disallow: / User-agent: Seekbot Disallow: / #sitemaps Sitemap: http://foro.angelesmanualidades.com/sitemap.xml