robots.txt

   1 # $Id: robots.txt,v 1.7.2.1 2007/03/23 18:57:07 drumm Exp $
   2 #
   3 # robots.txt
   4 #
   5 # This file is to prevent the crawling and indexing of certain parts
   6 # of your site by web crawlers and spiders run by sites like Yahoo!
   7 # and Google. By telling these "robots" where not to go on your site,
   8 # you save bandwidth and server resources.
   9 #
  10 # This file will be ignored unless it is at the root of your host:
  11 # Used:    http://example.com/robots.txt
  12 # Ignored: http://example.com/site/robots.txt
  13 #
  14 # For more information about the robots.txt standard, see:
  15 # http://www.robotstxt.org/wc/robots.html
  16 #
  17 # For syntax checking, see:
  18 # http://www.sxw.org.uk/computing/robots/check.html
  19
  20 User-agent: *
  21 Crawl-delay: 10
  22 # Directories
  23 Disallow: /database/
  24 Disallow: /includes/
  25 Disallow: /misc/
  26 Disallow: /modules/
  27 Disallow: /sites/
  28 Disallow: /themes/
  29 Disallow: /scripts/
  30 Disallow: /updates/
  31 Disallow: /profiles/
  32 # Files
  33 Disallow: /xmlrpc.php
  34 Disallow: /cron.php
  35 Disallow: /update.php
  36 Disallow: /install.php
  37 Disallow: /INSTALL.txt
  38 Disallow: /INSTALL.mysql.txt
  39 Disallow: /INSTALL.pgsql.txt
  40 Disallow: /CHANGELOG.txt
  41 Disallow: /MAINTAINERS.txt
  42 Disallow: /LICENSE.txt
  43 Disallow: /UPGRADE.txt
  44 # Paths (clean URLs)
  45 Disallow: /admin/
  46 Disallow: /aggregator/
  47 Disallow: /comment/reply/
  48 Disallow: /contact/
  49 Disallow: /logout/
  50 Disallow: /node/add/
  51 Disallow: /search/
  52 Disallow: /user/register/
  53 Disallow: /user/password/
  54 Disallow: /user/login/
  55 # Paths (no clean URLs)
  56 Disallow: /?q=admin/
  57 Disallow: /?q=aggregator/
  58 Disallow: /?q=comment/reply/
  59 Disallow: /?q=contact/
  60 Disallow: /?q=logout/
  61 Disallow: /?q=node/add/
  62 Disallow: /?q=search/
  63 Disallow: /?q=user/password/
  64 Disallow: /?q=user/register/
  65 Disallow: /?q=user/login/