robots.txt

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