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
19User-agent: *
20Crawl-delay: 10
21# Directories
22Disallow: /includes/
23Disallow: /misc/
24Disallow: /modules/
25Disallow: /profiles/
26Disallow: /scripts/
27Disallow: /themes/
28# Files
29Disallow: /CHANGELOG.txt
30Disallow: /cron.php
31Disallow: /INSTALL.mysql.txt
32Disallow: /INSTALL.pgsql.txt
33Disallow: /INSTALL.sqlite.txt
34Disallow: /install.php
35Disallow: /INSTALL.txt
36Disallow: /LICENSE.txt
37Disallow: /MAINTAINERS.txt
38Disallow: /update.php
39Disallow: /UPGRADE.txt
40Disallow: /xmlrpc.php
41# Paths (clean URLs)
42Disallow: /admin/
43Disallow: /comment/reply/
44Disallow: /filter/tips/
45Disallow: /node/add/
46Disallow: /search/
47Disallow: /user/register/
48Disallow: /user/password/
49Disallow: /user/login/
50Disallow: /user/logout/
51# Paths (no clean URLs)
52Disallow: /?q=admin/
53Disallow: /?q=comment/reply/
54Disallow: /?q=filter/tips/
55Disallow: /?q=node/add/
56Disallow: /?q=search/
57Disallow: /?q=user/password/
58Disallow: /?q=user/register/
59Disallow: /?q=user/login/
60Disallow: /?q=user/logout/
61# Stop access to videos used in overlays
62Disallow: /content/
63Sitemap: http://www.ox.ac.uk/sitemap.xml