|
1 # $Id: robots.txt,v 1.9.2.1 2008/12/10 20:12:19 goba 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: /includes/ |
|
24 Disallow: /misc/ |
|
25 Disallow: /modules/ |
|
26 Disallow: /profiles/ |
|
27 Disallow: /scripts/ |
|
28 Disallow: /sites/ |
|
29 Disallow: /themes/ |
|
30 # Files |
|
31 Disallow: /CHANGELOG.txt |
|
32 Disallow: /cron.php |
|
33 Disallow: /INSTALL.mysql.txt |
|
34 Disallow: /INSTALL.pgsql.txt |
|
35 Disallow: /install.php |
|
36 Disallow: /INSTALL.txt |
|
37 Disallow: /LICENSE.txt |
|
38 Disallow: /MAINTAINERS.txt |
|
39 Disallow: /update.php |
|
40 Disallow: /UPGRADE.txt |
|
41 Disallow: /xmlrpc.php |
|
42 # Paths (clean URLs) |
|
43 Disallow: /admin/ |
|
44 Disallow: /comment/reply/ |
|
45 Disallow: /contact/ |
|
46 Disallow: /logout/ |
|
47 Disallow: /node/add/ |
|
48 Disallow: /search/ |
|
49 Disallow: /user/register/ |
|
50 Disallow: /user/password/ |
|
51 Disallow: /user/login/ |
|
52 # Paths (no clean URLs) |
|
53 Disallow: /?q=admin/ |
|
54 Disallow: /?q=comment/reply/ |
|
55 Disallow: /?q=contact/ |
|
56 Disallow: /?q=logout/ |
|
57 Disallow: /?q=node/add/ |
|
58 Disallow: /?q=search/ |
|
59 Disallow: /?q=user/password/ |
|
60 Disallow: /?q=user/register/ |
|
61 Disallow: /?q=user/login/ |