1
#
2
# robots.txt for https://www.w3.org/
3
#
4
# $Id: robots.txt,v 1.89 2024/03/13 18:11:44 gerald Exp $
5
#
6
7
# For use by search.w3.org
8
User-agent: W3C-gsa
9
Disallow: /Out-Of-Date
10
11
User-agent: W3T_SE
12
Disallow: /Out-Of-Date
13
14
User-agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT; MS Search 4.0 Robot)
15
Disallow: /
16
17
# W3C Link checker
18
User-agent: W3C-checklink
19
Disallow:
20
21
# Applebot continues to make hundreds of thousands of reqs/day for this area
22
# even though it has been returning permanent redirects for years
23
User-agent: Applebot
24
Disallow: /People/domain/
25
26
# the following settings apply to all bots
27
User-agent: *
28
# Blogs - WordPress
29
# https://codex.wordpress.org/Search_Engine_Optimization_for_WordPress#Robots.txt_Optimization
30
Disallow: /*/wp-admin/
31
Disallow: /*/wp-includes/
32
Disallow: /*/wp-content/plugins/
33
Disallow: /*/wp-content/cache/
34
Disallow: /*/wp-content/themes/
35
Disallow: /blog/*/trackback/
36
Disallow: /blog/*/feed/
37
Disallow: /blog/*/comments/
38
Disallow: /blog/*/category/*/*
39
Disallow: /blog/*/*/trackback/
40
Disallow: /blog/*/*/feed/
...
</html>