mirror of
https://github.com/stefanocasazza/ULib.git
synced 2025-09-28 19:05:55 +08:00
42 lines
1.0 KiB
Plaintext
42 lines
1.0 KiB
Plaintext
# $Id: robots.txt,v 1.14 2009/09/11 04:17:07 webchick Exp $
|
|
#
|
|
# robots.txt
|
|
#
|
|
# This file is to prevent the crawling and indexing of certain parts
|
|
# of your site by web crawlers and spiders run by sites like Yahoo!
|
|
# and Google. By telling these "robots" where not to go on your site,
|
|
# you save bandwidth and server resources.
|
|
#
|
|
# This file will be ignored unless it is at the root of your host:
|
|
# Used: http://example.com/robots.txt
|
|
# Ignored: http://example.com/site/robots.txt
|
|
#
|
|
# For more information about the robots.txt standard, see:
|
|
# http://www.robotstxt.org/wc/robots.html
|
|
#
|
|
# For syntax checking, see:
|
|
# http://www.sxw.org.uk/computing/robots/check.html
|
|
|
|
User-agent: *
|
|
Crawl-delay: 10
|
|
# Directories
|
|
Disallow: /js/
|
|
Disallow: /css/
|
|
Disallow: /images/
|
|
Disallow: /form/
|
|
Disallow: /cgi-bin/
|
|
# Files
|
|
Disallow: /.htdigest
|
|
Disallow: /.htpasswd
|
|
Disallow: /favicon.ico
|
|
# Paths (clean URLs)
|
|
Disallow: /user/
|
|
Disallow: /admin/
|
|
Disallow: /search/
|
|
# Paths (no clean URLs)
|
|
Disallow: /?q=user/
|
|
Disallow: /?q=admin/
|
|
Disallow: /?q=search/
|
|
|
|
|