savannah.gnu.org

# Search engine crawlers restrictions

# This file is checked by crawlers only if installed at the root "/"
# of the website (it won't be read if you installed Savane in a
# subdirectory such as http://yoursite.tld/savane/), so paths in this
# file are relatives to the root of the website.

User-agent: *

# Disallow pages without indexable content
Disallow: /include/
Disallow: /images/
Disallow: /siteadmin/

# Disallow login.php because everypage links to it with a 'uri='
# parameter - this generates lots of useless pages to index, and lots
# of traffic for nothing
Disallow: /account/login.php

# There's one page per user and it doesn't contain any indexable
# content - let's exclude it:
Disallow: /sendmessage.php

# Disallow those which are hit thousands of time for some reason:
Disallow: /bugs/?func=search&group=
Disallow: /cookbook/?func=search&group=
Disallow: /patch/?func=search&group=
Disallow: /support/?func=search&group=
Disallow: /task/?func=search&group=

# Disallow dynamically generated gpg key pages.
Disallow: /project/memberlist-gpgkeys.php
Disallow: /project/release-gpgkeys.php

## Extended syntax ('*' wildcard)

# Disallow identical pages - less crawler traffic
Disallow: /*?reload=1
Disallow: /*?printer=1

# Disallow multi-fields sorts which exhibit thousands of URLs
Disallow: /*func=browse
Disallow: /*func=digest