crans/scripts
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

mnage uniquement

Browse source 
darcs-hash:20060505083659-72cb0-ebd538f09b6178702c3deccf96fa684a1f80a8d7.gz
This commit is contained in:
salles 2006-05-05 10:36:59 +02:00
parent 80b70a333d
commit 56e9249400
1 changed files with 0 additions and 150 deletions
Download patch file Download diff file Expand all files Collapse all files

150
google_sitemap/config_www.xml
View file

@ -1,69 +1,9 @@
<?xml version="1.0" encoding="UTF-8"?>
<!--
sitemap_gen.py example configuration script
This file specifies a set of sample input parameters for the
sitemap_gen.py client.
You should copy this file into "config.xml" and modify it for
your server.
********************************************************* -->
<!-- ** MODIFY **
The "site" node describes your basic web site.
Required attributes:
base_url - the top-level URL of the site being mapped
store_into - the webserver path to the desired output file.
This should end in '.xml' or '.xml.gz'
(the script will create this file)
Optional attributes:
verbose - an integer from 0 (quiet) to 3 (noisy) for
how much diagnostic output the script gives
suppress_search_engine_notify="1"
- disables notifying search engines about the new map
(same as the "testing" command-line argument.)
default_encoding
- names a character encoding to use for URLs and
file paths. (Example: "UTF-8")
-->
<site
base_url="http://www.crans.org/"
store_into="/var/www/site_www/www.xml.gz"
verbose="1"
>
<!-- ********************************************************
INPUTS
All the various nodes in this section control where the script
looks to find URLs.
MODIFY or DELETE these entries as appropriate for your server.
********************************************************* -->
<!-- ** MODIFY or DELETE **
"url" nodes specify individual URLs to include in the map.
Required attributes:
href - the URL
Optional attributes:
lastmod - timestamp of last modification (ISO8601 format)
changefreq - how often content at this URL is usually updated
priority - value 0.0 to 1.0 of relative importance in your site
<url href="http://www.example.com/stats?q=name" />
<url
href="http://www.example.com/stats?q=age"
lastmod="2004-11-14T01:00:00-07:00"
changefreq="yearly"
priority="0.3"
/>
-->
<url
href="http://www.crans.org/"
lastmod="2006-05-04T22:40:00+02:00"
@ -83,99 +23,9 @@
priority="0.5"
/>
<!-- ** MODIFY or DELETE **
"urllist" nodes name text files with lists of URLs.
An example file "example_urllist.txt" is provided.
Required attributes:
path - path to the file
Optional attributes:
encoding - encoding of the file if not US-ASCII
<urllist path="example_urllist.txt" encoding="UTF-8" />
-->
<!-- ** MODIFY or DELETE **
"directory" nodes tell the script to walk the file system
and include all files and directories in the Sitemap.
Required attributes:
path - path to begin walking from
url - URL equivalent of that path
Optional attributes:
default_file - name of the index or default file for directory URLs
<directory path="/var/www/icons" url="http://www.example.com/images/" />
<directory
path="/var/www/docroot"
url="http://www.example.com/"
default_file="index.html"
/>
-->
<!-- ** MODIFY or DELETE **
"accesslog" nodes tell the script to scan webserver log files to
extract URLs on your site. Both Common Logfile Format (Apache's default
logfile) and Extended Logfile Format (IIS's default logfile) can be read.
Required attributes:
path - path to the file
Optional attributes:
encoding - encoding of the file if not US-ASCII
<accesslog path="/etc/httpd/logs/access.log" encoding="UTF-8" />
<accesslog path="/etc/httpd/logs/access.log.0" encoding="UTF-8" />
<accesslog path="/etc/httpd/logs/access.log.1.gz" encoding="UTF-8" />
-->
<!-- ** MODIFY or DELETE **
"sitemap" nodes tell the script to scan other Sitemap files. This can
be useful to aggregate the results of multiple runs of this script into
a single Sitemap.
Required attributes:
path - path to the file
-->
<sitemap path="/var/www/site_www/www.xml.gz" />
<!-- ********************************************************
FILTERS
Filters specify wild-card patterns that the script compares
against all URLs it finds. Filters can be used to exclude
certain URLs from your Sitemap, for instance if you have
hidden content that you hope the search engines don't find.
Filters can be either type="wildcard", which means standard
path wildcards (* and ?) are used to compare against URLs,
or type="regexp", which means regular expressions are used
to compare.
Filters are applied in the order specified in this file.
An action="drop" filter causes exclusion of matching URLs.
An action="pass" filter causes inclusion of matching URLs,
shortcutting any other later filters that might also match.
If no filter at all matches a URL, the URL will be included.
Together you can build up fairly complex rules.
The default action is "drop".
The default type is "wildcard".
You can MODIFY or DELETE these entries as appropriate for
your site. However, unlike above, the example entries in
this section are not contrived and may be useful to you as
they are.
********************************************************* -->
<!-- Exclude URLs that end with a '~' (IE: emacs backup files) -->
<filter action="drop" type="wildcard" pattern="*~" />
<!-- Exclude URLs within UNIX-style hidden files or directories -->
<filter action="drop" type="regexp" pattern="/\.[^/]*" />
<filter action="drop" type="wildcard" pattern="*?action=fullsearch*" />