Yahoo Sitemaps

From ThinkLemon

This is a PHP file which will print out a text file containing all the links in your wiki on a separate line. This can then be submitted to Yahoo! like a primitive Google sitemap. This file was originally modified from the Google Sitemap by Elliot (psconclave.com). This will work with 1.5.x and 1.6.x.

[edit]

Instructions

Copy-paste the source code from below to an empty text file.
Save the file as yahoo_sitemap.php.
Upload the script to your root directory e.g http://www.mysite.com/yahoo_sitemap.php.
Edit your .htaccess file in your root directory (you may need to create this if it doesn't exist yet, add these lines to it

RewriteEngine On
RewriteRule ^urllist.txt$ /yahoo_sitemap.php [L]

Test your yahoo sitemap generator by going to http://www.mysite.com/urllist.txt (example: http://www.psconclave.com/urllist.txt.

[edit]

Sourcecode

<?php
# Mediawiki Yahoo sitemap generator
# Edited from the Google Sitemap Generator
# Edited by the brilliant Elliot Goodrich <rebornfromtheashes@gmail.com>

# .htaccess rewrite  must be used because yahoo only accepts urllist.txt
#
#         # yahoo rewrite
#         RewriteRule ^urllist.txt$ /yahoo_sitemap.php [L]
#

define( 'MEDIAWIKI', true );

require_once( './w/LocalSettings.php' );
require_once( './w/includes/GlobalFunctions.php' );

# -----------------------------------------------------
# Send text header, tell agents this is text file.
# -----------------------------------------------------

header("Content-Type: text/plain; charset=UTF-8");

# -----------------------------------------------------
# Start connection
# -----------------------------------------------------

$connWikiDB = mysql_pconnect($wgDBserver, $wgDBuser, $wgDBpassword) 
	or trigger_error(mysql_error(),E_USER_ERROR); 
mysql_select_db($wgDBname, $connWikiDB);

# -----------------------------------------------------
# Build query
# Skipping redirects and MediaWiki namespace
# -----------------------------------------------------

$query_rsPages = "SELECT page_namespace, page_title, page_touched ".
	"FROM ".$wgDBprefix."page ".
	"WHERE (page_is_redirect = 0 AND page_namespace NOT IN (8, 9)) ".
	"ORDER BY page_touched DESC";

# -----------------------------------------------------
# Fetch the data from the DB
# -----------------------------------------------------

$rsPages = mysql_query($query_rsPages, $connWikiDB) or die(mysql_error());
# Fetch the array of pages
$row_rsPages = mysql_fetch_assoc($rsPages);
$totalRows_rsPages = mysql_num_rows($rsPages);


// Find Project Namespace
if($wgMetaNamespace === FALSE)
	$wgMetaNamespace = str_replace( ' ', '_', $wgSitename );

do { 

	# -----------------------------------------------------
	# 1. Determine the pagetitle using namespace:page_name
	# -----------------------------------------------------
	

	switch ($row_rsPages['page_namespace']) {
		case "1":
			$sPageName = "Talk:".$row_rsPages['page_title'];
			break;
		case 2:
			$sPageName = "User:".$row_rsPages['page_title'];
			break;
		case 3:
			$sPageName = "User_talk:".$row_rsPages['page_title'];
			break;
		case 4:
			$sPageName = $wgMetaNamespace.":".$row_rsPages['page_title'];
			break;
		case 5:
			$sPageName = $wgMetaNamespace."_talk:".$row_rsPages['page_title'];
			break;
		case 6:
			$sPageName = "Image:".$row_rsPages['page_title'];
			break;
		case 7:
			$sPageName = "Image_talk:".$row_rsPages['page_title'];
			break;
		case 8:
			$sPageName = "MediaWiki:".$row_rsPages['page_title'];
			break;
		case 9:
			$sPageName = "MediaWiki_talk:".$row_rsPages['page_title'];
			break;
		case 10:
			$sPageName = "Template:".$row_rsPages['page_title'];
			break;
		case 11:
			$sPageName = "Template_talk:".$row_rsPages['page_title'];
			break;
		case 12:
			$sPageName = "Help:".$row_rsPages['page_title'];
			break;
		case 13:
			$sPageName = "Help_talk:".$row_rsPages['page_title'];
			break;
		case 14:
			$sPageName = "Category:".$row_rsPages['page_title'];
			break;
		case 15:
			$sPageName = "Category_talk:".$row_rsPages['page_title'];
			break;
		default:
			$sPageName = $row_rsPages['page_title'];
	}

# -----------------------------------------------------
# Start output
# -----------------------------------------------------

 print "http://" . $wgServerName . eregi_replace('\$1',$sPageName,$wgArticlePath) . "\n";

 } while ($row_rsPages = mysql_fetch_assoc($rsPages));

# -----------------------------------------------------
# Clear Connection
# -----------------------------------------------------

mysql_free_result($rsPages);



?>

[edit]