maintenance/generateSitemap.php

   1 <?php
   2 /**
   3  * @package MediaWiki
   4  * @subpackage Maintenance
   5  *
   6  * Creates a Google sitemap.
   7  * https://www.google.com/webmasters/sitemaps/docs/en/about.html
   8  */
   9
  10 # Copyright (C) 2005 Jens Frank <jeluf@gmx.de>, Brion Vibber <brion@pobox.com>
  11 # http://www.mediawiki.org/
  12 #
  13 # This program is free software; you can redistribute it and/or modify
  14 # it under the terms of the GNU General Public License as published by
  15 # the Free Software Foundation; either version 2 of the License, or
  16 # (at your option) any later version.
  17 #
  18 # This program is distributed in the hope that it will be useful,
  19 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  20 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  21 # GNU General Public License for more details.
  22 #
  23 # You should have received a copy of the GNU General Public License along
  24 # with this program; if not, write to the Free Software Foundation, Inc.,
  25 # 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  26 # http://www.gnu.org/copyleft/gpl.html
  27
  28 if ( $argc < 2) {
  29         print "Usage: php generateSitemap.php servername [options]\n";
  30         print " servername is the name of the website, e.g. mywiki.mydomain.org\n";
  31         exit ;
  32 }
  33 $_SERVER['HOSTNAME'] = $argv[1];
  34 print $argv[1] . "\n";
  35
  36
  37 /** */
  38 require_once( "commandLine.inc" );
  39  print "DB name: $wgDBname\n";
  40  print "DB user: $wgDBuser\n";
  41
  42 $priorities = array (
  43         NS_MAIN             => 0.9,
  44         NS_TALK             => 0.4,
  45         NS_USER             => 0.3,
  46         NS_USER_TALK        => 0.3,
  47         NS_PROJECT          => 0.5,
  48         NS_PROJECT_TALK     => 0.2,
  49         NS_IMAGE            => 0.2,
  50         NS_IMAGE_TALK       => 0.1,
  51         NS_MEDIAWIKI        => 0.1,
  52         NS_MEDIAWIKI_TALK   => 0.1,
  53         NS_TEMPLATE         => 0.1,
  54         NS_TEMPLATE_TALK    => 0.1,
  55         NS_HELP             => 0.3,
  56         NS_HELP_TALK        => 0.1,
  57         NS_CATEGORY         => 0.3,
  58         NS_CATEGORY_TALK    => 0.1,
  59 );
  60
  61 $dbr =& wfGetDB( DB_SLAVE );
  62 $page = $dbr->tableName( 'page' );
  63
  64 $findex = fopen( "sitemap-index-$wgDBname.xml", "wb" );
  65 fwrite( $findex, '<?xml version="1.0" encoding="UTF-8"?>' . "\n" .
  66 '<sitemapindex xmlns="http://www.google.com/schemas/sitemap/0.84">' . "\n" );
  67
  68 foreach ( $priorities as $ns => $priority) {
  69         $sql = "SELECT page_namespace,page_title,page_is_redirect,page_touched FROM $page WHERE page_namespace = $ns";
  70         print "DB query : $sql\nprocessing ...";
  71         $res = $dbr->query( $sql );
  72         print " done\n";
  73
  74         $gzfile = false;
  75         $rowcount=0;
  76         $sitemapcount=0;
  77         while ( $row = $dbr->fetchObject( $res ) ) {
  78                 if ( $rowcount % 9000 == 0 ) {
  79                         if ( $gzfile !== false ) {
  80                                 gzwrite( $gzfile, '</urlset>' );
  81                                 gzclose( $gzfile );
  82                         }
  83                         $sitemapcount ++;
  84                         $fname = "sitemap-{$wgDBname}-NS{$ns}-{$sitemapcount}.xml.gz";
  85                         $gzfile = gzopen( $fname, "wb" );
  86                         gzwrite( $gzfile, '<?xml version="1.0" encoding="UTF-8"?>' . "\n" .
  87                                 '<urlset xmlns="http://www.google.com/schemas/sitemap/0.84">' . "\n" );
  88                         fwrite( $findex, "\t<sitemap>\n\t\t<loc>$wgServer/$fname</loc>\n\t</sitemap>\n" );
  89                         print "$fname\n";
  90                 }
  91                 $rowcount ++;
  92                 $nt = Title::makeTitle( $row->page_namespace, $row->page_title );
  93                 $date = substr($row->page_touched, 0, 4). '-' .
  94                         substr($row->page_touched, 4, 2). '-' .
  95                         substr($row->page_touched, 6, 2);
  96                 gzwrite( $gzfile, "\t<url>\n\t\t<loc>" . $nt->getFullURL() .
  97                                 "</loc>\n\t\t<lastmod>$date</lastmod>\n" .
  98                                 "\t\t<priority>$priority</priority>\n" .
  99                                 "\t</url>\n" );
 100         }
 101         if ( $gzfile ) {
 102                 gzwrite( $gzfile, "</urlset>\n" );
 103                 gzclose( $gzfile );
 104         }
 105         print "\n";
 106 }
 107 fwrite( $findex, "</sitemapindex>\n" );
 108 fclose( $findex );
 109
 110
 111 ?>