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 # print "DB password: $wgDBpassword\n";
  42
  43
  44 $priorities = array (
  45         NS_MAIN             => 0.9,
  46         NS_TALK             => 0.4,
  47         NS_USER             => 0.3,
  48         NS_USER_TALK        => 0.3,
  49         NS_PROJECT          => 0.5,
  50         NS_PROJECT_TALK     => 0.2,
  51         NS_IMAGE            => 0.2,
  52         NS_IMAGE_TALK       => 0.1,
  53         NS_MEDIAWIKI        => 0.1,
  54         NS_MEDIAWIKI_TALK   => 0.1,
  55         NS_TEMPLATE         => 0.1,
  56         NS_TEMPLATE_TALK    => 0.1,
  57         NS_HELP             => 0.3,
  58         NS_HELP_TALK        => 0.1,
  59         NS_CATEGORY         => 0.3,
  60         NS_CATEGORY_TALK    => 0.1,
  61 );
  62
  63 $dbr =& wfGetDB( DB_SLAVE );
  64 $page = $dbr->tableName( 'page' );
  65 $rev = $dbr->tableName( 'revision' );
  66
  67 $findex = fopen( "sitemap_index.xml", "wb" );
  68 fwrite( $findex, '<?xml version="1.0" encoding="UTF-8"?>
  69    <sitemapindex xmlns="http://www.google.com/schemas/sitemap/0.84">
  70    ' );
  71
  72 foreach ( $priorities as $ns => $priority) {
  73         $sql = "SELECT page_namespace,page_title,page_is_redirect,rev_timestamp  FROM $page, $rev ".
  74                 "WHERE page_namespace = $ns AND page_latest = rev_id ";
  75         print "DB query : $sql\nprocessing ...";
  76         $res = $dbr->query( $sql );
  77         print " done\n";
  78
  79         $gzfile = false;
  80         $rowcount=0;
  81         $sitemapcount=0;
  82         while ( $row = $dbr->fetchObject( $res ) ) {
  83                 if ( $rowcount % 9000 == 0 ) {
  84                         if ( $gzfile !== false ) {
  85                                 gzwrite( $gzfile, '</urlset>' );
  86                                 gzclose( $gzfile );
  87                         }
  88                         $sitemapcount ++;
  89                         $fname = "sitemap-NS".$ns."-".$sitemapcount.".xml.gz";
  90                         $gzfile = gzopen( $fname, "wb" );
  91                         gzwrite( $gzfile, '<?xml version="1.0" encoding="UTF-8"?>
  92                                         < urlset xmlns="http://www.google.com/schemas/sitemap/0.84">' );
  93                         fwrite( $findex, '<sitemap><loc>'.$wgServer.'/'.$fname."</loc></sitemap>\n" );
  94                         print "$fname\n";
  95                 }
  96                 $rowcount ++;
  97                 $nt = Title::makeTitle( $row->page_namespace, $row->page_title );
  98                 $date = substr($row->rev_timestamp, 0, 4). '-' .
  99                         substr($row->rev_timestamp, 4, 2). '-' .
 100                         substr($row->rev_timestamp, 6, 2);
 101                 gzwrite( $gzfile, "<url>\n  <loc>" . $nt->getFullURL() .
 102                                 "</loc>\n  <lastmod>".$date."</lastmod>\n  " .
 103                                 '<priority>' . $priority . '</priority>' .
 104                                 "\n</url>\n" );
 105         }
 106         if ( $gzfile ) {
 107                 gzwrite( $gzfile, "</urlset>\n" );
 108                 gzclose( $gzfile );
 109         }
 110         print "\n";
 111 }
 112 fwrite( $findex, "</sitemapindex>\n" );
 113 fclose( $findex );
 114
 115
 116 ?>