SkipperGuide

SkipperGuide:Interne Dokumentation/Google Sitemaps: Unterschied zwischen den Versionen

VisuellWikitext
Peter (Diskussion | Beiträge)
Bürokraten, Oberflächenadministratoren, smwadministrator, smwcurator, smweditor, Administratoren
9.610 Bearbeitungen
Keine Bearbeitungszusammenfassung
 
Peter (Diskussion | Beiträge)
Bürokraten, Oberflächenadministratoren, smwadministrator, smwcurator, smweditor, Administratoren
9.610 Bearbeitungen
Keine Bearbeitungszusammenfassung
 
(2 dazwischenliegende Versionen desselben Benutzers werden nicht angezeigt)
Zeile 2: Zeile 2:


== crontab ==
== crontab ==
(Stündlicher Aufruf)
(Stündlicher Aufruf, inkl. Backup-Aufruf)


  0      *       *       *       *      /hp/aa/ac/dm/www/sitemaps/doit
  SHELL=/bin/sh
PATH=/usr/bin:/usr/sbin:/sbin:/bin
#min  hour  day  month  dow  user  command
# Command jede Stunde ausführen:
  0     *    *    *    *       /hp/aa/ac/dm/www/backup/doit
  0    *     *     *     *      /hp/aa/ac/dm/www/sitemaps/doit


== www/sitemaps/doit ==
== www/sitemaps/doit ==
Zeile 10: Zeile 16:


  #!/bin/sh
  #!/bin/sh
  /usr/bin/php /hp/aa/ac/dm/www/mediawiki/maintenance/generateSitemap.php www.skipperguide.de --fspath=/hp/aa/ac/dm/www/sitemaps/ -path=/hp/aa/ac/dm/www/mediawiki --compress=no
  /usr/bin/php /hp/aa/ac/dm/www/mediawiki/maintenance/generateSitemap.php www.skipperguide.de --fspath=/hp/aa/ac/dm/www/ -path=/hp/aa/ac/dm/www/mediawiki --compress=no


== maintenance/generateSitemaps.php == (siehe sourceforge)
== maintenance/generateSitemaps.php == (siehe sourceforge)
Zeile 32: Zeile 38:
  :
  :
  >            case TS_ISO_8601_FOR_GOOGLE_SITEMAP_HACK: // quick hack
  >            case TS_ISO_8601_FOR_GOOGLE_SITEMAP_HACK: // quick hack
  >                    return gmdate( 'Y-m-d\TH:i:s', $uts );
  >                    return gmdate( 'Y-m-d\TH:i:s+02:00', $uts ); // +02:00: MESZ
                      // liegt ein Zeitpunkt in der Zukunft,
                      // wird der mit "invalid date" abgewiesen
               default:
               default:
                       wfDebugDieBacktrace( 'wfTimestamp() called with illegal output type.');
                       wfDebugDieBacktrace( 'wfTimestamp() called with illegal output type.');
Zeile 40: Zeile 48:
== Sitemap-Url ==
== Sitemap-Url ==


  www.skipperguide.de/sitemaps/sitemap-index-<DB-Name>.xml
  www.skipperguide.de/sitemap-index-<DB-Name>.xml
 
 
== hacked Script ==
<pre>
<?php
define( 'GS_MAIN', -2 );
define( 'GS_TALK', -1 );
define('TS_ISO_8601_FOR_GOOGLE_SITEMAP_HACK', 99); // quick hack
 
 
/**
* Creates a Google sitemap for the site
*
* @package MediaWiki
* @subpackage Maintenance
*
* @copyright Copyright © 2005, Ævar Arnfjörð Bjarmason
* @copyright Copyright © 2005, Jens Frank <jeluf@gmx.de>
* @copyright Copyright © 2005, Brion Vibber <brion@pobox.com>
*
* @link http://www.google.com/webmasters/sitemaps/docs/en/about.html
* @link http://www.google.com/schemas/sitemap/0.84/sitemap.xsd
*
* @license http://www.gnu.org/copyleft/gpl.html GNU General Public License 2.0 or later
*/
 
class GenerateSitemap {
/**
* The maximum amount of urls in a sitemap file
*
* @link http://www.google.com/schemas/sitemap/0.84/sitemap.xsd
*
* @var int
*/
var $url_limit;
 
/**
* The maximum size of a sitemap file
*
* @link http://www.google.com/webmasters/sitemaps/docs/en/protocol.html#faq_sitemap_size
*
* @var int
*/
var $size_limit;
 
/**
* The path to prepend to the filename
*
* @var string
*/
var $fspath;
 
/**
* The path to append to the domain name
*
* @var string
*/
var $path;
 
/**
* Whether or not to use compression
*
* @var bool
*/
var $compress;
 
/**
* The number of entries to save in each sitemap file
*
* @var array
*/
var $limit = array();
 
/**
* Key => value entries of namespaces and their priorities
*
* @var array
*/
var $priorities = array(
// Custom main namespaces
GS_MAIN => '0.5',
// Custom talk namesspaces
GS_TALK => '0.1',
// MediaWiki standard namespaces
NS_MAIN => '1.0',
NS_TALK => '0.1',
NS_USER => '0.5',
NS_USER_TALK => '0.1',
NS_PROJECT => '0.5',
NS_PROJECT_TALK => '0.1',
NS_IMAGE => '0.5',
NS_IMAGE_TALK => '0.1',
NS_MEDIAWIKI => '0.0',
NS_MEDIAWIKI_TALK => '0.1',
NS_TEMPLATE => '0.0',
NS_TEMPLATE_TALK => '0.1',
NS_HELP => '0.5',
NS_HELP_TALK => '0.1',
NS_CATEGORY => '0.5',
NS_CATEGORY_TALK => '0.1',
);
 
/**
* A one-dimensional array of namespaces in the wiki
*
* @var array
*/
var $namespaces = array();
 
/**
* When this sitemap batch was generated
*
* @var string
*/
var $timestamp;
 
/**
* A database slave object
*
* @var object
*/
var $dbr;
 
/**
* A resource pointing to the sitemap index file
*
* @var resource
*/
var $findex;
 
 
/**
* A resource pointing to a sitemap file
*
* @var resource
*/
var $file;
 
/**
* A resource pointing to php://stderr
*
* @var resource
*/
var $stderr;
 
/**
* Constructor
*
* @param string $fspath The path to prepend to the filenames, used to
*                    save them somewhere else than in the root directory
* @param string $path The path to append to the domain name
* @param bool $compress Whether to compress the sitemap files
*/
function GenerateSitemap( $fspath, $path, $compress ) {
global $wgDBname, $wgScriptPath;
 
$this->url_limit = 50000;
$this->size_limit = pow( 2, 20 ) * 10;
$this->fspath = isset( $fspath ) ? $fspath : '';
$this->path = isset( $path ) ? $path : $wgScriptPath;
$this->compress = $compress;
 
$this->stderr = fopen( 'php://stderr', 'wt' );
$this->dbr =& wfGetDB( DB_SLAVE );
$this->generateNamespaces();
$this->timestamp = wfTimestamp( TS_ISO_8601_FOR_GOOGLE_SITEMAP_HACK, wfTimestampNow() );
$this->findex = fopen( "{$this->fspath}sitemap-index-$wgDBname.xml", 'wb' );
}
 
/**
* Generate a one-dimensional array of existing namespaces
*/
function generateNamespaces() {
$fname = 'GenerateSitemap::generateNamespaces';
 
$res = $this->dbr->select( 'page',
array( 'page_namespace' ),
array(),
$fname,
array(
'GROUP BY' => 'page_namespace',
'ORDER BY' => 'page_namespace',
)
);
 
while ( $row = $this->dbr->fetchObject( $res ) )
$this->namespaces[] = $row->page_namespace;
}
 
/**
* Get the priority of a given namespace
*
* @param int $namespace The namespace to get the priority for
+
* @return string
*/
 
function priority( $namespace ) {
return isset( $this->priorities[$namespace] ) ? $this->priorities[$namespace] : $this->guessPriority( $namespace );
}
 
/**
* If the namespace isn't listed on the priority list return the
* default priority for the namespace, varies depending on whether it's
* a talkpage or not.
*
* @param int $namespace The namespace to get the priority for
*
* @return string
*/
function guessPriority( $namespace ) {
return Namespace::isMain( $namespace ) ? $this->priorities[GS_MAIN] : $this->priorities[GS_TALK];
}
 
/**
* Return a database resolution of all the pages in a given namespace
*
* @param int $namespace Limit the query to this namespace
*
* @return resource
*/
function getPageRes( $namespace ) {
$fname = 'GenerateSitemap::getPageRes';
 
return $this->dbr->select( 'page',
array(
'page_namespace',
'page_title',
'page_touched',
),
array( 'page_namespace' => $namespace ),
$fname
);
}
 
/**
* Main loop
*
* @access public
*/
function main() {
global $wgDBname, $wgContLang;
 
fwrite( $this->findex, $this->openIndex() );
 
foreach ( $this->namespaces as $namespace ) {
$res = $this->getPageRes( $namespace );
$this->file = false;
$this->generateLimit( $namespace );
$length = $this->limit[0];
$i = $smcount = 0;
 
$fns = $wgContLang->getFormattedNsText( $namespace );
$this->debug( "$namespace ($fns)" );
while ( $row = $this->dbr->fetchObject( $res ) ) {
if ( $i++ === 0 || $i === $this->url_limit + 1 || $length + $this->limit[1] + $this->limit[2] > $this->size_limit ) {
if ( $this->file !== false ) {
$this->write( $this->file, $this->closeFile() );
$this->close( $this->file );
}
$filename = $this->sitemapFilename( $namespace, $smcount++ );
$this->file = $this->open( $this->fspath . $filename, 'wb' );
$this->write( $this->file, $this->openFile() );
fwrite( $this->findex, $this->indexEntry( $filename ) );
$this->debug( "\t$filename" );
$length = $this->limit[0];
$i = 1;
}
$title = Title::makeTitle( $row->page_namespace, $row->page_title );
$date = wfTimestamp( TS_ISO_8601_FOR_GOOGLE_SITEMAP_HACK, $row->page_touched );
$entry = $this->fileEntry( $title->getFullURL(), $date, $this->priority( $namespace ) );
$length += strlen( $entry );
$this->write( $this->file, $entry );
}
if ( $this->file ) {
$this->write( $this->file, $this->closeFile() );
$this->close( $this->file );
}
}
fwrite( $this->findex, $this->closeIndex() );
fclose( $this->findex );
}
 
/**
* gzopen() / fopen() wrapper
*
* @return resource
*/
function open( $file, $flags ) {
return $this->compress ? gzopen( $file, $flags ) : fopen( $file, $flags );
}
 
/**
* gzwrite() / fwrite() wrapper
*/
function write( &$handle, $str ) {
if ( $this->compress )
gzwrite( $handle, $str );
else
fwrite( $handle, $str );
}
 
/**
* gzclose() / fclose() wrapper
*/
function close( &$handle ) {
if ( $this->compress )
gzclose( $handle );
else
fclose( $handle );
}
 
/**
* Get a sitemap filename
*
* @static
*
* @param int $namespace The namespace
* @param int $count The count
*
* @return string
*/
function sitemapFilename( $namespace, $count ) {
global $wgDBname;
 
$ext = $this->compress ? '.gz' : '';
 
return "sitemap-$wgDBname-NS_$namespace-$count.xml$ext";
}
 
/**
* Return the XML required to open an XML file
*
* @static
*
* @return string
*/
function xmlHead() {
return '<?xml version="1.0" encoding="UTF-8"?>' . "\n";
}
 
/**
* Return the XML schema being used
*
* @static
*
* @returns string
*/
function xmlSchema() {
return 'http://www.google.com/schemas/sitemap/0.84';
}
 
/**
* Return the XML required to open a sitemap index file
*
* @return string
*/
function openIndex() {
return $this->xmlHead() . '<sitemapindex xmlns="' . $this->xmlSchema() . '">' . "\n";
}
 
/**
* Return the XML for a single sitemap indexfile entry
*
* @static
*
* @param string $filename The filename of the sitemap file
*
* @return string
*/
function indexEntry( $filename ) {
return
"\t<sitemap>\n" .
"\t\t<loc>http://www.skipperguide.de/$filename</loc>\n" .
"\t\t<lastmod>{$this->timestamp}</lastmod>\n" .
"\t</sitemap>\n";
}
 
/**
* Return the XML required to close a sitemap index file
*
* @static
*
* @return string
*/
function closeIndex() {
return "</sitemapindex>\n";
}
 
/**
* Return the XML required to open a sitemap file
*
* @return string
*/
function openFile() {
return $this->xmlHead() . '<urlset xmlns="' . $this->xmlSchema() . '">' . "\n";
}
 
/**
* Return the XML for a single sitemap entry
*
* @static
*
* @param string $url An RFC 2396 compilant URL
* @param string $date A ISO 8601 date
* @param string $priority A priority indicator, 0.0 - 1.0 inclusive with a 0.1 stepsize
*
* @return string
*/
function fileEntry( $url, $date, $priority ) {
return
"\t<url>\n" .
"\t\t<loc>$url</loc>\n" .
"\t\t<lastmod>$date</lastmod>\n" .
"\t\t<priority>$priority</priority>\n" .
"\t</url>\n";
}
 
/**
* Return the XML required to close sitemap file
*
* @static
* @return string
*/
function closeFile() {
return "</urlset>\n";
}
 
/**
* Write a string to stderr followed by a UNIX newline
*/
function debug( $str ) {
fwrite( $this->stderr, "$str\n" );
}
 
/**
* Populate $this->limit
*/
function generateLimit( $namespace ) {
$title = Title::makeTitle( $namespace, str_repeat( "\xf0\xa8\xae\x81", 63 ) . "\xe5\x96\x83" );
 
$this->limit = array(
strlen( $this->openFile() ),
strlen( $this->fileEntry( $title->getFullUrl(), wfTimestamp( TS_ISO_8601_FOR_GOOGLE_SITEMAP_HACK, wfTimestamp() ), $this->priority( $namespace ) ) ),
strlen( $this->closeFile() )
);
}
}
 
if ( in_array( '--help', $argv ) ) {
echo
"Usage: php generateSitemap.php [host] [options]\n" .
"\thost = hostname\n" .
"\toptions:\n" .
"\t\t--help\tshow this message\n" .
"\t\t--fspath\tThe file system path to save to, e.g /tmp/sitemap/\n" .
"\t\t--path\tThe http path to use, e.g. /wiki\n" .
"\t\t--compress=[yes|no]\tcompress the sitemap files, default yes\n";
die( -1 );
}
 
if ( isset( $argv[1] ) && strpos( $argv[1], '--' ) !== 0 )
$_SERVER['SERVER_NAME'] = $argv[1];
 
$optionsWithArgs = array( 'fspath', 'path', 'compress' );
require_once 'commandLine.inc';
 
$gs = new GenerateSitemap( @$options['fspath'], @$options['path'],  @$options['compress'] !== 'no' );
$gs->main();
?>
</pre>
Abgerufen von „https://skipperguide.de/wiki/SkipperGuide:Interne_Dokumentation/Google_Sitemaps“