php [sitemap parser] sitemap php parser #php

Posted 2021-05-04

<?php
/*
https://github.com/VIPnytt/SitemapParser
composer require vipnytt/sitemapparser
*/
//list of URLs only
use vipnytt\SitemapParser;
use vipnytt\SitemapParser\Exceptions\SitemapParserException;

try {
    $parser = new SitemapParser();
    $parser->parse('https://www.google.com/sitemap.xml');
    foreach ($parser->getURLs() as $url => $tags) {
        echo $url . '<br>';
    }
} catch (SitemapParserException $e) {
    echo $e->getMessage();
}

/*
	both Sitemaps and URLs
*/
$parser = new SitemapParser('MyCustomUserAgent');
$parser->parse('http://php.net/sitemap.xml');
foreach ($parser->getSitemaps() as $url => $tags) {
  echo 'Sitemap<br>';
  echo 'URL: ' . $url . '<br>';
  echo 'LastMod: ' . $tags['lastmod'] . '<br>';
  echo '<hr>';
}
foreach ($parser->getURLs() as $url => $tags) {
  echo 'URL: ' . $url . '<br>';
  echo 'LastMod: ' . $tags['lastmod'] . '<br>';
  echo 'ChangeFreq: ' . $tags['changefreq'] . '<br>';
  echo 'Priority: ' . $tags['priority'] . '<br>';
  echo '<hr>';
}

/*
	Parses any sitemap detected while parsing, to get an complete list of URLs
*/
$parser = new SitemapParser('MyCustomUserAgent');
$parser->parseRecursive('http://www.google.com/robots.txt');
echo '<h2>Sitemaps</h2>';
foreach ($parser->getSitemaps() as $url => $tags) {
  echo 'URL: ' . $url . '<br>';
  echo 'LastMod: ' . $tags['lastmod'] . '<br>';
  echo '<hr>';
}
echo '<h2>URLs</h2>';
foreach ($parser->getURLs() as $url => $tags) {
  echo 'URL: ' . $url . '<br>';
  echo 'LastMod: ' . $tags['lastmod'] . '<br>';
  echo 'ChangeFreq: ' . $tags['changefreq'] . '<br>';
  echo 'Priority: ' . $tags['priority'] . '<br>';
  echo '<hr>';
}