README.md

Sitemap HTML Tree

Generate a human-readable sitemap tree from an XML sitemap:

php sitemap-to-html.php https://xwp.co/sitemap_index.xml

Then open the generated sitemap-*.html file in your web browser.

Sitemap URL CSV

php sitemap-to-csv.php https://xwp.co/sitemap_index.xml

sitemap-to-csv.php

<?php

function urls_from_sitemap( $sitemap_file ) {
	$sitemap = simplexml_load_file( $sitemap_file );

	$urls = [];

	foreach ( $sitemap->url as $url ) {
		$urls[] = [ (string) $url->loc, $sitemap_file ];
	}

	printf( "Found %d URLs in %s\n", count( $urls ), $sitemap_file );

	// Resolve child sitemaps, if any.
	foreach ( $sitemap->sitemap as $sitemap ) {
		$urls = array_merge( $urls, urls_from_sitemap( (string) $sitemap->loc ) );
	}
	
	return $urls;
}

if ( empty( $argv[1] ) ) {
	die( 'Please specify the sitemap URL!' );
}

$sitemap_url = $argv[1]; // Accept local file path or URL as sitemap source.

$sitemap_html_file = sprintf( '%s/sitemap-%d.csv', getcwd(), time() );

if ( false !== strpos( $sitemap_url, '//' ) ) {
	$sitemap_html_file = sprintf( '%s/sitemap-%s.csv', getcwd(), parse_url( $sitemap_url, PHP_URL_HOST ) );
}

$fields = array_merge(
	[ [ 'URL', 'Sitemap URL' ] ],
	urls_from_sitemap( $sitemap_url )
);

$sitemap_fp = fopen( $sitemap_html_file, 'w' );

foreach ( $fields as $fields ) { 
	fputcsv( $sitemap_fp, $fields ); 
} 

fclose( $sitemap_fp );

printf( 'Generated CSV sitemap: %s', $sitemap_html_file );

sitemap-to-html.php

<?php

function parts_to_tree( $parts ) {
	if ( empty( $parts ) ) {
		return [];
	}

	return [ array_shift( $parts ) => parts_to_tree( $parts ) ];
}

function tree_to_list( $tree ) {
	$branches = [];

	foreach ( $tree as $branch => $children ) {
		$branches[] = sprintf( 
			'<li><details><summary>%s (%d)</summary>%s</details></li>', 
			$branch,
			count( $children, COUNT_RECURSIVE ),
			tree_to_list( $children ) 
		); 
	}

	if ( ! empty( $branches ) ) {
		return sprintf( '<ul>%s</ul>', implode( '', $branches ) );
	}

	return null;
}

function urls_from_sitemap( $sitemap_file ) {
	$sitemap = simplexml_load_file( $sitemap_file );

	$urls = [];

	// Resolve child sitemaps, if any.
	foreach ( $sitemap->sitemap as $sitemap ) {
		$urls = array_merge( urls_from_sitemap( (string) $sitemap->loc ), $urls );
	}

	foreach ( $sitemap->url as $url ) {
		$urls[] = (string) $url->loc;
	}
	
	return $urls;
}

if ( empty( $argv[1] ) ) {
	die( 'Please specify the sitemap URL!' );
}

$sitemap_url = $argv[1]; // Accept local file path or URL as sitemap source.

$tree = [];

foreach ( urls_from_sitemap( $sitemap_url ) as $url ) {
	$parts = explode( '/', trim( parse_url( $url, PHP_URL_PATH ), '/\\' ) );
	$tree = array_merge_recursive( $tree, parts_to_tree( $parts ) );
}

$sitemap_html_file = sprintf( '%s/sitemap-%d.html', getcwd(), time() );

if ( false !== strpos( $sitemap_url, '//' ) ) {
	$sitemap_html_file = sprintf( '%s/sitemap-%s.html', getcwd(), parse_url( $sitemap_url, PHP_URL_HOST ) );
}

file_put_contents( $sitemap_html_file, tree_to_list( $tree ) );

printf( 'Generated HTML sitemap: %s', $sitemap_html_file );