Read XML Sitemap to a CSV File

You may need to process a sitemap for redirects or get a list of all your pages for some testing or monitoring process.  Here is a simple script you can run to convert your sitemap to a CSV file.  It even supports multi-file sitemaps.



Simply save this script sitemap-to-csv.pl to your computer. You will need Perl to run in.

	#!/usr/bin/perl
	use strict;
	use warnings;
	use LWP::Simple;
	use Data::Dumper;
	use XML::Simple;
	sub ReadXml {
	my $url = $_[0];
	my $content;
	if($url =~ /https/) {
	my $browser = LWP::UserAgent->new;
	my $response = $browser->get($url);
	$content = $response->content;
	} else {
	$content = get($url);
	}
	die("Sitemap not found at $url.") if(!$content);
	print("Processing XML file $url.\r\n");
	my $parser = new XML::Simple;
	return $parser->XMLin($content);
	}
	sub ParseXml {
	my $xml = $_[0];
	my $fh = $_[1];
	for my $row ( @{ $xml->{sitemap} } ) {
	if($row->{loc} =~ /.xml$/) {
	my $xml = ReadXml($row->{loc});
	ParseXml($xml, $fh);
	$fh->flush();
	} else {
	print Dumper($row);
	}
	}
	if(ref($xml->{url}) eq 'ARRAY' ) {
	for my $row ( @{ $xml->{url} } ) {
	print $fh join(',',
	$row->{loc},
	defined $row->{lastmod} ? $row->{lastmod} : '',
	defined $row->{changefreq} ? $row->{changefreq} : '',
	defined $row->{priority} ? $row->{priority} : ''
	) . "\r\n";
	}
	}
	if(ref($xml->{url}) eq 'HASH' ) {
	print $fh join(',',
	$xml->{url}->{loc},
	defined $xml->{url}->{lastmod} ? $xml->{url}->{lastmod} : '',
	defined $xml->{url}->{changefreq} ? $xml->{url}->{changefreq} : '',
	defined $xml->{url}->{priority} ? $xml->{url}->{priority} : ''
	) . "\r\n";
	}
	}
	die("Please supply a website URL.") if($ARGV[0] !~ /:\/\//);
	print("Reading sitemap for $ARGV[0].\r\n");
	my $url = $ARGV[0];
	if($url !~ /.xml$/) {
	$url =~ s/\/?$/\/sitemap.xml/;
	}
	my $filename = 'sitemap.csv';
	open(my $fh, '>', $filename) or die "Could not open file '$filename' $!";
	my $xml = ReadXml($url);
	ParseXml($xml, $fh);
	close $fh;

view raw sitemap-to-csv.pl hosted with ❤ by GitHub

Then you can execute it from the command line with the following format:

// This will automatically append /sitemap.xml
./sitemap-to-csv.pl http://domain.com

// Or specify the exact file.
perl sitemap-to-csv.pl http://domain.com

// With SSL domain authentication override.
PERL_LWP_SSL_VERIFY_HOSTNAME=0 ./sitemap-to-csv.pl http://domain.com