#!/usr/bin/perl -w
use strict;
use URI;

# in the realworld, it comes from somewhere else
my $page_content = <<'EOT';
<a href="thepage.jsp?siteId=1&sectionId=443&amp;">
    <span class="small">Geography</span></a>
EOT

# the following regex will simply catch any anchor tags,
# making no assumptions about their structure
while($page_content =~ /<a\s[^>]*?href="([^"]+)"[^>]*>(.*?)<\/a>/sgi) {
	my $url = new URI $1;
	my %params = $url->query_form; # now we let URI do the dirty job for us
	next unless exists $params{sectionId}; # was there a sectionId parameter?

	# if we're still in the loop here, there was
	my $text = $2;
	$text =~ s/<[^>]*>//sgi; # strip all tags from the anchor's inner text
	$text =~ s/^\s+//sgi; # then strip any whitespace from the front
	$text =~ s/\s+$//sgi; # and from the end

	print "$params{sectionId},$text\n"; # some pretty output
}