use strict;
use Data::Dumper;

my @link;
my @data = <DATA>;
for (@data) {
  my ($url,$label) = $_ =~ /href\s*=\s*"([^"]+)"\s*>([^<]+)/;
  next unless $url and $label;
  push @link, [$url,$label];
}

print Dumper \@link;

__DATA__
<a href="http://foo.com">bar</a>
<a href="index.html">index</a>