use strict; use warnings; use HTML::TreeBuilder; my $html = <June 25, 1998

November 12,2006 September 21, 1999

December 36, 10

HTML my $tree = HTML::TreeBuilder->new_from_content ($html); for ($tree->look_down ('_tag', 'p')) { my $text = $_->as_text (); print "$1\n" while $text =~ /(\w+\s+\d+,\s*\d+)/g; } #### June 25, 1998 November 12,2006 September 21, 1999 December 36, 10