use HTML::Tagset; my %tags = %HTML::Tagset::isKnown; my $tagpattern = "(".join('|',keys %tags).")"; print STDERR "$tagpattern\n"; while (<>) { print strip_html_tags($_); } sub strip_html_tags { my $line = shift; $line =~ s/<\s*$tagpattern(?:\s*>|\s+[^>]*>)([^<]*)<\s*\/\1[^>]*>/$2/ig; return $line; }