open IN_FILE, "<temp.html";
while(<IN_FILE>) {
  my $text = $_;
  my $before;
  my $tag;
  my $after;
  while ($text) {
     if( ($before,$tag,$after) = ($text =~ /(.*?)<(.*?)>(.*)/) ) {
       print "text: $before\n" unless $before eq "";
       print "html: $tag\n";
       $text = $after;
     } else {
       print "text: $text\n";
       $text = undef;
     }
  }
}