misc/translator/text-extract.pl

   1 #!/usr/bin/perl
   2 use HTML::Tree;
   3 use Getopt::Std;
   4 getopt("f:");
   5         my $tree = HTML::TreeBuilder->new; # empty tree
   6
   7         $tree->parse_file($opt_f);
   8         sub give_id {
   9                 my $x = $_[0];
  10                 foreach my $c ($x->content_list) {
  11                         next if (ref($c) && $c->tag() eq "~comment");
  12                         print "$c\n" unless ref($c);
  13                         if (ref($c) && $c->attr('alt')) {
  14                                 print $c->attr('alt')."\n";
  15                         }
  16                         if (ref($c) && $c->tag() eq 'meta') {
  17                                 print $c->attr('content')."\n ";
  18                         }
  19                         give_id($c) if ref $c; # ignore text nodes
  20                 }
  21         };
  22         give_id($tree);
  23         $tree = $tree->delete;