view release on metacpan or  search on metacpan

WebSource/Parser.pm  view on Meta::CPAN

      if($a =~ m#[^\w_:\-]#) {
        $self->{verbose} and warn "Bad attribute $a detected and removed";
      } else {
        push @naseq, ($a);
        $nattr{$a} = $attr->{$a};
      }
    }
    $self->SUPER::start($tag,\%nattr,\@naseq,$origtext);
  }
  sub text {
    my ($self,$origtext,$iscdata) = @_;
    if(!$iscdata) {
      $origtext =~ /Sion/ and print "Text : $origtext\n";
      if($origtext =~ m/\0/) {
        $self->{verbose} and warn "Decected null char\n";
        $origtext =~ s/\0//g;
      }
      if($origtext =~ m/\&\#[0-9]\;/) {
        warn "Bad entity detected";
        $origtext =~ s/\&\#[0-9]\;//g;
       }
    }
    $self->SUPER::text($origtext,$iscdata);
  }

}

our @ISA = ("XML::LibXML");
=head1 NAME

WebSource::Parser - A XML/HTML parser extending XML::LibXML

=head1 DESCRIPTION