format_c@server:~/perl_scripts> cat test.pl && perl test.pl
#!/usr/bin/perl
use strict;
use HTML::Parser;
my $p = HTML::Parser->new(api_version => 3,
start_h => [\&b_start_handler, "self,tagname,attr"],
#report_tags => [qw(b)],
);
$p->parse_file(*DATA) || die "Konnte nicht parsen: $!";
sub b_start_handler
{
my($self, $tag, $attr) = @_;
return unless $tag eq "b";
$self->handler(text => [], '@{dtext}' );
$self->handler(end => \&b_end_handler, "self,tagname");
}
sub b_end_handler
{
my($self, $tag) = @_;
my $text = join("", @{$self->handler("text")});
$text =~ s/^\s+//;
$text =~ s/\s+$//;
$text =~ s/\s+/ /g;
print "T $text\n" if $text =~ /^name:\s?.*/i;
$self->handler("text", undef);
$self->handler("start", \&b_start_handler);
$self->handler("end", undef);
}
_ _ DATA _ _
Name: Name1
Name: Name2 Nachname2
Fetter Text
Name: format_c
_ _ END _ _
T Name: Name1
T Name: Name2 Nachname2
T Name: format_c
format_c@server:~/perl_scripts>