in reply to How to remove HTML tags from text

Personally I would go with HTML::Parser: 

#!/usr/bin/perl
use strict;
use warnings;
use HTML::Parser;
                                                                      
+          
my $data='abcd efgh<img src="http://test.com/image.gif">ijklmn';
my $parser = HTML::Parser->new( text_h => [ sub { $_[0]->{_data} .= $_
+[1]; },"self,dtext" ],
                                start_document_h => [ sub { $_[0]->{_d
+ata} = '';}, "self"]);
$parser->parse($data);
                                                                      
+          
print $parser->{_data};

[download]

/J\

Replies are listed 'Best First'.
Re^2: How to remove HTML tags from text
by holli (Abbot) on Feb 04, 2005 at 13:01 UTC
    Alternative using Html::Tokeparser: 
    use strict;
use HTML::TokeParser;

# from file
my $p = HTML::TokeParser->new("test.html") or die "Can't open: $!";
#from string
#my $p = HTML::TokeParser->new(\"text1 <b> text2 </b> text3");
my $t;

while (my $token = $p->get_token)
{
    $t .= $token->[1] if $token->[0] eq "T";
}

print $t;

    [download]

    holli, regexed monk
[reply]
[d/l]

In Section Seekers of Perl Wisdom