Re: Query about regular expression (HTML Parser)

[jeffa]

I would use a parser for that instead. Here's some code to get you started should you choose this path:

use strict;
use warnings;
use Data::Dumper;
use HTML::TokeParser::Simple;

my $p = HTML::TokeParser::Simple->new( *DATA );
my $count = 0;
my @array;
while ( my $token = $p->get_token ) {
    next unless $token->is_start_tag('li');
    next unless ++$count > 3;

    while ( $token = $p->get_token ) {
        last if $token->is_end_tag('li');
        my $text = $token->as_is;
        $text =~ s/^\s*//;
        $text =~ s/\s*$//;
        push @array, $text unless $token->is_tag('br');
    }
    last;
}

print Dumper \@array;


__DATA__
<ul>
<li><strong>site_user</strong></li>
<ul>
<li>user1</li>
</ul>
<li><strong>compare_hidden</strong></li>
<ul>
<li>average_speed_answer  25 60 30 60 ^M<br />
 calls_waiting  300 500 300 500 ^M<br />
 many more rows here
 post_ivr_calls_handled Wisconsin 50 100 50 100 ^M<br />
 post_ivr_calls_handled Wyoming 50 100 50 100 ^M<br />
</li>
<li><strong>calls_waiting_good_high</strong></li>
<ul>
<li>300</li>
</ul>
<li><strong>calls_waiting_warning_low</strong></li>
<ul>

[Anonymous Monk]

Too much work :) HTML::TreeBuilder::XPath is less work

#!/usr/bin/perl --
use strict;
use warnings;
use HTML::TreeBuilder::XPath;
my $tree = HTML::TreeBuilder::XPath->new;
$tree->ignore_unknown(0);;
$tree->implicit_tags(0);
$tree->no_expand_entities(1);
$tree->ignore_unknown(0);
$tree->ignore_ignorable_whitespace(0);
$tree->no_space_compacting(1);
$tree->store_comments(1);
$tree->store_pis(1);

$tree->parse(q{
<ul>
<li><strong>site_user</strong></li>
<ul>
<li>user1</li>
</ul>
<li><strong>compare_hidden</strong></li>
<ul>
<li>average_speed_answer  25 60 30 60 ^M<br />
 calls_waiting  300 500 300 500 ^M<br />
 many more rows here
 post_ivr_calls_handled Wisconsin 50 100 50 100 ^M<br />
 post_ivr_calls_handled Wyoming 50 100 50 100 ^M<br />
</li>
<li><strong>calls_waiting_good_high</strong></li>
<ul>
<li>300</li>
</ul>
<li><strong>calls_waiting_warning_low</strong></li>
<ul>});
$tree->eof;

my @li = $tree->findnodes( q{    //li[ contains( ., 'average' ) ]   } 
+) ;
for my $ll ( @li ){
    $ll->dump;
    print $ll->as_text, "\n";;
}

__END__
<li> @0.1.7.1
  "average_speed_answer  25 60 30 60 ^M"
  <br /> @0.1.7.1.1
  "\x0a calls_waiting  300 500 300 500 ^M"
  <br /> @0.1.7.1.3
  "\x0a many more rows here\x0a post_ivr_calls_handled Wisconsin 50 10
+0 50..."
  <br /> @0.1.7.1.5
  "\x0a post_ivr_calls_handled Wyoming 50 100 50 100 ^M"
  <br /> @0.1.7.1.7
  "\x0a"
average_speed_answer  25 60 30 60 ^M
 calls_waiting  300 500 300 500 ^M
 many more rows here
 post_ivr_calls_handled Wisconsin 50 100 50 100 ^M
 post_ivr_calls_handled Wyoming 50 100 50 100 ^M