Assuming you want to do this strictly in perl, you could do something like this:

while(<FH>)
  {
  my $line = $_;
  chomp($line);
  $line =~ /^[\d]+ rows in set \(([^\)]+)/;
  $retValue = $1 if (defined($1));
  }
close FH;

print "The value is '$retValue'\n";
[download]

My full test program is here:

#!/usr/bin/perl -w
#
my $text=<<EOL;
mysql> select * from shop;
+---------+--------+-------+
| article | dealer | price |
+---------+--------+-------+
|    0001 | A      |  3.45 |
|    0001 | B      |  3.99 |
|    0002 | A      | 10.99 |
|    0003 | B      |  1.45 |
|    0003 | C      |  1.69 |
|    0003 | D      |  1.25 |
|    0004 | D      | 19.95 |
+---------+--------+-------+
7 rows in set (0.00 sec)
EOL


if ( ! open(FH,"echo '$text' |" ) )
   {
   die "can't open\n";
   }

my $retValue = '';
while(<FH>)
  {
  my $line = $_;
  chomp($line);
  $line =~ /^[\d]+ rows in set \(([^\)]+)/;
  $retValue = $1 if (defined($1));
  }
close FH;

print "The value is '$retValue'\n";
[download]

To explain, the pattern match /^[\d]+ rows in set \(([^\)]+)/ captures everthing between the parens into $1.