My way (documented):

use strict;
use warnings;

sub rtrim {
   local $_ = (@_ ? $_[0] : $_);
   s/\s+$//;
   return $_;
}


{
   local $_;

   # Skip junk at top.
   do {
      defined($_ = <DATA>)
      or die("Bad data.\n");
   } while (!/^\s*-+\s+(-+)\s+-+\s+(-+)/);

   # Find field positions and lengths.
   # Could be hardcoded.
   my $match_start1  = $-[1];
   my $match_length1 = $+[1] - $match_start1;
   my $match_start2  = $-[2];
   my $match_length2 = $+[2] - $match_start2;

   # Extract the names.
   my @names1;
   my @names2;
   while (defined($_ = <DATA>) && !/^\s*$/) {
      push(@names1, rtrim(substr($_, $match_start1, $match_length1)))
         if length()-1 >= $match_start1;
      push(@names2, rtrim(substr($_, $match_start2, $match_length2)))
         if length()-1 >= $match_start2;
   }
   my @names = (@names1, @names2);

   # Display results.
   print(join(', ', @names), $/);
}
[download]

Update: Didn't notice there were two columns of names. Fixed.