open infile,$filepath;
my $Block;
while (<infile>) {
 if (/\<ppsarticle\>) {
  &Parse_XML($Block);
  undef $Block;
 }
 $Block .= $_;
}
&Parse_XML($Block); # Don't forget last block

##</code><code>##

use GDBM_File; # my favorite, but there are others
use Fcntl;
tie %md5,'GDBM_File','/tmp/md5.tmp',O_RDWR,0600; # You may need to add |O_CREAT after O_RDWR

##</code><code>##

open infile,$filepath;
open outfile,'>'.$outfilepath;
my $XML;
while (<infile>) {
 $XML .= $_;
 if (s/\<\ppsarticle\>(.*?)\<\/ppsarticle\>//) {
  my $Article = $1;
  my $MD5SUM = md5($Article);
  $md5{$MD5SUM} and next;
  $md5{$MD5SUM} = 1;
  print outfile $Article;
 }
}