#!/usr/bin/perl 

use strict;
use WWW::Mechanize;

open (FILE, "data.txt");

my $input;
while ($input = <FILE>){
chomp $input;

#download PDB html page
my $url = "http://www.rcsb.org/pdb/explore.do?structureId="."$input";
my $mech = WWW::Mechanize->new( autocheck => 1 );
   $mech->get( $url );
   
#write extracted data to an output file (.html)
my $file = "$input".".html";
print "$file";
use Data::Dumper;
open (OUTFILE, "> $file");
print OUTFILE Dumper($mech);
close(OUTFILE);

  #download the link (FASTA sequence)
 my $linkname = "fileFormat=FASTA&compression=NO&structureId="."$input";
 my @links = $mech->find_all_links( url_regex => qr/$linkname/ );
  for my $link ( @links ) {
  my $url = $link->url_abs;
  my $filename = $url;
  $filename =~ s[^.+/][];
   
  print "Fetching $url";
  $mech->get( $url, ':content_file' => $filename );

  print "   ", -s $filename, " bytes\n";
}
}
close (FILE);