#!/usr/bin/perl
#
#Written by Paul Stothard, Canadian Bioinformatics Help Desk
#based on a script by Oleg Khovayko http://olegh.spedia.net
#
#Modified by S.R. Santos, Sept. 2004
#
#Modified by S.R. Santos, Aug. 2007
#
#This script uses NCBI's Entrez Programming Utilities to perform
#batch requests to NCBI Entrez.
#
#See 'Entrez Programming Utilities' for more info at
#http://eutils.ncbi.nlm.nih.gov/entrez/query/static/eutils_help.html


use warnings;
use strict;
use LWP::Simple;

	print "\nWhich database will be searched? \n";
	print "The following values are supported: pubmed protein nucleotide\n";
    print "nuccore  nucgss  nucest  structure  genome books\n";
    print "cancerchromosomes  cdd  domains  gene  genomeprj  gensat  geo  gds\n";
    print "homologene journals  mesh  ncbisearch  nlmcatalog  omia  omim  pmc\n";
    print "popset  probe  pcassay pccompound  pcsubstance  snp  swissprot\n";
    print "taxonomy  unigene  unists.\n"; 
	print "> ";
	chomp (my $db = <STDIN>);
			
	print "\nWhat is the query to search for? \n";
	print "Ex. genus and/or species name[for seq data], author[for pubmed], ect.\n";
	print "Qualifiers can be used to restrict a search to a certain field (enclosed by [  ])\n";
	print "See NCBI for details.\n";
	print "> "; 
	chomp (my $query = <STDIN>);
			
	print "\nWhat type of report should be generated? \n";
	print "Ex. summary [all databases], fasta/genbank [for seq data], abstract [for pubmed].\n";
	print "> ";
	chomp (my $report = <STDIN>);
			
	print "\nWhat will be the name of the output file? \n";
	print "Hint: use a descriptive extension; e.g., .summary, .fasta, .abstract\n";
	print "> ";
	chomp (my $output_file = <STDIN>);
			
	if ($db eq '' or $query eq '' or $report eq '' or $output_file eq '') {
	print "\nThere were missing input fields.  Program terminating due to error(s)!\n\n";
	exit;
			}

my $url = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils";
my $esearch = "$url/esearch.fcgi?" . "db=$db&retmax=1&usehistory=y&term=";

my $esearch_result = get($esearch . $query);

$esearch_result =~  m/<Count>(\d+)<\/Count>.*<QueryKey>(\d+)<\/QueryKey>.*<WebEnv>(\S+)<\/WebEnv>/s;

my $count = $1;
my $query_key = $2;
my $web_env = $3;

my $retstart;
my $retmax = 500;

open (OUTFILE, ">" . $output_file) or die ("Error: Cannot open $output_file : $!");

print "\n$count entries to retrieve\n\n";

print "Would you like to continue and save these entries? (y will continue, all others will terminate)\n";
print "> ";
chomp (my $response = <STDIN>);

if ($response eq 'y') {

for ($retstart = 0; $retstart < $count; $retstart = $retstart + $retmax) {
    print "\nRequesting download of entries $retstart to " . ($retstart + $retmax) . "\n\n";
    my $efetch = "$url/efetch.fcgi?" . "rettype=$report&retmode=text&retstart=$retstart&retmax=$retmax&" . "db=$db&query_key=$query_key&WebEnv=$web_env";   

    my $efetch_result = get($efetch);

    print (OUTFILE $efetch_result);
    sleep(3);
}

close (OUTFILE) or die ("Error: Cannot close $output_file file: $!"); 
print "Download has completed.  Goodbye!\n\n";
		}
		
else {

print "\nNCBI search/download has been terminated.\n\n";
	exit;
				}