get request in perl and Use of uninitialized value - perl

Question

my $url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=journal+of+medical+virology[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]&usehistory=y";
print "\n before url \n";
print $url;
#post the esearch URL
my $output = get($url);
print $output;
I have not used perl ever before.
If I hit this URL in browser, I do get the XML.
However, From what I see in output from script, $output is empty and
print $output;
returns
Use of uninitialized value in print at ./extractEmails.pl line 48.
Please suggest what's wrong and how to fix it
Edit:
As suggested, complete code:
#!/usr/bin/perl -w
# A perlscript written by Joseph Hughes, University of Glasgow
# use this perl script to parse the email addressed from the affiliations in PubMed
use strict;
use LWP::Simple;
my ($query,#queries);
#Query the Journal of Virology from 2014 until the present (use 3000)
$query = 'journal+of+virology[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]';
push(#queries,$query);
#Journal of General Virology
$query = 'journal+of+general+virology[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]';
push(#queries,$query);
#Virology
$query = 'virology[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]';
push(#queries,$query);
#Archives of Virology
$query = 'archives+of+virology[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]';
push(#queries,$query);
#Virus Research
$query = 'virus+research[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]';
push(#queries,$query);
#Antiviral Research
$query = 'antiviral+research[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]';
push(#queries,$query);
#Viruses
$query = 'viruses[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]';
push(#queries,$query);
#Journal of Medical Virology
$query = 'journal+of+medical+virology[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]';
# global variables
push(#queries,$query);
my %emails;
my $emailcnt=0;
my $count=1;
#assemble the esearch URL
foreach my $query (#queries){
my $base = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/';
#my $url = $base . "esearch.fcgi?db=pubmed&term=$query&usehistory=y";
my $url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=journal+of+medical+virology[journal]+AND+2014[Date+-+Publication]:3000[Date+-+Publication]&usehistory=y";
print "\n before url \n";
print $url;
#post the esearch URL
my $output = get($url);
print "\n before output \n";
print get($url);
print $output;
#parse WebEnv, QueryKey and Count (# records retrieved)
my $web = $1 if ($output =~ /<WebEnv>(\S+)<\/WebEnv>/);
my $key = $1 if ($output =~ /<QueryKey>(\d+)<\/QueryKey>/);
my $count = $1 if ($output =~ /<Count>(\d+)<\/Count>/);
#retrieve data in batches of 500
my $retmax = 500;
for (my $retstart = 0; $retstart < $count; $retstart += $retmax) {
my $efetch_url = $base ."efetch.fcgi?db=pubmed&WebEnv=$web";
$efetch_url .= "&query_key=$key&retmode=xml";
my $efetch_out = get($efetch_url);
my #matches = $efetch_out =~ m(<Affiliation>(.*)</Affiliation>)g;
#print "$_\n" for #matches;
for my $match (#matches){
if ($match=~/\s([a-zA-Z0-9\.\_\-]+\#[a-zA-Z0-9\.\_\-]+)$/){
my $email=$1;
$email=~s/\.$//;
$emails{$email}++;
}
}
}
my $cnt= keys %emails;
print "$query\n$cnt\n";
}
print "Total number of emails: ";
my $cnt= keys %emails;
print "$cnt\n";
my #email = keys %emails;
my #VAR;
push #VAR, [ splice #email, 0, 100 ] while #email;
my $batch=100;
foreach my $VAR (#VAR){
open(OUT, ">Set_$batch\.txt") || die "Can't open file!\n";
print OUT join(",",#$VAR);
close OUT;
$batch=$batch+100;
}

Answer 1

I recommend against using LWP::Simple for any reason because it is impossible to configure it or handle errors usefully. Using LWP::UserAgent which it wraps is nearly as simple anyway (though the error handling is a bit complicated). The below examples would replace the use LWP::Simple; and my $output = get($url); lines.
use strict;
use warnings;
use LWP::UserAgent;
my $ua = LWP::UserAgent->new(timeout => 30);
my $response = $ua->get($url);
unless ($response->is_success) {
# the Client-Warning, Client-Aborted, and X-Died headers each may be set on client/transport errors
die $response->status_line;
}
my $output = $response->decoded_content;
The core HTTP::Tiny is also simple.
use strict;
use warnings;
use HTTP::Tiny;
my $ua = HTTP::Tiny->new;
my $response = $ua->get($url);
unless ($response->{success}) {
die $response->{status} == 599 ? $response->{content} : "$response->{status} $response->{reason}";
}
my $output = $response->{content};
If you really want an LWP::Simple approach that will at least report transport errors, try ojo from Mojolicious:
perl -Mojo -E'say g(shift)->text' http://example.com
In a script rather than a oneliner, you can use Mojo::UserAgent directly, and also handle HTTP errors like above:
use strict;
use warnings;
use Mojo::UserAgent;
my $ua = Mojo::UserAgent->new;
my $response = $ua->get($url)->result;
unless ($response->is_success) {
die $response->code . ' ' . $response->message;
}
my $output = $response->text;