#!/usr/bin/perl
use warnings;
use strict;

#############################################
# downloads the lists of journal names and their 
# abbreviations from the Web of Science database
# and generates a master list containing all
# of the journals listed.
#
# by Alex Chubaty (alex.chubaty@gmail.com)
# [12 Feb 2012]
#############################################
package jParser;
use base 'HTML::Parser';

my @contents = "";

my $flag = 0;

sub start {
	my ($self, $tag, $attr, $attrseq, $origtext) = @_;
	if ($tag eq "dl") {
		$flag = 1;
	}
}

sub text {
	my ($self, $text) = @_;
	if ($flag) {
		$text =~ s/&/&/g;
		$text =~ s/&/\\&/g;
		push(@contents, $text);
	}
}

sub end {
	my ($self, $tag, $origtext) = @_;
	if ($tag eq "dl") { $flag = 0; }
}



package main;
use LWP::Simple;

my $letter;
my $url;

my @jabbrev;
my @jfull;
my @letters = ("A".."Z");
my @urls = ("http://images.webofknowledge.com/WOK46/help/WOS/0-9_abrvjt.html");

foreach $letter (@letters) {
	$url = "http://images.webofknowledge.com/WOK46/help/WOS/" . $letter . "_abrvjt.html";
	push(@urls, $url);
}

foreach $url (@urls) {
	my $html = get($url);
	die "$0: get failed" unless defined $html;
	
	my $parser = new jParser;
	$parser->parse($html);
}

open(OUTFILE, ">output.txt") || die "$!";
print OUTFILE @contents, "\n";
close(OUTFILE);

open(INFILE, 'output.txt');
undef $/;
my $textfile = <INFILE>;
close(INFILE);

$textfile =~ s/\n\n/\n/g;
$textfile =~ s/\n\t/\t/g;
$textfile =~ s/\n\'92/\'92/;

open(OUTFILE, ">masterlist.txt");
print OUTFILE $textfile;

# add custom journal entries
print OUTFILE "THE AMERICAN NATURALIST\tAM NAT\n";
print OUTFILE "THE CANADIAN ENTOMOLOGIST\tCAN ENTOMOL\n";
print OUTFILE "TRENDS IN ECOLOGY AND EVOLUTION\tTRENDS ECOL EVOL\n";
close(OUTFILE);

unlink("output.txt");

exit