#!/usr/bin/perl -w

use warnings;
use strict;
use CAM::PDF;
use LWP::Simple;

my @ns_headers = (
	'User-Agent' => 'Mozilla/4.76 [en] (Win98; U)',
	'Accept' => 'image/gif, image/x-xbitmap, image/jpeg, 
	image/pjpeg, image/png, */*',
	'Accept-Charset' => 'iso-8859-1,*,utf-8',
	'Accept-Language' => 'en-US',
);

my $jacket_id = 746810;

my $ua = LWP::UserAgent->new;
# $ua->timeout(5);   # Is the site available?
my $response = $ua->get('https://contractorconnection.gpo.gov/abstract/'. $jacket_id , @ns_headers);
my $pdf = CAM::PDF->new($response->content) || die "$CAM::PDF::errstr\n";


# my $pdf = CAM::PDF->new('C:\dev\perl\file.pdf') || die "$CAM::PDF::errstr\n";
# print $pdf->toString();


for my $page (1..$pdf->numPages){
	my $text = $pdf->getPageText($page);
	my @lines = split (/$jacket_id\s+/, $text); # split on Jacket ID and a space

	foreach (@lines) {
		print "\n$_\n";

		if ( /^A/ ) { # A at the beginning of a line is the Award winner
			print $1;
		}
		if (/^(\d+\-)(\d+)/) {   # Contractor Code		
			print"Contractor code ". $1,$2 ."\n";
		}
		if (/(\w+)\s+\$/ ) {  # Does not work		
			print"Name ". $1 ."\n";  # Name
		}
	#	if (/\$?([0-9]{1,3},([0-9]{3},)*[0-9]{3}|[0-9]+)(\.[0-9][0-9])?$)/) {  	# Does not work	
	#		print"Amount ". $1 ."\n";  # Amount
	#	}
	#	if(1){ # Date
	#		print "Date " . $1;
	#	}
	}
}