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

use WWW::Mechanize;
use Data::Dumper;
use HTML::TableExtract;
use XML::FeedPP;
use UTF8;

# initialize
my $cols;
my $url;
my $depth;
my $count;
my $data;
my $tracking_code;
my $location;
my $job_title;
my $date_posted;
my $out_fh;

# get the data from the web.  Typically this is:
# https://commvault.silkroad.com/epostings/index.cfm?fuseaction=app.jobsearch#
# Either pass this in as --url <page_url> when invoking or just set it.

$cols = 'tracking_code,job_title,location,date_posted';
$url = "https://commvault.silkroad.com/epostings/index.cfm?fuseaction=app.jobsearch";

my $input;

my $directory = "/Users/coblem/testing/";
my $outfile = "cvlt_jobs.csv";


open( $out_fh, '>', $ directory . $outfile)
   or die("Unable to create output file \"$out_fh\": $!\n");

my $m = WWW::Mechanize->new();
$m->get($url);
$input = $m->content;

my $te;
if ( defined ($cols)) {
    
print ("columns ", $cols, "\n");
    my @headers = split(/,/, $cols);
    
    #    $te = HTML::TableExtract->new( attribs => { border => 1 } );
    $te = HTML::TableExtract->new(
                                headers => [qw( tracking_code job_title location date_posted )]
                                ) or die qq{$!};
print Dumper($te);
}

else
{
    $te = new HTML::TableExtract( depth => $depth, count=>$count);
};


$te->parse($input);
foreach my $row ($te->rows) {
        
    $tracking_code = $ { $row }[0];
    $job_title     = $ { $row }[1];
    $location      = $ { $row }[2];
    $date_posted   = $ { $row }[3];
    print "positions: $tracking_code $job_title $location $date_posted \n";
    }