web scraping part 1

This script download all emails of all recruiters. 

=============================================

using simple regex. 

=============================================

#!/usr/bin/perl

use strict;

use warnings;

use Data::Dumper;

use LWP::Simple;

my $url = 'http://www.cybercoders.com/recruiter/';

my $html =  get "$url";

my @html = split(/\n/,$html);

for my $i  (@html){

    next unless  $i =~ /<a href="\/recruiter\/(\S.*\/)">/ ;

    print "${url}${1}\n";

    my $indiv_recruiter = get("$url$1");

    my @indiv_recruiter = split(/\n/,$indiv_recruiter);

    for my $j (@indiv_recruiter ){

     next unless $j =~ /<a class="recruiter-email-link" href="mailto:(\S.*?\@CyberCoders\.com)">/ ;

        print "$1\n"

    }

}

=========================================================

Using HTM::treebuilder::Xpath

#!/usr/bin/perl

use strict;

use warnings;

use Data::Dumper;

use LWP::Simple;

use HTML::TreeBuilder;

use HTML::TreeBuilder::XPath;

my $url = 'http://www.cybercoders.com/recruiter/';

my $html =  get "$url";

my $tree = HTML::TreeBuilder::XPath->new_from_content();

$tree->parse($html);

my @customers = $tree->findnodes('//div[@class="recruiter-item"');

for my $custm (@customers){

    my @all_a_tag = $custm->look_down('_tag' => 'a'  ) ;

     my $recruiter_pth = $all_a_tag[0]->attr('href') ."\n" ;

      $recruiter_pth =~ s/\/recruiter\///g;

      get_email($recruiter_pth);

}

sub get_email {

my ($r_pth)=@_;

my $html =  get ("$url$r_pth") ;

my    $tree2 = HTML::TreeBuilder->new_from_content($html);

    my @mailto = $tree2->look_down( _tag => 'a' , class => 'recruiter-email-link' );

     print $mailto[0]->attr('href')."\n";

   print "get $url$r_pth";

}