Netcelal

<?php

function get_web_page( $url,$curl_data ) 
{ 
    $options = array( 
        CURLOPT_RETURNTRANSFER => true,         // return web page 
        CURLOPT_HEADER         => false,        // don't return headers 
        CURLOPT_FOLLOWLOCATION => true,         // follow redirects 
        CURLOPT_ENCODING       => "",           // handle all encodings 
        CURLOPT_USERAGENT      => "spider",     // who am i 

Netcelal

<?php

class helper {

	//---------------------------------------------------------------------------

	public function __construct() {

	}

Netcelal

include('simple_html_dom.php'); // DOM parsing library. 
$url = (isset($_GET['site'])) ? $_GET['site'] : 'http://www.yelp.com'; //just an example, clean this
$dom = file_get_html($url);
foreach ($dom->find('a') as $node) {
  // Replace href attribute value
  $node->href = 'http://YOURPROXYSERVER.COM?requestedurl='.urlencode($url.$node->href);
}
// Output modified DOM
echo $dom->outertext;

Netcelal

<?php
function getinboundLinks($domain_name) {
ini_set('user_agent', 'NameOfAgent (<a class="linkclass" href="http://localhost">http://localhost</a>)');
 $url = $domain_name;
$url_without_www=str_replace('http://','',$url);
$url_without_www=str_replace('www.','',$url_without_www);
 $url_without_www= str_replace(strstr($url_without_www,'/'),'',$url_without_www);
$url_without_www=trim($url_without_www);
$input = @file_get_contents($url) or die('Could not access file: $url');
 $regexp = "<a\s[^>]*href=(\"??)([^\" >]*?)\\1[^>]*>(.*)<\/a>";