Random proxy rotation

proxy_handler.php

<?php

// suggest buying proxies from http://buyproxies.org/ - I found this to be an excellent service and well-priced too.

// function returns a keyed array of proxy info
// if you want you can pass a specific ID in (for instand if you want to use the same proxy for a sequence of calls
function custom_proxy_handler_get_proxy($proxy_id = 0)
{

  $all_proxies = array(
        // below is an dummy / example proxy, add the rest from your list here
       0 => array(
            'server' => '42.108.23.37',
            'port' => '80',
            'username' => 'yourUsername',
            'password' => 'somePassword'
       ),
       // 1 => array()...
  );

    $proxies_count = variable_get('proxies_total', 0);
    if ($proxy_id == 0) {
        $proxy_id = rand(1, $proxies_count);
    }
    
    $proxy             = array();
    $proxy['server']   = $all_proxies[$proxy_id]['server'];
    $proxy['port']     = $all_proxies[$proxy_id]['port'];
    $proxy['username'] = $all_proxies[$proxy_id]['username'];
    $proxy['password'] = $all_proxies[$proxy_id]['password'];
    
    return $proxy;
}

// when you want to scrape a page, do something like the following (which uses simple_html_dom as the scraper / parser: http://simplehtmldom.sourceforge.net/)
// call a function like the below as follows:

custom_scraper_get_html('http://target-url.net/this_page.html', TRUE);

function custom_scraper_get_html($url, $use_proxy=FALSE)
{
    require_once '/simple_html_dom.php'; // set the path properly for your file location
    
    if ($use_proxy) {
        $proxy = custom_proxy_handler_get_proxy();
        $auth = base64_encode($proxy['username'].':'.$proxy['password']);

        // Define a context for HTTP. 
        $context      = array(
            'http' => array(
                'proxy' => $proxy['server'].':'.$proxy['port'], // This needs to be the server and the port of the NTLM Authentication Proxy Server. 
                'request_fulluri' => true,
                'header' => "Proxy-Authorization: Basic $auth",
            )
        );
        $context = stream_context_create($context);
        
        $html = file_get_html($url, false, $context);
    } else {
        // do it without a proxy
        $html = file_get_html($url);
    }
    
    return $html;
}

?>