proxies !

I got a site banned at Google so I got pissed and took a script from the blackbox @ digerati marketing to scrape proxy addresses, wired a database and curl into it, so now it scrapes proxies, random picks a proxy, prunes dead proxies and returns data.

Basic, it uses anonymous (level 2) proxies, but it works.

  1.  
  2. /* (mysql table)
  3. CREATE TABLE IF NOT EXISTS `serp_proxies` (
  4.   `id` int(11) NOT NULL auto_increment,
  5.   `ip` text NOT NULL,
  6.   `port` text NOT NULL,
  7.   PRIMARY KEY  (`id`)
  8. ) ENGINE=MyISAM  DEFAULT CHARSET=latin1 AUTO_INCREMENT=1 ;
  9. */
  10.  
  11. //initialize database class, replace with own code
  12. include('init.php');
  13.  
  14. //main class
  15. $p=new MyProxies;
  16.  
  17. //do I have proxies in the database ?
  18. //if not, get some and store them
  19. if($p->GetCount() < 1) {
  20.  $p->GetSomeAir(1);
  21.  $p->store2database();
  22. }
  23.  
  24. //pick one
  25. $p->RandomProxy();
  26.  
  27. //get the page
  28. $p->ThisProxy->DoRequest('http://www.domain.com/robots.txt');
  29.  
  30. //error handling
  31. if($p->ThisProxy->ProxyError > 0) {
  32. //7   no connect
  33. //28   timed out
  34. //52   empty reply
  35. //if it is dead, doesn't allow connections : prune it
  36.  if($p->ThisProxy->ProxyError==7) $p->DeleteProxy($p->ThisProxy->proxy_ip);
  37.  if($p->ThisProxy->ProxyError==52) $p->DeleteProxy($p->ThisProxy->proxy_ip);
  38. }
  39. //you could loop back until you get a 0-error proxy, but that ain't the point
  40.  
  41. //give me the content
  42. echo $p->ThisProxy->Content;
  43.  
  44.  
  45. Class MyProxies {
  46.  
  47.  var $Proxies = array();
  48.  var $ThisProxy;
  49.  var $MyCount;
  50.  
  51.  
  52. //picks a random proxy from the database
  53.  function RandomProxy() {
  54.  
  55.   global $serpdb;
  56.   $offset_result =  $serpdb->query("SELECT FLOOR(RAND() * COUNT(*)) AS `offset` FROM `serp_proxies`");
  57.   $offset_row = mysql_fetch_object($offset_result);
  58.   $offset = $offset_row->offset;
  59.   $result = $serpdb->query("SELECT * FROM `serp_proxies` LIMIT $offset, 1" );
  60.   while($row=mysql_fetch_assoc($result)) {
  61. //make instance of Proxy, with proxy_host ip and port
  62.    $this->ThisProxy = new Proxy($row['ip'].':'.$row['port']);
  63.    $this->ThisProxy->proxy_ip = $row['ip'];
  64.    $this->ThisProxy->proxy_port = $row['port'];
  65.    break;
  66.   }
  67.  }
  68.  
  69. //visit the famous russian site
  70.  function GetSomeAir($pages) {
  71.    for($index=0; $index< $pages; $index++)
  72.    {
  73.     $pageno = sprintf("%02d",$index+1);
  74.     $page_url = "http://www.samair.ru/proxy/proxy-" . $pageno . ".htm";
  75.     $page_html = @file_get_contents($page_url);
  76.  
  77. //get rid of the crap and extract the proxies
  78.     preg_match("/<tr><td>(.*)< \/td>< \/tr>/", $page_html, $matches);
  79.     $txt = $matches[1];
  80.     $main = split('</td><tr><td>', $txt);
  81.     for($x=0;$x<count ($main);$x++) {
  82.      $arr = split('</td><td>', $main[$x]);
  83.      $this->Proxies[] = split(':', $arr[0]);
  84.     }
  85.    }
  86.  }
  87.  
  88. //store the retrieved proxies (stored in this->Proxies) in the database
  89.  function store2database() {
  90.   global $serpdb;
  91.   foreach($this->Proxies as $p) {
  92.    $result = $serpdb->query("SELECT * FROM serp_proxies WHERE ip='".$p[0]."'");
  93.    if(mysql_num_rows($result)&lt;1) $serpdb->query("INSERT INTO serp_proxies (`ip`, `port`) VALUES ('".$p[0]."', '".$p[1]."')");
  94.   }
  95.   $serpdb->query("DELETE FROM serp_proxies WHERE `ip`=''");
  96.  }
  97.  
  98.  
  99.  function DeleteProxy($ip) {
  100.   global $serpdb;
  101.   $serpdb->query("DELETE FROM serp_proxies WHERE `ip`='".$ip."'");  
  102.  }
  103.  
  104.  
  105.  function GetCount()
  106.  {
  107. //use this to check how many proxies there are in the database
  108.   global $serpdb;
  109.   $this->MyCount = mysql_num_rows($serpdb->query("SELECT * FROM `serp_proxies`"));
  110.   return $this->MyCount;
  111.  }
  112.  
  113.  
  114. }
  115.  
  116. Class Proxy {
  117.  
  118.  var $proxy_ip;
  119.  var $proxy_port;
  120.  
  121.  var $proxy_host;
  122.  var $proxy_auth;
  123.  var $ch;
  124.  var $Content;
  125.  var $USERAGENT = "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)";
  126.  var $ProxyError = 0;
  127.  var $ProxyErrorMsg = '';
  128.  var $TimeOut=3;
  129.  var $IncludeHeaders = 0;
  130.  
  131.  function Proxy($host, $username='', $pwd='') {
  132. //initialize class, set host
  133.          $this->proxy_host = $host;
  134.          if (strlen($username) > 0 || strlen($pwd) > 0) {
  135.             $this->proxy_auth = $username.":".$pwd;
  136.          }
  137.       }
  138.  
  139.  function CURL_PROXY($cc) {
  140.    if (strlen($this->proxy_host) > 0) {
  141.     curl_setopt($cc, CURLOPT_PROXY, $this->proxy_host);
  142.     if (strlen($this->proxy_auth) > 0)
  143.      curl_setopt($cc, CURLOPT_PROXYUSERPWD, $this->proxy_auth);
  144.    }
  145.  }
  146.  
  147.  function DoRequest($url) {
  148.   $this->ch = curl_init();
  149.   curl_setopt($this->ch, CURLOPT_URL,$url);
  150.   $this->CURL_PROXY($this->ch);
  151.   curl_setopt($this->ch, CURLOPT_HEADER, $this->IncludeHeaders); // baca header
  152.  
  153.   curl_setopt($this->ch, CURLOPT_USERAGENT, $this->USERAGENT);
  154.   curl_setopt($this->ch, CURLOPT_RETURNTRANSFER, 1);
  155.   curl_setopt($this->ch, CURLOPT_TIMEOUT, $this->TimeOut);
  156.      $this->Content = curl_exec($this->ch);
  157.  
  158. //if an error occurs, store the number and message
  159.   if (curl_errno($this->ch))
  160.    {
  161.     $this->ProxyError =  curl_errno($this->ch);
  162.     $this->ProxyErrorMsg =  curl_error($this->ch);
  163.    }
  164.  }
  165.  
  166. }
  167. </td></count></td></tr>

There is not much to say about it, just a rough outline. I would prefer elite level 1 proxies but for now it will have to do.

Posted in php, seo tips and tricks and tagged , , .

Leave a Reply

Your email address will not be published. Required fields are marked *