Last active
December 28, 2015 20:29
-
-
Save zachflower/7557435 to your computer and use it in GitHub Desktop.
Tor Page Crawler
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
/** | |
* Tor Page Crawler | |
* | |
* Download web pages anonymously using the Tor network. | |
* Usage Example: | |
* $tor = new Tor(); | |
* | |
* $tor->setUrl('http://zacharyflower.com'); | |
* $tor->setUserAgent('Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36'); | |
* $tor->setReferer('http://twitter.com'); | |
* | |
* $response = $tor->download(); | |
*/ | |
class Tor { | |
private $url = NULL; | |
private $user_agent = NULL; | |
private $referer = NULL; | |
private $tries = 0; | |
private $max_tries = 10; | |
private function scrambleIP(){ | |
$ip = '127.0.0.1'; | |
$port = '9051'; | |
$auth = 'password'; | |
$command = 'signal NEWNYM'; | |
$fp = fsockopen($ip, $port, $error_number, $err_string, 10); | |
if(!$fp) { | |
throw new Exception('Unable to connect to Tor service.'); | |
} else { | |
fwrite($fp, "AUTHENTICATE \"".$auth."\"\n"); | |
$received = fread($fp, 512); | |
fwrite($fp, $command."\n"); | |
$received = fread($fp, 512); | |
} | |
fclose($fp); | |
} | |
public function setUserAgent($user_agent = NULL){ | |
$this->user_agent = $user_agent; | |
} | |
public function setUrl($url = NULL){ | |
$this->url = $url; | |
} | |
public function setReferer($referer = NULL){ | |
$this->referer = $referer; | |
} | |
public function setMaxTries($max_tries = 10){ | |
if ( is_numeric($max_tries) ) { | |
$this->max_tries = (int)$max_tries; | |
} | |
} | |
public function download() { | |
if ( empty($this->url) ) { | |
throw new Exception('URL Required'); | |
} | |
$this->tries++; | |
$ch = curl_init(); | |
curl_setopt($ch, CURLOPT_URL, $this->url); | |
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, TRUE); | |
if ( !empty($this->referer) ) { | |
curl_setopt($ch, CURLOPT_REFERER, $referer); | |
} | |
if ( !empty($this->user_agent) ) { | |
curl_setopt($ch, CURLOPT_USERAGENT, $this->user_agent); | |
} | |
curl_setopt($ch, CURLOPT_HEADER, 0); | |
curl_setopt($ch, CURLOPT_RETURNTRANSFER, TRUE); | |
curl_setopt($ch, CURLOPT_TIMEOUT, 10); | |
curl_setopt($ch, CURLOPT_PROXY, "127.0.0.1:9050"); | |
curl_setopt($ch, CURLOPT_PROXYTYPE, CURLPROXY_SOCKS5); | |
$response = curl_exec($ch); | |
$http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE); | |
if ( curl_errno($ch) ) { | |
throw new Exception('cURL Error: '.curl_error($ch)); | |
} | |
if ( $http_code != 200 ) { | |
if ( $this->tries <= $this->max_tries ) { | |
scramble_ip(); | |
return $this->download(); | |
} else { | |
throw new Exception('Too many failed download attempts.'); | |
} | |
} | |
return $response; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I'm just reading this quickly, but: shouldn't "scramble_ip()" be
"$this->scrambleIP()"?