function load_proxies_url($url)
{
$proxies = array();
$data = curl_cache_exec(array(CURLOPT_URL => $url), null, false);
if (!empty($data['data'])) {
$groups = array();
preg_match_all('/[0-9]+\\.[0-9]+\\.[0-9]+\\.[0-9]+:[0-9]+/', $data['data'], $groups);
if (isset($groups[0]) && !empty($groups[0])) {
foreach ($groups[0] as $ip) {
if (!in_array($ip, $proxies)) {
$proxies[] = $ip;
}
}
}
}
return $proxies;
}
private function handleCaptcha($html, $proxy, $dc, $origUrl)
{
global $dbc;
global $proxies;
global $captchaBrokenCurrentRun;
if ($dbc == null) {
$this->w("DeathByCaptcha not initialized");
return null;
}
$docCaptcha = new DOMDocument();
if (empty($html) || !@$docCaptcha->loadHTML($html)) {
$this->w("Can't parse captcha HTML");
return null;
}
$imgsrc = null;
$elts = $docCaptcha->getElementsByTagName("img");
if ($elts != null) {
foreach ($elts as $elt) {
$src = $elt->getAttribute("src");
if ($src != null && strncmp($src, "/sorry/image", 12) === 0) {
$imgsrc = "http://" . $dc . $src;
}
}
}
$groupRegex = array();
if ($imgsrc == null || !preg_match("|/sorry/image\\?id=([0-9]+)&?|", $imgsrc, $groupRegex)) {
$this->w("Can't extract captcha from HTML");
return null;
}
$params = array();
$params['id'] = $groupRegex[1];
$params['continue'] = $origUrl;
$params['submit'] = "Submit";
$data = curl_cache_exec(array(CURLOPT_URL => $imgsrc), $proxy, false);
$captcha = $data['data'];
if ($captcha == null || strlen($captcha) < 10 || ord($captcha[0]) !== 0xff || ord($captcha[1]) !== 0xd8) {
$this->w("Can't fetch captcha image");
return null;
}
$time = round(microtime(true) * 1000);
$solved = null;
try {
$solved = $dbc->decode(unpack('C*', $captcha), CAPTCHA_TIMEOUT);
++$captchaBrokenCurrentRun;
} catch (Exception $ex) {
$solved = null;
}
$time = round(microtime(true) * 1000) - $time;
if ($solved == null || !is_array($solved) || !isset($solved['is_correct']) || !isset($solved['text']) || !isset($solved['captcha'])) {
// not proxy fault
$proxies->preventfail($proxy);
$this->w("DeathByCaptcha failed breaking");
return null;
}
$this->w("Solved captcha to '" . $solved['text'] . "' in {$time} ms");
$params['captcha'] = $solved['text'];
$sendUrl = "http://" . $dc . "/sorry/Captcha?";
foreach ($params as $key => $value) {
$sendUrl .= $key . "=" . urlencode($value) . "&";
}
$sendUrl = rtrim($sendUrl, "&");
$data = curl_cache_exec(array(CURLOPT_URL => $sendUrl), $proxy, false);
if (empty($data['data'])) {
$this->w("Can't send captcha answer [1]");
return null;
}
if (strstr($data['data'], '<img src="/sorry/')) {
$this->w("Captcha incorrectly solved, report to DeathByCaptcha");
try {
$dbc->report($captcha['captcha']);
} catch (Exception $ex) {
}
// not proxy fault
$proxies->preventfail($proxy);
return null;
}
if (!strstr($data['data'], '<TITLE>Redirecting</TITLE>')) {
$this->w("Can't send captcha answer [1]");
return null;
}
$this->l("Captcha succesfully solved");
$data = curl_cache_exec(array(CURLOPT_URL => $origUrl), $proxy, false);
if ($data['status'] != 200) {
$this->w("Bad redirection after captcha solving");
print_r($data);
return null;
} else {
if (empty($data['data'])) {
$this->w("Bad content after captcha solving");
return null;
} else {
return $data['data'];
}
}
}
