/**
* @param GAQuery $pQuery
* @return array
*/
public function retrieveData(GAQuery $pQuery)
{
if (!$this->isAuth()) {
return null;
}
$r = new Request($pQuery->get());
$header[] = 'Authorization: GoogleLogin auth=' . $this->getAuth();
$r->setOption(CURLOPT_SSL_VERIFYPEER, 0);
$r->setOption(CURLOPT_HTTPHEADER, $header);
$r->setOption(CURLOPT_HEADER, false);
return SimpleJSON::decode($r->execute());
}
/**
* Méthode de demande d'authentication pour le service google souhaité
* @return void
*/
private function login()
{
$r = new Request(self::URL_LOGIN);
$r->setOption(CURLOPT_FOLLOWLOCATION, true);
$r->setOption(CURLOPT_SSL_VERIFYPEER, 0);
$data = array('accountType' => $this->account_type, 'Email' => $this->email, 'Passwd' => $this->password, 'source' => self::SOURCE, 'service' => $this->service);
$r->setDataPost($data);
$retour = $r->execute();
$retour = preg_replace("/(\n|\r)/", "", $retour);
$toParse = array("Auth", "LSID", "SID");
foreach ($toParse as $var) {
if (preg_match("/" . $var . "=(.*)\$/", $retour, $extract, PREG_OFFSET_CAPTURE)) {
try {
$this->{$var} = $extract[1][0];
$retour = preg_replace("/" . $var . "=.*\$/", "", $retour);
} catch (Exception $e) {
return;
}
} else {
return;
}
}
}
/**
* @return bool
*/
private function next()
{
$message = "" . count($this->urlsDone) . " done" . PHP_EOL;
$message .= "" . count($this->urlsToCrawl) . " left" . PHP_EOL;
if (count($this->urlsToCrawl) == 0) {
return false;
}
$url = array_shift($this->urlsToCrawl);
if (in_array($url, $this->urlsDone)) {
return true;
}
$message .= "Loading : " . $url . PHP_EOL;
$this->dispatchEvent(new SimpleCrawlerEvent(SimpleCrawlerEvent::OUTPUT, $message));
$r = new Request($url);
try {
$d = $r->execute();
} catch (\Exception $e) {
$d = false;
}
if (!$d) {
$this->urlsDone[] = $url;
$redirect = $r->getRedirectURL();
if ($redirect) {
$this->urlsToCrawl[] = $redirect;
} else {
$this->log($url, $r->getResponseHTTPCode(), $r->getRedirectURL());
}
return true;
}
$baseHref = $this->extract('/\\<base href="([^"]+)"/', $d);
$title = $this->extract('/\\<title\\>([^<]+)/', $d);
$description = $this->extract('/\\<meta name="description" content="([^"]+)"/', $d);
preg_match_all('/href\\="([^"]+)"/', $d, $matches);
if (isset($matches[1]) && !empty($matches[1])) {
foreach ($matches[1] as $u) {
if (strpos($u, 'http://') === 0 || strpos($u, 'https://') === 0 || strpos($u, 'javascript:') === 0 || strpos($u, '#') === 0 || $u === "/") {
continue;
}
if (strpos($u, "/") === 0) {
$u = substr($u, 1, strlen($u));
}
$u = $baseHref . $u;
if ($this->deepRunning && !in_array($u, $this->urlsToCrawl) && !in_array($u, $this->urlsDone)) {
$this->urlsToCrawl[] = $u;
}
}
}
$this->urlsDone[] = $url;
$this->log($url, $title, $description);
return true;
}
/**
* Exécute une requête HTTP via CURL
* Renvoie le résultat
* @throws Exception
* @param string $pUrl
* @return string
*/
public static function load($pUrl)
{
$r = new Request($pUrl);
try {
$d = $r->execute();
} catch (Exception $e) {
throw $e;
}
return $d;
}
