extranet/framework/default/_includes/curl.php

<?

//include_once(realpath(dirname(__FILE__) . '/timer.php'));

/** Parse une page Html et retourne son contenu dans un tableau :
 ** "code"   => Code réponse Serveur
 ** "header" => Headers du serveur
 ** "body"   => Page HTML
 **/
function parse_response($this_response,  $err_num, $err_msg) {
	
	// Split response into header and body sections
	list($response_headers, $response_body) = explode("\r\n\r\n", $this_response, 2);
	$response_header_lines = explode("\r\n", $response_headers);

	// First line of headers is the HTTP response code
	$http_response_line = array_shift($response_header_lines);
	if(preg_match('@^HTTP/[0-9]\.[0-9] ([0-9]{3})@',$http_response_line, $matches)) { $response_code = $matches[1]; }
	if ($response_code==100) {
		list($response_headers, $response_body) = explode("\r\n\r\n", $response_body, 2);
		$response_header_lines = explode("\r\n", $response_headers);
		$http_response_line = array_shift($response_header_lines);
		if(preg_match('@^HTTP/[0-9]\.[0-9] ([0-9]{3})@',$http_response_line, $matches)) { $response_code = $matches[1]; }
	}

	// put the rest of the headers in an array
	$response_header_array = array();
	$nbRMID=0;
	foreach($response_header_lines as $header_line)
	{
		list($header,$value) = explode(': ', $header_line, 2);
		
		if ($header=='Set-cookie' && substr($value,0,5)=='RMID=' && $nbRMID<5)//{
			$nbRMID++;
//			echo ("Je gicle le RMID n°$nbRMID\r\n");}
		else
			$response_header_array[$header] .= $value."\n";
	}
/*	if ($response_code==100) {
		print_r($response_headers);
//		print_r($response_header_lines);
	}*/
	return array('code' => $response_code, 'header' => $response_header_array, 'body' => $response_body, 'err_num'=>$err_num, 'err_msg'=>$err_msg);
}

/** Récupère une page HTML en fonction des paramètres :
 ** $url				Url distante de la page à récupérer
 ** $strCookies Chaine de caractère contenant les cookies
 ** $postData		Tableau des données à passer en POST uniquement
 ** $referer		Referer à indiquer lors de l'appel de la page
 ** $debug			Activer le débogage (True/False)
 **
 ** ... et retourne son contenu dans un tableau :
 ** "code"   => Code réponse Serveur
 ** "header" => Headers du serveur
 ** "body"   => Page HTML
 **/
function getUrl($url, $strCookies='', $postData='', $referer='', $debug=false, $host='', $proxy='', $timeout=0) {


	$ch = curl_init();

	if ($host=='')
		$this_header = array('Host: '. HOST_INSEE);
	else
		$this_header = array('Host: '. $host);

		
	curl_setopt($ch, CURLOPT_URL, $url);
	curl_setopt($ch, CURLOPT_HEADER, 1);
	if ($proxy<>'')	curl_setopt($ch, CURLOPT_PROXY, $proxy);
	
	if (((int)$timeout)<>0)	curl_setopt($ch, CURLOPT_TIMEOUT, (int)$timeout);
	
	//curl_setopt($ch, CURLOPT_PROXYUSERPWD, 'username:password'); // Pas nécessaire en authentification NT

	curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
	//curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
	//curl_setopt($ch, CURLOPT_MAXREDIRS, 1);

	$user_agent = 'Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)';
	curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);
	curl_setopt($ch, CURLOPT_REFERER, $referer);

	// Add each cookie that has been returned in the response
	// If cookies need to be added/deleted or value changed, then add code here
	if ($strCookies!='') {
		//die('"'.$strCookies.'"');
		//echo $strCookies."\r\n";
		$cookies = explode("\n", $strCookies);
		// Create the basic header
		foreach($cookies as $this_cookie) {
			if (trim($this_cookie)<>'')
				array_push($this_header, 'Cookie: '.$this_cookie);
		}
	}

	if ($postData!='') {
		if (is_array($postData))
		$post_data=$postData;

		$o="";
		foreach ($post_data as $k=>$v)
		{
//			$o.= "$k=".utf8_encode($v)."&";
                      $o.= "$k=".$v."&";
		}
		$post_data=substr($o,0,-1);

		curl_setopt($ch, CURLOPT_POST, 1);
		curl_setopt($ch, CURLOPT_POSTFIELDS, $post_data);
		//if in_array('',$this_header
	//	array_push($this_header, "Content-type: application/x-www-form-urlencoded");
	//	array_push($this_header, "Content-Length: ".strlen($post_data));
	}

	curl_setopt($ch, CURLOPT_HTTPHEADER, $this_header);
	//print_r($this_header);

	$page=curl_exec($ch);
	$response = parse_response($page, curl_errno($ch), curl_error($ch));
	if ($debug){
		$url2=str_replace('http://', '', $url);
		$url2=str_replace('/', '_', $url2);
		$url2=str_replace('?', '(param)', $url2);
		$url2=str_replace('&', '(et)', $url2);

		
		$fp=fopen('insee/'. date('Ymd-His') .'-'. microtime_float(true) .'-'. $url2 . '.html', 'a');
		fwrite($fp, $url."\r\n");
		fwrite($fp, $page);
		fclose($fp);
		//echo strip_tags(html_entity_decode($response['body']), '<td>');
	}
	//print_r(curl_getinfo($ch));
	curl_close($ch);
	return $response;
}

/** Recherche un texte dans une page HTML
 **
 **/
function getTextInHtml($pageHtml, $strToFind, $strDeb, $strEnd, $include_strDeb=false, $include_strEnd=false, $ltrim=true, $rtrim=true, &$fin, $nbOcc=1) {
	$tabRet=array();
	$deb=$nbOccTrouve=0;
	while( is_int(($deb=strpos($pageHtml,$strToFind,$fin))) ) {
		$deb++;
		$deb2 = strpos($pageHtml,$strDeb, $deb);
		$fin = strpos($pageHtml,$strEnd, $deb2);
		if (!$include_strDeb)
			$deb2+=strlen($strDeb);
		$s_temp = substr($pageHtml, $deb2, ($fin-$deb2));
		
		if ($ltrim)	$s_temp=ltrim($s_temp);
		if ($rtrim)	$s_temp=rtrim($s_temp);

		if ($nbOcc==1) return $s_temp;
		//echo $s_temp."\r\n";
		//$a_temp = explode('" class="basic">', $s_temp);
		$tabUrl[$nbOccTrouve]=$s_temp;
		$nbOccTrouve++;
		
		if ($nbOcc==$nbOccTrouve) {
			//	echo "j'ai trouvé le nb demandé, je sort\r\n";
				break;
		};
	}

	return $tabUrl;
	/*<span class="mongrasvert">
    <li>Le type de voie a été modifié<br>
    <li>L'orthographe du mot directeur a été modifiée<br>
    <li>Le code postal a été forcé à partir du département et de la localité<br>                        </span>
*/
}

?>