2013-07-17 01:54:44 +02:00
|
|
|
<?php
|
|
|
|
|
|
|
|
namespace PicoFeed;
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
use LogicException;
|
|
|
|
use Clients\Curl;
|
|
|
|
use Clients\Stream;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Client class
|
|
|
|
*
|
|
|
|
* @author Frederic Guillot
|
|
|
|
* @package client
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
abstract class Client
|
|
|
|
{
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Flag that say if the resource have been modified
|
|
|
|
*
|
|
|
|
* @access private
|
|
|
|
* @var bool
|
|
|
|
*/
|
|
|
|
private $is_modified = true;
|
|
|
|
|
2014-10-19 20:42:31 +02:00
|
|
|
/**
|
|
|
|
* Flag that say if the resource is a 404
|
|
|
|
*
|
|
|
|
* @access private
|
|
|
|
* @var bool
|
|
|
|
*/
|
|
|
|
private $is_not_found = false;
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* HTTP encoding
|
|
|
|
*
|
|
|
|
* @access private
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
private $encoding = '';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* HTTP Etag header
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
protected $etag = '';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* HTTP Last-Modified header
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
protected $last_modified = '';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Proxy hostname
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
protected $proxy_hostname = '';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Proxy port
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var integer
|
|
|
|
*/
|
|
|
|
protected $proxy_port = 3128;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Proxy username
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
protected $proxy_username = '';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Proxy password
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
protected $proxy_password = '';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Client connection timeout
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var integer
|
|
|
|
*/
|
|
|
|
protected $timeout = 10;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* User-agent
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
protected $user_agent = 'PicoFeed (https://github.com/fguillot/picoFeed)';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Real URL used (can be changed after a HTTP redirect)
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
protected $url = '';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Page/Feed content
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var string
|
|
|
|
*/
|
|
|
|
protected $content = '';
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Number maximum of HTTP redirections to avoid infinite loops
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var integer
|
|
|
|
*/
|
|
|
|
protected $max_redirects = 5;
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Maximum size of the HTTP body response
|
|
|
|
*
|
|
|
|
* @access protected
|
|
|
|
* @var integer
|
|
|
|
*/
|
|
|
|
protected $max_body_size = 2097152; // 2MB
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Get client instance: curl or stream driver
|
|
|
|
*
|
|
|
|
* @static
|
|
|
|
* @access public
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public static function getInstance()
|
2013-07-17 01:54:44 +02:00
|
|
|
{
|
|
|
|
if (function_exists('curl_init')) {
|
|
|
|
|
|
|
|
require_once __DIR__.'/Clients/Curl.php';
|
|
|
|
return new Clients\Curl;
|
2014-05-20 20:20:27 +02:00
|
|
|
}
|
|
|
|
else if (ini_get('allow_url_fopen')) {
|
2013-07-17 01:54:44 +02:00
|
|
|
|
|
|
|
require_once __DIR__.'/Clients/Stream.php';
|
|
|
|
return new Clients\Stream;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
throw new LogicException('You must have "allow_url_fopen=1" or curl extension installed');
|
2013-07-17 01:54:44 +02:00
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Perform the HTTP request
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param string $url URL
|
|
|
|
* @return bool
|
|
|
|
*/
|
|
|
|
public function execute($url = '')
|
2013-07-17 01:54:44 +02:00
|
|
|
{
|
2014-05-20 20:20:27 +02:00
|
|
|
if ($url !== '') {
|
|
|
|
$this->url = $url;
|
2013-07-17 01:54:44 +02:00
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
Logging::setMessage(get_called_class().' Fetch URL: '.$this->url);
|
|
|
|
Logging::setMessage(get_called_class().' Etag provided: '.$this->etag);
|
|
|
|
Logging::setMessage(get_called_class().' Last-Modified provided: '.$this->last_modified);
|
2013-07-17 01:54:44 +02:00
|
|
|
|
|
|
|
$response = $this->doRequest();
|
|
|
|
|
|
|
|
if (is_array($response)) {
|
2014-10-19 20:42:31 +02:00
|
|
|
$this->handleNotModifiedResponse($response);
|
|
|
|
$this->handleNotFoundResponse($response);
|
|
|
|
$this->handleNormalResponse($response);
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Handle not modified response
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param array $response Client response
|
|
|
|
*/
|
|
|
|
public function handleNotModifiedResponse(array $response)
|
|
|
|
{
|
|
|
|
if ($response['status'] == 304) {
|
|
|
|
$this->is_modified = false;
|
|
|
|
}
|
|
|
|
else if ($response['status'] == 200) {
|
2013-07-17 01:54:44 +02:00
|
|
|
|
2014-10-19 20:42:31 +02:00
|
|
|
$etag = $this->getHeader($response, 'ETag');
|
|
|
|
$last_modified = $this->getHeader($response, 'Last-Modified');
|
|
|
|
|
|
|
|
if ($this->isPropertyEquals('etag', $etag) || $this->isPropertyEquals('last_modified', $last_modified)) {
|
2013-07-17 01:54:44 +02:00
|
|
|
$this->is_modified = false;
|
|
|
|
}
|
2014-05-20 20:20:27 +02:00
|
|
|
|
2014-10-19 20:42:31 +02:00
|
|
|
$this->etag = $etag;
|
|
|
|
$this->last_modified = $last_modified;
|
2013-07-17 01:54:44 +02:00
|
|
|
}
|
|
|
|
|
2014-10-19 20:42:31 +02:00
|
|
|
if ($this->is_modified === false) {
|
|
|
|
Logging::setMessage(get_called_class().' Resource not modified');
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Handle not found response
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param array $response Client response
|
|
|
|
*/
|
|
|
|
public function handleNotFoundResponse(array $response)
|
|
|
|
{
|
|
|
|
if ($response['status'] == 404) {
|
|
|
|
$this->is_not_found = true;
|
|
|
|
Logging::setMessage(get_called_class().' Resource not found');
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Handle normal response
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param array $response Client response
|
|
|
|
*/
|
|
|
|
public function handleNormalResponse(array $response)
|
|
|
|
{
|
|
|
|
if ($response['status'] == 200) {
|
|
|
|
$this->content = $response['body'];
|
|
|
|
$this->encoding = $this->findCharset($response);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Check if a class property equals to a value
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param string $property Class property
|
|
|
|
* @param string $value Value
|
|
|
|
* @return boolean
|
|
|
|
*/
|
|
|
|
private function isPropertyEquals($property, $value)
|
|
|
|
{
|
|
|
|
return $this->$property && $this->$property === $value;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Find charset from response headers
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param array $response Client response
|
|
|
|
*/
|
|
|
|
public function findCharset(array $response)
|
|
|
|
{
|
|
|
|
$result = explode('charset=', strtolower($this->getHeader($response, 'Content-Type')));
|
|
|
|
return isset($result[1]) ? $result[1] : '';
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Get header value from a client response
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param array $response Client response
|
|
|
|
* @param string $header Header name
|
|
|
|
* @return string
|
|
|
|
*/
|
|
|
|
public function getHeader(array $response, $header)
|
|
|
|
{
|
|
|
|
return isset($response['headers'][$header]) ? $response['headers'][$header] : '';
|
2014-05-20 20:20:27 +02:00
|
|
|
}
|
2013-07-17 01:54:44 +02:00
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Parse HTTP headers
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param array $lines List of headers
|
|
|
|
* @return array
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
public function parseHeaders(array $lines)
|
|
|
|
{
|
|
|
|
$status = 200;
|
|
|
|
$headers = array();
|
|
|
|
|
|
|
|
foreach ($lines as $line) {
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
if (strpos($line, 'HTTP') === 0) {
|
2013-07-17 01:54:44 +02:00
|
|
|
$status = (int) substr($line, 9, 3);
|
|
|
|
}
|
|
|
|
else if (strpos($line, ':') !== false) {
|
|
|
|
|
2013-07-19 01:24:17 +02:00
|
|
|
@list($name, $value) = explode(': ', $line);
|
|
|
|
if ($value) $headers[trim($name)] = trim($value);
|
2013-07-17 01:54:44 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
Logging::setMessage(get_called_class().' HTTP status code: '.$status);
|
2013-07-17 01:54:44 +02:00
|
|
|
|
|
|
|
foreach ($headers as $name => $value) {
|
2014-05-20 20:20:27 +02:00
|
|
|
Logging::setMessage(get_called_class().' HTTP header: '.$name.' => '.$value);
|
2013-07-17 01:54:44 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
return array($status, $headers);
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Set the Last-Modified HTTP header
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param string $last_modified Header value
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
public function setLastModified($last_modified)
|
|
|
|
{
|
|
|
|
$this->last_modified = $last_modified;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Get the value of the Last-Modified HTTP header
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @return string
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
public function getLastModified()
|
|
|
|
{
|
|
|
|
return $this->last_modified;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Set the value of the Etag HTTP header
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param string $etag Etag HTTP header value
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
public function setEtag($etag)
|
|
|
|
{
|
|
|
|
$this->etag = $etag;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Get the Etag HTTP header value
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @return string
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
public function getEtag()
|
|
|
|
{
|
|
|
|
return $this->etag;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Get the final url value
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @return string
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
public function getUrl()
|
|
|
|
{
|
|
|
|
return $this->url;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Set the url
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @return string
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setUrl($url)
|
|
|
|
{
|
|
|
|
$this->url = $url;
|
|
|
|
return $this;
|
|
|
|
}
|
2013-07-17 01:54:44 +02:00
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Get the body of the HTTP response
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @return string
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
public function getContent()
|
|
|
|
{
|
|
|
|
return $this->content;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Get the encoding value from HTTP headers
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @return string
|
|
|
|
*/
|
2013-10-04 05:14:39 +02:00
|
|
|
public function getEncoding()
|
|
|
|
{
|
|
|
|
return $this->encoding;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Return true if the remote resource has changed
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @return bool
|
|
|
|
*/
|
2013-07-17 01:54:44 +02:00
|
|
|
public function isModified()
|
|
|
|
{
|
|
|
|
return $this->is_modified;
|
|
|
|
}
|
2014-05-20 20:20:27 +02:00
|
|
|
|
2014-10-19 20:42:31 +02:00
|
|
|
/**
|
|
|
|
* Return true if the remote resource is not found
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @return bool
|
|
|
|
*/
|
|
|
|
public function isNotFound()
|
|
|
|
{
|
|
|
|
return $this->is_not_found;
|
|
|
|
}
|
|
|
|
|
2014-05-20 20:20:27 +02:00
|
|
|
/**
|
|
|
|
* Set connection timeout
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param integer $timeout Connection timeout
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setTimeout($timeout)
|
|
|
|
{
|
|
|
|
$this->timeout = $timeout ?: $this->timeout;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Set a custom user agent
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param string $user_agent User Agent
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setUserAgent($user_agent)
|
|
|
|
{
|
|
|
|
$this->user_agent = $user_agent ?: $this->user_agent;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Set the mximum number of HTTP redirections
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param integer $max Maximum
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setMaxRedirections($max)
|
|
|
|
{
|
|
|
|
$this->max_redirects = $max ?: $this->max_redirects;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Set the maximum size of the HTTP body
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param integer $max Maximum
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setMaxBodySize($max)
|
|
|
|
{
|
|
|
|
$this->max_body_size = $max ?: $this->max_body_size;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Set the proxy hostname
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param string $hostname Proxy hostname
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setProxyHostname($hostname)
|
|
|
|
{
|
|
|
|
$this->proxy_hostname = $hostname ?: $this->proxy_hostname;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Set the proxy port
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param integer $port Proxy port
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setProxyPort($port)
|
|
|
|
{
|
|
|
|
$this->proxy_port = $port ?: $this->proxy_port;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Set the proxy username
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param string $username Proxy username
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setProxyUsername($username)
|
|
|
|
{
|
|
|
|
$this->proxy_username = $username ?: $this->proxy_username;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Set the proxy password
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param string $password Password
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setProxyPassword($password)
|
|
|
|
{
|
|
|
|
$this->proxy_password = $password ?: $this->proxy_password;
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* Set config object
|
|
|
|
*
|
|
|
|
* @access public
|
|
|
|
* @param \PicoFeed\Config $config Config instance
|
|
|
|
* @return \PicoFeed\Client
|
|
|
|
*/
|
|
|
|
public function setConfig($config)
|
|
|
|
{
|
2014-10-19 20:42:31 +02:00
|
|
|
if ($config !== null) {
|
|
|
|
$this->setTimeout($config->getGrabberTimeout());
|
|
|
|
$this->setUserAgent($config->getGrabberUserAgent());
|
|
|
|
$this->setMaxRedirections($config->getMaxRedirections());
|
|
|
|
$this->setMaxBodySize($config->getMaxBodySize());
|
|
|
|
$this->setProxyHostname($config->getProxyHostname());
|
|
|
|
$this->setProxyPort($config->getProxyPort());
|
|
|
|
$this->setProxyUsername($config->getProxyUsername());
|
|
|
|
$this->setProxyPassword($config->getProxyPassword());
|
|
|
|
}
|
2014-05-20 20:20:27 +02:00
|
|
|
|
|
|
|
return $this;
|
|
|
|
}
|
|
|
|
}
|