下面是网上找到的一个类,是说可以实现 php 异步抓取数据,但是 php 一直是同步的,打印出的结果也是同步的,但是通过下面 rolling_curl 的方法,的确可以节省一定的时间,但是既然都是同步的 ,为什么会节约时间呢? 希望各位大神能给出一些指导。 /**
/**
单一的请求对象
/
class Curl_request {
public $url = '';
public $method = 'GET';
public $post_data = null;
public $headers = null;
public $options = null;
/
*
* @param string $url
* @param string $method
* @param string $post_data
* @param string $headers
* @param array $options
* @return void
/
public function __construct($url, $method = 'GET', $post_data = null, $headers = null, $options = null) {
$this->url = $url;
$this->method = strtoupper( $method );
$this->post_data = $post_data;
$this->headers = $headers;
$this->options = $options;
}
/*
* @return void
/
public function __destruct() {
unset ( $this->url, $this->method, $this->post_data, $this->headers, $this->options );
}
}
/*
请求 url 个数
@var int
/
private $size = 1;
/*
等待所有 cURL 批处理中的活动连接等待响应时间
@var int
/
private $timeout = 5;
/*
完成请求回调函数
@var string
/
private $callback = null;
/*
cRUL 配置
@var array
/
private $options = array (CURLOPT_SSL_VERIFYPEER => 0,CURLOPT_RETURNTRANSFER => 1,CURLOPT_CONNECTTIMEOUT => 30 );
/*
请求头
@var array
/
private $headers = array ();
/*
请求列队
@var array
/
private $requests = array ();
/*
请求列队索引
@var array
/
private $request_map = array ();
/*
错误
@var array
/
private $errors = array ();
/*
@access public
@param string $callback 回调函数
该函数有 4 个参数($response,$info,$error,$request)
$response url 返回的 body
$info cURL 连接资源句柄的信息
$error 错误
$request 请求对象
/
public function __construct($callback = null) {
$this->callback = $callback;
}
/*
添加一个请求对象到列队
@access public
@param object $request
@return boolean
/
public function add($request) {
$this->requests [] = $request;
return TRUE;
}
/*
创建一个请求对象并添加到列队
@access public
@param string $url
@param string $method
@param string $post_data
@param string $headers
@param array $options
@return boolean
/
public function request($url, $method = 'GET', $post_data = null, $headers = null, $options = null) {
$this->requests [] = new Curl_request ( $url, $method, $post_data, $headers, $options );
return TRUE;
}
/*
创建 GET 请求对象
@access public
@param string $url
@param string $headers
@param array $options
@return boolean
/
public function get($url, $headers = null, $options = null) {
return $this->request ( $url, "GET", null, $headers, $options );
}
/*
创建一个 POST 请求对象
@access public
@param string $url
@param string $post_data
@param string $headers
@param array $options
@return boolean
/
public function post($url, $post_data = null, $headers = null, $options = null) {
return $this->request ( $url, "POST", $post_data, $headers, $options );
}
/*
执行 cURL
@access public
@param int $size 最大连接数
@return Ambigous <boolean, mixed>|boolean
/
public function execute($size = null) {
if (sizeof ( $this->requests ) == 1) {
return $this->single_curl ();
} else {
return $this->rolling_curl ( $size );
}
}
/*
单个 url 请求
@access private
@return mixed|boolean
*/
private function single_curl() {
$ch = curl_init ();
$request = array_shift ( $this->requests );
$options = $this->get_options ( $request );
curl_setopt_array ( $ch, $options );
$output = curl_exec ( $ch );
$info = curl_getinfo ( $ch );
// it's not neccesary to set a callback for one-off requests
if ($this->callback) {
$callback = $this->callback;
if (is_callable ( $this->callback )) {
call_user_func ( $callback, $output, $info, $request );
}
} else
return $output;
return true;
}
/**
多个 url 请求
@access private
@param int $size 最大连接数
@return boolean
*/
private function rolling_curl($size = null) {
if ($size)
$this->size = $size;
else
$this->size = count($this->requests);
if (sizeof ( $this->requests ) < $this->size)
$this->size = sizeof ( $this->requests );
if ($this->size < 2)
$this->set_error ( 'size must be greater than 1' );
$master = curl_multi_init ();
//添加 cURL 连接资源句柄到 map 索引
for($i = 0; $i < $this->size; $i ++) {
$ch = curl_init ();
$options = $this->get_options ( $this->requests [$i] );
curl_setopt_array ( $ch, $options );
curl_multi_add_handle ( $master, $ch );
$key = ( string ) $ch;
$this->request_map [$key] = $i;
}
$active = $done = null;
do {
while ( ($execrun = curl_multi_exec ( $master, $active )) == CURLM_CALL_MULTI_PERFORM )
;
if ($execrun != CURLM_OK)
break;
//有一个请求完成则回调
while ( $done = curl_multi_info_read ( $master ) ) {
//$done 完成的请求句柄
$info = curl_getinfo ( $done ['handle'] );//
$output = curl_multi_getcontent ( $done ['handle'] );//
$error = curl_error ( $done ['handle'] );//
$this->set_error ( $error );
//调用回调函数,如果存在的话
$callback = $this->callback;
if (is_callable ( $callback )) {
$key = ( string ) $done ['handle'];
$request = $this->requests [$this->request_map [$key]];
unset ( $this->request_map [$key] );
call_user_func ( $callback, $output, $info, $error, $request );
}
curl_close ( $done ['handle'] );
//从列队中移除已经完成的 request
curl_multi_remove_handle ( $master, $done ['handle'] );
}
//等待所有 cURL 批处理中的活动连接
if ($active)
curl_multi_select ( $master, $this->timeout );
} while ( $active );
//完成关闭
curl_multi_close ( $master );
return true;
}
/**
获取没得请求对象的 cURL 配置
@access private
@param object $request
@return array
*/
private function get_options($request) {
$options = $this->__get ( 'options' );
if (ini_get ( 'safe_mode' ) == 'Off' || ! ini_get ( 'safe_mode' )) {
$options [CURLOPT_FOLLOWLOCATION] = 1;
$options [CURLOPT_MAXREDIRS] = 5;
}
//$headers = $this->__get ( 'headers' );
$headers = $request->headers;
if ($request->options) {
$options = $request->options + $options;
}
$options [CURLOPT_URL] = $request->url;
if ($request->post_data && strtolower($request->method) == 'post' ) {
$options [CURLOPT_POST] = 1;
$options [CURLOPT_POSTFIELDS] = $request->post_data;
}
if ($headers) {
$options [CURLOPT_HEADER] = 0;
$options [CURLOPT_HTTPHEADER] = $headers;
}
return $options;
}
/**
设置错误信息
@access public
@param string $msg
/
public function set_error($msg) {
if (! empty ( $msg ))
$this->errors [] = $msg;
}
/*
获取错误信息
@access public
@param string $open
@param string $close
@return string
/
public function display_errors($open = '
', $close = '
') {@access public
@param string $name
@param string $value
@return boolean
/
public function __set($name, $value) {
if ($name == 'options' || $name == 'headers') {
$this->{$name} = $value + $this->{$name};
} else {
$this->{$name} = $value;
}
return TRUE;
}
/*
@param string $name
@return mixed
@access public
/
public function __get($name) {
return (isset ( $this->{$name} )) ? $this->{$name} : null;
}
/*
@return void
@access public
/
public function __destruct() {
unset ( $this->size, $this->timeout, $this->callback, $this->options, $this->headers, $this->requests, $this->request_map, $this->errors );
}
}
// END Curl Class
/ End of file curl.class.php */
这是一个专为移动设备优化的页面(即为了让你能够在 Google 搜索结果里秒开这个页面),如果你希望参与 V2EX 社区的讨论,你可以继续到 V2EX 上打开本讨论主题的完整版本。
V2EX 是创意工作者们的社区,是一个分享自己正在做的有趣事物、交流想法,可以遇见新朋友甚至新机会的地方。
V2EX is a community of developers, designers and creative people.