当前位置: 首页 > 图文教程 > 网络编程 > PHP > 一个用php实现的获取URL信息的类

PHP
PHP 手机归属地查询 api
php 自写函数代码 获取关键字 去超链接
检查url链接是否已经有参数的php代码 添加 ? 或 &
PHP生成网页快照 不用COM不用扩展.
一步一步学习PHP(1) php开发环境配置
一步一步学习PHP(2):PHP类型
一步一步学习PHP(3) php 函数
一步一步学习PHP(4) php 函数 补充2
提高PHP编程效率 引入缓存机制提升性能
php 数组的合并、拆分、区别取值函数集
PHP采集相关教程之一 CURL函数库
IP138 IP地址查询小偷实现代码
php 生成静态页面的办法与实现代码详细版
一步一步学习PHP(5) 类和对象
一步一步学习PHP(6) 面向对象
Apache环境下PHP利用HTTP缓存协议原理解析及应用分析
PHP 截取字符串函数整理(支持gb2312和utf-8)
php foreach 使用&(与运算符)引用赋值要注意的问题
PHP IPV6正则表达式验证代码
用PHP ob_start()控制浏览器cache、生成html实现代码

PHP 中的 一个用php实现的获取URL信息的类


出处:互联网   整理: 软晨网(RuanChen.com)   发布: 2009-09-13   浏览: 150 ::
收藏到网摘: n/a

获取URL信息的类
使用这个类,你能获得URL的如下信息:
- Host
- Path
- Statuscode (eg. 404,200, ...)
- HTTP Version
- Server
- Content Type
- Date
- The whole header string of the URL
复制代码 代码如下:

<?
/**
* Class for getting information about URL's
* @author Sven Wagener <[email][email protected][/email]>
* @copyright Intertribe limited
* @PHP中文社区收集整理 [url]www.phpNet.cn[/url]
* @include Funktion:_include_
*/
class url{
var $url="";
var $url_host;
var $url_path;
var $file="";
var $code="";
var $code_desc="";
var $http_version=""; // Variable for HTTP version
var $header_stream;
var $header_array;
var $timeout="1";
/**
* Constructor of class url
* @param string $url the complete url
* @desc Constructor of class url
*/
function url($url){
$this->url=$url;
$url_array=parse_url($this->url);
$this->url_host=$url_array['host'];
$this->url_path=$url_array['path'];
if($this->url_path==""){
$this->url_path="/";
}
$this->refresh_headerinfo();
}
/**
* Returns the whole url
* @return string $url the whole url
* @desc Returns the whole url
*/
function get_url(){
return $this->url;
}
/**
* Returns the host of the url
* @return string $url_host the host of the url
* @desc Returns the host of the url
*/
function get_url_host(){
return $this->url_host;
}
/**
* Returns the path of the url
* @return string $url_path the path of the url
* @desc Returns the path of the url
*/
function get_url_path(){
return $this->url_path;
}
/**
* Returns the status code of the url
* @return string $status_code the status code
* @desc Returns the status code of the url
*/
function get_statuscode(){
return $this->code;
}
/**
* Returns the status code description of the url
* @return string $status_code_desc the status code description
* @desc Returns the status code description of the url
*/
function get_statuscode_desc(){
return $this->code_desc;
}
/**
* Returns the http version of the url by the returned headers of the server
* @return string $http_version the http version
* @desc Returns the http version of the url by the returned headers of the server
*/
function get_info_http_version(){
return $this->http_version;
}
/**
* Returns the server type of the url's host by the returned headers of the server
* @return string header_array['Server'] the server type
* @desc Returns the server type of the url's host by the returned headers of the server
*/
function get_info_server(){
return $this->header_array['Server'];
}
/**
* Returns the date of the url's host by the returned headers of the server
* @return string $header_array['Date'] the date
* @desc Returns the date of the url's host by the returned headers of the server
*/
function get_info_date(){
return $this->header_array['Date'];
}
/*
function get_info_content_length(){
return $this->header_array['Content-Length'];
}
*/
/**
* Returns the content type by the returned headers of the server
* @return string header_array['Content-Type'] the content type
* @desc Returns the content type by the returned headers of the server
*/
function get_info_content_type(){
return $this->header_array['Content-Type'];
}
/**
* Returns the content of the url without the headers
* @return string $content the content
* @desc Returns the content of the url without the headers
*/
function get_content(){
// Get a web page into a string
$string = implode ('', file ($this->url));
return $string;
}
/**
* Returns the whole header of url without content
* @return string $header the header
* @desc Returns the whole header of url without content
*/
function get_header_stream(){
return $this->header_stream;
}
/**
* Returns the whole headers of the url in an array
* @return array $header_array the headers in an array
* @desc Returns the whole headers of the url in an array
*/
function get_headers(){
return $this->header_array;
}
/**
* Refreshes the header information
* @desc Refreshes the header information
*/
function refresh_headerinfo(){
// Open socket for connection via port 80 to put headers
$fp = fsockopen ($this->url_host, 80, $errno, $errstr, 30);
if (!$fp) {
// echo "$errstr ($errno)";
if($errno==0){
$errstr="Server Not Found";
}
$this->code=$errno;
$this->code_desc=$errstr;
} else {
$put_string="GET ".$this->url_path." HTTP/1.0rnHost: ".$this->url_host."rnrn";
fputs ($fp, $put_string);
@socket_set_timeout($fp,$this->timeout);
$stream="";
$this->header_array="";
$header_end=false;
// Getting header string and creating header array
$i=0;
while (!feof($fp) && !$header_end) {
$line=fgets($fp,128);
if(strlen($line)==2){
$header_end=true;
}else{
if($i==0){
$line1=$line;
}
$stream.=$line;
$splitted_line=split(":",$line);
$this->header_array[$splitted_line[0]]=$splitted_line[1];
$i++;
}
}
fclose ($fp);
$this->header_stream=$stream;
$splitted_stream=split(" ",$line1);
// Getting status code and description of the URL
$this->code=$splitted_stream[1];
$this->code_desc=$splitted_stream[2];
if(count($splitted_stream)>3){
for($i=3;$i<count($splitted_stream);$i++){
$this->code_desc.=" ".$splitted_stream[$i];
}
}
// Cleaning up for n and r
$this->code_desc=preg_replace("[\n]","",$this->code_desc);
$this->code_desc=preg_replace("[\r]","",$this->code_desc);
// Getting Http Version
$http_array=split("/",$splitted_stream[0]);
$this->http_version=$http_array[1];
}
}
/**
* Sets the timeout for getting header data from server
* @param int $seconds time for timeout in seconds
* @desc Sets the timeout for getting header data from server
*/
function set_timeout($seconds){
$this->timeout=$seconds;
}
}
?>

复制代码 代码如下:

<?php
include("url.class.php");
$url=new url("[url]http://www.phpNet.cn/[/url]");
echo $url->get_header_stream();
$headers=$url->get_headers();
echo $headers['Server'];
echo $url->get_content();
echo "URL: <b>".$url->get_url()."</b><br>n";
echo "URL Host: ".$url->get_url_host()."<br>n";
echo "URL Path: ".$url->get_url_path()."<br>n<br>n";
echo "Statuscode: ".$url->get_statuscode()."<br>n";
echo "Statuscode description: ".$url->get_statuscode_desc()."<br>n";
echo "HTTP Version: ".$url->get_info_http_version()."<br>n";
echo "Server: ".$url->get_info_server()."<br>n";
echo "Content Type: ".$url->get_info_content_type()."<br>n";
echo "Date: ".$url->get_info_date()."<br>n<br>n";
echo "WHOLE HEADERS:<br>n";
echo $url->get_header_stream();
?>