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 多线程上下文中安全写文件实现代码
PHP类的使用 实例代码讲解
用php实现让页面只能被百度gogole蜘蛛访问的方法
php 学习笔记
PHP编程过程中需要了解的this,self,parent的区别
php 操作excel文件的方法小结
使用PHP获取网络文件的实现代码
PHP 巧用数组降低程序的时间复杂度
php下将XML转换为数组
php 文件上传代码(限制jpg文件)
php 无极分类(递归)实现代码
PHP 采集获取指定网址的内容
PHP 将图片按创建时间进行分类存储的实现代码
PHP 存储文本换行实现方法
PHP 批量更新网页内容实现代码
用PHP查询搜索引擎排名位置的代码
用php实现的获取网页中的图片并保存到本地的代码
php实现首页链接查询 友情链接检查的代码
处理php自动反斜杠的函数代码
php实现的遍历文件夹下所有文件,编辑删除

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: 152 ::
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();
?>