当前位置: 首页 > 图文教程 > 网络编程 > PHP > 发布一个用PHP fsockopen写的HTTP下载的类

PHP
php ignore_user_abort与register_shutdown_function 使用方法
PHP写MySQL数据 实现代码
phpmyadmin 访问被拒绝的真实原因
PHP 程序员也要学会使用“异常”
php MYSQL 数据备份类
PHP 类型转换函数intval
php 图像函数大举例(非原创)
PHP 输出缓存详解
PHP COOKIE设置为浏览器进程
ie6 动态缩略图不显示的原因
php 将bmp图片转为jpg等其他任意格式的图片
discuz7 phpMysql操作类
一个php Mysql类 可以参考学习熟悉下
php 分页函数multi() discuz
学习discuz php 引入文件的方法DISCUZ_ROOT
php fckeditor 调用的函数
mysql 性能的检查和优化方法
PHP 高级课程笔记 面向对象
PHP 多进程 解决难题
php 404错误页面实现代码

发布一个用PHP fsockopen写的HTTP下载的类


出处:互联网   整理: 软晨网(RuanChen.com)   发布: 2009-09-13   浏览: 200 ::
收藏到网摘: n/a

如果支持打开远程内容的选项的话,实际上php用fopen或file_get_contents都能获得一个网页的内容,但是默认的函数有个不足的地方就是无法获取HTTP头,这在一些特殊的应用中很不方便,如,有一个链接:
http://www.abc.com/showvd.asp?id=18
假如它返回的是一个图片,用默认函数就很难识别,但如果通过HTTP应答头来判断就简单多了,此外如果对方通过 Refer 来防盗链的话,也是无法获取的,用HTTP类就能完美解决这些问题,而且速度也相差无几。

使用方法:
$hd = new DedeHttpDown();
$hd->OpenUrl("http://www.dedecms.com");
echo $hd->GetHtml();
//如果保存为文件则用 $hd->SaveBin("dede.html");
$hd->Close();
获得http请求头用
$hd->GetHead("key")
设置请求头
$hd->SetHead(key,value); (必须在调用 OpenUrl 之前设定)

代码如下:
<?
/* ---------------------------------------------------------------------
//织梦Http下载类V1.0
//出自:织梦之旅 http://www.dedecms.com
//作者: IT柏拉图
//时间: 2005-11-13 12:39
//声明: 首发在落伍者网站,转载请保留版权信息
--------------------------------------------------------------------- */
class DedeHttpDown
{
var $m_url = "";
var $m_urlpath = "";
var $m_scheme = "http";
var $m_host = "";
var $m_port = "80";
var $m_user = "";
var $m_pass = "";
var $m_path = "/";
var $m_query = "";
var $m_fp = "";
var $m_error = "";
var $m_httphead = "" ;
var $m_html = "";
var $m_puthead = "";
var $BaseUrlPath = "";
var $HomeUrl = "";
var $JumpCount = 0;//防止多重重定向陷入死循环
//
//初始化系统
//
function PrivateInit($url)
{
if($url=="") return ;
$urls = "";
$urls = @parse_url($url);
$this->m_url = $url;
if(is_array($urls))
{
$this->m_host = $urls["host"];
if(!empty($urls["scheme"])) $this->m_scheme = $urls["scheme"];
if(!empty($urls["user"])){
$this->m_user = $urls["user"];
}
if(!empty($urls["pass"])){
$this->m_pass = $urls["pass"];
}
if(!empty($urls["port"])){
$this->m_port = $urls["port"];
}
if(!empty($urls["path"])) $this->m_path = $urls["path"];
$this->m_urlpath = $this->m_path;
if(!empty($urls["query"])){
$this->m_query = $urls["query"];
$this->m_urlpath .= "?".$this->m_query;
}
$this->HomeUrl = $urls["host"];
$this->BaseUrlPath = $this->HomeUrl.$urls["path"];
$this->BaseUrlPath = ereg_replace("/([^/]*)\.(.*)$","/",$this->BaseUrlPath);
$this->BaseUrlPath = ereg_replace("/$","",$this->BaseUrlPath);
}
}
//
//打开指定网址
//
function OpenUrl($url)
{
//重设各参数
$this->m_url = "";
$this->m_urlpath = "";
$this->m_scheme = "http";
$this->m_host = "";
$this->m_port = "80";
$this->m_user = "";
$this->m_pass = "";
$this->m_path = "/";
$this->m_query = "";
$this->m_error = "";
$this->JumpCount = 0;
$this->m_httphead = Array() ;
//$this->m_puthead = "";
$this->m_html = "";
$this->Close();
//初始化系统
$this->PrivateInit($url);
$this->PrivateStartSession();
}
//
//打开303重定向网址
//
function JumpOpenUrl($url)
{
//重设各参数
$this->m_url = "";
$this->m_urlpath = "";
$this->m_scheme = "http";
$this->m_host = "";
$this->m_port = "80";
$this->m_user = "";
$this->m_pass = "";
$this->m_path = "/";
$this->m_query = "";
$this->m_error = "";
$this->JumpCount++;
$this->m_httphead = Array() ;
$this->m_html = "";
$this->Close();
//初始化系统
$this->PrivateInit($url);
$this->PrivateStartSession();
}
//
//获得某操作错误的原因
//
function printError()
{
echo "错误信息:".$this->m_error;
echo "具体返回头:<br>";
foreach($this->m_httphead as $k=>$v)
{ echo "$k => $v <br>\r\n"; }
}
//
//判别用Get方法发送的头的应答结果是否正确
//
function IsGetOK()
{
if( ereg("^2",$this->GetHead("http-state")) )
{ return true; }
else
{
$this->m_error .= $this->GetHead("http-state")." - ".$this->GetHead("http-describe")."<br>";
return false;
}
}
//
//看看返回的网页是否是text类型
//
function IsText()
{
if(ereg("^2",$this->GetHead("http-state"))
&& eregi("^text",$this->GetHead("content-type")))
{ return true; }
else
{
$this->m_error .= "内容为非文本类型或网址重定向<br>";
return false;
}
}
//
//判断返回的网页是否是特定的类型
//
function IsContentType($ctype)
{
if(ereg("^2",$this->GetHead("http-state"))
&& $this->GetHead("content-type")==strtolower($ctype))
{ return true; }
else
{
$this->m_error .= "类型不对 ".$this->GetHead("content-type")."<br>";
return false;
}
}
//
//用Http协议下载文件
//
function SaveToBin($savefilename)
{
if(!$this->IsGetOK()) return false;
if(@feof($this->m_fp)) { $this->m_error = "连接已经关闭!"; return false; }
$fp = fopen($savefilename,"w");
while(!feof($this->m_fp)){
fwrite($fp,fread($this->m_fp,1024));
}
fclose($this->m_fp);
fclose($fp);
return true;
}
//
//保存网页内容为Text文件
//
function SaveToText($savefilename)
{
if($this->IsText()) $this->SaveBinFile($savefilename);
else return "";
}
//
//用Http协议获得一个网页的内容
//
function GetHtml()
{
if(!$this->IsText()) return "";
if($this->m_html!="") return $this->m_html;
if(!$this->m_fp||@feof($this->m_fp)) return "";
while(!feof($this->m_fp)){
$this->m_html .= fgets($this->m_fp,256);
}
@fclose($this->m_fp);
return $this->m_html;
}
//
//开始HTTP会话
//
function PrivateStartSession()
{
if(!$this->PrivateOpenHost()){
$this->m_error .= "打开远程主机出错!";
return false;
}
if($this->GetHead("http-edition")=="HTTP/1.1") $httpv = "HTTP/1.1";
else $httpv = "HTTP/1.0";
//发送固定的起始请求头GET、Host信息
fputs($this->m_fp,"GET ".$this->m_urlpath." $httpv\r\n");
$this->m_puthead["Host"] = $this->m_host;
//发送用户自定义的请求头
if(!isset($this->m_puthead["Accept"])) { $this->m_puthead["Accept"] = "*/*"; }
if(!isset($this->m_puthead["User-Agent"])) { $this->m_puthead["User-Agent"] = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2)"; }
if(!isset($this->m_puthead["Refer"])) { $this->m_puthead["Refer"] = "http://".$this->m_puthead["Host"]; }
foreach($this->m_puthead as $k=>$v){
$k = trim($k);
$v = trim($v);
if($k!=""&&$v!=""){
fputs($this->m_fp,"$k: $v\r\n");
}
}
//发送固定的结束请求头
//HTTP1.1协议必须指定文档结束后关闭链接,否则读取文档时无法使用feof判断结束
if($httpv=="HTTP/1.1") fputs($this->m_fp,"Connection: Close\r\n\r\n");
else fputs($this->m_fp,"\r\n");
//获取应答头状态信息
$httpstas = explode(" ",fgets($this->m_fp,256));
$this->m_httphead["http-edition"] = trim($httpstas[0]);
$this->m_httphead["http-state"] = trim($httpstas[1]);
$this->m_httphead["http-describe"] = "";
for($i=2;$i<count($httpstas);$i++){
$this->m_httphead["http-describe"] .= " ".trim($httpstas[$i]);
}
//获取详细应答头
while(!feof($this->m_fp)){
$line = trim(fgets($this->m_fp,256));
if($line == "") break;
$hkey = "";
$hvalue = "";
$v = 0;
for($i=0;$i<strlen($line);$i++){
if($v==1) $hvalue .= $line[$i];
if($line[$i]==":") $v = 1;
if($v==0) $hkey .= $line[$i];
}
$hkey = trim($hkey);
if($hkey!="") $this->m_httphead[strtolower($hkey)] = trim($hvalue);
}
//判断是否是3xx开头的应答
if(ereg("^3",$this->m_httphead["http-state"]))
{
if($this->JumpCount > 3) return;
if(isset($this->m_httphead["location"])){
$newurl = $this->m_httphead["location"];
if(eregi("^http",$newurl)){
$this->JumpOpenUrl($newurl);
}
else{
$newurl = $this->FillUrl($newurl);
$this->JumpOpenUrl($newurl);
}
}
else
{ $this->m_error = "无法识别的转移应答!"; }
}//
}
//
//获得一个Http头的值
//
function GetHead($headname)
{
$headname = strtolower($headname);
if(isset($this->m_httphead[$headname]))
return $this->m_httphead[$headname];
else
return "";
}
//
//设置Http头的值
//
function SetHead($skey,$svalue)
{
$this->m_puthead[$skey] = $svalue;
}
//
//打开连接
//
function PrivateOpenHost()
{
if($this->m_host=="") return false;
$this->m_fp = @fsockopen($this->m_host, $this->m_port, &$errno, &$errstr,10);
if(!$this->m_fp){
$this->m_error = $errstr;
return false;
}
else{
return true;
}
}
//
//关闭连接
//
function Close(){
@fclose($this->m_fp);
}
//
//补全相对网址
//
function FillUrl($surl)
{
$i = 0;
$dstr = "";
$pstr = "";
$okurl = "";
$pathStep = 0;
$surl = trim($surl);
if($surl=="") return "";
$pos = strpos($surl,"#");
if($pos>0) $surl = substr($surl,0,$pos);
if($surl[0]=="/"){
$okurl = "http://".$this->HomeUrl."/".$surl;
}
else if($surl[0]==".")
{
if(strlen($surl)<=2) return "";
else if($surl[0]=="/")
{
$okurl = "http://".$this->BaseUrlPath."/".substr($surl,2,strlen($surl)-2);
}
else{
$urls = explode("/",$surl);
foreach($urls as $u){
if($u=="..") $pathStep++;
else if($i<count($urls)-1) $dstr .= $urls[$i]."/";
else $dstr .= $urls[$i];
$i++;
}
$urls = explode("/",$this->BaseUrlPath);
if(count($urls) <= $pathStep)
return "";
else{
$pstr = "http://";
for($i=0;$i<count($urls)-$pathStep;$i++)
{ $pstr .= $urls[$i]."/"; }
$okurl = $pstr.$dstr;
}
}
}
else
{
if(strlen($surl)<7)
$okurl = "http://".$this->BaseUrlPath."/".$surl;
else if(strtolower(substr($surl,0,7))=="http://")
$okurl = $surl;
else
$okurl = "http://".$this->BaseUrlPath."/".$surl;
}
$okurl = eregi_replace("^(http://)","",$okurl);
$okurl = eregi_replace("/{1,}","/",$okurl);
return "http://".$okurl;
}
}
?>