带详细申明,公布一个用PHP

作者: 计算机网络  发布:2019-09-26

程序主要是使用 HTTP 协议下载文件,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,可以有两种使用方法,具体请下载查看源码。

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:

 代码如下

 

<?php
/**
 * 下载远程文件类支持断点续传
 */
class HttpDownload {
    private $m_url = "";
     private $m_urlpath = "";
     private $m_scheme = "http";
     private $m_host = "";
     private $m_port = "80";
     private $m_user = "";
     private $m_pass = "";
     private $m_path = "/";
     private $m_query = "";
     private $m_fp = "";
     private $m_error = "";
    private $m_httphead = "" ;
    private $m_html = "";
 
    /**
     * 初始化
     */
    public function PrivateInit($url){
        $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;
             }
          }
    }
 
    /**
    * 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->m_httphead = "" ;
        $this->m_html = "";
        $this->Close();
        #初始化系统
        $this->PrivateInit($url);
        $this->PrivateStartSession();
    }

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。

    /**
    * 获得某操作错误的原因
    */
    public 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>rn";
        }
    }
 
    /**
    * 判别用Get方法发送的头的应答结果是否正确
    */
    public 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
    */
    public function IsText() {
        if (ereg("^2",$this->GetHead("http-state")) && eregi("^text",$this->GetHead("content-type"))) {
            return true;
        } else {
            $this->m_error .= "内容为非文本类型<br>";
            return false;
        }
    }
    /**
    * 判断返回的网页是否是特定的类型
    */
    public function IsContentType($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
    */
    public 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") or die("写入文件 $savefilename 失败!");
        while (!feof($this->m_fp)) {
            @fwrite($fp,fgets($this->m_fp,256));
        }
        @fclose($this->m_fp);
        return true;
    }
   
    /**
    * 保存网页内容为 Text 文件
    */
    public function SaveToText($savefilename) {
        if ($this->IsText()) {
            $this->SaveBinFile($savefilename);
        } else {
            return "";
        }
    }
   
    /**
    * 用 HTTP 协议获得一个网页的内容
    */
    public 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
    */
    public 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 {
            $httpv = "HTTP/1.0";
        }
        fputs($this->m_fp,"GET ".$this->m_urlpath." $httpvrn");
        fputs($this->m_fp,"Host: ".$this->m_host."rn");
        fputs($this->m_fp,"Accept: */*rn");
        fputs($this->m_fp,"User-Agent: Mozilla/4.0+(compatible;+MSIE+6.0;+Windows+NT+5.2)rn");
        #HTTP1.1协议必须指定文档结束后关闭链接,否则读取文档时无法使用feof判断结束
        if ($httpv=="HTTP/1.1") {
            fputs($this->m_fp,"Connection: Closernrn");
        } else {
            fputs($this->m_fp,"rn");
        }
        $httpstas = fgets($this->m_fp,256);
        $httpstas = split(" ",$httpstas);
        $this->m_httphead["http-edition"] = trim($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[$i]);
        }
        while (!feof($this->m_fp)) {
            $line = str_replace(""","",trim(fgets($this->m_fp,256)));
            if($line == "") break;
            if (ereg(":",$line)) {
                $lines = split(":",$line);
                $this->m_httphead[strtolower(trim($lines[0]))] = trim($lines[1]);
            }
        }
    }
   
    /**
    * 获得一个Http头的值
    */
    public function GetHead($headname) {
        $headname = strtolower($headname);
        if (isset($this->m_httphead[$headname])) {
            return $this->m_httphead[$headname];
        } else {
            return "";
        }
    }
   
    /**
    * 打开连接
    */
    public 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
    */
    public function Close(){
        @fclose($this->m_fp);
    }
}

使用方法:

#两种使用方法,分别如下:

$hd = new DedeHttpDown();
$hd->OpenUrl("");
echo $hd->GetHtml();
//如果保存为文件则用 $hd->SaveBin("dede.html");
$hd->Close();

#打开网页
$httpdown = new HttpDownload();
$httpdown->OpenUrl("");
echo $httpdown->GetHtml();
$httpdown->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)

#下载文件
$file = new HttpDownload(); # 实例化类
$file->OpenUrl(""); # 远程文件地址
$file->SaveToBin("rust020.pdf"); # 保存路径及文件名
$file->Close(); # 释放资源
?>

代码如下:

<?
/* ---------------------------------------------------------------------
//织梦Http下载类V1.0
//出自:织梦之旅 
//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 => $v <br>rn"; }
        }
        //
        //判别用Get方法发送的头的应答结果是否正确
        //
        function IsGetOK()
        {
                if( ereg("^2",$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." $httpvrn");
                $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"])) { $this->m_puthead["Refer"] = "]; }
                foreach($this->m_puthead as $k=>$v){
                        $k = trim($k);
                        $v = trim($v);
                        if($k!=""&&$v!=""){
                                fputs($this->m_fp,"$k: $vrn");
                        }
                }

                //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: Closernrn");
                else fputs($this->m_fp,"rn");

                //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]=="/"){
            $okurl = ";
    }
    else if($surl[0]==".")
    {
      if(strlen($surl)<=2) return "";
      else if($surl[0]=="/")
      {
              $okurl = ");
            }
      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)
        $okurl = ";
      else if(strtolower(substr($surl,0,7))=="http://")
        $okurl = $surl;
      else
        $okurl = ";
    }
    $okurl = eregi_replace("^();
    $okurl = eregi_replace("/{1,}","/",$okurl);
    return ";
  }
}
?>

您可能感兴趣的文章:

  • 利用PHP fsockopen 模拟POST/GET传送数据的方法
  • php使用fsockopen函数发送post,get请求获取网页内容的方法
  • php fsockopen伪造post与get方法的详解
  • php自动提交表单的方法(基于fsockopen与curl)
  • php中fsockopen用法实例
  • php fsockopen解决办法 php实现多线程
  • php利用fsockopen GET/POST提交表单及上传文件

本文由金沙澳门官网送注册58发布于计算机网络,转载请注明出处:带详细申明,公布一个用PHP

关键词: