dede采集php网页,织梦cms的php采集类

本文档介绍了一个PHP类DedeHttpDown,用于实现HTTP下载功能,支持GET和POST方式,处理重定向,获取网页内容并保存为文件。类中包含了初始化系统、打开URL、处理HTTP响应头、保存文件等方法,适用于网页内容抓取和文件下载场景。
摘要由CSDN通过智能技术生成

以下为引用的内容:

@set_time_limit(0);

/*=======================================

//织梦Http下载类V1.1版,本版增加了POST发送数据的方式

//把要POST的数据像GET一样跟在网址后,程序会自动处理,并用POST方式发送

//POST仅支持application/x-www-form-urlencoded方式

=======================================*/

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"];

$this->BaseUrlPath = preg_replace("/\/([^\/]*)\.(.*)$/","/",$this->BaseUrlPath);

$this->BaseUrlPath = preg_replace("/\/$/","",$this->BaseUrlPath);

}

}

function ResetAny()

{

//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 = "";

}

//

//打开指定网址

//

function OpenUrl($url,$requestType="GET")

{

$this->ResetAny();

$this->JumpCount = 0;

$this->m_httphead = Array() ;

$this->m_html = "";

$this->Close();

//初始化系统

$this->PrivateInit($url);

$this->PrivateStartSession($requestType);

}

//

//转到303重定向网址

//

function JumpOpenUrl($url)

{

$this->ResetAny();

$this->JumpCount++;

$this->m_httphead = Array() ;

$this->m_html = "";

$this->Close();

//初始化系统

$this->PrivateInit($url);

$this->PrivateStartSession('GET');

}

//

//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:
";

foreach($this->m_httphead as $k=>$v){ echo "$k => $v
\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")."
";

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
";

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")."
";

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 "";

}

function SaveFile($savefilename,$somecontent=''){

$filename=$savefilename;

$somecontent = $somecontent==''?$this->GetHtml():$somecontent;

// if (is_writable($filename)) {

// 在这个例子里,我们将使用添加模式打开$filename,

// 因此,文件指针将会在文件的开头,

// 那就是当我们使用fwrite()的时候,$somecontent将要写入的地方。

if (!$handle = fopen($filename, 'w')) {

echo "can not open $filename";

return false;

//exit;

}

// 将$somecontent写入到我们打开的文件中。

if (!fwrite($handle, $somecontent) ) {

echo "can not write $filename";

//exit;

return false;

}

//echo "成功地将 $somecontent 写入到文件$filename";

fclose($handle);

//die( $savefilename);

return true;

/*     } else {

echo "file $filename cannot";

return false;

}*/

}

//

//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($requestType="GET")

{

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";

$ps = explode('?',$this->m_urlpath);

//发送固定的起始请求头GET、Host信息

if($requestType=="GET") fputs($this->m_fp,"GET ".$this->m_urlpath." $httpv\r\n");

else fputs($this->m_fp,"POST ".$ps[0]." $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(!empty($GLOBALS['RfUrl'])) $this->m_puthead["Refer"] = $GLOBALS['RfUrl'];

else 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");

}

}

if($requestType=="POST"){

$postdata = "";

if(count($ps)>1){

for($i=1;$i

}

else{ $postdata = "OK"; }

$plen = strlen($postdata);

fputs($this->m_fp,"Content-Type: application/x-www-form-urlencoded\r\n");

fputs($this->m_fp,"Content-Length: $plen\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");

if($requestType=="POST"){

fputs($this->m_fp,$postdata);

}

//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

$this->m_httphead["http-describe"] .= " ".trim($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

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 = "无法识别的答复!"; }

}//

}

//

//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;

$errno = "";

$errstr = "";

$this->m_fp = @fsockopen($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)<=1) return "";

else if($surl[1]=="/")

{

$okurl = "http://".$this->BaseUrlPath."/".substr($surl,2,strlen($surl)-2);

}

else{

$urls = explode("/",$surl);

foreach($urls as $u){

if($u=="..") $pathStep++;

else if($i

else $dstr .= $urls[$i];

$i++;

}

$urls = explode("/",$this->BaseUrlPath);

if(count($urls) <= $pathStep)

return "";

else{

$pstr = "http://";

for($i=0;$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;

}

$okurl = eregi_replace("^([url]http://)[/url]","",$okurl);

$okurl = eregi_replace("/{1,}","/",$okurl);

return "http://".$okurl;

}

}

?>

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值