PHP のクローリングとコレクション クラスの概要 snoopy_PHP チュートリアル

<?php
$snoopy->proxy_host = "http://www.bkjia.com/librarys/veda/";
$snoopy->proxy_port = "8080"; //使用代理
$snoopy->maxredirs = 2; //重定向次数
$snoopy->expandlinks = true; //是否补全链接 在采集的时候经常用到
// 例如链接为 /images/taoav.gif 可改为它的全链接 http://www.4wei.cn/images/taoav.gif
$snoopy->maxframes = 5 //允许的最大框架数
//注意抓取框架的时候 $snoopy->results 返回的是一个数组
$snoopy->error //返回报错信息
?>

/**
* You need the snoopy.class.php from 
* http://snoopy.sourceforge.net/
*/
include("snoopy.class.php");
 
$snoopy = new Snoopy;
// need an proxy?:
//$snoopy->proxy_host = "my.proxy.host";
//$snoopy->proxy_port = "8080";
 
// set browser and referer:
$snoopy->agent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)";
$snoopy->referer = "http://www.jonasjohn.de/";
 
// set some cookies:
$snoopy->cookies["SessionID"] = '238472834723489';
$snoopy->cookies["favoriteColor"] = "blue";
 
// set an raw-header:
$snoopy->rawheaders["Pragma"] = "no-cache";
 
// set some internal variables:
$snoopy->maxredirs = 2;
$snoopy->offsiteok = false;
$snoopy->expandlinks = false;
 
// set username and password (optional)
//$snoopy->user = "joe";
//$snoopy->pass = "bloe";
 
// fetch the text of the website www.google.com:
if($snoopy->fetchtext("http://www.google.com")){ 
    // other methods: fetch, fetchform, fetchlinks, submittext and submitlinks
 
    // response code:
    print "response code: ".$snoopy->response_code."<br/>n";
 
    // print the headers:
 
    print "<b>Headers:</b><br/>";
    while(list($key,$val) = each($snoopy->headers)){
        print $key.": ".$val."<br/>n";
    }
 
    print "<br/>n";
 
    // print the texts of the website:
    print htmlspecialchars($snoopy->results)."n";
}
else {
    print "Snoopy: error while fetching document: ".$snoopy->error."n";
}

<meta http-equiv='content-type' content='text/html;charset=utf-8'>
<?php    
include 'Snoopy.class.php';   //加载Snoopy类     
$snoopy = new Snoopy();       //实例化一个对象
$sourceURL = "http://www.bkjia.com/librarys/veda/";    //要抓取的网页
$snoopy->fetchlinks($sourceURL);        //获得网页的链接
$a = $snoopy->results;     //得到网页链接的结果
$re = "/d+.html$/";     //匹配的正则
//过滤获取指定的文件地址请求  
foreach ($a as $tmp) { 
	if (preg_match($re, $tmp)) {
		$aa=$tmp;        
 	}    
}  
getImgURL($aa);
function getImgURL($siteName) 
{        
 	$snoopy = new Snoopy();        
 	$snoopy->fetch($siteName);                
 	$fileContent = $snoopy->results;    //获取过滤后的页面的内容            
 	//匹配图片的正则表达式        
 	$reTag = "/<img[^s]+src="(http://[^"]+).(jpg|png|gif|jpeg)"[^/]*/>/i";                
	if (preg_match($reTag, $fileContent)) {  
   		//过滤图片
		$ret = preg_match_all($reTag, $fileContent, $matchResult);                     
		for ($i = 0, $len = count($matchResult[1]); $i < $len; ++$i) 
		{      
			saveImgURL($matchResult[1][$i], $matchResult[2][$i]);            
		}        
	}    
}        
function saveImgURL($name, $suffix) { 
	$url = $name.".".$suffix;                
 	echo "请求的图片地址：".$url."<br/>";                
 	$imgSavePath = "E:/123/images/";  //图片保存地址      
 	$imgId =mt_rand(); //产生一个随机的文件名
 	if ($suffix == "gif") { 
		//根据图片类型，放入不同的文件夹下面           
  		$imgSavePath .= "emotion";        
 	} 
	else 
	{            
  		$imgSavePath .= "topic";        
 	}        
 	$imgSavePath .= ("/".$imgId.".".$suffix);  //组装要保存的文件名
 	if (is_file($imgSavePath)) {   
		//判断文件名是否存在，存在则删除         
  		unlink($imgSavePath);            
  		echo "<p style='color:#f00;'>文件".$imgSavePath."已存在，将被删除</p>";        
 	}  
 	$imgFile = file_get_contents($url); //读取网络文件     
 	$flag = file_put_contents($imgSavePath,$imgFile);   //写入到本地 
 	if ($flag) {            
  		echo "<p>文件".$imgSavePath."保存成功</p>";        
 	}    
}
?>