请帮我看看这个程序，为什么数据抓不出来呢

[xiaopingshen]

我这个程序是要将网页源文件中的的数据抓出来，可是我怎么弄也只能抓到网址，里面的内容却读不出来，请各位高手帮我看看哈
以下是程序代码:

import java.io.*; 
import java.net.*; 
import java.util.*; 
import Catch.Catchwork; 

public class trade { 
public static void main(String args[]) throws Exception { 
PrintWriter fout = new PrintWriter(new FileWriter("trade4.txt")); 
for(int i=2;i <552;i++) { 
URL url = new URL("http://www.ccen.net/company/search.html?q=%u516C%u53F8&page="+i); 
System.out.println("现在抓到这一页："+url); 
BufferedReader br = new BufferedReader(new InputStreamReader(url.openStream())); 
String s,temp = null; 
ArrayList list = new ArrayList(); 
while((s = br.readLine()) !=null) { 
if((s.indexOf("a target=\"_blank\" href='http://")) !=-1) { 
temp = Catchwork.CatchFilework(s,"a target=\"_blank\" href='http://",".ccen.net"); 
list.add(temp); 
} 
} 
for(int j=0;j <list.size();j++) { 
try{ 
String temps = (String)list.get(j); 
temps ="http://"+temps+".ccen.net/?type=contactus"; 
URL url2 = new URL(temps); 
System.out.println("正在抓取这家公司："+url2); 
BufferedReader br2 = new BufferedReader(new InputStreamReader(url2.openStream())); 
String ss,tempss = null; 
String phone="",company="",adress="",fax="",email="",web="",zip="",product="",person="",tel=""; 
while((ss = br2.readLine()) !=null) { 
if((ss.indexOf("class=\"STYLE12\">联系人：")) !=-1) { 
ss=br2.readLine(); 
person=Catchwork.CatchFilework(ss," <span class=\"STYLE12\">"," </span> </td>"); 
System.out.println("联系人："+person); 
} 
if((ss.indexOf("企业名称： ")) !=-1) { 
company=Catchwork.CatchFilework(ss,"企业名称： "," <br>"); 
System.out.println("公司名称："+company); 
} 
if((ss.indexOf("电话： ")) !=-1) { 
tel=Catchwork.CatchFilework(ss,"电话： "," <br>"); 
System.out.println("电话："+tel); 
} 
if((ss.indexOf("传真： ")) !=-1) { 
fax=Catchwork.CatchFilework(ss,"传真： "," <br>"); 
System.out.println("传真："+fax); 
} 
if((ss.indexOf("公司网址：")) !=-1) { 
web=Catchwork.CatchFilework(ss,"target=\"_blank\">"," </a> <br>"); 
System.out.println("网址："+web); 
} 
if((ss.indexOf("详细地址： ")) !=-1) { 
adress=Catchwork.CatchFilework(ss,"详细地址： "," <br>"); 
System.out.println("公司地址："+adress); 
} 
if((ss.indexOf("邮政编码：")) !=-1) { 
zip=Catchwork.CatchFilework(ss,"邮政编码："," <br>"); 
System.out.println("邮编："+zip); 
} 
if((ss.indexOf("联系手机： ")) !=-1) { 
email=Catchwork.CatchFilework(ss,"联系手机： "," <BR>"); 
System.out.println("手机："+phone); 
} 
if((ss.indexOf("e-mail： ")) !=-1) { 
email=Catchwork.CatchFilework(ss,"[e-mail]'>"," </a> </span>"); 
System.out.println("电子邮箱："+email); 
} 
} 
if(company.equals("")) continue; 
fout.print(company+" "); 
fout.print(person+" "); 
fout.print(adress+" "); 
fout.print(tel+" "); 
fout.print(fax+" "); 
    fout.print(zip+" "); 
fout.print(email+" "); 
fout.print(phone+" "); 
fout.println(web+" "); 
            fout.flush(); 
            } catch(Exception e) { 
                System.out.println("该页面无法打开！"); 
            } 
} 

} 
} 
} 

这个是那个ｃａｔｃｈ包的程序

package Catch; 

import java.io.*; 
import java.net.*; 
import java.util.*; 

public class Catchwork { 
public static void DownLoadPages(String urlStr, String outPath) { 
int chByte = 0; 
URL url = null; 
HttpURLConnection httpConn = null; 
InputStream in = null; 
FileOutputStream out = null; 
try { 
url = new URL(urlStr); 
httpConn = (HttpURLConnection) url.openConnection(); 
HttpURLConnection.setFollowRedirects(true); 
httpConn.setRequestMethod("GET"); 
httpConn.setRequestProperty("User-Agent","Mozilla/4.0 (compatible; MSIE 6.0; Windows 2000)"); 
            
// logger.info(httpConn.getResponseMessage()); 
in = httpConn.getInputStream(); 
out = new FileOutputStream(new File(outPath)); 

chByte = in.read(); 
while (chByte != -1) { 
out.write(chByte); 
chByte = in.read(); 
} 
}catch (MalformedURLException e) { 
e.printStackTrace(); 
}catch (IOException e) { 
e.printStackTrace(); 
} 
finally { 
try { 
out.close(); 
in.close(); 
httpConn.disconnect(); 
} catch (Exception ex) { 
ex.printStackTrace(); 
} 
} 
} 
public static String CatchFilework(String s,String a,String b) { 
String temp = null; 
int index; 
if((a !="") && (b !="")) { 
if((index = s.indexOf(a)) !=-1) { 
temp = s.substring(index+a.length()); 
if((index = temp.indexOf(b)) !=-1) { 
temp = temp.substring(0,index); 
temp = temp.trim(); 
} 
} 
} 
if((a =="") && (b !="")) { 
if((index = s.indexOf(b)) !=-1) { 
temp = s.substring(0,index); 
temp = temp.trim(); 
} 
} 
if((a !="") && (b =="")) { 
if((index = s.indexOf(a)) !=-1) { 
temp = s.substring(index+a.length()); 
temp = temp.trim(); 
} 
} 
return temp; 
} 
public static String CatchTelwork(String temp) { 
int index,index1,index2; 
String temp1=null,temp2=null,temp3=null,Qu="",tel=""; 
if(((index1 = temp.indexOf("-")) != -1) && (index1+1 <temp.length())) { 
temp1 = temp.substring(0,index1); 
temp2 = temp.substring(index1+1); 
if(((index = temp1.indexOf("86")) != -1) && (temp1.length() <6)) { 
if(((index2 = temp2.indexOf("-")) != -1) && (index2+1 <temp2.length())) { 
temp3 = temp2.substring(index2+1); 
temp2 = temp2.substring(0,index2); 
if(temp2.length() <6) { 
Qu = temp2; 
tel = temp3; 
}else { 
tel = temp2+"-"+temp3; 
} 
}else { 
tel = temp2; 
} 
}else if(temp1.length() <6) { 
Qu = temp1; 
tel = temp2; 
}else { 
tel = temp1; 
} 
}else { 
tel = temp; 
} 
return Qu+" "+tel; 
} 
public static void main(String args[]) throws Exception { 

} 
}

[yjfjebj789]

前一个贴子就和你说了,不要在它读一行的时候就去 indexOf,如果你的内容一半在上一行一半在下一行 不就找不到了吗
你应该读完之后再去indexOf

[lanlanq]

数据抓不出来，有没有错误提示
如果没有错误提示，跟踪Debug一下，看看BufferedReader br 有没有内容
看看s的内容，一步步的调试以下，看看问题在哪里

[yjfjebj789]

我做过一个和你这个一样的东西, 其实我也不会用正则, 都是通过 indexOf,substring 来做的
我做了10多个找这种公司的网站,做成GUI的,以前女在做销售要找资料,用这东西挺方便的.....

[小刚asdf]

学学抓取网页的代码

[小刚asdf]

学学抓取网页的代码

[老紫竹]

不细看了，代码太多，抓不到原因
1 连接错误
2 对方要求验证
3 你代码错了

1，2的可能性高

[無名VF]

[Quote=引用 4 楼 java2000_net 的回复:]
不细看了，代码太多，抓不到原因
1 连接错误
2 对方要求验证
3 你代码错了

1，2的可能性高
[/Quote]
...

[lihan6415151528]

[Quote=引用 4 楼 java2000_net 的回复:]
不细看了，代码太多，抓不到原因
1 连接错误
2 对方要求验证
3 你代码错了

1，2的可能性高
[/Quote]

我觉得代码错了可能高 -_-!

[guishuanglin]

代码有错误
if((ss.indexOf("企业名称： ")) !=-1) {
company=Catchwork.CatchFilework(ss,"企业名称： "," <br>");
System.out.println("公司名称："+company);
}
你不能读完了在缓存中 indexOf?