手写的爬虫程序，程序可以成功运行，只是效率太低，十几秒才爬一条数据，求大神指点提高效率，谢谢_html/css_WEB-ITnose

import .....
/**
 * 获取****的数据
 */
public class domain3 {
/**
* 根据网页url获取页面内容
*/
public string gethtmlstring(string url){
string hs="";
try {
url u = new url(url);
httpurlconnection conn = (httpurlconnection)u.openconnection(); 
conn.setrequestproperty("user-agent","msie 7.0");
stringbuffer htmlstring = new stringbuffer();
bufferedreader br = new bufferedreader(new inputstreamreader(conn.getinputstream(),"utf-8"));
string line="";
while((line=br.readline())!=null){
htmlstring.append(line+"\n");
}
hs=htmlstring.tostring();
system.out.println(url);
} catch (exception e) {
system.out.println("url地址加载出错！！");
e.printstacktrace();
}
return hs;
}
public static void main(string rags[]){
dao d = new dao();
domain3 dm = new domain3();
string title="";
string section="";
string content="";
string contenttitle="";
int count=110;

string url="http://*************************" ;
if(d.createtable()){
system.out.println("建表成功！！！");
try {
//加载标题页面
document doc = jsoup.parse(dm.gethtmlstring(url));
element titles = doc.getelementbyid("maincontent");
elements lis=titles.getelementsbytag("li");
//*********************标题****************************
for(int i=1;ielements a = lis.get(i).getelementsbytag("a");
if(a.tostring().equals("")){
title=lis.get(i).text();
contenttitle=title;
string data[]={contenttitle,title,section,content,url};
if(d.pinsertdata(data)){
system.out.println("第"+(i+1)+"题数据插入成功！！！");
system.out.println("*****************"+count+"*****************");
}else{
system.out.println("第"+(i+1)+"题节数据插入失败！！！");
system.out.println("*****************"+count+"*****************");
break;
}
count++;
continue;
}else{
title=a.get(0).text();
url="http://****************"+a.get(0).attr("href");
//加载章节页面
document doc2=jsoup.parse(dm.gethtmlstring(url));
element sections =doc2.getelementbyid("maincontent");
elements ls = sections.getelementsbytag("li");
//**********************节************************
for(int j=0;jelements link = ls.get(j).getelementsbytag("a");
if(link.tostring().equals("")){
section=ls.get(j).text();
contenttitle=title+" "+section;
}else{
section = link.get(0).text();
url="http:*******************"+link.get(0).attr("href");
//加载内容页面
document doc3=jsoup.parse(dm.gethtmlstring(url));
element contents=doc3.getelementbyid("maincontent");
content=contents.text();
//处理内容字符串
content=content.substring(content.indexof("?")+"?".length());
content=content.replace("'", "''");
contenttitle=title+" "+section;
}
system.out.println("****************"+count+"******************");
system.out.println("正在读第"+(i+1)+"题"+(j+1)+"节");


//往数据库插入数据
string data[]={contenttitle,title,section,content,url};
if(d.pinsertdata(data)){
system.out.println("第"+(i+1)+"题"+(j+1)+"节数据插入成功！！！");
system.out.println("*****************"+count+"*****************");
count++;
}else{
system.out.println("第"+(i+1)+"题"+(j+1)+"节数据插入失败！！！");
system.out.println("*****************"+count+"*****************");
break;
}
}//end for
}

system.out.println("第"+(i+1)+"题采集完毕");


}//end for

system.out.println("采集完毕！！");

} catch (exception e) {
// todo auto-generated catch block
e.printstacktrace();
}

?

回复讨论(解决方案)

开多个线程跑

主要是这两句，debug的时候老是在这两句停好长时间
1.BufferedReader br = new BufferedReader(new InputStreamReader(conn.getInputStream(),"utf-8"))

2.while((line=br.readLine())!=null){
HtmlString.append(line+"\n");
}

用jsoup吧，很简单，也很好爬

一开始就是用的jsoup  效率比这个还低，就在 Document doc = Jsoup.parse(method.getResponseBodyAsString()); 这一步就走不动了，很头疼，有人建议我用sax解析，但是sax能用来解析html吗？

多线程+提高带宽

** 
 * 获取**************的数据 
 * @author wf 
 * 
 */ 
public class DoMain5 { 


public Document getDoc(String url){ 
Document doc=null; 
try { 
doc=Jsoup.connect(url).get(); 
} catch (Exception e) { 
System.out.println("文档解析失败！！"); 
e.printStackTrace(); 
} 
return doc; 
} 

public static void main(String rags[]){ 
Dao d = new Dao(); 
DoMain5 dm = new DoMain5(); 

String title=""; 
String section=""; 
String content=""; 
String contentTitle=""; 
int count=630; 

String url="******************" ; 

if(d.createTable()){ 
System.out.println("建表成功！！！"); 

try { 
Document doc = dm.getDoc(url); 
System.out.println(doc); 
Element titles = doc.getElementById("maincontent"); 
Elements lis=titles.getElementsByTag("li"); 
//*********************标题**************************** 
for(int i=1;iElements a = lis.get(i).getElementsByTag("a"); 
if(a.toString().equals("")){ 
title=lis.get(i).text(); 
contentTitle=title; 

String data[]={contentTitle,title,section,content,url}; 
if(d.pinsertData(data)){ 
System.out.println("第"+(i+1)+"题数据插入成功！！！"); 
System.out.println("*****************"+count+"*****************"); 
}else{ 
System.out.println("第"+(i+1)+"题节数据插入失败！！！"); 
System.out.println("*****************"+count+"*****************"); 
break; 
} 
count++; 
continue; 
}else{ 
title=a.get(0).text(); 

url="http:***************"+a.get(0).attr("href"); 
Document doc2=dm.getDoc(url); 
Element sections =doc2.getElementById("maincontent"); 
Elements ls = sections.getElementsByTag("li"); 
//**********************节************************ 
for(int j=507;jElements link = ls.get(j).getElementsByTag("a"); 
if(link.toString().equals("")){ 
section=ls.get(j).text(); 
contentTitle=title+" "+section; 
}else{ 
section = link.get(0).text(); 
url="http:****************"+link.get(0).attr("href"); 
Document doc3=dm.getDoc(url); 
Element contents=doc3.getElementById("maincontent"); 
content=contents.text(); 
//处理内容字符串 
content=content.substring(content.indexOf("?")+"?".length()); 
content=content.replace("'", "''"); 
contentTitle=title+" "+section; 
} 
System.out.println("****************"+count+"******************"); 
System.out.println("正在读第"+(i+1)+"题"+(j+1)+"节"); 


String data[]={contentTitle,title,section,content,url}; 

if(d.pinsertData(data)){ 
System.out.println("第"+(i+1)+"题"+(j+1)+"节数据插入成功！！！"); 
System.out.println("*****************"+count+"*****************"); 
count++; 
}else{ 
System.out.println("第"+(i+1)+"题"+(j+1)+"节数据插入失败！！！"); 
System.out.println("*****************"+count+"*****************"); 
break; 
} 
}//end for 
} 

System.out.println("第"+(i+1)+"题采集完毕"); 
break; 
}//end for 

System.out.println("采集完毕！！"); 

} catch (Exception e) { 

e.printStackTrace(); 
} 

经过各位大声指点修改后  这个程序效率有明显提高，不过现在运行起来随时随地会抛出下面两个异常，还请各位大虾指点怎么解决：

1.java.net.SocketTimeoutException: Read timed out
at java.net.SocketInputStream.socketRead0(Native Method)
at java.net.SocketInputStream.read(SocketInputStream.java:129)
at java.io.BufferedInputStream.fill(BufferedInputStream.java:218)
at java.io.BufferedInputStream.read1(BufferedInputStream.java:258)
at java.io.BufferedInputStream.read(BufferedInputStream.java:317)
at sun.net.www.http.HttpClient.parseHTTPHeader(HttpClient.java:687)
at sun.net.www.http.HttpClient.parseHTTP(HttpClient.java:632)
at sun.net.www.protocol.http.HttpURLConnection.getInputStream
(HttpURLConnection.java:1064)
at java.net.HttpURLConnection.getResponseCode(HttpURLConnection.java:373)
at org.jsoup.helper.HttpConnection$Response.execute(HttpConnection.java:429)
at org.jsoup.helper.HttpConnection$Response.execute(HttpConnection.java:410)
at org.jsoup.helper.HttpConnection.execute(HttpConnection.java:164)
at org.jsoup.helper.HttpConnection.get(HttpConnection.java:153)
at com.wanfang.dousact.DoMain5.getDoc(DoMain5.java:35)
at com.wanfang.dousact.DoMain5.main(DoMain5.java:61)

2.java.net.SocketTimeoutException: connect timed out 
at java.net.PlainSocketImpl.socketConnect(Native Method) 
at java.net.PlainSocketImpl.doConnect(PlainSocketImpl.java:333) 
at java.net.PlainSocketImpl.connectToAddress(PlainSocketImpl.java:195) 
at java.net.PlainSocketImpl.connect(PlainSocketImpl.java:182) 
at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:366) 
at java.net.Socket.connect(Socket.java:519) 
at sun.net.NetworkClient.doConnect(NetworkClient.java:158) 
at sun.net.www.http.HttpClient.openServer(HttpClient.java:394) 
at sun.net.www.http.HttpClient.openServer(HttpClient.java:529) 
at sun.net.www.http.HttpClient.(HttpClient.java:233) 
at sun.net.www.http.HttpClient.New(HttpClient.java:306) 
at sun.net.www.http.HttpClient.New(HttpClient.java:323) 
at sun.net.www.protocol.http.HttpURLConnection.getNewHttpClient 
(HttpURLConnection.java:852) 
at sun.net.www.protocol.http.HttpURLConnection.plainConnect 
(HttpURLConnection.java:793) 
at sun.net.www.protocol.http.HttpURLConnection.connect(HttpURLConnection.java:718) 
at org.jsoup.helper.HttpConnection$Response.execute(HttpConnection.java:425) 
at org.jsoup.helper.HttpConnection$Response.execute(HttpConnection.java:410) 
at org.jsoup.helper.HttpConnection.execute(HttpConnection.java:164) 
at org.jsoup.helper.HttpConnection.get(HttpConnection.java:153) 
at com.wanfang.dousact.DoMain5.getDoc(DoMain5.java:35) 
at com.wanfang.dousact.DoMain5.main(DoMain5.java:87) 

你可以参考这个看看

  https://www.baidu.com/s?wd=jsoup%20%E5%A4%AA%E6%85%A2&rsv_spt=1&rsv_iqid=0xa4c58e5b0001928e&issp=1&f=3&rsv_bp=1&rsv_idx=2&ie=utf-8&tn=baiduhome_pg&rsv_enter=1&oq=java%2520write%2520%255Ct%2520%25E6%25B2%25A1%25E7%2594%25A8&inputT=11038&rsv_t=64ecKnkhyG%2Bspt6MnEr2Ttfue0gE4iYduVY65jj1n6jePnM1gL%2FwO3GVvk4XcSPt8z5R&rsv_pq=e14f800e00019f3d&sug=jsoup%E8%A7%A3%E6%9E%90html&rsv_sug3=27&rsv_sug1=19&rsv_n=1&rsv_sug2=0&prefixsug=jsoup%2520%25E5%25A4%25AA%25E6%2585%25A2&rsp=0&rsv_sug4=12115