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!!
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;i<lis.size();i++){
Elements 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;j<ls.size();j++){
Elements 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();
}