利用HttpClient和Jsoup实现从网站中抓取数据

HttpClient的下载地址：http://hc.apache.org/downloads.cgi

Jsoup的下载地址：http://jsoup.org/download

在Eclipse中导入所下载的包即可。

首先利用HttpClient获取目标网站的的html文件，然后通过jsoup来解析。

  代码如下：

import java.io.IOException;

import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.util.EntityUtils;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;

public class Select_Element_Demo {
	public static void main(String[] args) throws IOException {
		HttpClient httpclient = new DefaultHttpClient();
		try{
			HttpGet httpget = new HttpGet("http://www.ibm.com/developerworks/cn/java/j-lo-jsouphtml/");//把目标网站设置进去
			System.out.println("executing request " + httpget.getURI());
			
			HttpResponse response = httpclient.execute(httpget);//获得response
			
			HttpEntity entity = response.getEntity();//获得网站的内容
			
			System.out.println("getStatusLine"+response.getStatusLine());
			if (entity != null){
				System.out.println("Response content length: " + entity.getContentLength());
				String html =  EntityUtils.toString(entity);//将网站的内容转成字符串
				
				Document doc = Jsoup.parse(html);//把html封装进Document
				Element element= doc.getElementById("ibm-content");//提取目标板块的信息
				System.out.println("body:"+element.text());
				
			}
			
		}catch(Exception e){
			e.printStackTrace();
		}finally{ 
			//关闭连接,释放资源 
			httpclient.getConnectionManager().shutdown();
		}
	}
}

从上面可以看到，利用HttpClient和Jsoup来从网站爬取信息很容易。