Question

怎么用java程序抓取网页源代码

Answer 1

用httpclient吧，网上很多例子的。下面有一个你看看。

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;
    
    public String getWeChatUserInfo(String token,String openid){
        String urlNameString = "https://api.weixin.qq.com/sns/userinfo?access_token=TOKEN&openid=OPENID";
        urlNameString=urlNameString.replace("TOKEN", token);
        urlNameString=urlNameString.replace("OPENID",openid);
        String result="";
          try {
                // 根据地址获取请求
                HttpGet request = new HttpGet(urlNameString);//这里发送get请求
                // 获取当前客户端对象
                HttpClient httpClient = new DefaultHttpClient();
                // 通过请求对象获取响应对象
                HttpResponse response = httpClient.execute(request);
                
                // 判断网络连接状态码是否正常(0--200都数正常)
                if (response.getStatusLine().getStatusCode() == HttpStatus.SC_OK) {
                    result= EntityUtils.toString(response.getEntity(),"utf-8");
                } 
            } catch (Exception e) {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }
        return result;
        //....result是用户信息,站内业务以及具体的json转换这里也不写了...
    }