android 抓取网页源码 示例代码

【实例截图】

【核心代码】

package com.example.checkupdata;

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;

import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.impl.client.DefaultHttpClient;

import utils.HtmlParser;
import android.app.Activity;
import android.os.Bundle;
import android.os.StrictMode;
import android.util.Log;
import android.view.Menu;
import android.view.View;
import android.view.View.OnClickListener;
import android.widget.Button;
import android.widget.TextView;

/**
 * @author Jasonzhou
 * @since 2013-03-21
 * @功能 读取网页内容
 * @说明 获取网页的全部代码后使用jsuop进行处理， 以便得到想要的内容
 **/

public class MainActivity extends Activity {
	// 指定网页地址
	public String url = "http://blog.csdn.net/jasonzhou613/article/details/7905388";

	private Button parseBtn;
	private TextView tv;
	private TextView sourceUrl;
	@Override
	public void onCreate(Bundle savedInstanceState) {
		super.onCreate(savedInstanceState);
		setContentView(R.layout.activity_main);
		
		manageException();// 处理抛出异常
		tv = (TextView) findViewById(R.id.text);
		sourceUrl = (TextView) findViewById(R.id.sourceUrl);
		parseBtn=(Button) findViewById(R.id.parseBtn);
//		String myString = null;
//		myString = posturl(url);
//		// 设置屏幕显示
//		 Log.i("---网页代码---", ""   myString);
//		String html = myString;
//		Document doc = Jsoup.parse(html);
//		tv.setText(doc.body().text());
		 
//		 String sourceCode = HtmlParser.getHtmlContent("www.baidu.com","utf-8");
//		 tv.setText(sourceCode);

		 
		 parseBtn.setOnClickListener(new OnClickListener() {
				public void onClick(View v) {
					
					String sourceCode = HtmlParser.getHtmlContent("www.baidu.com","utf-8");
					tv.setText(sourceCode);
				}
			});
		 
		 
		// getWebCode();
	}
	
	private void getWebCode(){
		try {
			URL url = new URL("http://www.baidu.com");
			HttpURLConnection con = (HttpURLConnection)url.openConnection();
			con.connect();
			InputStream is = con.getInputStream();

			BufferedReader br = new BufferedReader(new InputStreamReader(is));
			String line;
			StringBuilder builder = new StringBuilder();
			while((line = br.readLine()) != null){
			builder.append(line);
			}

			System.out.println(builder.toString());
		} catch (Exception e) {
			// TODO: handle exception
		}
		
	}

	/**
	 * 获取参数指定的网页代码，将其返回给调用者，由调用者对其解析 返回String
	 */
	public String posturl(String url) {
		InputStream is = null;
		String result = "";

		try {
			HttpClient httpclient = new DefaultHttpClient();
			HttpPost httppost = new HttpPost(url);
			HttpResponse response = httpclient.execute(httppost);
			HttpEntity entity = response.getEntity();
			is = entity.getContent();
		} catch (Exception e) {
			return "Fail to establish http connection!"   e.toString();
		}

		try {
			BufferedReader reader = new BufferedReader(new InputStreamReader(
					is, "utf-8"));
			StringBuilder sb = new StringBuilder();
			String line = null;
			while ((line = reader.readLine()) != null) {
				sb.append(line   "\n");
			}
			is.close();

			result = sb.toString();
		} catch (Exception e) {
			return "Fail to convert net stream!";
		}

		return result;
	}

	public void manageException() {
		StrictMode.setThreadPolicy(new StrictMode.ThreadPolicy.Builder()
				.detectDiskReads().detectDiskWrites().detectNetwork() // or
																		// .detectAll()
																		// for
																		// all
																		// detectable
																		// problems
				.penaltyLog().build());
		StrictMode.setVmPolicy(new StrictMode.VmPolicy.Builder()
				.detectLeakedSqlLiteObjects().penaltyLog().penaltyDeath()
				.build());
	}

	@Override
	public boolean onCreateOptionsMenu(Menu menu) {
		getMenuInflater().inflate(R.menu.activity_main, menu);
		return true;
	}

}