androidJsoup获取网站内容android获取新闻标题实例

import android.app.Activity; 
import android.content.Intent; 
import android.net.Uri; 
import android.os.AsyncTask; 
import android.os.Bundle; 
import android.text.method.ScrollingMovementMethod; 
import android.util.Log; 
import android.view.Menu; 
import android.view.View; 
import android.widget.AdapterView; 
import android.widget.AdapterView.OnItemClickListener; 
import android.widget.ArrayAdapter; 
import android.widget.ListView; 
import android.widget.TextView; 
 
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 org.apache.http.util.EntityUtils; 
import org.jsoup.Jsoup; 
import org.jsoup.nodes.Document; 
import org.jsoup.nodes.Element; 
import org.jsoup.select.Elements; 
 
import java.util.ArrayList; 
import java.util.List; 
 
@SuppressWarnings("unused") 
public class MainActivity extends Activity { 
  private TextView TV_HTMLCode; 
  //此处搞一个TextView主要来显示News列表里面存储的内容，仅仅便于分析和理解 
 
  private String URL_EOL = "http://www.cnwust.com/newsList/1_1", 
      TAG = "ATAG"; 
  //这是索要获取内容的网址 
 
  private List NewsList; 
  //自定义的News的类，用于存放索要获取新闻的目录、时间以及点击后显示的网址 
 
  private ListView LV_Result; 
  private ArrayAdapter LV_Adapter; 
 
  @Override 
  protected void onCreate(Bundle savedInstanceState) { 
    super.onCreate(savedInstanceState); 
    setContentView(R.layout.activity_main); 
    LV_Result = (ListView) findViewById(R.id.LV_Result); 
    TV_HTMLCode = (TextView) findViewById(R.id.TV_HTMLCode); 
    TV_HTMLCode.setMovementMethod(ScrollingMovementMethod.getInstance()); 
 
    ConnectTask C1 = new ConnectTask(); 
    C1.execute(); 
 
  } 
 
  @Override 
  public boolean onCreateOptionsMenu(Menu menu) { 
    getMenuInflater().inflate(R.menu.menu_main, menu); 
    return true; 
  } 
 
  public class ConnectTask extends AsyncTask { 
 
    @Override 
    protected String doInBackground(Void... params) { 
      String result = ConnectEOL(); 
      return result; 
    } 
 
    @Override 
    protected void onPostExecute(String result) { 
      // TV_HTMLCode.setText(result); 
      NewsList = getNews(result); 
      List NewsTitles = new ArrayList(); 
      for (News news : NewsList) { 
        TV_HTMLCode.append(news.getNewsTitle() + "\n"); 
        TV_HTMLCode.append(news.getNewsTime() + "\n"); 
        TV_HTMLCode.append(news.getNewsUrl() + "\n"); 
        NewsTitles.add(news.getNewsTitle()); 
      } 
    /* 为ListView添加适配器 */ 
 
      LV_Adapter = new ArrayAdapter(MainActivity.this, 
          android.R.layout.simple_list_item_1, NewsTitles); 
      LV_Result.setAdapter(LV_Adapter); 
 
    /* 为ListView添加点击打开对应网页功能 */ 
      LV_Result.setOnItemClickListener(new OnItemClickListener() { 
 
        @Override 
        public void onItemClick(AdapterView<?> arg0, View arg1, 
                    int arg2, long arg3) { 
          final Uri uri = Uri.parse(NewsList.get(arg2).getNewsUrl()); 
          final Intent it = new Intent(Intent.ACTION_VIEW, uri); 
          startActivity(it); 
        } 
 
      }); 
      //此处为了方便就点击就直接调用设备默认浏览器打开网址 
 
      super.onPostExecute(result); 
 
 
    } 
 
  } 
 
  /* 连接EOL的方法 返回整个网页经过截取之后的的源代码 */ 
  public String ConnectEOL() { 
    String result = ""; 
    try { 
      HttpClient httpclient = new DefaultHttpClient(); 
      HttpPost httppost = new HttpPost(URL_EOL); 
      HttpResponse response = httpclient.execute(httppost); 
      String Res = EntityUtils.toString(response.getEntity(), "UTF-8"); 
 
      int st = Res.indexOf("
"); 
      int ed = Res.indexOf("
"); 
      //这边算是最重要的部分，代码获取的便是这两段之间的部分。 
 
      String content = Res.substring(st, ed); 
      st = content.indexOf("
") + 4; 
      ed = content.indexOf("
"); 
      content = content.substring(st, ed); 
      result = content; 
    } catch (Exception e) { 
      Log.d(TAG, e.toString()); 
    } 
    return result; 
  } 
 
  /* 对源代码进行解析截取的方法 返回一个News数组 */ 
  public List getNews(String HTMLCode) { 
    List newsList = new ArrayList(); 
    Document doc = Jsoup.parse(HTMLCode); 
    Log.d(TAG, "解析html中"); 
    Elements lis = doc.getElementsByTag("li"); 
    Log.d(TAG, "lis的size " + lis.size()); 
    for (Element li : lis) { 
      String newstime = li.getElementsByTag("span").text(); 
      String newstitle = li.getElementsByTag("a").text(); 
      String newsurl = li.getElementsByTag("a").attr("href"); 
      //这三段算是Jsoup从html中获取内容的关键了，很容易理解。 
 
      newsurl = newsurl.replace("/news", "http://www.cnwust.com/news"); 
      //直接从html的代码中获取的URL是相对路径，此处使用replace改为绝对路径 
 
      Log.d(TAG, newstime); 
      Log.d(TAG, newstitle); 
      Log.d(TAG, newsurl); 
 
      News newst = new News(); 
      newst.setNewsTime(newstime); 
      newst.setNewsTitle(newstitle); 
      newst.setNewsUrl(newsurl); 
      newsList.add(newst); 
    } 
    return newsList; 
  } 
} 

public class News { 
  private String newsTime; 
  private String newsUrl; 
  private String newsTitle; 
 
  public News() { 
 
  } 
 
  public News(String newsTitle, String newsTime, String newsUrl) { 
    this.newsTime = newsTime; 
    this.newsUrl = newsUrl; 
    this.newsTitle = newsTitle; 
  } 
 
  public String getNewsTime() { 
    return newsTime; 
  } 
 
  public void setNewsTime(String newsTime) { 
    this.newsTime = newsTime; 
  } 
 
  public String getNewsUrl() { 
    return newsUrl; 
  } 
 
  public void setNewsUrl(String newsUrl) { 
    this.newsUrl = newsUrl; 
  } 
 
  public String getNewsTitle() { 
    return newsTitle; 
  } 
 
  public void setNewsTitle(String newsTitle) { 
    this.newsTitle = newsTitle; 
  } 
 
}