Android之Jsoup解析数据

最新推荐文章于 2021-07-12 20:15:54 发布

冰糖葫芦三剑客

最新推荐文章于 2021-07-12 20:15:54 发布

阅读量1.1k

点赞数 1

分类专栏： Android之Jsoup解析数据

本文链接：https://blog.csdn.net/shenggaofei/article/details/52044370

版权

Android之Jsoup解析数据专栏收录该内容

1 篇文章 0 订阅

订阅专栏

Android之Jsoup解析数据

jsoup 简介

Java 程序在解析 HTML 文档时，相信大家都接触过 htmlparser 这个开源项目，我曾经在 IBM DW 上发表过两篇关于 htmlparser 的文章，分别是：从 HTML 中攫取你所需的信息和扩展 HTMLParser 对自定义标签的处理能力。但现在我已经不再使用 htmlparser 了，原因是 htmlparser 很少更新，但最重要的是有了 jsoup 。

jsoup 是一款 Java 的 HTML 解析器，可直接解析某个 URL 地址、HTML 文本内容。它提供了一套非常省力的 API，可通过 DOM，CSS 以及类似于 jQuery 的操作方法来取出和操作数据。

jsoup 的主要功能如下：

1. 从一个 URL，文件或字符串中解析 HTML；

2. 使用 DOM 或 CSS 选择器来查找、取出数据；

3. 可操作 HTML 元素、属性、文本；

jsoup 是基于 MIT 协议发布的，可放心使用于商业项目。

jsoup 的主要类层次结构如图 1 所示：

图 1. jsoup 的类层次结构

下面我们来看看Jsoup解析的一个案例：

1.主函数：MaActivity.class

import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;



import android.os.Bundle;
import android.os.Handler;
import android.app.Activity;
import android.content.Intent;
import android.util.Log;
import android.view.Menu;
import android.view.View;
import android.widget.AdapterView;
import android.widget.AdapterView.OnItemClickListener;
import android.widget.ListView;

public class MainActivity extends Activity {

	protected static final String TAG = "MainActivity";
	private ListView listView;
	private ArrayList<Info> list;
	Handler handler=new Handler(){
		public void handleMessage(android.os.Message msg) {
			if(msg.what==0){
				listView.setAdapter(new ListViewAdapter(MainActivity.this, list));
			}
		};
	};

	@Override
	protected void onCreate(Bundle savedInstanceState) {
		super.onCreate(savedInstanceState);
		setContentView(R.layout.activity_main);
		//初始化数据
		listView = (ListView) findViewById(R.id.listview);
		//创建集合
		list = new ArrayList<Info>();
		//解析数据
		parseHtml();
		//对ListView设置点击事件
		listView.setOnItemClickListener(new OnItemClickListener() {

			@Override
			public void onItemClick(AdapterView<?> arg0, View arg1, int arg2,
					long arg3) {
				Intent intent=new Intent(MainActivity.this,WebActivity.class);
				intent.putExtra("path", list.get(arg2).getHref());
				startActivity(intent);
			}
		});
	}

	private void parseHtml() {
		new Thread(){
			public void run() {
				try {
					Document parse = Jsoup.parse(new URL("http://www.cnbeta.com/topics/444.htm"),5000);
					Elements Eleclass = parse.getElementsByClass("title");
					Elements Elenewsinfo = parse.getElementsByClass("newsinfo");
					Elements Elepic = parse.getElementsByClass("pic");
					int size = Eleclass.size();
					for (int i = 0; i < size; i++) {
						String title = Eleclass.get(i).getElementsByTag("a").text();
						String href = Eleclass.get(i).getElementsByTag("a").attr("href");
						String newsinfo = Elenewsinfo.get(i).getElementsByTag("p").text();
						String pic = Elepic.get(i).getElementsByTag("img ").attr("src");
						list.add(new Info(title, newsinfo, pic, href));
					}
					for (Info info : list) {
						Log.i(TAG, info.toString());
					}
					handler.sendEmptyMessage(0);
				} catch (IOException e) {
					e.printStackTrace();
				}
			};
		}.start();
	}

	

}

2.主函数的布局：activity_main.xml

<RelativeLayout xmlns:android="http://schemas.android.com/apk/res/android"
    xmlns:tools="http://schemas.android.com/tools"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
     >

    <ListView
        android:id="@+id/listview"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:text="@string/hello_world" />

</RelativeLayout>

3.适配器的布局：listview_item.xml

<?xml version="1.0" encoding="utf-8"?>
<LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    android:orientation="horizontal" >

    
    <LinearLayout 
        android:layout_width="match_parent"
        android:layout_height="wrap_content"
        android:layout_weight="1"
        android:orientation="vertical"
        >
        
        <TextView
        android:id="@+id/title"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:text="Large Text"
        android:padding="10dp"
        android:textSize="20dp"
        android:singleLine="true"
        android:textAppearance="?android:attr/textAppearanceLarge" />

    <TextView
        android:id="@+id/textView3"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:padding="5dp"
         />

    <TextView
        android:id="@+id/info"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:text="Large Text"
        android:textSize="15dp"
        android:lines="3"
		android:ellipsize="end"
        android:textAppearance="?android:attr/textAppearanceLarge" />
        
        
    </LinearLayout>

    <com.example.webview.ImageViewCircle
        android:id="@+id/img"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:padding="20dp"
        android:src="@drawable/ic_launcher" />
    
</LinearLayout>

4.主函数的适配器：ListViewAdapter.class

import java.util.ArrayList;


import com.lidroid.xutils.BitmapUtils;

import android.content.Context;
import android.view.View;
import android.view.ViewGroup;
import android.widget.BaseAdapter;
import android.widget.ImageView;
import android.widget.TextView;

public class ListViewAdapter extends BaseAdapter {
	private Context context;
	private ArrayList<Info> list;

	public ListViewAdapter(Context context,ArrayList<Info> list){
		this.context=context;
		this.list=list;
	}

	@Override
	public int getCount() {
		return list.size();
	}

	@Override
	public Object getItem(int position) {
		return list.get(position);
	}

	@Override
	public long getItemId(int position) {
		return position;
	}

	@Override
	public View getView(int position, View convertView, ViewGroup parent) {
		ViewHolder holder;
		if(convertView==null){
			convertView = View.inflate(context, R.layout.listview_item, null);
			holder=new ViewHolder();
			holder.img = (ImageViewCircle) convertView.findViewById(R.id.img);
			holder.title = (TextView) convertView.findViewById(R.id.title);
			holder.info = (TextView) convertView.findViewById(R.id.info);
			convertView.setTag(holder);
		}else{
			holder = (ViewHolder) convertView.getTag();
		}
		holder.info.setText(list.get(position).getNewsinfo());
		holder.title.setText(list.get(position).getTitle());
		BitmapUtils bitmapUtils=new BitmapUtils(context);
		bitmapUtils.display(holder.img, list.get(position).getPic());
		return convertView;
	}
	class ViewHolder{
		TextView title,info;
		
		ImageViewCircle img;
	}

	

}

5. WebActivity的布局：activity_web.xml

<RelativeLayout xmlns:android="http://schemas.android.com/apk/res/android"
    xmlns:tools="http://schemas.android.com/tools"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
  >

   <WebView
        android:layout_width="match_parent"
        android:layout_height="match_parent"
        android:id="@+id/webView" />

</RelativeLayout>

6.实体类 Info.class

import java.io.Serializable;

public class Info implements Serializable{
	private String title;
	private String newsinfo;
	private String pic;
	private String href;
	public String getTitle() {
		return title;
	}
	public void setTitle(String title) {
		this.title = title;
	}
	public String getNewsinfo() {
		return newsinfo;
	}
	public void setNewsinfo(String newsinfo) {
		this.newsinfo = newsinfo;
	}
	public String getPic() {
		return pic;
	}
	public void setPic(String pic) {
		this.pic = pic;
	}
	public String getHref() {
		return href;
	}
	public void setHref(String href) {
		this.href = href;
	}
	public Info(String title, String newsinfo, String pic, String href) {
		super();
		this.title = title;
		this.newsinfo = newsinfo;
		this.pic = pic;
		this.href = href;
	}
	public Info() {
		super();
	}
	@Override
	public String toString() {
		return "Info [title=" + title + ", newsinfo=" + newsinfo + ", pic="
				+ pic + ", href=" + href + "]";
	}
	
}

7.ImageViewCircle工具类

import android.annotation.SuppressLint;
import android.content.Context;
import android.graphics.Bitmap;
import android.graphics.BitmapShader;
import android.graphics.Canvas;
import android.graphics.Color;
import android.graphics.Matrix;
import android.graphics.Paint;
import android.graphics.Rect;
import android.graphics.Shader.TileMode;
import android.graphics.drawable.BitmapDrawable;
import android.graphics.drawable.ColorDrawable;
import android.graphics.drawable.Drawable;
import android.util.AttributeSet;
import android.widget.ImageView;

public class ImageViewCircle extends ImageView {

	private Paint mPaintBitmap = new Paint(Paint.ANTI_ALIAS_FLAG);
	private Bitmap mRawBitmap;
	private BitmapShader mShader;
	private Matrix mMatrix = new Matrix();


	public ImageViewCircle(Context context, AttributeSet attrs, int defStyle) {
		super(context, attrs, defStyle);
		// TODO Auto-generated constructor stub
	}

	public ImageViewCircle(Context context, AttributeSet attrs) {
		super(context, attrs);
		// TODO Auto-generated constructor stub
	}

	public ImageViewCircle(Context context) {
		super(context);
		// TODO Auto-generated constructor stub
	}

	@Override
	protected void onDraw(Canvas canvas) {
		Bitmap rawBitmap = getBitmap(getDrawable());
		if (rawBitmap != null){
			int viewWidth = getWidth();
			int viewHeight = getHeight();
			int viewMinSize = Math.min(viewWidth, viewHeight);
			float dstWidth = viewMinSize;
			float dstHeight = viewMinSize;
			if (mShader == null || !rawBitmap.equals(mRawBitmap)){
				mRawBitmap = rawBitmap;
				mShader = new BitmapShader(mRawBitmap, TileMode.CLAMP, TileMode.CLAMP);
			}
			if (mShader != null){
				mMatrix.setScale(dstWidth / rawBitmap.getWidth(), dstHeight / rawBitmap.getHeight());
				mShader.setLocalMatrix(mMatrix);
			}
			mPaintBitmap.setShader(mShader);
			float radius = viewMinSize / 2.0f;
			canvas.drawCircle(radius, radius, radius, mPaintBitmap);
		} else {
			super.onDraw(canvas);
		}
	}

	@SuppressLint("NewApi")
	private Bitmap getBitmap(Drawable drawable){
		if (drawable instanceof BitmapDrawable){
			return ((BitmapDrawable)drawable).getBitmap();
		} else if (drawable instanceof ColorDrawable){
			Rect rect = drawable.getBounds();
			int width = rect.right - rect.left;
			int height = rect.bottom - rect.top;
			int color = ((ColorDrawable)drawable).getColor();
			Bitmap bitmap = Bitmap.createBitmap(width, height, Bitmap.Config.ARGB_8888);
			Canvas canvas = new Canvas(bitmap);
			canvas.drawARGB(Color.alpha(color), Color.red(color), Color.green(color), Color.blue(color));
			return bitmap;
		} else {
			return null;
		}
	}	
}

8.WebActivity.class

import android.os.Bundle;
import android.app.Activity;
import android.content.Intent;

import android.webkit.WebChromeClient;
import android.webkit.WebView;

public class WebActivity extends Activity {

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_web);
        WebView webView = (WebView) findViewById(R.id.webView);
		Intent intent = getIntent();
		String path = intent.getStringExtra("path");
		webView.setWebChromeClient(new WebChromeClient());
		webView.loadUrl("http://www.cnbeta.com"+path);
        
    }


    
    
}

最后别忘了配置网络权限。