使用Jsoup解析html

在前面一些文章中介紹了Jsoup的一些常用類的使用：jsoup的Document類、Jsoup類、jsoup的Node類、jsoup的Element類、jsoup的Elements類。都是其常用API的翻譯，這裡給一個簡單例子：

MainActivity：

package com.home.testjsoup;import java.io.IOException;import java.net.MalformedURLException;import java.net.URL;import org.jsoup.Jsoup;import org.jsoup.nodes.Document;import org.jsoup.nodes.Element;import org.jsoup.select.Elements;import android.app.Activity;import android.os.Bundle;import android.view.View;import android.view.View.OnClickListener;import android.widget.Button;public class MainActivity extends Activity implements OnClickListener {private Button btn;private static final String URL_STR = "http://vip.astro.sina.com.cn/iframe/astro/view/aries/day/";@Overrideprotected void onCreate(Bundle savedInstanceState) {super.onCreate(savedInstanceState);setContentView(R.layout.main);btn = (Button) findViewById(R.id.main_btn);btn.setOnClickListener(this);}@Overridepublic void onClick(View v) {if (v == btn) {new Thread(r).start();}}Runnable r = new Runnable() {Document doc;@Overridepublic void run() {try {doc = Jsoup.parse(new URL(URL_STR), 10000);} catch (MalformedURLException e) {e.printStackTrace();} catch (IOException e) {e.printStackTrace();}if (doc != null) {doParse(doc);}}};/** * 解析html中部分內容 *  * @param doc */private void doParse(Document doc) {// 解析出星座描述String describe = doc.getElementsByClass("lotconts").first().text();System.out.println(describe);// 解析出有效日期String validDate = doc.getElementsByClass("datea").first().text();System.out.println(validDate);// 解析出星座名稱和日期String constellationDate = doc.select("span").first().text();System.out.println(constellationDate);// 解析所有class為“tab”的內容Elements elements = doc.getElementsByClass("tab");if (elements != null) {for (Element e : elements) {// 模組標題String title = e.select("h4").get(0).text();System.out.println(title);// p標籤之間的常值內容，沒有則為nullString pText = e.select("p").get(0).text();System.out.println(pText);// src連結地址Elements linkText = e.select("[src]");System.out.println(linkText.attr("src"));}}}}