在前面一些文章中介绍了Jsoup的一些常用类的使用:jsoup的Document类、Jsoup类、jsoup的Node类、jsoup的Element类、jsoup的Elements类。都是其常用API的翻译,这里给一个简单例子:
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/";
-
@Override
-
protected void onCreate(Bundle savedInstanceState) {
-
super.onCreate(savedInstanceState);
-
setContentView(R.layout.main);
-
btn = (Button) findViewById(R.id.main_btn);
-
btn.setOnClickListener(this);
-
}
-
@Override
-
public void onClick(View v) {
-
if (v == btn) {
-
new Thread(r).start();
-
}
-
}
-
Runnable r = new Runnable() {
-
Document doc;
-
@Override
-
public 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中部分内容
-
*
-
* @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);
-
// 解析出星座名称和日期
-
String constellationDate = doc.select("span").first().text();
-
System.out.println(constellationDate);
-
// 解析所有class为“tab”的内容
-
Elements elements = doc.getElementsByClass("tab");
-
if (elements != null) {
-
for (Element e : elements) {
-
// 模块标题
-
String title = e.select("h4").get(0).text();
-
System.out.println(title);
-
// p标签之间的文本内容,没有则为null
-
String pText = e.select("p").get(0).text();
-
System.out.println(pText);
-
// src链接地址
-
Elements linkText = e.select("[src]");
-
System.out.println(linkText.attr("src"));
-
}
-
}
-
}
-
}