|
使用Jsoup解析html中的指定数据,十分方便。Jsoup工具十分强大,十分好用。但网上似乎没有很好的例子,本文的目的即在于此。建议仔细阅读代码中的几个例子,Jsoup解析数据不外乎这几种类型。
第一步:将Jsoup JAR包导入项目
第二步:使用Jsoup API
1, 定位
通过div的属性值,定位到html的div(块),即所需要内容对应的块。
示例代码如下:
2, 筛选数据
a, 通过标签头,在div中继续筛选数据。可能会找到很多的数据,这里会用到循环。见eg1。
- //eg1:解析百度音乐
- Document doc = Jsoup.connect("http://list.mp3.baidu.com/top/singer/A.html").get();
- Element singerListDiv = doc.getElementsByAttributeValue("class", "content").first();
- Elements links = singerListDiv.getElementsByTag("a");
-
- for (Element link: links) {
- String linkHref = link.attr("href");
- String linkText = link.text().trim();
- System.out.println(linkHref);
- }
b, 通过标签名,在div中筛选数据,选中此标签内的所有数据。见eg2
- //eg2:解析万年历
- Document doc = Jsoup.connect("http://www.nongli.com/item4/index.asp?dt=2012-03-03").get();
- Element infoTable = doc.getElementsByAttributeValue("class", "table002").first();
- Elements tableLineInfos = infoTable.select("tr");
- for (Element lineInfo : tableLineInfos) {
- String lineInfoContent = lineInfo.select("td").last().text().trim();
- System.out.println("jsoup is :" + lineInfoContent);
- }
c, 限定筛选条件。如果eg5
- //eg5:查找html元素
- File input = new File("/tmp/input.html");
- Document doc = Jsoup.parse(input, "UTF-8", "http://www.oschina.net/");
- Elements links = doc.select("a[href]"); // 链接
- Elements pngs = doc.select("img[src$=.png]"); // 所有 png 的图片
- Element masthead = doc.select("div.masthead").first();// div with class=masthead
- Elements resultLinks = doc.select("h3.r > a"); // direct a after h3
NOTE: <td colspan="2" class="l3">二月15日<br>壬辰年<br>癸卯月<br>丁卯日<br></td>
此处不能直接单独获得三组数据,获得的是总的三个数据。可通过正则表达式分解
3, 获取数据
即element.text()即可获得相关数据
plus: Jsoup有灵活的语法,比如通过class-value对指定div块,可通过select(div.value)找到,更多用法请参考文档!
以下给出所有示例代码:
- package com.mike.activity;
-
- import java.io.File;
- import java.io.IOException;
-
- import org.jsoup.Connection;
- 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.util.Log;
- import android.view.View;
- import android.widget.TextView;
-
- public class JsoupDemoActivity extends Activity {
- /** Called when the activity is first created. */
-
- private StringBuilder sb ;
-
-
- @Override
- public void onCreate(Bundle savedInstanceState) {
- super.onCreate(savedInstanceState);
- setContentView(R.layout.main);
-
- sb = new StringBuilder();
- TextView textView = (TextView) findViewById(R.id.textView1);
-
- try {
- // //eg1:解析百度音乐
- // Document doc = Jsoup.connect("http://list.mp3.baidu.com/top/singer/A.html").get();
- // Element singerListDiv = doc.getElementsByAttributeValue("class", "content").first();
- // Elements links = singerListDiv.getElementsByTag("a");
- //
- // for (Element link: links) {
- // String linkHref = link.attr("href");
- // String linkText = link.text().trim();
- // System.out.println(linkHref);
- // }
- //
- //
- // //eg2:解析万年历
- // Document doc = Jsoup.connect("http://www.nongli.com/item4/index.asp?dt=2012-03-03").get();
- // Element infoTable = doc.getElementsByAttributeValue("class", "table002").first();
- // Elements tableLineInfos = infoTable.select("tr");
- // for (Element lineInfo : tableLineInfos) {
- // String lineInfoContent = lineInfo.select("td").last().text().trim();
- // System.out.println("jsoup is :" + lineInfoContent);
- // }
-
-
- //eg3:解析指定段落的内容----注意此代码中的语法:<div class="artHead">
- // Document doc = Jsoup.connect("http://passover.blog.51cto.com").get();
- // Elements divs = doc.select("div.artHead");
- // for (Element div: divs) {
- // System.out.println(div.select("h3[class=artTitle]"));
- // }
-
- //eg4:
- // Document doc = Jsoup.connect("http://passover.blog.51cto.com").get();
-
-
-
- // //eg5:查找html元素
- File input = new File("/tmp/input.html");
- Document doc = Jsoup.parse(input, "UTF-8", "http://www.oschina.net/");
- Elements links = doc.select("a[href]"); // 链接
- Elements pngs = doc.select("img[src$=.png]"); // 所有 png 的图片
- Element masthead = doc.select("div.masthead").first();// div with class=masthead
- Elements resultLinks = doc.select("h3.r > a"); // direct a after h3
-
-
- // //test
- // File input = new File("D:/test.html");
- // Document doc = Jsoup.parse(input,"UTF-8","http://www.oschina.net/");
-
-
- /*
- * 项目数据准备
- */
-
- //eg5:万年历:http://www.zdic.net/nongli/2012-3-7.htm
-
- //data1:dayFav(宜)
- // Document doc = Jsoup.connect("http://www.zdic.net/nongli/2012-3-7.htm").get();
- // Element dayFav = doc.getElementsByAttributeValue("class", "ly2").first();
- // Elements dayFavItems = dayFav.getElementsByTag("a");
- // for (Element dayFavItem:dayFavItems) {
- // System.out.println(dayFavItem.text());
- // }
-
- //data2:dayUnfav(忌)
- // Element dayUnfav = doc.getElementsByAttributeValue("class", "lj2").first();
- // Elements dayUnfavItems = dayUnfav.getElementsByTag("a");
- // for (Element dayUnfavItem:dayUnfavItems) {
- // System.out.println(dayUnfavItem.text());
- // }
-
- //data3:taiSheng(胎神)
- // Element taiSheng = doc.getElementsByAttributeValue("class", "lts2").first();
- // System.out.println(taiSheng.text());
-
- //data4:chong sha(冲煞信息)
- // Element chong = doc.getElementsByAttributeValue("class", "lcs").first();
- // Element sha = doc.getElementsByAttributeValue("class", "lcs").get(1);
- // System.out.println(chong.text());
- // System.out.println(sha.text());
-
- //data5:zhengChong(正冲)和zhiXing(值星)
- // Element zhengChong = doc.getElementsByAttributeValue("class", "lzc2").first();
- // Element zhiXing = doc.getElementsByAttributeValue("class", "lzx2").first();
- // System.out.println(zhengChong.text());
- // System.out.println(zhiXing.text());
-
-
- //data6:godFav(吉神宜趋)
- // Element godUnfav = doc.getElementsByAttributeValue("class", "js2").first();
- // System.out.println(godUnfav.text());
-
- //data7:godUnfav(凶神宜忌)
- // Element godFav = doc.getElementsByAttributeValue("class", "xs2").first();
- // System.out.println(godFav.text());
-
- //data8:pengZuBaiJi(彭祖百忌)
- // Element pengZuBaiJi = doc.getElementsByAttributeValue("class", "pz2").first();
- // System.out.println(pengZuBaiJi.text());
-
- //data9:wuXing(五行)
- // Element wuXing = doc.getElementsByAttributeValue("class", "wuh2").first();
- // System.out.println(wuXing.text());
-
-
-
- } catch (IOException e) {
- // TODO Auto-generated catch block
- e.printStackTrace();
- }
-
-
- }
- }
|
|