Java通过关键字搜索出百度百科词条摘要的代码

package com.hply.kuzo.baidu.baike;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.ListIterator;


import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;


public class BaikeUtil {


public static List<String> queryBaike(String keyword) throws IOException {
Document doc = Jsoup.connect(
"http://baike.baidu.com/search/none?word=" + keyword
+ "&pn=0&rn=10&enc=utf8").get();
String url = doc.select("a.result-title").first().attr("href");
System.out.println(url);


doc = Jsoup.connect(url).get();
List<String> result = new ArrayList<String>();
ListIterator<Element> paras = doc.select("div.lemma-summary")
.select("div.para").listIterator();
while (paras.hasNext()) {
result.add(paras.next().text());
}
return result;
}


public static void main(String[] args) throws Exception {
// System.out.println(queryBaike("耳根"));
// System.out.println("-------------------------");
// System.out.println(queryBaike("诛仙"));
System.out.println("-------------------------");
System.out.println(queryBaike("马自达"));
}

}

依赖于

<dependencies>
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.8.3</version>
</dependency>
</dependencies>

jsoup的使用参考的这篇文章：

 

非常好用的一个Html解析的java类库 Jsoup

http://blog.csdn.net/huangxy10/article/details/8185108