Java使用Jsoup解析网页代码实现

本文转载自：https://www.cnblogs.com/boy1025/p/5040495.html，有少许修改

一、Jsoup官网网站：http://jsoup.org/      

 通俗的讲，Jsoup就是一个解析网页的工具，官方解释：

二、Jsoup的基本用法：http://www.open-open.com/jsoup/parsing-a-document.htm

三、demo演示  解析的url：http://sex.guokr.com/

     1.解析一个ul –>li

 

 

 

 

 

 

 

 

 

 

 

 

 

我们来看下这段的源代码：

 

 

 

 

 

 

 

 

 

 

 

 

由此我们知道了大体的样子，现在我们来写编码

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

import java.io.IOException;

/**
 * 使用Jsoup解析url
 * @tag：url ：http://sex.guokr.com/
 * Created by monster on 2015/12/11.
 */
public class JsoupZX {
    public static void main(String[] args){
        final String url="http://sex.guokr.com/" ;

        try {

            Document doc = Jsoup.connect(url).get();

           Elements container = doc.getElementsByClass("container");

            Document containerDoc = Jsoup.parse(container.toString());

            Elements module = containerDoc.getElementsByClass("module-list");

            Document moduleDoc = Jsoup.parse(module.toString());

            //Elements clearfix = moduleDoc.getElementsByClass("clearfix");  //DOM的形式

            Elements clearfix = moduleDoc.select(".clearfix");  //选择器的形式

            for (Element clearfixli : clearfix){
                Document clearfixliDoc = Jsoup.parse(clearfixli.toString());
                Elements kind = clearfixliDoc.select(".board-tag");  //选择器的形式
                Elements title = clearfixliDoc.select(".tit-post");
                Elements author = clearfixliDoc.select("span a");


               System.out.println("类别"+kind.text());  //分类
               System.out.println("标题"+title.text());  //标题
               System.out.println("作者"+author.text());  //作者
                System.out.println("详情链接"+title.attr("href"));  //标题下的链接

                System.out.println("=====================");

            }
              //  String title = clearfixli.getElementsByTag("a").text();


          //  System.out.println(clearfix);

        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

结果：

=================================================================================================

2.解析详情页面和评论，链接：http://sex.guokr.com/post/1100992/

  

上述就是页面的内容， 然后我们看下源码：

内容：

评论：

看完源码后，我们进行编码：

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

import java.io.IOException;

/**
 * 使用Jsoup解析帖子详情和评论
 * @tag: url:http://sex.guokr.com/post/1100992/
 * Created by monster on 2015/12/11.
 */
public class JSoupDetail {

    public static void main(String args[]){
        final String url=  "http://sex.guokr.com/post/1100992/";


        try {

            Document doc = Jsoup.connect(url).get();

            Elements container = doc.getElementsByClass("container");

            Document containerDoc = Jsoup.parse(container.toString());

            String articleTitle =  containerDoc.getElementById("articleTitle").text();
            String authorName = containerDoc.getElementById("authorName").text();
            String time = containerDoc.select("span").first().text();
            String imgphotoUrl=containerDoc.select("img").get(1).attr("src");
            System.out.println("标题：" + articleTitle); //标题
            System.out.println("作者："+authorName); //作者
            System.out.println("发布时间："+time); //发布时间
            System.out.println("作者头像的url："+imgphotoUrl); //发布时间


            Element articleContent =  containerDoc.getElementById("articleContent");
            Document articleContentDoc = Jsoup.parse(articleContent.toString());


           int size=  articleContentDoc.select("p").size();
            System.out.println("段落数："+size);

            System.out.println("帖子内容：");

            for (int i=0;i<size;i++){
               String content =  articleContentDoc.select("p").get(i).text();
                System.out.println(content);
            }

            System.out.println("================================================");
        System.out.println("帖子评论区域（按照楼层分布）");

            Elements cmts =containerDoc.getElementsByClass("cmts");
            Document cmtsDoc = Jsoup.parse(cmts.toString());
            System.out.println("评论楼层："+cmtsDoc.select("span").first().text());

            Elements cmtslist =cmtsDoc.getElementsByClass("cmts-list");

            for (Element clearfix:cmtslist){
                String user =  clearfix.select("a").get(1).text();
                String userPhotoUrl =clearfix.select("img").get(0).attr("src");
                String replyTime = clearfix.select("a").get(3).text();
               String floor=clearfix.select("span").text();

                System.out.println("评论者："+user+"\n"+"评论者头像url："+userPhotoUrl+"\n"+"回复时间："+replyTime+"\n"+"所在楼层："+floor);
                Document replyContentDoc = Jsoup.parse(clearfix.toString());
               Elements replyContent =  replyContentDoc.getElementsByClass("cmt-content");
                System.out.println("评论内容：");
                int s =replyContent.select("p").size();
               for (int j=0;j<s;j++){
                 String replycontent =   replyContent.select("p").get(j).text();
                   System.out.println(replycontent);


               }
                System.out.println("================================================");
            }

        } catch (IOException e) {
            e.printStackTrace();
        }


    }

}

输出结果：