Jsoup 网络爬虫

1. Jsoup下载地址：

http://jsoup.org/packages/jsoup-1.8.1.jar

或者Maven Central

http://central.maven.org/maven2/org/jsoup/jsoup/1.8.1/jsoup-1.8.1.jar

2.实现源码

public classRun {

public static voidmain(String[] args)throwsCommonException,IOException{

String urlStr ="https://m.XXXXx.com";

// 将获取的网页 HTML 源代码转化为 Document

// Document doc = Jsoup.parse(htmlStr);

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

//head元素中内容

Element articleEle = doc.head();

//body元素中内容

Element contentEle = doc.body();

// 标题

String titleStr = articleEle.text();

System.out.println(titleStr);

Elements images = contentEle.getElementsByTag("img");

String[] imageUrls =newString[images.size()];

for(inti =0;i < imageUrls.length;i++) {

imageUrls[i] = images.get(i).attr("src");

System.out.println(imageUrls[i]);

}

}

}

3.运行结果