jsoup遍历html,jsoup深度遍历html中所有的子链接

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

import org.jsoup.nodes.Element;

import org.jsoup.select.Elements;

import java.io.IOException;

import java.util.*;

public class testDOM {

public static void main(String[] args) {

String url = "https://mirrors.edge.kernel.org/pub/software/libs/glibc/hjl/";

getAllUrl(url);

}

public static List getAllUrl(String url){

List list = new ArrayList();

try {

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

Elements links = ((Element) doc).select("a[href]");

for (Element link : links) {

String linkHref = link.attr("abs:href");

String linkText = link.text();

String test = linkHref+"............................"+linkText;

System.out.println(test);

list.add(linkHref);

if(!linkText.endsWith("../")&&linkText.endsWith("/")){

getAllUrl(linkHref);

}

}

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

return list;

}

}

改进版如下：

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

import org.jsoup.nodes.Element;

import org.jsoup.select.Elements;

import java.io.IOException;

import java.util.*;

public class testDOM {

private static List list;

public static void main(String[] args) {

list = new ArrayList();

String url = "https://mirrors.edge.kernel.org/pub/software/libs/glibc/hjl/";

List list2 = getAllUrl(url);

for (int i = 0; i

所需jar包链接：密码: 9ir5