java正则提取html数据,java - 如何用正则提取html内容

伊谢尔伦2017-05-17 10:08:132楼

可以使用jsoup和regex, 推荐使用jsoup!

jsoup document:

https://jsoup.org/cookbook/in...

http://www.open-open.com/jsoup/

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

import org.jsoup.nodes.Element;

import java.util.regex.Matcher;

import java.util.regex.Pattern;

public class Main {

public static void main(String[] args) {

// 方法１: jsoup

String html = "

财富

";

Document doc = Jsoup.parse(html);

Element element = doc.getElementById("info_detail_head_classify_type");

System.out.println(element.text());

// 方法2: regex

Pattern r = Pattern.compile("(.*)");

Matcher m = r.matcher(html);

if (m.find()) {

System.out.println(m.group(1));

}

}

}