vlambda博客
学习文章列表

 <dependency> <groupId>com.ibm.icu</groupId> <artifactId>icu4j</artifactId> <version>67.1</version> </dependency>

package com.lovnx.note.util;
import com.ibm.icu.text.CharsetDetector;import com.ibm.icu.text.CharsetMatch;import org.jsoup.Jsoup;import org.jsoup.nodes.Document;import org.jsoup.select.Elements;
import java.io.IOException;import java.net.URL;import java.nio.file.Files;import java.nio.file.Path;import java.nio.file.Paths;
/** * @author https://github.com/TianPuJun @256g的胃 * @ClassName HtmlParse * @Description * @Date 15:32 2020/7/9 **/public class HtmlParse {
 public static String getEncode(String filePath) throws IOException {
 Path path = Paths.get(filePath); byte[] data = Files.readAllBytes(path);
 CharsetDetector detector = new CharsetDetector(); detector.setText(data); CharsetMatch match = detector.detect(); String encoding = match.getName(); System.out.println("The Content in " + match.getName()); return encoding; } public static void main(String[] args) throws Exception { System.out.println(HtmlParse.getEncode("/Users/cxt/Downloads/test.html")); }}

Document doc = Jsoup.parse("读取的文本字符串，此处应该是带html标签的");String text = doc.text();