简单统计html页面标签数量_java统计html中的字数-优快云博客

这个Java程序读取名为D:index.txt的文件，通过正则表达式匹配统计了包括div, span, input等在内的多个HTML标签的出现数量。这是一个简单的HTML标签统计分析示例。" 133303811,19973989,StoneDB主从切换实战指南,"['数据库管理', '高可用架构', 'MySQL', '数据同步']

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Count2 {
public static void main(String[] args) {
BufferedReader br = null;
try {
br = new BufferedReader(new FileReader(“D:\index.txt”));
StringBuffer sb = new StringBuffer();
String str = null;
while ((str = br.readLine()) != null) {
sb.append(str);
}
String[] regex = new String[] { “<div”, “<span”, “<nz-input-group”, “<input”, “<ng-template”, “<i”, “<h1”,
“<h2”, “<h3”, “<h4”, “<p”, “<button”, “<nz-autocomplete”, “<strong”, “<a”, “<label”, “<ul”, “<li”,
“<ng-container”, “<nz-spin”, “<img”, “<nz-anchor”, “<nz-link”, “<hr”, “<textarea”, “<h”,
“<nz-select”, “<nz-pagination”, “<nz-table”, “<tr”, “<th”, “<thead”, “<tbody”, “<td”, “<nz-modal” };
for (int i = 0; i < regex.length; i++) {

			Pattern pattern = Pattern.compile(regex[i]);
			Matcher matcher = pattern.matcher(sb);
			int num = 0;
			while (matcher.find()) {
				num++;
			}
			if (num != 0) {
				System.out.println(regex[i] + "： " + num);
			}
		}

	} catch (Exception e) {
		e.printStackTrace();
	} finally {
		try {
			if (null != br) {
				// 关闭资源
				br.close();
			}
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

}

}