java读取html文件_java读取html文件,并获取body中所有的标签及内容的案例

这里的获取的是html文件中body中的所有标签以及内容

package com.lmt.service.file;

import java.io.BufferedReader;

import java.io.File;

import java.io.FileInputStream;

import java.io.InputStreamReader;

import java.io.Reader;

import org.springframework.stereotype.Component;

import com.lmt.config.UrlConstants;

@Component

public class ParseFile {

/**

* 解析html文件

* @param file

* @return

*/

public String readHtml(File file){

String body = "";

try {

FileInputStream iStream = new FileInputStream(file);

Reader reader = new InputStreamReader(iStream);

BufferedReader htmlReader = new BufferedReader(reader);

String line;

boolean found = false;

while (!found && (line = htmlReader.readLine()) != nul