java读取html文件,并获取body中所有的标签及内容的案例

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()) != null) {
        if (line.toLowerCase().indexOf("的前面可能存在空格
          found = true;
        }
      }
      
      found = false;
      while (!found && (line = htmlReader.readLine()) != null) {
        if (line.toLowerCase().indexOf("元素，则分行进行替代
            String[] splitLines = line.split("元素
   * @return 文件名
   */
  public static String extractFilename(String htmlLine) {
    int srcIndex = htmlLine.toLowerCase().indexOf("src=");
    if (srcIndex == -1) { // 图片不存在，返回空字符串
      return "";
    } else {
      String htmlSrc = htmlLine.substring(srcIndex + 4);
      char splitChar = '\"'; // 默认为双引号，但也有可能为单引号
      if (htmlSrc.charAt(0) == '\'') {
        splitChar = '\'';
      } 
      String[] firstSplit = htmlSrc.split(String.valueOf(splitChar));
      String path = firstSplit[1]; // 第0位为空字符串
      String[] secOndSplit= path.split("[/\\\\]"); // 匹配正斜杠或反斜杠
      return secondSplit[secondSplit.length - 1];
    }
  }
  
}