java读读取取html文文件件,并并获获取取body中中所所有有的的标标签签及及内内容容的的案案例例

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()) != 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("

found = true;

} else {

// 果存在图片，则将相对路径转换为绝对路径

String lowerCaseLine = line.toLowerCase();

if (lowerCaseLine.contains("src")) {

//这里是定义图片的访问路径

String directory = "D:/test";

// 果路径名不以反斜杠结尾，则手动添加反斜杠

/*if (!directory.endsWith("\\")) {

directory = directory + "\\";

}*/

// line = line.substring(0, lowerCaseLine.indexOf("src") + 5) + directory +

line.substring(lowerCaseLine.indexOf("src") + 5);

/*String filename = extractFilename(line);

line = line.substri