html TagStream流的实现

最新推荐文章于 2021-07-31 14:39:09 发布

azhoulinux

最新推荐文章于 2021-07-31 14:39:09 发布

阅读量250

点赞数

文章标签： HTML Java

我想对于一个html文件进行如下的处理：
1）把html里面的文本也看成tag，对于tag有三种属性，一种是开始的tag，如<body>，一种是结束的tag，比如</body>，还有一种就是封闭在对应的开始和封闭的tag的文本，比如<p>that is a p item</p>，其中that is a p item就是普通文本。
2）把html里面的所有tag（包括文本），形成一个数组，加入了hasnext(),next()方法
3）如果文本tag的isempty()，就忽略不计

如下的html：

<html>
	<head>
		<title>title content</title>
	</head>
	<body>
		<font>font content</font>
		<p>p content</p>
		body content
	</body>
</html>

形成下面的tag 流：
html>head>title>title content>/title>/head>body>font>font content>/font>p>pcontent>/p>body content>/body>/html

tag属性类：

public class Tagattribute {
	/*attribute set mostly as 't':text 's':start tag  'e':end tag*/
	private char attribute;
	private String content;

	public Tagattribute(char attribute,String content){
		this.attribute = attribute;
		this.content = content;
	}
        /*get set method*/
}

使用java.io.*;形成数组，按照数组下标读取：

package org.biti.html;

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.util.ArrayList;

public class TagStream {
	private Tagattribute[] tas = null;
	private int order = 0;

	public static void main(String[] args){
		TagStream ts = new TagStream("d:\\data\\index.html","GB2312");
		while(ts.hasnext()){
			Tagattribute ta = ts.next();
			System.out.println(ta.getattribute()+":"+ta.getcontent());
		}
	}

	public TagStream(String file,String charset){
		InputStreamReader is;
		ArrayList<Tagattribute> al = new ArrayList<Tagattribute>();
		try {
			is = new InputStreamReader(new FileInputStream(file),charset);
			BufferedReader buffer = new BufferedReader(is);
			char[] cbuff = new char[1];
			StringBuffer tag = new StringBuffer();

			while( buffer.read(cbuff) != -1){
				char start = cbuff[0];
				if(start=='<'){			
					String content = tag.toString();
					content = content.replaceAll("^\\s+|\\s+$|\r+|\n+", "");
					content = content.replaceAll(" ","");
					if(!content.isEmpty()){
//						System.out.println("content:"+content);
						al.add(new Tagattribute('t',content));
					}
					tag.delete(0, tag.length());

					String webtag = "";
					while(buffer.read(cbuff)!=-1){
						char end = cbuff[0];
						if(end=='>'){
							webtag = tag.toString();
							break;
						}
						tag.append(end);
					}

					if(webtag.charAt(0)=='/'){
						webtag = webtag.substring(1);	
						al.add(new Tagattribute('e',webtag));
					}else{
						webtag = webtag.trim().split("\\s+")[0];
						al.add(new Tagattribute('s',webtag));
					}
//					System.out.println(webtag);

					tag.delete(0, tag.length());
				}else{
					tag.append(start);
				}
			}
			tas = (Tagattribute[]) al.toArray(new Tagattribute[0]);
		} catch (IOException e){
			e.printStackTrace();
		}
	}

	public boolean hasnext(){
		if(order<tas.length){
			return true;
		}
		return false;
	}

	public Tagattribute next(){
		if(order<tas.length){
			Tagattribute ta = tas[order];
			order++;
			return ta;
		}else{
			return null;
		}
	}
}