parsehtml.java

java开发网络蜘蛛的核心parseHTML源码

import java.net.*;
import java.io.*;
import java.util.*;

public class ParseHTML {

	public ParseHTML() {

	}

	public String toString() {
      	  String parsed = new String();
	  try{

		String htm = new String();
	  	FileInputStream fis = new FileInputStream("ret.htm");
	  	int n;
	  	while ((n=fis.available()) > 0)
	  	{
	  	    byte[] b = new byte[n];
	  	    int result = fis.read(b);
	  	    if (result == -1) break;
	  	    String t = new String(b);
	  	    htm += t;                 //<-- 眖Stream 锣