resolvedurlfilter.java

java写的搜索引擎网络爬虫 java写的搜索引擎网络爬虫 java写的搜索引擎网络爬虫

/*
 * File name : ResolvedUrlFilter.java
 * Create Time : 2006-5-19 15:08:16
 * Author : shiwei
 * Descript : 判断是否属于完整的URL类型
 * Version : 
 */
package com.snoics.reptile.regex.filter;

import java.util.Iterator;
import java.util.List;
import java.util.regex.Pattern;

import com.snoics.base.util.StringClass;
import com.snoics.base.util.regex.Regex;
import com.snoics.reptile.system.common.Common;

public class ResolvedUrlFilter implements IRegexFilter{
	private String url="";
	private Regex regex=new Regex();
	
	/**
	 * 获取当前URL
	 * @return Returns the url.
	 */
	public String getUrl() {
		return url;
	}
	/**
	 * 设置当前URL
	 * @param url The url to set.
	 */
	public void setUrl(String url) {
		this.url = url;
	}
	
	/**
	 * 判断是否属于远程URL
	 * @return boolean
	 */
	public boolean filter() {
		String remoteUrlFlags=".*:(//|\\\\)";
		List remoteUrlFlagList=null;
		remoteUrlFlagList=StringClass.getInterString(Common.STRING_SEPARATE_FLAG,remoteUrlFlags);
		boolean flag=false;
		if((remoteUrlFlagList!=null)&&(remoteUrlFlagList.size()>0)){
			Iterator iterator=remoteUrlFlagList.iterator();
			while(iterator.hasNext()) {
				String remoteUrlFlag=(String)iterator.next();
				if(regex.find(url,remoteUrlFlag,Pattern.CASE_INSENSITIVE)) {
					return true;
				}
			}
		}
		return flag;
	}
	
	public static void main(String[] args) {
		ResolvedUrlFilter resolvedUrlFilter=new ResolvedUrlFilter();
		String url="HTTPs://fjdsklfjkdslfjldsf";
		resolvedUrlFilter.setUrl(url);
		System.out.println(resolvedUrlFilter.filter());
		

		url="HTTPs://fjdsklfjkdsl/fjldsf";
		resolvedUrlFilter.setUrl(url);
		System.out.println(resolvedUrlFilter.filter());
		
		url="http:\\www.squarecn.com/fjdsklfjkdslfjldsf";
		resolvedUrlFilter.setUrl(url);
		System.out.println(resolvedUrlFilter.filter());
		
	}
}