singleregexlurl.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

/*
 * FileName SingleRegexlFilter.java
 * Create Date 2006-5-16
 * Author shiwei
 * Descript 使用单个正则表达式从HTML里面提取URL
 * Version 
 */
package com.snoics.reptile.regex.url.impl;

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

import com.snoics.base.util.regex.Regex;
import com.snoics.reptile.regex.url.IGetRegexUrl;
import com.snoics.reptile.regex.url.ISingleRegexUrl;
import com.snoics.reptile.regex.url.IUrlRegex;

public class SingleRegexlUrl implements ISingleRegexUrl{
	private String url="";
	private IUrlRegex urlRegex;
	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;
	}
	
	/**
	 * @return Returns the urlRegex.
	 */
	public IUrlRegex getUrlRegex() {
		return urlRegex;
	}
	/**
	 * @param urlRegex The urlRegex to set.
	 */
	public void setUrlRegex(IUrlRegex urlRegex) {
		this.urlRegex = urlRegex;
	}
	/**
	 * 使用单个正则表达式从HTML里面提取URL
	 * @return List
	 */
	public List filterUrls(){
		List newUrlList=null;
		String urlregex=urlRegex.getRegexUrl();
		IGetRegexUrl getUrlRegex=urlRegex.getGetRegexUrl();
		List urlList=regex.group(url,urlregex,Pattern.CASE_INSENSITIVE);
		if((urlList!=null)&&(urlList.size()>0)) {
			newUrlList=new ArrayList();
			Iterator iterator=urlList.iterator();
			while(iterator.hasNext()) {
				String nowUrl=(String)iterator.next();
				List theUrlList=getUrlRegex.getUrl(nowUrl);
				if(theUrlList!=null) {
					newUrlList.addAll(theUrlList);
				}
			}
		}
		return newUrlList;
	}
	
	public static void main(String[] args) {
		SingleRegexlUrl singleUrlFilter=new SingleRegexlUrl();
		String url="<a href = fdsjkf>";
		singleUrlFilter.setUrl(url);
	}
}