replaceurl.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 : ReplaceUrl.java
 * Create Time : 2006-5-23 10:36:23
 * Author : shiwei
 * Descript : 替换字符串
 * Version : 
 */
package com.snoics.reptile.parse;

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.regex.url.IUrlRegex;
import com.snoics.reptile.system.common.Common;

public class ReplaceUrl implements IReplaceUrl {
	private String htmlString="";
	private List urlRegexList=null;
	private String url="";
	private String replaceUrl="";
	private Regex regex=new Regex();
	
	public void setHtmlString(String htmlString) {
		this.htmlString=htmlString;
	}

	public String getHtmlString() {
		return htmlString;
	}

	public List getUrlRegexList() {
		return urlRegexList;
	}

	public void setUrlRegexList(List urlRegexList) {
		this.urlRegexList=urlRegexList;
	}

	public void setUrl(String url) {
		this.url=url;
	}

	public String getUrl() {
		return url;
	}

	public void setReplaceUrl(String replaceUrl) {
		this.replaceUrl=replaceUrl;
	}

	public String getReplaceUrl() {
		return replaceUrl;
	}

	public String replace() {
		//System.out.println("url="+url);
		url=StringClass.getSpecialReplaceString(url,"\\","\\\\");
		url=StringClass.getSpecialReplaceString(url,".","\\.");
		url=StringClass.getSpecialReplaceString(url,"?","\\?");
		url=StringClass.getSpecialReplaceString(url,"*","\\*");
		url=StringClass.getSpecialReplaceString(url,"^","\\^");
		url=StringClass.getSpecialReplaceString(url,"+","\\+");
		url=StringClass.getSpecialReplaceString(url,"$","\\$");
		//System.out.println("url1="+url);
		String finalReplaceRegex="[\\s'\"]?"+url+"[\\s'\"]?";
		String newReplaceString="'"+replaceUrl+"' ";
		if(urlRegexList==null){
			return htmlString;
		}
		Iterator it=urlRegexList.iterator();
		while(it.hasNext()){
			IUrlRegex urlRegex=(IUrlRegex)it.next();
			String replaceRegexUrl=urlRegex.getReplaceRegexUrl();
			String oldReplaceRegexUrl=StringClass.getSpecialReplaceString(replaceRegexUrl,Common.REPLACEREGEXURL_FLAG,url);
			List oldUrlList=null;
			try{
				oldUrlList=regex.group(htmlString,oldReplaceRegexUrl,Pattern.CASE_INSENSITIVE);
			}catch(Exception e){
				e.printStackTrace();
			}
			if((oldUrlList!=null)&&(oldUrlList.size()>0)) {
				Iterator iterator=oldUrlList.iterator();
				while(iterator.hasNext()) {
					String oldUrl=(String)iterator.next();
					String newUrlString="";
					try{
						newUrlString=regex.getReplaceAll(oldUrl,newReplaceString,finalReplaceRegex,Pattern.CASE_INSENSITIVE);
						htmlString=StringClass.getSpecialReplaceString(htmlString,oldUrl,newUrlString);
					}catch(Exception e){
						e.printStackTrace();
					}
				}
			}
			
		}
		return htmlString;
	}
}