一道面试题

[liuzhe_2008]

给定一个URL 下载这个页面和这个页面中的所有连接 怎么做 ？

[i11111]

噢,不错,学习了,我想到是用一般下载软件,呵呵

[fczfr]

不错，很犀利

[DBMS_TTT]

学习学习

[popoweiqi]

mark，学习了。不介意我把代码带走了吧，哈哈。

[feifei694893239]

这个必须要收藏啊

[shauxiaoxin]

不错！不错！

[thegodofwar]

[Quote=引用 1 楼 ticmy 的回复:]
Java code
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.util.ArrayList;
import java.util.List;
……
[/Quote]
类似这种

<[a|A][^>]*[h|H][r|R][e|E][f|F][^>]*>

的正则表达式写的都不对，比如这个它还能匹配

String str="<| agghd||||ggdhhdj>";

这样的字符串，‘或’应该是这样写

<[aA][^>]*[hH][rR][eE][fF][^>]*>

[龙四]

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class ObtainLinks {
	private String pageSrc;
	private String url;

	public ObtainLinks(String url) throws MalformedURLException,IOException{
		this.url = url;
		pageSrc = getPageSrc(url);
	}

	/**
	 * 根据strUrl获取网页源文件.
	 * @param strURL
	 * @return 源文件为空，返回空串
	 * @throws MalformedURLException
	 * @throws IOException
	 */
	private String getPageSrc(String strUrl) throws MalformedURLException,IOException {
		StringBuffer sb = new StringBuffer();
		java.net.URL url = new java.net.URL(strUrl);
		BufferedReader in = new BufferedReader(new InputStreamReader(url.openStream()));
		String line;
		while ((line = in.readLine()) != null) {
			sb.append(line);
		}
		in.close();
		return sb.toString();
	}
	
	/**
	 * 获取网页中所有包含href属性的<a>标签.
	 * @return pageSrc(网页源码)为空，返回null
	 */
	private List<String> getAnchorContent(){
		if(pageSrc == null) {
			return null;
		}
		List<String> list = new ArrayList<String>();
		String regex = "<[a|A][^>]*[h|H][r|R][e|E][f|F][^>]*>";
		Pattern pattern = Pattern.compile(regex);
		Matcher matcher = pattern.matcher(pageSrc);
		while(matcher.find()){
			list.add(matcher.group());
		}
		return list;
	}
	
	
	public List<String> getUrls() {
		List<String> anchorList = getAnchorContent();
		if(anchorList == null){
			return null;
		}
		
		List<String> list = new ArrayList<String>();
		Pattern pattern;
		for(String anchor:anchorList) {
			
			//<a href="www.baidu.com">
			if(anchor.matches(".*[h|H][r|R][e|E][f|F]\\s*=\\s*\"[^\"]*\".*")) {
				pattern = Pattern.compile("[h|H][r|R][e|E][f|F]\\s*=\\s*\"[^\"]+\"");
				Matcher matcher = pattern.matcher(anchor);
				while(matcher.find()){
					list.add(matcher.group());
				}
				continue;
			}
			
			//<a href='www.baidu.com'>
			if(anchor.matches(".*[h|H][r|R][e|E][f|F]\\s*=\\s*\'[^\']*\'.*")) {
				pattern = Pattern.compile("[h|H][r|R][e|E][f|F]\\s*=\\s*\'[^\"]+\'");
				Matcher matcher = pattern.matcher(anchor);
				while(matcher.find()){
					list.add(matcher.group());
				}
				continue;
			}
			
			//<a href=www.baidu.com>
			if(anchor.matches(".*[h|H][r|R][e|E][f|F]\\s*=\\s*[^\\s]*.*")) {
				pattern = Pattern.compile("[h|H][r|R][e|E][f|F]\\s*=\\s*[^\\s]+[\\s+|>]");
				Matcher matcher = pattern.matcher(anchor);
				while(matcher.find()){
					String str = matcher.group();
					list.add(str.substring(0, str.length()-1));
				}
				continue;
			}
		}
		
		
		return list;
	}
	public static void main(String[] args) throws Exception{
		List<String> list = new ObtainLinks("http://sports.sina.com.cn/nba/").getUrls();
		for(String str:list){
			System.out.println(str);
		}
	}
}

[voice1122]

学习了

[rjzou2006]

http://wolfchina.bokee.com/5117147.html

[有一天呵呵]

呵呵，不错

[chenbb110]

很强大

[aijezdm915]

<[aA][^>]*[hH][rR][eE][fF][^>]*>
???