Java正则匹配原理

Java正则匹配原理

WebSpiderCore.java

package Spider;

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

/*
 * 网络爬虫爬取数据
 */
public class WebSpiderCore {
    /*
     * 获得urlStr对应的网页的源码
     */
    public static String getUrlContent(String urlStr,String charset) {
        StringBuilder sb=new StringBuilder();
        try {
            URL url=new URL(urlStr);
            BufferedReader reader=new BufferedReader(new InputStreamReader(url.openStream(),Charset.forName(charset)));
            String temp="";
            while((temp=reader.readLine())!=null) {
//                sb.append("\n\t");
                sb.append(temp);
            }
            
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return sb.toString();
    }
    
    public static List getMatherSubstrs(String destStr,String regexStr){
        Pattern p=Pattern.compile(regexStr);  //取到超链接的地址
        Matcher m=p.matcher(destStr);
        List result=new ArrayList();
        while(m.find()) {
            result.add(m.group(1));
        }
        return result;
    }
    public static void main(String[] args) {
        String destStr=getUrlContent("https://www.163.com/","gbk");
//        System.out.println(destStr);
        List result=getMatherSubstrs(destStr,"href=\"([\\w\\s./:]+?)\"");
        for(String temp:result) {
            System.out.println(temp);
        }
    }
}

打印结果

 

GitHub地址：https://github.com/mentality-sun/Java/blob/master/WebSpiderCore.java

转载于:https://www.cnblogs.com/ssxblog/p/11346623.html