正则表达式匹配url

[西蒙海耶]

url1 = "http://www.pythonchallenge.com/pc/def/abc123.html"
url2 = "http://ggg.pythonchallenge.net/pc/def/abc123.php"
url3 = "http://rrr.pythonchallenge.gov/pc/def/abc123.jsp"

Q1：我想获得adb123如何用re实现呢？
Q2：如果我想获取pythonchallenge如何实现呢？
Q3：如果我想获取pc 或者 def如何实现呢？
好像挺有难度的哦

[rickylin86]

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Test{
	public static void main(String[] args){
		String url1 = "http://www.pythonchallenge.com/pc/def/abc123.html";
		String url2 = "http://ggg.pythonchallenge.net/pc/def/abc123.php";
		String url3 = "http://rrr.pythonchallenge.gov/pc/def/abc123.jsp";


		process1(url1);
		System.out.println("-------------------------------------------");
		process2(url2);
		System.out.println("-------------------------------------------");
		process3(url3);
	}

	private static void process1(String url){
		String regex = "(?<=/)(?<content>[^/.]+)[.]\\w+$";
		Matcher matcher = Pattern.compile(regex).matcher(url);
		if(matcher.find()){
			System.out.println(matcher.group("content"));
		}
	}

	private static void process2(String url){
		String regex = "(?<=[.])(?<content>[^.]+)[.]\\w+(?=/)";
		Matcher matcher = Pattern.compile(regex).matcher(url);
		if(matcher.find()){
			System.out.println(matcher.group("content"));
		}
	}

	private static void process3(String url){
		String regex = "(?<=/)(?<content>\\w+)(?=/)";
		Matcher matcher = Pattern.compile(regex).matcher(url);
		while(matcher.find()){
			System.out.println(matcher.group("content"));
		}
	}
}

[西蒙海耶]

引用 1 楼 rickylin86 的回复:

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Test{
	public static void main(String[] args){
		String url1 = "http://www.pythonchallenge.com/pc/def/abc123.html";
		String url2 = "http://ggg.pythonchallenge.net/pc/def/abc123.php";
		String url3 = "http://rrr.pythonchallenge.gov/pc/def/abc123.jsp";


		process1(url1);
		System.out.println("-------------------------------------------");
		process2(url2);
		System.out.println("-------------------------------------------");
		process3(url3);
	}

	private static void process1(String url){
		String regex = "(?<=/)(?<content>[^/.]+)[.]\\w+$";
		Matcher matcher = Pattern.compile(regex).matcher(url);
		if(matcher.find()){
			System.out.println(matcher.group("content"));
		}
	}

	private static void process2(String url){
		String regex = "(?<=[.])(?<content>[^.]+)[.]\\w+(?=/)";
		Matcher matcher = Pattern.compile(regex).matcher(url);
		if(matcher.find()){
			System.out.println(matcher.group("content"));
		}
	}

	private static void process3(String url){
		String regex = "(?<=/)(?<content>\\w+)(?=/)";
		Matcher matcher = Pattern.compile(regex).matcher(url);
		while(matcher.find()){
			System.out.println(matcher.group("content"));
		}
	}
}

感谢您的回答，很正确，您所用的是?<content>是re采集器吗，能用在Python上吗？ 还有个问题：

 
//为啥我定义2个regex相同的会报错呢？
   private static void process1(String url){
        String regex = "(?<=/)(?<content>[^/.]+)[.]\\w+$";
        String regex2 = "(?<=/)(?<content>[^/.]+)[.]\\w+$";
        Matcher matcher = Pattern.compile(regex).matcher(url);
        Matcher matcher2 = Pattern.compile(regex2).matcher(url);
        if(matcher.find()){
            System.out.println("p1:"+matcher.group("content"));
            System.out.println("pm2:"+matcher2.group("content"));
        }
    }
p1:abc123
Exception in thread "main" java.lang.IllegalStateException: No match found
	at java.util.regex.Matcher.group(Matcher.java:524)
	at com.xzh.re.Test.process1(Test.java:26)
	at com.xzh.re.Test.main(Test.java:12)

[rickylin86]

(?<>)这个是在java1.7后引用的.至于你说的Python没学过,你可以试下. 至于你那个报错的问题.改成这样就没问题了.因为java中正则的匹配存在一个指针的概念,每次匹配都会改变起始位置,如果你没调用find()方法的那么就会报错.

 private static void process1(String url){
        String regex = "(?<=/)(?<content>[^/.]+)[.]\\w+$";
        String regex2 = "(?<=/)(?<content>[^/.]+)[.]\\w+$";
        Matcher matcher = Pattern.compile(regex).matcher(url);
        Matcher matcher2 = Pattern.compile(regex2).matcher(url);
        if(matcher.find()){
            System.out.println("p1:"+matcher.group("content"));
        }
		if(matcher2.find()){
			 System.out.println("pm2:"+matcher2.group("content"));
		}
    }