正则表达式(Java)

​​正则在线测试​​

---

---

​​Demo01​​

package RegexTest;
/**
 * 正则基本操作
 */
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Demo01 {
  
  public static void main(String args[]) {

    Pattern p = Pattern.compile("\\w+");

    Matcher m = p.matcher("123kjd&@akjda");  // 尝试将整个字符序列与该模式匹配

//    System.out.println(m.matches());  // 匹配时候成功

//    System.out.println(m.find());  // 该方法扫描输入的序列,查找与该模式匹配的下一个子序列
//    System.out.println(m.find());
//    System.out.println(m.find());

    while (m.find()){
      // 输出匹配结果
      System.out.println(m.group());  // group()和group(0)匹配整个表达式的字符串
      System.out.println(m.group(0));
    }
  }
}

​​Demo02​​

package RegexTest;
/**
 * group分组
 */

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

public class Demo02 {
  
  public static void main(String args[]) {

    Pattern p = Pattern.compile("([a-z]+)([0-9]+)");

    Matcher m = p.matcher("kj123**dd59aw&@akj36da");  // 尝试将整个字符序列与该模式匹配

    while (m.find()){

      System.out.println(m.group());  // group()和group(0)匹配整个表达式的字符串
      System.out.println(m.group(1));
      System.out.println(m.group(2));
      System.out.println("------------");
    }
  }
}

​​​Demo03​​

package RegexTest;
/**
 * 字符串的替换
 */

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

public class Demo03 {
  
  public static void main(String args[]) {
    // 表达式对象
    Pattern p = Pattern.compile("[0-9]");
    // 创建Matcher对象
    Matcher m = p.matcher("kj123**dd59aw&@akj36da");

    // 替换匹配到的字符
    String nStr = m.replaceAll("#");
    System.out.println(nStr);
  }
}

​​Demo04​​

package RegexTest;

import java.util.Arrays;

/**
 * 字符串的分割
 */

public class Demo04 {
  
  public static void main(String args[]) {

    String s = "adylgt29389ad23ljd";
    String[] sArr = s.split("\\d+");

    System.out.println(Arrays.toString(sArr));
  }
}

​​java爬虫-用正则表达式爬取超链接​​

package RegexTest;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class WebSpiderTest {

    /**
     * 获得url对应网页的源码内容
     * @param urlStr
     * @return
     */
    public static String getURLContent(String urlStr, String code){

        StringBuilder content = new StringBuilder();

        try {

            URL url = new URL(urlStr);

            BufferedReader reader = new BufferedReader(new InputStreamReader(url.openStream(), code));
            String temp = "";
            while ((temp=reader.readLine())!=null){

                content.append(temp);
            }

        } catch (IOException e) {
            e.printStackTrace();
        }

        return content.toString();
    }

    public static void main(String[] args) {

        String destStr = getURLContent("https://www.163.com", "gbk");
        Pattern p = Pattern.compile("(http[s]?://[a-zA-Z0-9./]+?)\"");

        Matcher m = p.matcher(destStr);

        while (m.find()){
            System.out.println(m.group(1));
        }

    }
}