regex.java

来自「SSHMail Ajax方式提交,自动抓取页面内容,统计关键字个数.」· Java 代码 · 共 45 行

JAVA
45
字号
package com.leo.util;

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 RegEx {

	private static final String REG_REX = "《.*?异人.*?》";
	private static final String URL_PATH = "http://post.baidu.com/f?z=0&ct=318767104&lm=11&sc=0&rn=50&tn=baiduKeywordSearch&rs3=0&rs4=0&word=%D2%EC%C8%CB%B0%C1%CA%C0%C2%BC&pn=50";

	public static int doRegEx() throws IOException {
		URL totalURL = new URL(URL_PATH);
		BufferedReader reader = new BufferedReader(new InputStreamReader(
				totalURL.openStream()));
		StringBuffer html = new StringBuffer();
		String tmp = "";
		while ((tmp = reader.readLine()) != null) {
			html.append(tmp + "\n");
		}

		Pattern pattern = Pattern.compile(REG_REX);
		Matcher matcher = pattern.matcher(html.toString());
		int i = 0;
		while (matcher.find()) {
			System.out.println("找到了第 " + ++i + "个: " + matcher.group());
		}
		return i;
	}

	public static void main(String... strings) {

		System.out.println("开始运行.....");
		try {
			RegEx.doRegEx();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

}

⌨️ 快捷键说明

复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?