java模拟爬虫_java实现一个简单的爬虫小程序

import java.io.*;importjava.net.URL;importjava.net.URLConnection;importjava.text.SimpleDateFormat;importjava.util.ArrayList;importjava.util.Date;importjava.util.List;importjava.util.Map;importjava.util.concurrent.CopyOnWriteArrayList;importjava.util.regex.Matcher;importjava.util.regex.Pattern;/*** @ClassName BKYPageReptile

* @Description TODO(爬取博客园文章)

* @Author 我恰芙蓉王

* @Date 2020年08月11日 9:38

* @Version 2.0.0

**/

public classBKYPageReptile {//请求地址

private static final String URL = "https://www.cnblogs.com";//保存路径

private static final String TARGET_PATH = "F://" + "博客园";//行匹配正则

private static final Pattern LINE_PATTERN = Pattern.compile(".*?");//url正则

private static final Pattern URL_PATTERN = Pattern.compile("https://www.cnblogs.com/.*?\\.html");//标题/文件名正则

private static final Pattern TITLE_PATTERN = Pattern.compile(">.*?");//标题缓存

private static final List TITLE_LIST = new CopyOnWriteArrayList<>();//当前页数

private static int PAGE = 1;//最大拉取页数

private static final int MAX_PAGE = 200;//一共拉取博客篇数

private static int ALL_COUNT = 0;//时间格式

private static final SimpleDateFormat SDF = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");public static voidmain(String[] args) {//创建根目录

File rootDir = newFile(TARGET_PATH);if (!rootDir.exists()) {

rootDir.mkdir();

}//创建日志文件夹

String logPath = TARGET_PATH + "//拉取日志";

File logDir= newFile(logPath);if (!logDir.exists()) {

logDir.mkdir();

}//创建日志文件

File logFile = new File(logPath + "//log.txt");if (!logFile.exists()) {try{

logFil