一、导入jsoup的maven依赖
org.jsoup
jsoup
1.8.3
二、运行代码 也可以自定义爬取的网站这里就以https://gank.io/special/Girl为例
package com.song;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.UUID;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class SpyderTest {
/**
* [url=home.php?mod=space&uid=686208]@AuThor[/url] Maoyan
* [url=home.php?mod=space&uid=264116]@data[/url] 2020/3/31 12:30
* [url=home.php?mod=space&uid=1248337]@version[/url] 1.0.0
*/
private static HttpURLConnection conn = null;
private static InputStream inp