<dependency>
 <groupId>org.jsoup</groupId>
 <artifactId>jsoup</artifactId>
 <version>1.12.1</version>
</dependency>

/**
 * jsoup方式 獲取虎撲新聞列表頁(yè)
 * @param url 虎撲新聞列表頁(yè)url
 */
public void jsoupList(String url){
 try {
  Document document = Jsoup.connect(url).get();
  // 使用 css選擇器 提取列表新聞 a 標(biāo)簽
  // <a  rel="external nofollow" target="_blank">霍華德：夏休期內(nèi)曾節(jié)食30天，這考驗(yàn)了我的身心</a>
  Elements elements = document.select("div.news-list > ul > li > div.list-hd > h4 > a");
  for (Element element:elements){
//    System.out.println(element);
   // 獲取詳情頁(yè)鏈接
   String d_url = element.attr("href");
   // 獲取標(biāo)題
   String title = element.ownText();

   System.out.println("詳情頁(yè)鏈接："+d_url+" ,詳情頁(yè)標(biāo)題："+title);

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

public static void main(String[] args) {
 String url = "https://voice.hupu.com/nba";
 CrawlerBase crawlerBase = new CrawlerBase();
 crawlerBase.jsoupList(url);
}

<dependency>
 <groupId>org.apache.httpcomponents</groupId>
 <artifactId>httpclient</artifactId>
 <version>4.5.10</version>
</dependency>
<dependency>
 <groupId>org.apache.httpcomponents</groupId>
 <artifactId>httpcore</artifactId>
 <version>4.4.10</version>
</dependency>
<dependency>
 <groupId>org.apache.httpcomponents</groupId>
 <artifactId>httpmime</artifactId>
 <version>4.5.10</version>
</dependency>

/**
 * httpclient + 正則表達(dá)式 獲取虎撲新聞列表頁(yè)
 * @param url 虎撲新聞列表頁(yè)url
 */
public void httpClientList(String url){
 try {
  CloseableHttpClient httpclient = HttpClients.createDefault();
  HttpGet httpGet = new HttpGet(url);
  CloseableHttpResponse response = httpclient.execute(httpGet);
  if (response.getStatusLine().getStatusCode() == 200) {
   HttpEntity entity = response.getEntity();
   String body = EntityUtils.toString(entity,"utf-8");
 
   if (body!=null) {
     /*
     * 替換掉換行符、制表符、回車(chē)符，去掉這些符號(hào)，正則表示寫(xiě)起來(lái)更簡(jiǎn)單一些
     * 只有空格符號(hào)和其他正常字體
     */
    Pattern p = Pattern.compile("\t|\r|\n");
    Matcher m = p.matcher(body);
    body = m.replaceAll("");
    /*
     * 提取列表頁(yè)的正則表達(dá)式
     * 去除換行符之后的 li
     * <div class="list-hd">         <h4>          <a  rel="external nofollow" target="_blank">與球迷親切互動(dòng)！凱爾特人官方曬球隊(duì)開(kāi)放訓(xùn)練日照片</a>         </h4>        </div>
     */
    Pattern pattern = Pattern
      .compile("<div class=\"list-hd\">\\s* <h4>\\s* <a href=\"(.*?)\"\\s* target=\"_blank\">(.*?)</a>\\s* </h4>\\s* </div>" );

    Matcher matcher = pattern.matcher(body);
    // 匹配出所有符合正則表達(dá)式的數(shù)據(jù)
    while (matcher.find()){
//      String info = matcher.group(0);
//      System.out.println(info);
     // 提取出鏈接和標(biāo)題
     System.out.println("詳情頁(yè)鏈接："+matcher.group(1)+" ,詳情頁(yè)標(biāo)題："+matcher.group(2));
    }
   }else {
    System.out.println("處理失?。。?！獲取正文內(nèi)容為空");
   }
  } else {
   System.out.println("處理失?。。?！返回狀態(tài)碼：" + response.getStatusLine().getStatusCode());
  }
 }catch (Exception e){
  e.printStackTrace();
 }

}

public static void main(String[] args) {
 String url = "https://voice.hupu.com/nba";
 CrawlerBase crawlerBase = new CrawlerBase();
//  crawlerBase.jsoupList(url);
 crawlerBase.httpClientList(url);
}