如何使用cheerio仅从html链接中获取文本

问题描述

你好，我有一个像这样的 HTML 的网页

<div class="css-content">
   <div class="css-2aj">
      <img src="" >
      <div data-bn-type="text" id="/48" class="">Latest News</div>
   </div>
   <div class="css-6f9">
      <div class="css-content">
         <a data-bn-type="link" href="/en/blog/news/523hshhshhshhs3331adc0" class="css-1ej">US Could be on cusp of new Covid surge</a>

         <a data-bn-type="link" href="/en/blog/news/423hshhshhshhs3331adc0" class="css-1ej">Stop sharing your vaccine cards on social media</>
            <a data-bn-type="link" href="/en/blog/news/2222hshhshhshhs3331adc0" class="css-1ej">Italians can be fined up to $60,000 for selling the world's 'most dangerous' cheese</a>

         <a data-bn-type="link" href="/en/blog/news/2223hshhshhshhs3331adc0" class="css-1ej">The Masked Singer' reveals the identity of The Phoenix<a/>

        
      </div>
   </div>
</div>

我想要这样的结果

美国可能正处于新的 Covid 激增的风口
意大利人出售世界上“最危险的'奶酪
《蒙面歌手》揭露凤凰的身份

这是我试过的

    var list = [];
$('div[class="css-6f9"]').find('div  > a').each(function (index,element) {
    list.push($(element).attr('href'));
});


console.log(list);

结果为空数组

我是个新手，不知道如何获取 <a></a> 标签中的结果请帮忙

解决方法

试试这个

不需要 cheerio 作为 $

const html = `<div class="css-content">
<div class="css-2aj">
   <img src="" >
   <div data-bn-type="text" id="/48" class="">Latest News</div>
</div>
<div class="css-6f9">
   <div class="css-content">
      <a data-bn-type="link" href="/en/blog/news/523hshhshhshhs3331adc0" class="css-1ej">US could be on cusp of new Covid surge</a>

      <a data-bn-type="link" href="/en/blog/news/423hshhshhshhs3331adc0" class="css-1ej">Stop sharing your vaccine cards on social media</>
         <a data-bn-type="link" href="/en/blog/news/2222hshhshhshhs3331adc0" class="css-1ej">Italians can be fined up to $60,000 for selling the world's 'most dangerous' cheese</a>

      <a data-bn-type="link" href="/en/blog/news/2223hshhshhshhs3331adc0" class="css-1ej">The Masked Singer' reveals the identity of The Phoenix<a/>

     
   </div>
</div>
</div>`;
const cheerio = require('cheerio');
const $ = cheerio.load(html);
let list = [];
$('.css-content > a').each(function () {
  list.push($(this).text().trim());
});
console.log(list.filter((item) => Boolean(item)));

cheerio