Nodejs cheerio 拿走所有的文字

Question

我有以下 html 页面代码：

<div class="textwidget">
  <p>
    <strong>Monday-Tuesday (Feb 21-22)</strong>
    <br />

    <a href="https://dramaday.net/moonshine/">Moonshine</a> 15-16 (KBS2)<br />
    <a href="https://dramaday.net/ghost-doctor/">Ghost Doctor</a> 15-16 (tvN)<br />

    <strong>Wednesday-Thursday (Feb 23-24)</strong>
    <br />

    <a href="https://dramaday.net/rookie-cops/">Rookie Cops</a> 9-10
    (Disney+)<br />
    <a href="https://dramaday.net/grid/">Grid</a> 2 (Disney+)<br />
    <a href="https://dramaday.net/thirty-nine/">Thirty Nine</a> 3-4 (JTBC)<br />

    Kill Heel 1-2 (tvN)<br /> <!-- It is not taken -->
    Sponsor 1-2 (MBN)<br /> <!-- It is not taken -->

    <strong>Friday-Sunday (Feb 25-27)</strong>
    <br />

    Juvenile Justice 1-10 (Netflix)<br /> <!-- It is not taken -->

    <a href="https://dramaday.net/through-the-darkness/"
      >Through the Darkness</a
    >
    7-8 (SBS)<br />
    <a href="https://dramaday.net/twenty-five-twenty-one/"
      >Twenty Five Twenty One</a
    >
    5-6 (tvN)<br />
    <a href="https://dramaday.net/forecasting-love-and-weather/"
      >Forecasting Love and Weather</a
    >
    5-6 (JTBC)<br />
    <a href="https://dramaday.net/young-lady-and-gentleman/"
      >Young Lady and Gentleman</a
    >
    43-44 (KBS2)<br />
    <a href="https://dramaday.net/love-ft-marriage-and-divorce/"
      >Love (ft. Marriage and Divorce) S3</a
    >
    1-2 (CSTV)
  </p>
</div>

我有以下js代码从页面获取信息：

async function getData() {
  let element = [];

  try {
    const { data } = await axios.get("https://dramaday.net");
    const $ = cheerio.load(data);
    let day = 0;
    let date = ""

    $("div.textwidget > p >").each((_idx, el) => {
      const text = $(el).text();

      if(text.includes("Monday-Tuesday")){
        day = 0;
        date = text.replace('(','').replace(')','').split(' ')
      } else if(text.includes("Wednesday-Thursday")){
        day = 1;
        date = text.replace('(','').replace(')','').split(' ')
      } else if(text.includes("Friday-Sunday")){
        day = 2;
        date = text.replace('(','').replace(')','').split(' ')
      } else  {
        const obj = {
          name: text,
          day,
          date
        }

        element.push(obj);
      }
    });

    return element;
  } catch (error) {
    throw error;
  }
}

问题是不包含标签的文本不会被采用。

请参阅 html 代码中的示例，其中显示“未使用”。

我得到的结果是这样的，你可以看到有很多空名，我认为这是由于 br 标签造成的。

我可以通过将 else 替换为条件 text! == '' 的 else if 来解决它，但我没有解决文本未包含在任何标记中的问题。除了我无法在 a 标签之后获取剧集编号和频道的文本之外。

你能帮帮我吗？

[
  { name: '', day: 0, date: [ 'Monday-Tuesday', 'Feb', '21-22' ] },
  {
    name: 'Moonshine',
    day: 0,
    date: [ 'Monday-Tuesday', 'Feb', '21-22' ]
  },
  { name: '', day: 0, date: [ 'Monday-Tuesday', 'Feb', '21-22' ] },
  {
    name: 'Ghost Doctor',
    day: 0,
    date: [ 'Monday-Tuesday', 'Feb', '21-22' ]
  },
  { name: '', day: 0, date: [ 'Monday-Tuesday', 'Feb', '21-22' ] },
  { name: '', day: 1, date: [ 'Wednesday-Thursday', 'Feb', '23-24' ] },
  {
    name: 'Rookie Cops',
    day: 1,
    date: [ 'Wednesday-Thursday', 'Feb', '23-24' ]
  },
  { name: '', day: 1, date: [ 'Wednesday-Thursday', 'Feb', '23-24' ] },
  {
    name: 'Grid',
    day: 1,
    date: [ 'Wednesday-Thursday', 'Feb', '23-24' ]
  },
  { name: '', day: 1, date: [ 'Wednesday-Thursday', 'Feb', '23-24' ] },
  {
    name: 'Thirty Nine',
    day: 1,
    date: [ 'Wednesday-Thursday', 'Feb', '23-24' ]
  },
  { name: '', day: 1, date: [ 'Wednesday-Thursday', 'Feb', '23-24' ] },
  { name: '', day: 1, date: [ 'Wednesday-Thursday', 'Feb', '23-24' ] },
  { name: '', day: 1, date: [ 'Wednesday-Thursday', 'Feb', '23-24' ] },
  { name: '', day: 2, date: [ 'Friday-Sunday', 'Feb', '25-27' ] },
  { name: '', day: 2, date: [ 'Friday-Sunday', 'Feb', '25-27' ] },
  {
    name: 'Through the Darkness',
    day: 2,
    date: [ 'Friday-Sunday', 'Feb', '25-27' ]
  },
  { name: '', day: 2, date: [ 'Friday-Sunday', 'Feb', '25-27' ] },
  {
    name: 'Twenty Five Twenty One',
    day: 2,
    date: [ 'Friday-Sunday', 'Feb', '25-27' ]
  },
  { name: '', day: 2, date: [ 'Friday-Sunday', 'Feb', '25-27' ] },
  {
    name: 'Forecasting Love and Weather',
    day: 2,
    date: [ 'Friday-Sunday', 'Feb', '25-27' ]
  },
  { name: '', day: 2, date: [ 'Friday-Sunday', 'Feb', '25-27' ] },
  {
    name: 'Young Lady and Gentleman',
    day: 2,
    date: [ 'Friday-Sunday', 'Feb', '25-27' ]
  },
  { name: '', day: 2, date: [ 'Friday-Sunday', 'Feb', '25-27' ] },
  {
    name: 'Love (ft. Marriage and Divorce) S3',
    day: 2,
    date: [ 'Friday-Sunday', 'Feb', '25-27' ]
  }
]

Answer 1

var element = [];

var day = -1, date = '', name = '';
$("div.textwidget > p").html().split('<br>').forEach(function (row) {
  var el = $('<div>').append(row);
  var text = el.text();
  text = text.replace(/^\s+|\s+$/g, ''); // trim
  text = text.replace(/\s+/g, ' ');
  if (el.find('strong').size()) {
    day += 1;
    date = text.replace('(','').replace(')','').split(' ');
    return;
  }
  name = text;
  element.push({
    name,
    day,
    date
  });
})

console.log(element);

Nodejs cheerio 拿走所有的文字

Nodejs cheerio take all the texts

javascript

node.js

json

web-scraping

cheerio