Home > database >  Nodejs cheerio take all the texts
Nodejs cheerio take all the texts

Time:02-26

I have the following html code of the page:

<div >
  <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>

I have the following js code to get information from the page:

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;
  }
}

The problem is that texts that do not contain a tag are not taken.

See for example in the html code, where it says "It is not taken".

The result I get is this, as you can see there are a lot of empty names, I think it's due to the br tag.

I can solve it by replacing else with an else if with condition text! == '', but I don't solve the problem of text not being included in any tag. Besides the fact that I can't get the text after the a tag which would be the episode number and channel.

Can you give me a hand?

[
  { 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' ]
  }
]

CodePudding user response:

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);
  • Related