Search code examples
node.jscsvtext-parsingbyte-order-markcharacter-set

Parsing of CSV file using Node/Express spits out weird \x001 codes


I'm using Node and Express to fetch a .CSV file from a URL that I want to parse. The process of downloading it works just fine.

But when I use csv-parser to parse the file the output in the console looks like this: enter image description here

Just tonnes of lines of weird looking byte code? If I use excel or numbers to open the CSV file regularly it works fine.

This is how the data in the csv file looks like: enter image description here

My goal is to use a csv parser to convert each row into an object - I've seen many examples of parsers doing this.

Here's the code from node:

const broadcasterController = require('./broadcasterController');
const https = require('https');
const fs = require('fs');
const parser = require('csv-parser');

exports.queryFi = async (io) => {
    // let today = new Date().toISOString().slice(0, 10);
    // let today = '2021-03-20';

    fetchInsidersCSV = async () => {
        //  Download a file and extract the destination
        function downloadFromUrl(url, dest) {
            return new Promise((resolve, reject) => {
                var file = fs.createWriteStream(dest);
                https.get(url, function (response) {
                    response.pipe(file);
                    file.on('finish', function () {
                        file.close();
                        resolve(dest);
                    });
                }).on('error', function (err) {
                    // Handle errors
                    fs.unlinkSync(dest);
                    reject(new Error('Download failed.'));
                });
            });
        }
        await downloadFromUrl(
            `https://marknadssok.fi.se/Publiceringsklient/sv-SE/Search/Search?SearchFunctionType=Insyn&Utgivare=&PersonILedandeSt%C3%A4llningNamn=&Transaktionsdatum.From=&Transaktionsdatum.To=&Publiceringsdatum.From=2021-04-01&Publiceringsdatum.To=2021-04-01&button=export&Page=1`,
            'bar.csv'
        );
    };

    try {
        const results = [];
        // crawl the web page and start att page 1
        await fetchInsidersCSV();

        fs.createReadStream('bar.csv')
            .pipe(parser({ separator: ';' }))
            .on('data', (data) => results.push(data))
            .on('end', () => {
                console.log(results);
            });

    } catch (error) {
        console.log(error);
    }
};

Could anyone please help me with a code solution where the output is correct?


Solution

  • It looks to me like that data is in utf-16 encoding. So if we specify this in our fs.createReadStream(), we should get the correct result:

    fs.createReadStream('bar.csv', { encoding: "utf-16le" })
        .pipe(parser({ separator: ';' }))
        .on('data', (data) => results.push(data))
        .on('end', () => {
            console.log(results);
        });
    

    With this setting, I see an output like so:

    [
      {
        Publiceringsdatum: '2021-04-01 23:59:28',
        Utgivare: 'Attana AB',
        'LEI-kod': '549300KAI93YCW5ISI45',
        'Anmälningsskyldig': 'Arne Nabseth',
        'Person i ledande ställning': 'Arne Nabseth',
        Befattning: 'Styrelseordförande',
        'Närstående': '',
        Korrigering: '',
        'Beskrivning av korrigering': '',
        'Är förstagångsrapportering': 'Ja',
        'Är kopplad till aktieprogram': '',
        'Karaktär': 'Avyttring',
        Instrumenttyp: 'Aktie',
        Instrumentnamn: 'Attana ',
        ISIN: 'SE0015222583',
        Transaktionsdatum: '2021-02-26 00:00:00',
        Volym: '80000',
        Volymsenhet: 'Antal',
        Pris: '1,6',
        Valuta: 'SEK',
        Handelsplats: 'NORDIC SME',
        Status: 'Aktuell',
        '': ''
      }
    ]