我如何过滤我的网络刮擦结果，没有 /n或选项卡

Question

我正在从工作市场网站上刮擦数据。我的刮擦返回了我想要的结果，但充满了 /n， /t或大量间距。如何过滤结果以获取内容？

这是我的代码：

async function start() {

    const browser = await puppeteer.launch({
        headless: true,
        defaultViewport: null,
        args: ['--ignore-certificate-errors']
    });

    var name = ["Job Name"];
    var country = ["Country"];
    var company = ["Company Name"];
    var type = ["Job Type"];
    var salary = ["Salary"];
    var skills = ["Skills Require"];
    var desc = ["Job Description"];
    var req = ["Job Requirements"];
    var resp = ["Job Responsibility"];
    var industry = ["Industry"];

    for (var j = 1; j < 2; j++) {

        const page = await browser.newPage();
        page.setDefaultNavigationTimeout(0);

        await page.goto('https://startupjobs.asia/job/search?q=&job-list-dpl-page=' + j, {
            waitUntil: "networkidle2",
            timeout: 3000000
        });

        console.log('browsing page ' + j);

        for (var i = 1; i < 31; i++) {

            await page.waitForXPath("/html/body/div[1]/div[3]/div[1]/div/div[1]/ul/li[" + i + "]/div/div[1]/div/h5/a")
            var b = await page.$x("/html/body/div[1]/div[3]/div[1]/div/div[1]/ul/li[" + i + "]/div/div[1]/div/h5/a")
            await b[0].click();

            const elementsToFind = [
                { xpath: "/html/body/div[1]/div[3]/div[1]/div/div[1]/ul/li[" + i + "]/div/div[1]/div/h5/a", propName: 'job_name' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[1]/div[2]/div/h6[2]/a', propName: 'country' },
                { xpath: "/html/body/div[1]/div[3]/div[1]/div/div[1]/ul/li[" + i + "]/div/div[1]/div/p[1]/a", propName: 'company' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[2]/div[1]/div[3]/p', propName: 'job_type' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[2]/div[1]/div[1]/p', propName: 'salary' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[2]/div[1]/div[4]/p', propName: 'skills' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[2]/div[2]/div[1]/div', propName: 'job_description' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[2]/div[2]/div[3]/div', propName: 'job_requirement' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[2]/div[2]/div[2]/div', propName: 'job_responsibility' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[2]/div[1]/div[2]/p', propName: 'industry' },
                // ...
            ];
            /*const elementsToFind2 = [
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[3]/div[1]/div[1]/p/a',      propName2: 'website' },
                { xpath: '/html/body/div[1]/div[3]/div[2]/div[2]/div[1]/div[3]/div[2]/div[1]/div',      propName2: 'about' },
                // ...
            ];*/

            var results = {};

            for (var { xpath, propName } of elementsToFind) {
                await page.waitForXPath(xpath);
                var [el] = await page.$x(xpath);
                results[propName] = !el ? 'Not Found' : await (await el.getProperty('textContent')).jsonValue();
            }

            name.push(results['job_name']);
            country.push(results['country']);
            company.push(results['company']);
            type.push(results['job_type']);
            salary.push(results['salary']);
            skills.push(results['skills']);
            desc.push(results['job_description']);
            req.push(results['job_requirement']);
            resp.push(results['job_responsibility']);
            industry.push(results['industry']);

            //await page.evaluate(() => document.querySelector("#suj-single-jobdetail-wrapper > div.detail-body > div.row > div.col.s12.tabs-wrapper.suj-company-review-tabs-wrapper > ul > li:nth-child(2) > a").click())            
        }
        await page.close();
    }

    await browser.close();

我得到的结果是：

'\ n' + '\ n' + '兼职\ n' + '| \ n' + '\ n' + '临时\ n' + '| \ n' + '\ n' + '合同\ n' + '

我希望这只是兼职，临时和合同。

Answer 1

您可以使用REGEX \ s+与字符串中的所有Whitespace（Space，Tab和Newline）匹配，并使用 替换 。然后，您可以代码> 带有逗号的|字符的替换的结果 comma：

let s = '\n' + ' \n' + ' Part-Time \n' + ' | \n' + ' \n' + ' Temporary \n' + ' | \n' + ' \n' + ' Contract \n';

// remove whitespace
s = s.replace(/\s+/g, '')

// various output options
console.log(s.split('|'))
console.log(s.replace(/\|/g, ', '))   // for older browsers
console.log(s.replaceAll('|', ', '))  // for more modern browsers