Home

Index

How to use the load function from cheerio

Find comprehensive JavaScript cheerio.load code examples handpicked from public code repositorys.

cheerio.load is a method that creates a jQuery-style DOM manipulator for a given HTML string or DOM.

webpack.config.js

66
67
68
69
70
71
72
73
74
75
if ('development' === wpMode) {
    // Locate all E2E cases
    const caseFiles = [];
    fs.readdirSync(path.resolve(__dirname, 'test/html/')).forEach(file => {
        const absPath = path.resolve(__dirname, 'test/html/', file);
        const caseHtml = cheerio.load(fs.readFileSync(absPath));
        const publicName = file.replace('.tpl', '');

        plugins.push(new HtmlWebpackPlugin({
            template: path.resolve(__dirname, 'test/html/', file),

316

673

194

+ 5 other calls in file

build.js

GitHub: teadocs/teadocs

176
177
178
179
180
181
182
183
184
185
  })
  return liParents.reverse()
}

_buildErrorPage(errorFrameHtml) {
  let $ = cheerio.load(errorFrameHtml, { decodeEntities: false })
  let p404 = {
    title: "页面未找到 - " + this.config.doc.name,
    path: this.buildDir + "/teadocs_error_pages/404.html",
    description: "404错误！该页面未找到，试试从左边菜单栏访问别的页面，或者从左上角搜索你想要的内容。"

157

+ 7 other calls in file

How does cheerio.load work?

cheerio.load() is a function in the Cheerio library that loads an HTML string into a jQuery-like DOM representation, allowing users to manipulate and traverse the DOM using familiar jQuery syntax. When invoked, it returns a Cheerio instance which can be used to perform various operations on the HTML, such as selecting and manipulating DOM elements, querying for attributes or content, and more.

extractor.js

GitHub: ahkimkoo/neocrawler

179
180
181
182
183
184
185
186
187
188
extractor.prototype.extract = function(crawl_info){
    if(crawl_info['origin']['format']=='binary')return crawl_info;
    var extract_rule = this.spiderCore.spider.getDrillerRule(crawl_info['origin']['urllib'],'extract_rule');

    if(crawl_info['origin']['drill_rules']||extract_rule['rule']){
        var $ = cheerio.load(crawl_info['content']);
    }

    if(crawl_info['origin']['drill_rules']){
        if(crawl_info['drill_link']){

151

+ 3 other calls in file

prepare-docs

GitHub: purecloudlabs/iframe-coordinator

17
18
19
20
21
22
23
24
25
26
  htmlFiles.forEach(processFile);
}

function processFile(path) {
  const originalText = fs.readFileSync(path, 'utf8');
  let $ = cheerio.load(originalText);

  hideExternals($);
  if (process.env.CDN_ROOT) {
    addCdnPrefix($, process.env.CDN_ROOT);

+ 3 other calls in file

Ai Example

1
2
3
4
const cheerio = require("cheerio");
const html = " Hello, world! ";
const $ = cheerio.load(html);
console.log($("h1").text()); // Output: "Hello, world!"

In this example, we require the cheerio library and create a string variable html containing some HTML content. We then use cheerio.load(html) to create a Cheerio object, $, from the HTML string. Finally, we use $ to select the h1 element and log its text content to the console.

reptile.js

GitHub: geekape/geek-navigation

25
26
27
28
29
30
31
32
33
34
}

async start() {
  request(this.url, async (error, res, body) => {
    if (!error && res.statusCode == 200) {
      const $ = cheerio.load(body)
      const $cardBlock = $('.panel')

      for (let i = 0; i < $cardBlock.length; i++) {
        const secondCategoryName = $('.panel-title.card').eq(i).text().trim()

424

+ 5 other calls in file

index.js

GitHub: matthewmueller/x-ray

210
211
212
213
214
215
216
217
218
  }
}

function load (html, url) {
  html = html || ''
  var $ = html.html ? html : cheerio.load(html, { decodeEntities: false })
  if (url) $ = absolutes(url, $)
  return $
}

372

110

+ 5 other calls in file

build.js

GitHub: tamagui/tamagui

13
14
15
16
17
18
19
20
21
22
fs.writeFileSync(path.join(rootDir, 'src', 'index.ts'), '', 'utf-8')

icons.forEach((i) => {
  const svg = fs.readFileSync(i, 'utf-8')
  const id = path.basename(i, '.svg')
  const $ = cheerio.load(svg, {
    xmlMode: true,
  })
  const fileName = path.basename(i).replace('.svg', '.tsx')
  const location = path.join(rootDir, 'src/icons', fileName)

241

plugin.js

GitHub: dablelv/go-coding-advice

336
337
338
339
340
341
342
343
344
345
346
347
    }
    return html;
}


function start(bookIns, page) {
    var $ = cheerio.load(page.content);
    var modifyHeader = !/<!--[ \t]*ex_nolevel[ \t]*-->/.test(page.content)


    // 处理toc相关，同时处理标题和id
    var tocs = handlerTocs($, page, modifyHeader);

+ 9 other calls in file

qa.js

GitHub: mashirozx/RSSHub

12
13
14
15
16
17
18
19
20
21
const response = await got({
    method: 'get',
    url: currentUrl,
});

const $ = cheerio.load(response.data);

let items = $('a.question-title')
    .slice(0, ctx.query.limit ? parseInt(ctx.query.limit) : 25)
    .toArray()

+ 3 other calls in file

bot.js

GitHub: losparviero/Truecaller-Telegram-Bot

97
98
99
100
101
102
103
104
105
106
  output: "HTML",
};
var sn = truecallerjs.searchNumber(searchData);
sn.then(async function (response) {
  //console.log(response);
  const $ = cheerio.load(response);
  let name = "";
  $("td").each(function (i, el) {
    if ($(this).text() === "name") {
      if ($(this).next().text() !== "") {

+ 4 other calls in file

server.js

GitHub: ptcrealitylab/vuforia-spatial-edge-server

1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
html = html.replace('objectDefaultFiles/envelope.js', level + 'objectDefaultFiles/envelope.js');
html = html.replace('objectDefaultFiles/envelopeContents.js', level + 'objectDefaultFiles/envelopeContents.js');

html = html.replace('objectDefaultFiles/gl-worker.js', level + 'objectDefaultFiles/gl-worker.js');

var loadedHtml = cheerio.load(html);
var scriptNode = '<script src="' + level + 'objectDefaultFiles/object.js"></script>';
scriptNode += '<script src="' + level + 'objectDefaultFiles/pep.min.js"></script>';

// inject the server IP address, but don't inject the objectKey and frameKey, as those come from the editor

+ 9 other calls in file

plugins.js

GitHub: Seeroy/kubek-minecraft-dashboard

13
14
15
16
17
18
19
20
21
22
if (error) {
  return console.error(error);
}

if (!error && res.statusCode == 200) {
  const $ = cheerio.load(body);
  $(".results-name").each(function (i, plugin) {
    if (typeof (plugin.parent.parent.children[1].children[1].children[1]) !== "undefined") {
      var pluginn = {
        name: plugin.children[1].children[0].data,

+ 5 other calls in file

common.js

GitHub: mrvautin/squido

345
346
347
348
349
350
351
352
353
354
355
    return file;
};


const builtToc = (html) => {
    const toc = {};
    const $ = cheerio.load(html);
    $('h1, h2, h3, h4, h5, h6').map((_, element) => {
        if(!toc[element.name]){
            toc[element.name] = [];
        }

+ 4 other calls in file

parse.js

GitHub: chrisburnell/chrisburnell.com

4
5
6
7
8
9
10
11
12
13
14
15
	return input.replace(/\s{2,}/g, "").replace(/\'/g, '"')
}


module.exports = async (value, outputPath) => {
	if (outputPath && outputPath.endsWith(".html")) {
		const $ = cheerio.load(value)


		// We have to process headings from table of contents before adding
		// the permalink to them later, or the links will include the text of
		// the permalink.

test-data.js

GitHub: butaca/covid19uy.com

415
416
417
418
419
420
421
422
423
424
    dataTotalTests += (todayData.tests || todayData.positives);
}

return request(reportURL).then(reportData => {

    const html = cheerio.load(reportData.replace(/[\n]/g, ''));

    const text = html('.Page-document p').text();

    function parseReportNumber(text, regExp) {

+ 4 other calls in file

templatize.js

GitHub: BCIT-LTC/dewordify

16
17
18
19
20
21
22
23
24
25
function putIntoTemplate(page, templatePath) {
	if (!templateHTML) {
		templateHTML = loadTemplate(templatePath);
	}
	
	var $template = cheerio.load(templateHTML, cheerioOptions);
	var $ = cheerioLoader.load(page);
	var title = $("h1").text();
	var $primaryTarget = $template("content");
	var $secondaryTarget = $template(".container");

.eleventy.js

GitHub: thiagomgd/geekosaurblog

20
21
22
23
24
25
26
27
28
29
30
  const hasBody = /<\s*body(\w|\s|=|"|-)*>/gm;
  return hasBody.test(content);
}


async function replaceSpecialLinks(content, options) {
  const $ = cheerio.load(content);
  // TODO: only block links
  const replace = ['bookmark', 'embed','textTweet'];
  let links = $("a").filter((i, el) => {
    const text = $(el).text();

gh-elternportal.js

GitHub: philippdormann/elternportal-api

46
47
48
49
50
51
52
53
54
55
	removeScriptTypeAttributes: true
},
parsers: {
	get_kids: (html, callback = () => {}) => {
		html = minify(html, this.Parsing_Interface.minify_options);
		let cheerio2 = cheerio.load(html);
		let kids = [];
		cheerio2('.pupil-selector .form-group .form-control').each((i, elem) => {
			kids.push({ name: cheerio2(elem).text(), id: cheerio2(elem).val() });
		});

+ 131 other calls in file

smp.js

GitHub: cnshsliu/smp.nvim

534
535
536
537
538
539
540
541
542
543
try {
	const options = {
		timeout: 5000,
	};
	const { payload } = await Wreck.get(url, options);
	const $ = Cheerio.load(payload.toString());
	const title = $('title').text();
	return title;
} catch (err) {
	if (err.isBoom && err.output.statusCode === 504) {

+ 3 other calls in file

null.js

GitHub: NEXUSAT12/Xiao-MD-2

1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
    })
}


async function mediafire(url) {
let query = await axios.get(url) 
let cher = cheerio.load(query.data)
let hasil = []
let link = cher('a#downloadButton').attr('href')
let size = cher('a#downloadButton').text().replace('Download', '').replace('(', '').replace(')', '').replace('\n', '').replace('\n', '').replace(' ', '')
let seplit = link.split('/')

+ 359 other calls in file

Other functions in cheerio

Sorted by popularity

cheerio.load is the most popular function in cheerio (6167 examples)

Other popular packages:

Home

About