Last active
October 19, 2018 08:07
-
-
Save sakshamsaxena/d9eaf50d0067ff02f7f7c75b76b42d0a to your computer and use it in GitHub Desktop.
A simple JavaScript Snippet to get the list of all the links with titles on it's "Must Do Coding Questions" page.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// Extracted from "https://www.geeksforgeeks.org/must-do-coding-questions-for-companies-like-amazon-microsoft-adobe/" on April 7, 2018 | |
/* How To Use : | |
1. Install Node.js | |
2. Fire up your console and create a fresh directory and enter it. | |
3. Run `npm init -y && npm i superagent cheerio` | |
4. Save this file in that directory. | |
5. Run it with `node GFGExtractor.js` | |
*/ | |
/* | |
Required Modules | |
*/ | |
const request = require('superagent') | |
const cheerio = require('cheerio') | |
/* | |
Global Variables | |
*/ | |
var url, $ | |
/* | |
Main Application | |
*/ | |
url = 'https://www.geeksforgeeks.org/must-do-coding-questions-for-companies-like-amazon-microsoft-adobe/' | |
request | |
.get(url) | |
.end(function (err, res) { | |
// The HTML is returned with Content-Type "text/plain", hence it is added to the res.text key | |
$ = cheerio.load(res.text) | |
// $ now is exact equivalent to the jQuery object which consists of the entire DOM Tree. | |
// Extract the meat! | |
var titles = {} | |
$("p[align='center']").each(function(){ | |
var title = $(this).text().trim().replace(" :", "") | |
var list = $(this).next("ol") | |
var urls = [] | |
$(list).find("li").each(function() { | |
var o = {} | |
o.name = $(this).text().trim() | |
o.url = $(this).find("a").attr("href").trim() | |
urls.push(o) | |
}) | |
titles[title] = urls | |
}) | |
// Log the meat for now | |
console.log(titles) | |
}) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment