Sitemap parsing of Jekyll-powered sites

node v6.17.1
version: 1.0.0
This script parses the sitemap.xml of different Jekyll-powered sites to show the amount of URLs each websites consists of. The outcome was used for my Thesis presentation at the FH Hagenberg.
const Promise = require('bluebird'); const got = require('got'); const xml = require('xml2js').parseString; // The sites from which the sitemap.xml files are fetched const urls = [ '', '', '', ]; // Create an array of promises const promises = => got(`https://${url}/sitemap.xml`, { // Set the encoding to 'utf8' to not receive a Buffer encoding: 'utf8', }) .then(res => res.body) .then(body => new Promise((resolve, reject) => { // Parse the returned XML file xml(body, (err, json) => { if (err) { return reject(err); } return resolve(json); }); })) // Return a string containing the number of URL entries in each sitemap.xml .then(result => `${url} contains ${result.urlset.url.length} URL entries.`)); // Call Promise.all to wait until every sitemap.xml was fetched and parsed, // then console.log() their outcome Promise.all(promises) .then(results => results.forEach(entry => console.log(entry)));

no comments

    sign in to comment