@public-square/sitemapper v3.2.5

Sitemap-parser

Parse through a sitemaps xml to get all the urls for your crawler.

Version 2

Installation

npm install sitemapper --save

Simple Example

const Sitemapper = require('sitemapper');

const sitemap = new Sitemapper();

sitemap.fetch('https://wp.seantburke.com/sitemap.xml').then(function(sites) {
  console.log(sites);
});

Examples in ES6

import Sitemapper from 'sitemapper';

(async () => {
  const Google = new Sitemapper({
    url: 'https://www.google.com/work/sitemap.xml',
    timeout: 15000, // 15 seconds
  });

  try {
    const { sites } = await Google.fetch();
    console.log(sites);
  } catch (error) {
    console.log(error);
  }
})();

// or

const sitemapper = new Sitemapper();
sitemapper.timeout = 5000;

sitemapper.fetch('https://wp.seantburke.com/sitemap.xml')
  .then(({ url, sites }) => console.log(`url:${url}`, 'sites:', sites))
  .catch(error => console.log(error));

Options

You can add options on the initial Sitemapper object when instantiating it.

• lastmod: (Number) - Timestamp of the minimum lastmod value allowed for returned urls
• requestHeaders: (Object) - Additional Request Headers (e.g. User-Agent)
• timeout: (Number) - Maximum timeout in ms for a single URL. Default: 15000 (15 seconds)
• url: (String) - Sitemap URL to crawl
• debug: (Boolean) - Enables/Disables debug console logging. Default: False
• concurrency: (Number) - Sets the maximum number of concurrent sitemap crawling threads. Default: 10
• retries: (Number) - Sets the maximum number of retries to attempt in case of an error response (e.g. 404 or Timeout). Default: 0
• rejectUnauthorized: (Boolean) - If true, it will throw on invalid certificates, such as expired or self-signed ones. Default: True

const sitemapper = new Sitemapper({
  url: 'https://art-works.community/sitemap.xml',
  rejectUnauthorized: true,
  timeout: 15000,
  requestHeaders: {
    'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:81.0) Gecko/20100101 Firefox/81.0'
  }
});

An example using all available options:

const sitemapper = new Sitemapper({
  url: 'https://art-works.community/sitemap.xml',
  timeout: 15000,
  requestHeaders: {
    'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:81.0) Gecko/20100101 Firefox/81.0'
  },
  debug: true,
  concurrency: 2,
  retries: 1,
});

Examples in ES5

var Sitemapper = require('sitemapper');

var Google = new Sitemapper({
  url: 'https://www.google.com/work/sitemap.xml',
  timeout: 15000 //15 seconds
});

Google.fetch()
  .then(function (data) {
    console.log(data);
  })
  .catch(function (error) {
    console.log(error);
  });


// or


var sitemapper = new Sitemapper();

sitemapper.timeout = 5000;
sitemapper.fetch('https://wp.seantburke.com/sitemap.xml')
  .then(function (data) {
    console.log(data);
  })
  .catch(function (error) {
    console.log(error);
  });

Version 1

npm install sitemapper@1.1.1 --save

Simple Example

var Sitemapper = require('sitemapper');

var sitemapper = new Sitemapper();

sitemapper.getSites('https://wp.seantburke.com/sitemap.xml', function(err, sites) {
    if (!err) {
     console.log(sites);
    }
});