Parser for XML Sitemaps to be used with Robots.txt and web crawlers


Keywords
parse, sitemap, xml, robots.txt, sitemaps, crawlers, webcrawler, javascript, sitemap-xml
License
MIT
Install
npm install sitemapper@3.1.11

Documentation

Sitemap-parser

Build Status Monthly Downloads npm version dependencies Status Inline docs

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

Examples in ES6

import Sitemapper from 'sitemapper';

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

Google.fetch()
  .then(data => console.log(data.sites))
  .catch(error => console.log(error));


// or


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

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

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