Skip to content
Simple sitemap generator for .NET and .NET Core
C#
Branch: master
Clone or download
Latest commit 0442404 Jul 31, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
src Cleanup and refactor Jul 31, 2019
.gitattributes Initial commit Mar 12, 2013
.gitignore Update gitignore Mar 12, 2018
LICENSE.md rename file Jul 28, 2019
README.md Update README.md Jul 27, 2019
azure-pipelines.yml Set up CI with Azure Pipelines Nov 22, 2018

README.md

X.Web.Sitemap

NuGet version Part of awesome .NET Core

Simple sitemap generator for .NET and .NET Core You can download it from nuget.org at http://nuget.org/packages/xsitemap/

Usage example

Below is an example of basic usage in a non-testable manner

    class Program
    {    
        static void Main(string[] args)
        {
            var sitemap = new Sitemap();

            sitemap.Add(new Url
                {
                    ChangeFrequency = ChangeFrequency.Daily,
                    Location = "http://www.example.com",
                    Priority = 0.5,
                    TimeStamp = DateTime.Now
                });

            sitemap.Add(CreateUrl("http://www.example.com/link1"));
            sitemap.Add(CreateUrl("http://www.example.com/link2"));
            sitemap.Add(CreateUrl("http://www.example.com/link3"));
            sitemap.Add(CreateUrl("http://www.example.com/link4"));
            sitemap.Add(CreateUrl("http://www.example.com/link5"));


            //Save sitemap structure to file
            sitemap.Save(@"d:\www\example.com\sitemap.xml");

            //Split a large list into pieces and store in a directory
            sitemap.SaveToDirectory(@"d:\www\example.com\sitemaps");

            //Get xml-content of file
            Console.Write(sitemap.ToXml());

            Console.ReadKey();
        }

        private static Url CreateUrl(string url)
        {
            return new Url
                {
                    ChangeFrequency = ChangeFrequency.Daily,
                    Location = url,
                    Priority = 0.5,
                    TimeStamp = DateTime.Now
                };
        }
    }

Below is a more comprehensive example that demonstrates how to create many sitemaps and how to add them to a sitemap index file in a unit-testable fashion.

	public class SitemapGenerationWithSitemapIndexExample
    {
        private readonly ISitemapGenerator _sitemapGenerator;
        private readonly ISitemapIndexGenerator _sitemapIndexGenerator;

        //--this is a bogus interface defined in this example to simulate something you might use to get a list of URls from your CMS or something like that
        private readonly IWebsiteUrlRetriever _websiteUrlRetriever;

        //--and IoC/Dependency injection framework should inject this in
        public SitemapGenerationWithSitemapIndexExample(
            ISitemapGenerator sitemapGenerator, 
            ISitemapIndexGenerator sitemapIndexGenerator, 
            IWebsiteUrlRetriever websiteUrlRetriever)
        {
            _sitemapGenerator = sitemapGenerator;
            _sitemapIndexGenerator = sitemapIndexGenerator;
            _websiteUrlRetriever = websiteUrlRetriever;
        }

        //--this is an example showing how you might take a large list of URLs of different kinds of resources and build both a bunch of sitemaps (depending on
        //  how many URls you have) as well as a sitemap index file to go with it
        public void GenerateSitemapsForMyEntireWebsite()
        {
            //--imagine you have an interface that can return a list of URLs for a resource that you consider to be high priority -- for example, the product detail pages (PDPs)
            //  of your website
            var productPageUrlStrings = _websiteUrlRetriever.GetHighPriorityProductPageUrls();

            //--build a list of X.Web.Sitemap.Url objects and determine what is the appropriate ChangeFrequency, TimeStamp (aka "LastMod" or date that the resource last had changes),
            //  and the a priority for the page. If you can build in some logic to prioritize your pages then you are more sophisticated than most! :)
            var allUrls = productPageUrlStrings.Select(url => new Url
            {
                //--assign the location of the HTTP request -- e.g.: https://www.somesite.com/some-resource
                Location = url,
                //--let's instruct crawlers to crawl these pages monthly since the content doesn't change that much
                ChangeFrequency = ChangeFrequency.Monthly,
                //--in this case we don't know when the page was last modified so we wouldn't really set this. Only assigning here to demonstrate that the property exists.
                //  if your system is smart enough to know when a page was last modified then that is the best case scenario
                TimeStamp = DateTime.UtcNow,
                //--set this to between 0 and 1. This should only be used as a relative ranking of other pages in your site so that search engines know which result to prioritize
                //  in SERPS if multiple pages look pertinent from your site. Since product pages are really important to us, we'll make them a .9
                Priority = .9
            }).ToList();

            var miscellaneousLowPriorityUrlStrings = _websiteUrlRetriever.GetMiscellaneousLowPriorityUrls();
            var miscellaneousLowPriorityUrls = miscellaneousLowPriorityUrlStrings.Select(url => new Url
            {
                Location = url,
                //--let's instruct crawlers to crawl these pages yearly since the content almost never changes
                ChangeFrequency = ChangeFrequency.Yearly,
                //--let's pretend this content was changed a year ago
                TimeStamp = DateTime.UtcNow.AddYears(-1),
                //--these pages are super low priority
                Priority = .1
            }).ToList();

            //--combine the urls into one big list. These could of course bet kept seperate and two different sitemap index files could be generated if we wanted
            allUrls.AddRange(miscellaneousLowPriorityUrls);

            //--pick a place where you would like to write the sitemap files in that folder will get overwritten by new ones
            var targetSitemapDirectory = new DirectoryInfo("\\SomeServer\\some_awesome_file_Share\\sitemaps\\");

            //--generate one or more sitemaps (depending on the number of URLs) in the designated location.
            var fileInfoForGeneratedSitemaps = _sitemapGenerator.GenerateSitemaps(allUrls, targetSitemapDirectory);

            var sitemapInfos = new List<SitemapInfo>();
            var dateSitemapWasUpdated = DateTime.UtcNow.Date;
            foreach (var fileInfo in fileInfoForGeneratedSitemaps)
            {
                //--it's up to you to figure out what the URI is to the sitemap you wrote to the file sytsem. In this case we are assuming that the directory above
                //  has files exposed via the /sitemaps/ subfolder of www.mywebsite.com
                var uriToSitemap = new Uri($"https://www.mywebsite.com/sitemaps/{fileInfo.Name}");
               
                sitemapInfos.Add(new SitemapInfo(uriToSitemap, dateSitemapWasUpdated));
            }

            //--now generate the sitemap index file which has a reference to all of the sitemaps that were generated. 
            _sitemapIndexGenerator.GenerateSitemapIndex(sitemapInfos, targetSitemapDirectory, "sitemap-index.xml");

            //-- After this runs you'll want to make sure your robots.txt has a reference to the sitemap index (at the bottom of robots.txt) like this: 
            //  "Sitemap: https://www.mywebsite.com/sitemaps/sitemap-index.xml"
            //  You could do this manually (since this may never change) or if you are ultra-fancy, you could dynamically update your robots.txt with the names of the sitemap index
            //  file(s) you generated

        }


        //--some bogus interface that is meant to simulate pulling urls from your CMS/website
        public interface IWebsiteUrlRetriever
        {
            List<string> GetHighPriorityProductPageUrls();
            List<string> GetMiscellaneousLowPriorityUrls();
        }
    }
You can’t perform that action at this time.