Custom Sitemap.xml generator in Optimizely CMS 12

This is a step by step guide to generate sitemap.xml file for all the sites in optimizely cms 12. The sitemaps are generated under wwwroot/sitemaps with the name of the site configured.

Step 1: Add a new field in Home Page to store the name of the sitemap file

Step 2: Create an interface for Sitemap generator service

Step 3: Implement the interface with sitemap generation logic

Step 4: Register the Service in startup.cs

Step 5: Create a scheduled job that will run the sitemap generator service

Step 6:  Create a Controlller that will serve sitemap

Step 7: Access the sitemap using the the url for example https://localhost:5000/seo-sitemap.xml

Home.cs

namespace CustomSitemap.Web.Pages
{
    [ContentType(DisplayName = "Home Page", GroupName = "Corporate", GUID = "8F0896B1-E3F2-4E8C-81AC-4FE52C519402")]
    public class HomePage : PageData
    {        
        [Display(Name = "SEO sitemap.xml file name",
            Description = "Provide meaning full name for SEO sitemap like site-sitemap.xml",
          GroupName = SystemTabNames.Settings,
          Order = 550)]
        public virtual string SitemapFileName { get; set; }
    }
}

ISitemapGeneratorService.cs

namespace CustomSitemap.Web.Business.Sitemap
{
    public interface ISitemapGeneratorService
    {
        IEnumerable<SiteDefinition> GetAllSites();
        bool GenerateSitemaps();
        void DeleteSitemaps();
    }
}

SitemapGeneratorService.cs

using EPiServer.Filters;
using EPiServer.Web;
using EPiServer.Web.Routing;
using EPiServer.Logging;
using System.Globalization;
using CustomSitemap.Web.Business.Extensions;

namespace CustomSitemap.Web.Business.Sitemap
{
 /// <summary>
/// Get the site names from configuration and generate sitemap with the sitename and save to wwwroot/sitemaps
/// </summary>    
public class SitemapGeneratorService : ISitemapGeneratorService
    {
        private readonly IContentLoader _contentLoader;
        private readonly IContentRepository _contentRepository;
        private readonly UrlResolver _urlResolver;
        private readonly ISiteDefinitionRepository _siteDefinitionRepository;
        private readonly ILanguageBranchRepository _languageBranchRepository;
        private readonly IWebHostEnvironment _webHostingEnvironment;
        private readonly EPiServer.Logging.ILogger _logger;

        /// <summary>
        /// constructor
        /// </summary>
        /// <param name="contentLoader"></param>
        /// <param name="urlResolver"></param>
        /// <param name="siteDefinitionRepository"></param>
        public SitemapGeneratorService(
            IContentLoader contentLoader,
            IContentRepository contentRepository,
            UrlResolver urlResolver,
            ISiteDefinitionRepository siteDefinitionRepository,
            ILanguageBranchRepository languageBranchRepository,
            IWebHostEnvironment webHostingEnvironment) 
        {
            _contentLoader = contentLoader;
            _contentRepository = contentRepository;
            _urlResolver = urlResolver;
            _siteDefinitionRepository = siteDefinitionRepository;
            _languageBranchRepository = languageBranchRepository;
            _webHostingEnvironment = webHostingEnvironment;
            _logger = LogManager.GetLogger(typeof(SitemapGeneratorService));
        }

        /// <summary>
        /// List all the sites created in optimizely cms
        /// </summary>
        /// <returns></returns>
        public IEnumerable<SiteDefinition> GetAllSites()
        {
            return _siteDefinitionRepository.List();
        }
        
        public void DeleteSitemaps()
        {
            // Get the path to the wwwroot folder
            var wwwrootPath = _webHostingEnvironment.WebRootPath;
            
            // Check if the directory exists
            if (!Directory.Exists(wwwrootPath))
                return;

            // Get the path for sitemap files wwwroot/sitemaps
            var sitemapsPath = Path.Combine(_webHostingEnvironment.WebRootPath, "sitemaps");            
            var sitemapFiles = Directory.GetFiles(sitemapsPath, "*sitemap.xml", SearchOption.TopDirectoryOnly);

            foreach (var file in sitemapFiles)
            {
                try
                {
                    // Delete each file
                    File.Delete(file);
                    _logger.Warning($"Deleted: {file}");
                }
                catch (Exception ex)
                {
                    // Log the error or handle it as needed
                    _logger.Error($"Error deleting file {file}: {ex.Message}");
                }
            }
        }

        public bool GenerateSitemaps()
        {
            try
            {
                //Delete already created sitemap files
                DeleteSitemaps();

                // Iterate over all sites and generate sitemaps
                foreach (var siteDefinition in GetAllSites())
                {
                    //get the start page for the current site
                    var startPage = _contentLoader.Get<PageData>(siteDefinition.StartPage);                    
                    
                    //get the url of the host
                    var primaryHostUrl = siteDefinition.Hosts.FirstOrDefault(host => host.Type == HostDefinitionType.Primary).Url;

                    //generate sitemap
                    var sitemapContent = GenerateSitemapForSite(startPage, primaryHostUrl);

                    // Save the generated sitemap.xml to a specified location
                    var sitemapPath = Path.Combine(_webHostingEnvironment.WebRootPath, "sitemaps", siteDefinition.Name.Replace(" ", "-").ToLower() + "-sitemap.xml");
                    File.WriteAllText(sitemapPath, sitemapContent);
                }

                return true;
            }
            catch
            {
                return false;
            }
        }

        private string GenerateSitemapForSite(PageData startPage, Uri primaryHostUrl)
        {
            var publishedFilter = new FilterPublished();
            var accessFilter = new FilterAccess();
            var sitemapEntries = new List<string>();

            //var availablePageLanguages = FilterForVisitor.Filter(pageLanguagesBranches).OfType<PageData>();
            //var currentPageLanguages = availablePageLanguages.Select(page => page.Language.Name).ToList();

           //Get the available languages for the start page of the site
            var pageLanguagesBranches = _contentRepository.GetLanguageBranches<PageData>(startPage.ContentLink).ToList();
            
            //var hostname = startPage.
            foreach (var availablePage in pageLanguagesBranches)
            {
                var culture = new CultureInfo(availablePage.Language.Name);                
                
                //Add home page to the sitemap
                var homePageUrl = _urlResolver.GetUrl(availablePage.ContentLink, availablePage.Language.Name);
                sitemapEntries.Add($"<url><loc>{homePageUrl}</loc><lastmod>{Convert.ToDateTime(availablePage.GetLastPublishDate()).ToString("yyyy-MM-ddTHH:mm:sszzz")}</lastmod><priority>0.80</priority></url>");

                //get the children of the home page
                var pages = _contentLoader.GetDescendents(availablePage.ContentLink);

                foreach (var pageLink in pages)
                {
                    if (_contentLoader.TryGet(pageLink, culture, out PageData page))
                    {
                        //check if the page is set to exclude from sitemap 
                        bool excludeFromSitemap = bool.TryParse(page["ExcludeFromSitemap"] as string, out bool result);

                        //if the page is published, is allowed in the sitemap and is not a shortcut
                        if (!publishedFilter.ShouldFilter(page) && !accessFilter.ShouldFilter(page) && !excludeFromSitemap && page.LinkType != PageShortcutType.Shortcut)
                        {
                            var url = _urlResolver.GetUrl(page.ContentLink, availablePage.Language.Name);
                            if (!string.IsNullOrEmpty(url))
                            {
                                sitemapEntries.Add($"<url><loc>{url}</loc><lastmod>{Convert.ToDateTime(page.GetLastPublishDate()).ToString("yyyy-MM-ddTHH:mm:sszzz")}</lastmod><priority>0.64</priority></url>");
                            }
                        }
                    }
                }
            }

            return $"<urlset xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\" xsi:schemaLocation=\"http://www.sitemaps.org/schemas/sitemap/0.9 http://www.sitemaps.org/schemas/sitemap/0.9/sitemap.xsd\">{string.Join("", sitemapEntries)}</urlset>";
        }
    }
}

Startup.cs

public void ConfigureServices(IServiceCollection services)
{
	services.AddTransient<ISitemapGeneratorService, SitemapGeneratorService>();
	services.AddCms();
}

SitemapGeneratorJob.cs

namespace CustomSitemap.Web.Business.ScheduledJobs
{
    /// <summary>
    /// Scheduled job for generating SEO sitemaps.
    /// </summary>
    [ScheduledPlugIn(DisplayName = "Generate SEO Sitemaps", Description = "Generates sitemap for each site", GUID = "5C3DDEC2-0CD5-4734-B8EE-FDA8BE08C46E")]
    public class SitemapGeneratorJob : ScheduledJobBase
    {
        private readonly EPiServer.Logging.ILogger _logger;        
        private ISitemapGeneratorService _sitemapGeneratorService;
        private readonly IWebHostEnvironment _environment;
        private bool _stopSignaled;
        /// <summary>
        /// Default constructor
        /// </summary>
        /// <param name="siteConfigService"></param>
        public SitemapGeneratorJob(
            ISitemapGeneratorService sitemapGeneratorService,
            IWebHostEnvironment environment)
        {
            _sitemapGeneratorService = sitemapGeneratorService;
            _logger = LogManager.GetLogger(typeof(SitemapGeneratorJob));
            IsStoppable = true;
            _environment = environment;
        }

        /// <summary>
        /// stop
        /// </summary>
        public override void Stop()
        {
            _stopSignaled = true;
        }

        /// <summary>
        /// Set the primary hosts
        /// </summary>
        /// <returns></returns>
        public override string Execute()
        {
            OnStatusChanged("Starting execution of SitemapGeneratorJob");

            _logger.Information("Starting the job : SitemapGeneratorJob");

            //Call the method to Generate Sitemaps

            if (_environment.IsDevelopment())
            {
                _logger.Information($"Current environment is {_environment.EnvironmentName}");
                _logger.Warning($"This job is not intended to run on the environment {_environment.EnvironmentName}");
                return "SitemapGeneratorJob will not run in development environment";
            }
            var status = _sitemapGeneratorService.GenerateSitemaps();

            if (!status)
                return "SitemapGeneratorJob did not run successfully. Please check the logs for more information";

            if (_stopSignaled)
            {                
                return "SitemapGeneratorJob was stopped";
            }

            return "SitemapGeneratorJob completed successfully";
        }
    }
}

SitemapController.cs

namespace CustomSitemap.Web.Controllers
{
    /// <summary>
    /// controller to get SEO sitemap or regular xml file.
    /// </summary>
    [Route("{sitemapName}.xml")]
    public class SitemapController : Controller
    {
        private readonly IWebHostEnvironment _webHostEnvironment;
        private readonly ISiteDefinitionResolver _siteDefinitionResolver;
        private readonly IHttpContextAccessor _httpContextAccessor;
        private readonly IContentLoader _contentLoader;
        
        public SitemapController(IWebHostEnvironment webHostEnvironment,
            ISiteDefinitionResolver siteDefinitionResolver,
            IHttpContextAccessor httpContextAccessor,
            IContentLoader contentLoader)
        {
            _webHostEnvironment = webHostEnvironment;
            _siteDefinitionResolver = siteDefinitionResolver;
            _httpContextAccessor = httpContextAccessor;
            _contentLoader = contentLoader;
        }

        /// <summary>
        /// action method to serve sitemap or any xml file
        /// </summary>
        /// <param name="sitemapName"></param>
        /// <returns></returns>
        [HttpGet]
        public IActionResult Index(string sitemapName)
        {
            if (!string.IsNullOrEmpty(sitemapName) && !sitemapName.ToLower().EndsWith(".xml"))
            {
                sitemapName = $"{sitemapName}.xml";
            }

            //get the start page for the site
            var startPage = _contentLoader.Get<PageData>(ContentReference.StartPage);
            //read the sitemap file name from the home page
            var sitemapFileName = startPage["SitemapFileName"] as string;            

            //if the requested file name is same as sitemap file name configured in home page or if it is not configured but it is sitemap.xml
            if ((!string.IsNullOrEmpty(sitemapFileName) && sitemapFileName.Equals(sitemapName, StringComparison.OrdinalIgnoreCase)) || (string.IsNullOrEmpty(sitemapFileName) && sitemapName.ToLower().Equals("sitemap.xml")))
            {
                var httpContext = _httpContextAccessor.HttpContext;
                if (httpContext == null)
                {
                    return NotFound();
                }

                // Attempt to resolve the site by host
                var currentSite = _siteDefinitionResolver.GetByHostname(httpContext.Request.Host.Host, true);

                // Fallback to hostname with port
                if (currentSite == null)
                {
                    var hostWithPort = httpContext.Request.Host.Value; // Host with port, e.g., "localhost:5000"
                    currentSite = _siteDefinitionResolver.GetByHostname(hostWithPort, true);
                }

                //get the sitemap from wwwroot/sitemaps
                var filePath = Path.Combine(_webHostEnvironment.WebRootPath, "sitemaps", currentSite.Name.Replace(" ", "-").ToLower() + "-sitemap.xml");
                if (!System.IO.File.Exists(filePath))
                {
                    return NotFound();
                }

                //read the contents of the sitemap file and return
                var fileContent = System.IO.File.ReadAllText(filePath);
                return Content(fileContent, "application/xml");
            }
            else
            {
                //this is not a sitemap file, so try getting the requested file from wwwroot
                var filePath = Path.Combine(_webHostEnvironment.WebRootPath, sitemapName);
                if (!System.IO.File.Exists(filePath))
                {
                    return NotFound();
                }
                
                //return the requested file
                var fileContent = System.IO.File.ReadAllText(filePath);
                return Content(fileContent, "application/xml");
            }
        }
    }
}