[WIP] Add webpart extractor to page scan component

.gitignore

@@ -350,4 +350,6 @@ MigrationBackup/
 .ionide/
 
 # mac OS
-.ds_store
+.ds_store
+
+.idea/

src/PnP.Scanning/PnP.Scanning.Core/Constants.cs

@@ -58,5 +58,119 @@ internal static class Constants
         #region PnPContext properties
         internal const string PnPContextPropertyScanId = "ScanId";
         #endregion
+
+        #region Classic WebParts Without Proper Property Mappings
+        /// <summary>
+        /// Classic SharePoint web part types that do not have proper property mappings to modern client side web parts
+        /// </summary>
+        internal static readonly string[] ClassicWebPartsWithoutProperMappings = new[]
+        {
+            // Search Web Parts (minimal or no property mappings)
+            "Microsoft.Office.Server.Search.WebControls.SearchNavigationWebPart",
+            "Microsoft.Office.Server.Search.WebControls.CatalogItemReuseWebPart",
+            "Microsoft.Office.Server.Search.WebControls.TaxonomyRefinementScriptWebPart",
+            "Microsoft.Office.Server.Search.WebControls.AdvancedSearchBox",
+            "Microsoft.Office.Server.Search.WebControls.SearchBoxScriptWebPart",
+            "Microsoft.Office.Server.Search.WebControls.RefinementScriptWebPart",
+
+            // SharePoint Portal WebControls (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.SiteDocuments",
+            "Microsoft.SharePoint.Portal.WebControls.RSSAggregatorWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.SocialCommentWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.ProfileBrowser",
+            "Microsoft.SharePoint.Portal.WebControls.TagCloudWebPart",
+
+            // Project Site Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.ProjectSummaryWebPart",
+
+            // KPI Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.IndicatorWebpart",
+            "Microsoft.SharePoint.Portal.WebControls.KPIListWebPart",
+
+            // Community Site Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.CommunityAdminWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.CommunityJoinWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.DashboardWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.AboutUsWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.MyMembershipWebPart",
+
+            // OWA Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.OWAInboxPart",
+            "Microsoft.SharePoint.Portal.WebControls.OWACalendarPart",
+            "Microsoft.SharePoint.Portal.WebControls.OWAContactsPart",
+            "Microsoft.SharePoint.Portal.WebControls.OWATasksPart",
+
+            // Category Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.CategoryWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.CategoryResultsWebPart",
+
+            // Announcements Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.AnnouncementTilesWebPart",
+
+            // Tasks and Tools Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.TasksAndToolsWebPart",
+
+            // Week in Pictures Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.ThisWeekInPicturesWebPart",
+
+            // User Tasks Web Parts (no mappings)
+            "Microsoft.SharePoint.WebPartPages.UserTasksWebPart",
+
+            // Timeline Web Parts (no mappings)
+            "Microsoft.SharePoint.WebPartPages.SPTimelineWebPart",
+
+            // Taxonomy Web Parts (no mappings)
+            "Microsoft.SharePoint.Taxonomy.TermProperty",
+
+            // Business Data Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.BusinessDataListWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.BusinessDataFilterWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.BusinessDataDetailsWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.BusinessDataAssociationWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.BusinessDataActionsWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.BusinessDataItemBuilder",
+
+            // Filter Web Parts (no mappings)
+            "Microsoft.SharePoint.Portal.WebControls.ScorecardFilterWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.ApplyFiltersWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.DateFilterWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.UserContextFilterWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.SPSlicerTextWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.SpListFilterWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.QueryStringFilterWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.PageContextFilterWebPart",
+            "Microsoft.SharePoint.Portal.WebControls.SPSlicerChoicesWebPart",
+
+            // Blog Site Web Parts (no mappings)
+            "Microsoft.SharePoint.WebPartPages.BlogLinksWebPart",
+            "Microsoft.SharePoint.WebPartPages.BlogAdminWebPart",
+            "Microsoft.SharePoint.WebPartPages.BlogMonthQuickLaunch",
+            "Microsoft.SharePoint.WebPartPages.BlogYearArchive",
+
+            // Error Web Parts (no mappings)
+            "Microsoft.SharePoint.WebPartPages.ErrorWebPart",
+
+            // App Catalog Web Parts (no mappings)
+            "Microsoft.SharePoint.WebPartPages.GettingStartedWithAppCatalogSiteWebPart",
+
+            // Document Set Web Parts (no mappings)
+            "Microsoft.Office.Server.WebControls.DocIdSearchWebPart",
+            "Microsoft.Office.Server.WebControls.DocumentSetPropertiesWebPart",
+            "Microsoft.Office.Server.WebControls.DocumentSetContentsWebPart",
+
+            // Analytics Web Parts (no mappings)
+            "Microsoft.Office.Server.WebAnalytics.Reporting.WhatsPopularWebPart",
+
+            // Chart Web Parts (no mappings)
+            "Microsoft.Office.Server.WebControls.ChartWebPart",
+
+            // Web Parts with empty mappings (drop without transformation)
+            "Microsoft.SharePoint.WebPartPages.GettingStartedWebPart",
+            "Microsoft.Office.InfoPath.Server.Controls.WebUI.BrowserFormWebPart",
+            "Microsoft.SharePoint.WebPartPages.SPUserCodeWebPart",
+            "Microsoft.SharePoint.WebPartPages.TitleBarWebPart",
+            "Microsoft.SharePoint.Publishing.WebControls.TableOfContentsWebPart"
+        };
+        #endregion
     }
 }

src/PnP.Scanning/PnP.Scanning.Core/Scanners/AddInsACS/AddInACSScanComponent.cs

@@ -36,7 +36,7 @@ internal static async Task ExecuteAsync(ScannerBase scannerBase, PnPContext cont
                     CurrentWebId = addIn.CurrentWebId,
                     CurrentWebName = addIn.CurrentWebName,
                     InstalledBy = addIn.InstalledBy,
-                    InstalledSiteId = addIn.InstalledSiteId,
+                    InstalledSiteId = addIn.InstalledSiteId, 
                     InstalledWebFullUrl = addIn.InstalledWebFullUrl,
                     InstalledWebId = addIn.InstalledWebId,
                     InstalledWebName = addIn.InstalledWebName,

src/PnP.Scanning/PnP.Scanning.Core/Scanners/Classic/PageScanComponent.cs

@@ -2,7 +2,9 @@
 using PnP.Core.Model.SharePoint;
 using PnP.Core.QueryModel;
 using PnP.Core.Services;
+using PnP.Scanning.Core.Scanners.Classic;
 using PnP.Scanning.Core.Storage;
+using Serilog;
 
 namespace PnP.Scanning.Core.Scanners
 {
@@ -37,6 +39,7 @@ internal static async Task ExecuteAsync(ScannerBase scannerBase, PnPContext cont
         {
 
             List<ClassicPage> pagesList = new();
+            List<ClassicWebPart> webPartsList = new();
             int modernPageCounter = 0;
             HashSet<string> remediationCodes = new();
 
@@ -147,6 +150,45 @@ await QueryListAsync(sitePagesLibrary, PageQuery(new List<string> { HtmlFileType
 
             if (pagesList.Count > 0)
             {
+                // Extract web parts from each page
+                foreach (var page in pagesList)
+                {
+                    try
+                    {
+                        var webParts = await WebPartExtractor.ExtractWebPartsFromPageAsync(
+                            scannerBase.ScanId,
+                            scannerBase.SiteUrl,
+                            scannerBase.WebUrl,
+                            page.PageUrl,
+                            page.PageName,
+                            page.ListId,
+                            page.ModifiedAt,
+                            csomContext);
+
+                        webPartsList.AddRange(webParts);
+
+                        // Add web part remediation codes to the overall set
+                        foreach (var webPart in webParts)
+                        {
+                            if (!string.IsNullOrEmpty(webPart.RemediationCode))
+                            {
+                                remediationCodes.Add(webPart.RemediationCode);
+                            }
+                        }
+                    }
+                    catch (Exception ex)
+                    {
+                        // Log the error but continue processing other pages
+                        Log.Warning("Failed to extract web parts from page {PageUrl}: {Error}", page.PageUrl, ex.Message);
+                    }
+                }
+
+                // Store web parts if any were found
+                if (webPartsList.Count > 0)
+                {
+                    await scannerBase.StorageManager.StoreWebPartInformationAsync(scannerBase.ScanId, webPartsList);
+                }
+
                 await scannerBase.StorageManager.StorePageInformationAsync(scannerBase.ScanId, pagesList);
             }
 

src/PnP.Scanning/PnP.Scanning.Core/Scanners/Classic/RemediationCodes.cs

@@ -107,6 +107,17 @@ internal enum RemediationCodes
         /// Other ribbon/UI extensions via User Custom Actions
         /// </summary>
         CE9,
+
 
+        WP1,
+
+        /// <summary>
+        /// Web part without proper mapping
+        /// </summary>
+        WP2,
+        /// <summary>
+        ///  Unknown web part type
+        /// </summary>
+        WP3,
     }
 }