add CrawlerHasBeenDetectedException

src/Laraue.Crawling.Crawler/BaseCrawlerJob.cs

@@ -46,22 +46,28 @@ public override async Task<TimeSpan> ExecuteAsync(JobState<TState> jobState, Can
             {
                 var link = await GetNextLinkAsync(jobState, stoppingToken).ConfigureAwait(false);
                 _logger.LogInformation("Page {Page} processing started", link);
-            
+
                 var result = await ParseLinkAsync(link, jobState, stoppingToken).ConfigureAwait(false);
                 await AfterLinkParsedAsync(link, result, jobState, stoppingToken).ConfigureAwait(false);
-            
+
                 _logger.LogInformation(
                     "Page {Page} processing finished for {Time}",
                     link,
                     pageStopwatch.Elapsed);
-        
+
                 stoppingToken.ThrowIfCancellationRequested();
             }
             catch (SessionInterruptedException e)
             {
                 _logger.LogInformation("Session should be finished. Reason: {Message}", e.Message);
-
-                return await RunSessionFinishAsync(jobState, stoppingToken);
+
+                return await RunSessionFinishAsync(jobState, stoppingToken).ConfigureAwait(false);
+            }
+            catch (CrawlerHasBeenDetectedException e)
+            {
+                _logger.LogInformation("Crawler has been detected. {Message}", e.Message);
+
+                await e.SwitchToCorrectStateAsync().ConfigureAwait(false);
             }
         }
     }

src/Laraue.Crawling.Crawler/CrawlerHasBeenDetectedException.cs

@@ -0,0 +1,23 @@
+namespace Laraue.Crawling.Crawler;
+
+/// <summary>
+/// Exception that describe to the system that crawler has been detected and the passed
+/// delegate should be executed to continue the crawling process.
+/// </summary>
+public sealed class CrawlerHasBeenDetectedException : Exception
+{
+    /// <summary>
+    /// Delegate to return a crawler to the normal state.
+    /// </summary>
+    public Func<Task> SwitchToCorrectStateAsync { get; }
+
+    /// <summary>
+    /// Initializes a new instance of <see cref="SessionInterruptedException"/> with description of interrupting.
+    /// </summary>
+    /// <param name="message"></param>
+    /// <param name="switchToCorrectStateAsync"></param>
+    public CrawlerHasBeenDetectedException(string message, Func<Task> switchToCorrectStateAsync) : base(message)
+    {
+        SwitchToCorrectStateAsync = switchToCorrectStateAsync;
+    }
+}

src/Laraue.Crawling.Dynamic.PuppeterSharp/Abstractions/IPageParser.cs

@@ -14,5 +14,5 @@ public interface IPageParser
     /// <param name="page"></param>
     /// <param name="schema"></param>
     /// <returns></returns>
-    Task<TResult?> ParseAsync<TResult>(IPage page, ICompiledHtmlSchema<IElementHandle, TResult> schema);
+    Task<TResult> ParseAsync<TResult>(IPage page, ICompiledHtmlSchema<IElementHandle, TResult> schema);
 }

src/Laraue.Crawling.Dynamic.PuppeterSharp/Extensions/ServiceCollectionExtensions.cs

@@ -17,7 +17,7 @@ public static class ServiceCollectionExtensions
     /// <param name="serviceCollection"></param>
     /// <param name="launchOptions"></param>
     /// <returns></returns>
-    public static IServiceCollection AddPuppeterFactory(
+    public static IServiceCollection AddCrawlingServices(
         this IServiceCollection serviceCollection,
         LaunchOptions launchOptions)
     {

src/Laraue.Crawling.Dynamic.PuppeterSharp/PageParser.cs

@@ -15,7 +15,7 @@ public PageParser(IHtmlSchemaParser<IElementHandle> schemaParser)
     }
 
     /// <inheritdoc />
-    public async Task<TResult?> ParseAsync<TResult>(IPage page, ICompiledHtmlSchema<IElementHandle, TResult> schema)
+    public async Task<TResult> ParseAsync<TResult>(IPage page, ICompiledHtmlSchema<IElementHandle, TResult> schema)
     {
         var element = await page.QuerySelectorAsync("body")
             .ConfigureAwait(false);