Option to replace images with placeholders

PortablePorts/NReadability/DomSerializationParams.cs

@@ -42,6 +42,11 @@ namespace ReadSharp.Ports.NReadability
     /// </summary>
     public bool DontIncludeGeneratorMetaElement { get; set; }
 
+    /// <summary>
+    /// If [true], replace all img-tags with placeholders.
+    /// </summary>
+    public bool ReplaceImagesWithPlaceholders { get; set; }
+
     /// <summary>
     /// Render complete Website or only the Body
     /// </summary>

PortablePorts/NReadability/NReadabilityTranscoder.cs

@@ -253,6 +253,14 @@ namespace ReadSharp.Ports.NReadability
           out nextPageUrl);
 
       IEnumerable<XElement> images = transcodedXmlDocument.GetElementsByTagName("img");
+      List<XElement> realImages = images.ToList();
+
+      if (transcodingInput.DomSerializationParams.ReplaceImagesWithPlaceholders)
+      {
+        int i = 1;
+        images.ForEach(ximage => ximage.AddAfterSelf(new XComment("IMG_" + (i++))));
+        images.Remove();
+      }
 
       string transcodedContent =
         _sgmlDomSerializer.SerializeDocument(
@@ -297,7 +305,7 @@ namespace ReadSharp.Ports.NReadability
             ExtractedImage = image,
             NextPageUrl = nextPageUrl,
             Charset = charset,
-            Images = images
+            Images = realImages
           };
     }
 

README.md

@@ -51,8 +51,11 @@ You can pass `HttpOptions` to the `Reader` constructor, which count for all requ
 
 - `HttpMessageHandler` **CustomHttpHandler**<br>Use your own HTTP handler
 - `int?` **RequestTimeout**<br>Define a custom timeout _in seconds_, after which requests should cancel
+- `bool` **UseMobileUserAgent**<br>Gets or sets a value indicating whether [use mobile user agent]
 - `string` **UserAgent**<br>Override the user agent, which is passed to the destination server
+- `string` **UserAgentMobile**<br>Override the mobile user agent, which is passed to the destination server
 - `bool` **UseMobileUserAgent**<br>There are desktop and mobile default user agents. By enabling this property, the mobile user agent is used. _If you pass a custom user agent, this property is ignored!_
+- `int` **MultipageLimit**<br>Gets or sets the download limit for articles with multiple pages (default: 10)
 
 ### ReadOptions
 
@@ -62,6 +65,8 @@ There are also `ReadOptions` available, which are passed on every request:
 - `bool` **HasNoHeadline**<br>Removes `<h1>` title from the article
 - `bool` **UseDeepLinks**<br>If you check this option, deep-links (containing hashes, e.g. `href="#article"`) are not transformed into absolute URIs
 - `bool` **PrettyPrint**<br>Determines whether the HTML output will be formatted
+- `bool` **MultipageDownload**<br>Download all pages for articles with multiple pages (default: false)
+- `bool` **ReplaceImagesWithPlaceholders**<br>If true, replace all img-tags with placeholders
 
 ## Article Model
 

ReadSharp.Tests/ReadTests.cs

@@ -52,6 +52,23 @@ namespace ReadSharp.Tests
     }
 
 
+    [Fact]
+    public async Task ReadArticleWithImagePlaceholdersTest()
+    {
+      ReadOptions options = ReadOptions.CreateDefault();
+      options.ReplaceImagesWithPlaceholders = true;
+      Article result = await reader.Read(new Uri("https://hacks.mozilla.org/2013/12/application-layout-with-css3-flexible-box-module/"), options);
+      List<ArticleImage> images = result.Images.ToList();
+
+      Assert.True(images.Count >= 3);
+      Assert.True(images[0].Uri.ToString().StartsWith("https://hacks.mozilla.org"));
+      Assert.True(images[1].Uri.ToString().EndsWith(".gif"));
+
+      Assert.Contains("<!--IMG_1-->", result.Content);
+      Assert.DoesNotContain("<img ", result.Content);
+    }
+
+
     [Fact]
     public async Task ReadArticleWithNoImagesTest()
     {

ReadSharp/Models/ReadOptions.cs

@@ -43,6 +43,11 @@ namespace ReadSharp
     /// </value>
     public bool MultipageDownload { get; set; }
 
+    /// <summary>
+    /// If true, replace all img-tags with placeholders.
+    /// </summary>
+    public bool ReplaceImagesWithPlaceholders { get; set; }
+
     /// <summary>
     /// Creates the default options.
     /// </summary>
@@ -55,7 +60,8 @@ namespace ReadSharp
         HasHeadline = false,
         UseDeepLinks = false,
         PrettyPrint = false,
-        MultipageDownload = false
+        MultipageDownload = false,
+        ReplaceImagesWithPlaceholders = false
       };
     }
   }

ReadSharp/Properties/AssemblyInfo.cs

@@ -22,5 +22,5 @@
 // You can specify all the values or you can default the Build and Revision Numbers
 // by using the '*' as shown below:
 // [assembly: AssemblyVersion("1.0.*")]
-[assembly: AssemblyVersion("6.1.0")]
-[assembly: AssemblyFileVersion("6.1.0")]
+[assembly: AssemblyVersion("6.2.0")]
+[assembly: AssemblyFileVersion("6.2.0")]

ReadSharp/Reader.cs

@@ -165,10 +165,10 @@ namespace ReadSharp
             Title = image.GetAttributeValue("title", null),
             AlternativeText = image.GetAttributeValue("alt", null)
           };
-        })
-        .GroupBy(image => image.Uri)
-        .Select(g => g.First())
-        .Where(image => image.Uri != null);
+        });
+        //.GroupBy(image => image.Uri)
+        //.Select(g => g.First())
+        //.Where(image => image.Uri != null);
 
       // get word count and plain text
       string plainContent;
@@ -236,7 +236,8 @@ namespace ReadSharp
           DontIncludeContentTypeMetaElement = true,
           DontIncludeMobileSpecificMetaElements = true,
           DontIncludeDocTypeMetaElement = false,
-          DontIncludeGeneratorMetaElement = true
+          DontIncludeGeneratorMetaElement = true,
+          ReplaceImagesWithPlaceholders = options.ReplaceImagesWithPlaceholders
         }
       };