From b54e4b84c1a52cbd04c6acf4727c67ae322909f8 Mon Sep 17 00:00:00 2001 From: Tobias Klika Date: Sat, 14 Jun 2014 14:59:08 +0200 Subject: [PATCH] add Raw HTML to Article; fixes #9 --- ReadSharp/Models/Article.cs | 8 ++++++++ ReadSharp/Reader.cs | 10 ++++++++-- 2 files changed, 16 insertions(+), 2 deletions(-) diff --git a/ReadSharp/Models/Article.cs b/ReadSharp/Models/Article.cs index 6895993..498f46b 100644 --- a/ReadSharp/Models/Article.cs +++ b/ReadSharp/Models/Article.cs @@ -41,6 +41,14 @@ namespace ReadSharp /// public bool ContentExtracted { get; set; } + /// + /// Gets or sets the raw HTML. + /// + /// + /// The raw HTML. + /// + public string Raw { get; set; } + /// /// Plain content without HTML tags. /// diff --git a/ReadSharp/Reader.cs b/ReadSharp/Reader.cs index 65dffab..099de85 100644 --- a/ReadSharp/Reader.cs +++ b/ReadSharp/Reader.cs @@ -44,6 +44,11 @@ namespace ReadSharp /// protected List _currentPages = new List(); + /// + /// The raw HTML from the last request + /// + private string _rawHTML = String.Empty; + /// /// Redirect faulty mobile URIs to desktop equivalents /// @@ -186,6 +191,7 @@ namespace ReadSharp Description = response.TranscodingResult.ExtractedDescription, Content = response.TranscodingResult.ExtractedContent, ContentExtracted = response.TranscodingResult.ContentExtracted ? wordCount > 0 : false, + Raw = _rawHTML, PlainContent = plainContent, WordCount = wordCount, PageCount = response.PageCount, @@ -216,10 +222,10 @@ namespace ReadSharp // response stream to text textStream.Position = 0; StreamReader streamReader = new StreamReader(textStream, encoding ?? Encoding.UTF8); - string text = streamReader.ReadToEnd(); + _rawHTML = streamReader.ReadToEnd(); // set properties for processing - TranscodingInput transcodingInput = new TranscodingInput(text) + TranscodingInput transcodingInput = new TranscodingInput(_rawHTML) { Url = uri.ToString(), DomSerializationParams = new DomSerializationParams()