Extract text from a XPS Document [closed]

Answer 1

Method that returns text from all pages (modified Amir:s code, hope that's ok):

/// 

///   Get all text strings from an XPS file.
///   Returns a list of lists (one for each page) containing the text strings.
/// 
private static List> ExtractTextFromXps(string xpsFilePath)
{
   var xpsDocument = new XpsDocument(xpsFilePath, FileAccess.Read);
   var fixedDocSeqReader = xpsDocument.FixedDocumentSequenceReader;
   if (fixedDocSeqReader == null)
      return null;

   const string UnicodeString = "UnicodeString";
   const string GlyphsString = "Glyphs";

   var textLists = new List>();
   foreach (IXpsFixedDocumentReader fixedDocumentReader in fixedDocSeqReader.FixedDocuments)
   {
      foreach (IXpsFixedPageReader pageReader in fixedDocumentReader.FixedPages)
      {
         var pageContentReader = pageReader.XmlReader;
         if (pageContentReader == null)
            continue;

         var texts = new List();
         while (pageContentReader.Read())
         {
            if (pageContentReader.Name != GlyphsString)
               continue;
            if (!pageContentReader.HasAttributes)
               continue;
            if (pageContentReader.GetAttribute(UnicodeString) != null)
               texts.Add(pageContentReader.GetAttribute(UnicodeString));
         }
         textLists.Add(texts);   
      }
   }
   xpsDocument.Close();
   return textLists;
}

Usage:

var txtLists = ExtractTextFromXps(@"C:\myfile.xps");

int pageIdx = 0;
foreach (List txtList in txtLists)
{
   pageIdx++;
   Console.WriteLine("== Page {0} ==", pageIdx);
   foreach (string txt in txtList)
      Console.WriteLine(" "+txt);
   Console.WriteLine();
}