Extract text from a XPS Document [closed]

Answer 1

Add References to ReachFramework and WindowsBase and the following using statement:

using System.Windows.Xps.Packaging;

Then use this code:

XpsDocument _xpsDocument=new XpsDocument("/path",System.IO.FileAccess.Read);
IXpsFixedDocumentSequenceReader fixedDocSeqReader 
    =_xpsDocument.FixedDocumentSequenceReader;
IXpsFixedDocumentReader _document = fixedDocSeqReader.FixedDocuments[0];
IXpsFixedPageReader _page 
    = _document.FixedPages[documentViewerElement.MasterPageNumber];
StringBuilder _currentText = new StringBuilder();
System.Xml.XmlReader _pageContentReader = _page.XmlReader;
if (_pageContentReader != null)
{
  while (_pageContentReader.Read())
  {
    if (_pageContentReader.Name == "Glyphs")
    {
      if (_pageContentReader.HasAttributes)
      {
        if (_pageContentReader.GetAttribute("UnicodeString") != null )
        {                                   
          _currentText.
            Append(_pageContentReader.
            GetAttribute("UnicodeString"));                              
        }
      }
    }
  }
}
string _fullPageText = _currentText.ToString();

Text exists in Glyphs -> UnicodeString string attribute. You have to use XMLReader for fixed page.