Code to read content of Word/.doc file

Introduction: In this article I will explain how to read the content of a .doc file and show this in a Rich Textbox. And further we will filter the Email IDs form the content of the file.

NameSpace :

First of all you need to add a reference for ‘Microsoft.Office.Interop.Word’

And the use this namespace on your page.

using System.Reflection;

using Microsoft.Office.Interop.Word;

using System.Runtime.InteropServices;

using System.Text.RegularExpressions;

    

Code :

Here is the complete code:

private void button1_Click(object sender, EventArgs e)

        {

            OpenFileDialog op1 = new OpenFileDialog();

            op1.Multiselect = false;

            op1.ShowDialog();

            int count = 0;

            string[] FName;

            foreach (string s in op1.FileNames)

            {

                FName = s.Split('\\');

                //createting the object of application class 

                Microsoft.Office.Interop.Word.Application Objword = new Microsoft.Office.Interop.Word.Application();

                //creating the object of document class 

                Document objdoc = new Document();

                //get the uploaded file full path 

                dynamic FilePath = s;

                //pass the optional (missing) parameter to API 

                dynamic NA = System.Type.Missing;

                //open Word file document  

                objdoc = Objword.Documents.Open

                              (ref FilePath, ref NA, ref NA, ref NA, ref NA,

                               ref NA, ref NA, ref NA, ref NA,

                               ref NA, ref NA, ref NA, ref NA,

                               ref NA, ref NA, ref NA

                               );

                //creating the object of string builder class 

                StringBuilder sb = new StringBuilder();

                for (int Line = 0; Line < objdoc.Paragraphs.Count; Line++)

                {

                    string Filedata = objdoc.Paragraphs[Line + 1].Range.Text.Trim();

                    if (Filedata != string.Empty)

                    {

                        //Append word files data to stringbuilder 

                        sb.AppendLine(Filedata);

                    }

                }

                //closing document object  

                ((_Document)objdoc).Close();

                //Quit application object to end process 

                ((_Application)Objword).Quit();

                //assign stringbuilder object to show text in textbox 

                richTextBox1.Text = Convert.ToString(sb);

            }

            // Code to Find Email Ids from the file content.

            MatchCollection mc;

            mc = Regex.Matches(richTextBox1.Text, "([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})");

            string res = (mc.Count - 1).ToString();

            for (int i = 0; i < mc.Count; i++)

            {

                MessageBox.Show (mc[i].Value);

            }

        }