简体   繁体   中英

windows application extract name email id and contact no from doc file

i want to extract name,contactno and emailid from the word document file how i can extract plz any one help my code is here

public void Opendoc(object file)
        {
            Microsoft.Office.Interop.Word.Application wpp = new Microsoft.Office.Interop.Word.Application();
            object nobj = System.Reflection.Missing.Value;

            Microsoft.Office.Interop.Word.Document doc = wpp.Documents.Open(ref file, ref nobj, ref nobj, ref nobj,
                            ref nobj, ref nobj, ref nobj, ref nobj, ref nobj, ref nobj,
                            ref nobj, ref nobj, ref nobj, ref nobj, ref nobj, ref nobj);
            int i = 1;
            List <string> emailCollection = new  List<string>();
            foreach (Microsoft.Office.Interop.Word.Paragraph objParagraph in doc.Paragraphs)
 try
                {
                    string emailaddress = document.Paragraphs[1].Range.Text;
                    emailaddress = EmailExtractot(emailaddress).TrimEnd();
                    if (IsEmail(emailaddress))
                    {
                        emailCollection.Add(emailaddress);
                    }
                }
                catch (Exception ex) { throw ex; } i++;

            } // close document and Quit Word 
            document.Close(ref nullobj, ref nullobj, ref nullobj);

        }

 public const string MatchEmailPattern = @"^(([\w-]+\.)+[\w-]+|([a-zA-Z]{1}|[\w-]{2,}))@"
     + @"((([0-1]?[0-9]{1,2}|25[0-5]|2[0-4][0-9])\.([0-1]?
                [0-9]{1,2}|25[0-5]|2[0-4][0-9])\."
     + @"([0-1]?[0-9]{1,2}|25[0-5]|2[0-4][0-9])\.([0-1]?
                [0-9]{1,2}|25[0-5]|2[0-4][0-9])){1}|"
     + @"([a-zA-Z]+[\w-]+\.)+[a-zA-Z]{2,4})$";
  public static bool IsEmail(string email)
        {
            if (email != null) return Regex.IsMatch(email, MatchEmailPattern);
            else return false;
        }

 private static string EmailExtractot(string orginal)
        {

            int index = orginal.IndexOf('@',' ');
            int beforeEmptySpace = orginal.Substring(0, index).LastIndexOf(' ');
            string spiled = orginal.Substring(index, (orginal.Length - index));
            int afterEmptySpace = spiled.IndexOf(' ');
            string emailAddress = orginal.Substring(beforeEmptySpace + 1, (index - beforeEmptySpace) + afterEmptySpace);
            return emailAddress;
        }

but this code not working

    private void button1_Click(object sender, EventArgs e)
    {
        // Reference Microsoft.Office.Interop.Word

        // using System;
        // using System.IO;
        // using System.Windows.Forms;
        // using Microsoft.Office.Interop.Word; 

        MessageBox.Show(GetEmailAddress("C:\\Sample.docx"));
    }

    private string GetEmailAddress(string file)
    {

        string emails = "";

        // Open a doc file.
        Microsoft.Office.Interop.Word.Application application = new Microsoft.Office.Interop.Word.Application();
        Document document = application.Documents.Open(file);

        // Loop through all words in the document.
        int count = document.Words.Count;
        for (int i = 1; i <= count; i++)
        {
            // Write the word.
            string text = document.Words[i].Text;

            //Extract Emails
            if (document.Words[i].Text.Contains("@"))
            {
                emails += document.Words[i - 1].Text + text + document.Words[i + 1].Text + "; ";
            }
        }
        // Close word.
        application.Quit();
        return emails;
    }
}

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM