Read Word file paragraph and save in database using OpenXml in ASP.Net

Hicms9651,

You can read the doc using paragraph. But can't distinguish between the paragraph for subheading and contents.

So there is no logical way read between the subheading and content for inserting the data in database.

But as per your doc i have read the data and inserted in DataTable. You can use the DataTable to insert the record in database.

If format changed you need to change the code accordingly.

HTML

<asp:GridView ID="gvChapters" runat="server"></asp:GridView>

Namespaces

C#

using System.Data;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

VB.Net

Imports System.Data
Imports DocumentFormat.OpenXml.Packaging
Imports DocumentFormat.OpenXml.Wordprocessing

Code

C#

protected void Page_Load(object sender, EventArgs e)
{
    if (!IsPostBack)
    {
        DataTable dt = new DataTable();
        dt.Columns.Add("Chapter");
        dt.Columns.Add("SubHeading");
        dt.Columns.Add("Content");

        string file = @"C:\file.docx";
        using (WordprocessingDocument wordDoc = WordprocessingDocument.Open(file, true))
        {
            Body body = wordDoc.MainDocumentPart.Document.Body;
            string chapter = "";
            string subHeading = "";
            string content = "";
            foreach (var paragraph in body)
            {
                if (!string.IsNullOrEmpty(paragraph.InnerText.Trim()))
                {
                    if (paragraph.InnerText.Trim().Contains("Chapter"))
                    {
                        chapter = paragraph.InnerText.Trim();
                    }
                    else
                    {
                        if (paragraph.InnerText.Trim().StartsWith("-"))
                        {
                            subHeading = paragraph.InnerText.Trim();
                        }
                        else
                        {
                            content = paragraph.InnerText.Trim();
                            dt.Rows.Add(chapter, subHeading, content);
                        }
                    }
                }
            }
        }

        gvChapters.DataSource = dt;
        gvChapters.DataBind();
    }
}

VB.Net

Protected Sub Page_Load(ByVal sender As Object, ByVal e As EventArgs) Handles Me.Load
    If Not IsPostBack Then
        Dim dt As DataTable = New DataTable()
        dt.Columns.Add("Chapter")
        dt.Columns.Add("SubHeading")
        dt.Columns.Add("Content")
        Dim file As String = "C:\file.docx"
        Using wordDoc As WordprocessingDocument = WordprocessingDocument.Open(file, True)
            Dim body As Body = wordDoc.MainDocumentPart.Document.Body
            Dim chapter As String = ""
            Dim subHeading As String = ""
            Dim content As String = ""
            For Each paragraph In body
                If Not String.IsNullOrEmpty(paragraph.InnerText.Trim()) Then
                    If paragraph.InnerText.Trim().Contains("Chapter") Then
                        chapter = paragraph.InnerText.Trim()
                    Else

                        If paragraph.InnerText.Trim().StartsWith("-") Then
                            subHeading = paragraph.InnerText.Trim()
                        Else
                            content = paragraph.InnerText.Trim()
                            dt.Rows.Add(chapter, subHeading, content)
                        End If
                    End If
                End If
            Next
        End Using
        gvChapters.DataSource = dt
        gvChapters.DataBind()
    End If
End Sub

Screenshot