Read PDF file and import data to database in ASP.Net using iTextSharp

Hi Smile,

Please refer below sample.

HTML

<asp:Button Text="Save" runat="server" OnClick="Export" />

Namespaces

C#

using System.Configuration;
using System.Data;
using System.Data.SqlClient;
using System.Text;
using System.Text.RegularExpressions;
using iTextSharp.text.pdf;

VB.Net

Imports System.Configuration
Imports System.Data
Imports System.Data.SqlClient
Imports System.Text
Imports System.Text.RegularExpressions
Imports iTextSharp.text.pdf

Code

C#

protected void Export(object sender, EventArgs e)
{
    string file = Server.MapPath("~/Q1.pdf");
    StringBuilder text = new StringBuilder();
    PdfReader pdfReader = new PdfReader(file);
    for (int page = 1; page <= pdfReader.NumberOfPages; page++)
    {
        PdfContentParser parser = new PdfContentParser(new PRTokeniser(pdfReader.GetPageContent(page)));
        StringBuilder sb = new StringBuilder();
        while (parser.Tokeniser.NextToken())
        {
            if (parser.Tokeniser.TokenType == PRTokeniser.TK_STRING)
            {
                sb.Append(parser.Tokeniser.StringValue);
            }
        }
        string currentText = sb.ToString();
        currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.UTF8.GetBytes(currentText)));
        text.Append(currentText);
        pdfReader.Close();
    }

    DataTable dt = new DataTable();
    dt.Columns.Add("Question");
    dt.Columns.Add("Option1");
    dt.Columns.Add("Option2");
    dt.Columns.Add("Option3");
    string[] lines = Regex.Split(text.ToString(), @"Q[0-9]{0,3}:");
    for (int i = 1; i < lines.Length; i++)
    {
        if (!string.IsNullOrEmpty(lines[i].Trim()))
        {
            string[] chars = new string[] { "i)", "ii)", "iii)" };
            string[] questionoptions = lines[i].Trim().Split(chars, StringSplitOptions.RemoveEmptyEntries);
            dt.Rows.Add(questionoptions[0], questionoptions[1], questionoptions[2], questionoptions[3]);
        }
    }

    for (int i = 0; i < dt.Rows.Count; i++)
    {
        using (SqlConnection con = new SqlConnection(ConfigurationManager.ConnectionStrings["constr"].ConnectionString))
        {
            using (SqlCommand cmd = new SqlCommand("INSERT INTO ExamSet(Question, Option1, Option2, Option3) VALUES (@Question, @Option1, @Option2, @Option3)", con))
            {
                cmd.Parameters.AddWithValue("@Question", dt.Rows[i][0]);
                cmd.Parameters.AddWithValue("@Option1", dt.Rows[i][1]);
                cmd.Parameters.AddWithValue("@Option2", dt.Rows[i][2]);
                cmd.Parameters.AddWithValue("@Option3", dt.Rows[i][3]);
                con.Open();
                cmd.ExecuteNonQuery();
                con.Close();
            }
        }
    }
}

VB.Net

Protected Sub Export(ByVal sender As Object, ByVal e As EventArgs)
    Dim file As String = Server.MapPath("~/Q1.pdf")
    Dim text As StringBuilder = New StringBuilder()
    Dim pdfReader As PdfReader = New PdfReader(file)
    For page As Integer = 1 To pdfReader.NumberOfPages Step 1
        Dim parser As PdfContentParser = New PdfContentParser(New PRTokeniser(pdfReader.GetPageContent(page)))
        Dim sb As StringBuilder = New StringBuilder()
        While parser.Tokeniser.NextToken()
            If parser.Tokeniser.TokenType = PRTokeniser.TK_STRING Then
                sb.Append(parser.Tokeniser.StringValue)
            End If
        End While
        Dim currentText As String = sb.ToString()
        currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.UTF8.GetBytes(currentText)))
        text.Append(currentText)
        pdfReader.Close()
    Next

    Dim dt As DataTable = New DataTable()
    dt.Columns.Add("Question")
    dt.Columns.Add("Option1")
    dt.Columns.Add("Option2")
    dt.Columns.Add("Option3")
    Dim lines As String() = Regex.Split(text.ToString(), "Q[0-9]{0,3}:")
    For i As Integer = 1 To lines.Length - 1
        If Not String.IsNullOrEmpty(lines(i).Trim()) Then
            Dim chars As String() = New String() {"i)", "ii)", "iii)"}
            Dim questionoptions As String() = lines(i).Trim().Split(chars, StringSplitOptions.RemoveEmptyEntries)
            dt.Rows.Add(questionoptions(0), questionoptions(1), questionoptions(2), questionoptions(3))
        End If
    Next

    For i As Integer = 0 To dt.Rows.Count - 1
        Using con As SqlConnection = New SqlConnection(ConfigurationManager.ConnectionStrings("constr").ConnectionString)
            Using cmd As SqlCommand = New SqlCommand("INSERT INTO ExamSet(Question, Option1, Option2, Option3) VALUES (@Question, @Option1, @Option2, @Option3)", con)
                cmd.Parameters.AddWithValue("@Question", dt.Rows(i)(0))
                cmd.Parameters.AddWithValue("@Option1", dt.Rows(i)(1))
                cmd.Parameters.AddWithValue("@Option2", dt.Rows(i)(2))
                cmd.Parameters.AddWithValue("@Option3", dt.Rows(i)(3))
                con.Open()
                cmd.ExecuteNonQuery()
                con.Close()
            End Using
        End Using
    Next
End Sub

Screenshot