How to find and replace specific text in document
using C# and VB.NET.


This code example shows how to find and replace certain text in the example.docx (or RTF, PDF formats) only on the specified page.

Let's find the "italic" text on the second page of the document and then replace it with this text "This word has been corrected".

Download the resulting file: result.docx

Complete code

using System;
using System.IO;
using SautinSoft.Document;
using System.Linq;
using System.Text;
using System.Text.RegularExpressions;

namespace Sample
{
    class Sample
    {
        static void Main(string[] args)
        {
            FindAndReplaceSpecificTextWay1();
            //FindAndReplaceSpecificTextWay2();
        }
        /// <summary>
        /// Find and replace a certain text only on the second page of the DOCX document.
        /// Way #1:
        /// The DOCX document is loaded, then the analysis of the number of pages inside (GetPaginator).
        /// DOCX is not a "paged" format and has to be paginated. 
        /// There may be problems with the text in the tables, since the transfer to a new page is possible.
        /// </summary>
        /// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/insert-text-in-specific-page-after-specific-text-net-csharp-vb.php
        /// </remarks>
        public static void FindAndReplaceSpecificTextWay1()
        {
            string inpFileWord = @"..\..\example.docx";
            string outFileWord = @"result1.docx";
            var searchText = "italic";

            DocumentCore dc = DocumentCore.Load(inpFileWord);
            Regex regex = new Regex(searchText, RegexOptions.IgnoreCase);

            DocumentPaginator dp = dc.GetPaginator();

            if (dp.Pages.Count > 2)
            { 
                // Find and replace a certain text only on the second page of the DOCX document.
                // If you need the first page - 0, the third page - 2, etc.
                foreach (ContentRange item in dp.Pages[1].Content.Find(regex).Reverse())
                {
                    item.Replace("This word has been corrected", new CharacterFormat() { BackgroundColor = Color.Yellow, FontName = "Arial", Size = 16.0 });
                }
            }
            dc.Save(outFileWord, new DocxSaveOptions());
            System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(inpFileWord) { UseShellExecute = true });
            System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFileWord) { UseShellExecute = true });
        }

        /// <summary>
        /// Find and replace a certain text only on the second page of the DOCX document.
        /// Way #2:
        /// The DOCX document is loaded. DOCX is not a "paged" format and has to be paginated. 
        /// We will convert DOCX to PDF and then to save in DOCX back.
        /// There may be problems with Formatting, because we are doing reverse format conversion.
        /// </summary>
        /// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/insert-text-in-specific-page-after-specific-text-net-csharp-vb.php
        /// </remarks>
        public static void FindAndReplaceSpecificTextWay2()
        {
            string inpFileWord = @"..\..\example.docx";
            string tempPDFFile = @"example_temp.pdf";
            string outFileWord = @"result2.docx";
            var searchText = "italic";

            DocumentCore dc1 = DocumentCore.Load(inpFileWord);
            dc1.Save(tempPDFFile);
            DocumentCore dc2 = DocumentCore.Load(tempPDFFile);
            Regex regex = new Regex(searchText, RegexOptions.IgnoreCase);

            {
                for (int index = 0; index < dc2.Sections.Count; index++)
                {
                    var page = dc2.Sections[index];
                    if (dc2.Sections.Count > 2)
                    {
                        // Find and replace a certain text only on the second page of the DOCX document.
                        // If you need the first page - 0, the third page - 2, etc.
                        foreach (ContentRange item in dc2.Sections[1].Content.Find(regex).Reverse())
                        {
                            item.Replace("This word has been corrected", new CharacterFormat() { BackgroundColor = Color.Yellow, FontName = "Arial", Size = 16.0 });
                        }
                    }
                }
                dc2.Save(outFileWord);
                System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(inpFileWord) { UseShellExecute = true });
                System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFileWord) { UseShellExecute = true });
            }
        }
    }
}

Download.

        
            Option Infer On
Imports System
Imports System.IO
Imports SautinSoft.Document
Imports System.Linq
Imports System.Text
Imports System.Text.RegularExpressions

Namespace Sample
	Friend Class Sample
		Shared Sub Main(ByVal args() As String)
			FindAndReplaceSpecificTextWay1()
			'FindAndReplaceSpecificTextWay2();
		End Sub
		''' <summary>
		''' Find and replace a certain text only on the second page of the DOCX document.
		''' Way #1:
		''' The DOCX document is loaded, then the analysis of the number of pages inside (GetPaginator).
		''' DOCX is not a "paged" format and has to be paginated. 
		''' There may be problems with the text in the tables, since the transfer to a new page is possible.
		''' </summary>
		''' <remarks>
		''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/insert-text-in-specific-page-after-specific-text-net-csharp-vb.php
		''' </remarks>
		Public Shared Sub FindAndReplaceSpecificTextWay1()
			Dim inpFileWord As String = "..\example.docx"
			Dim outFileWord As String = "result1.docx"
			Dim searchText = "italic"

			Dim dc As DocumentCore = DocumentCore.Load(inpFileWord)
			Dim regex As New Regex(searchText, RegexOptions.IgnoreCase)

			Dim dp As DocumentPaginator = dc.GetPaginator()

			If dp.Pages.Count > 2 Then
				' Find and replace a certain text only on the second page of the DOCX document.
				' If you need the first page - 0, the third page - 2, etc.
				For Each item As ContentRange In dp.Pages(1).Content.Find(regex).Reverse()
					item.Replace("This word has been corrected", New CharacterFormat() With {
						.BackgroundColor = Color.Yellow,
						.FontName = "Arial",
						.Size = 16.0
					})
				Next item
			End If
			dc.Save(outFileWord, New DocxSaveOptions())
			System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(inpFileWord) With {.UseShellExecute = True})
			System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(outFileWord) With {.UseShellExecute = True})
		End Sub

		''' <summary>
		''' Find and replace a certain text only on the second page of the DOCX document.
		''' Way #2:
		''' The DOCX document is loaded. DOCX is not a "paged" format and has to be paginated. 
		''' We will convert DOCX to PDF and then to save in DOCX back.
		''' There may be problems with Formatting, because we are doing reverse format conversion.
		''' </summary>
		''' <remarks>
		''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/insert-text-in-specific-page-after-specific-text-net-csharp-vb.php
		''' </remarks>
		Public Shared Sub FindAndReplaceSpecificTextWay2()
			Dim inpFileWord As String = "..\example.docx"
			Dim tempPDFFile As String = "example_temp.pdf"
			Dim outFileWord As String = "result2.docx"
			Dim searchText = "italic"

			Dim dc1 As DocumentCore = DocumentCore.Load(inpFileWord)
			dc1.Save(tempPDFFile)
			Dim dc2 As DocumentCore = DocumentCore.Load(tempPDFFile)
			Dim regex As New Regex(searchText, RegexOptions.IgnoreCase)

			If True Then
				For index As Integer = 0 To dc2.Sections.Count - 1
					Dim page = dc2.Sections(index)
					If dc2.Sections.Count > 2 Then
						' Find and replace a certain text only on the second page of the DOCX document.
						' If you need the first page - 0, the third page - 2, etc.
						For Each item As ContentRange In dc2.Sections(1).Content.Find(regex).Reverse()
							item.Replace("This word has been corrected", New CharacterFormat() With {
								.BackgroundColor = Color.Yellow,
								.FontName = "Arial",
								.Size = 16.0
							})
						Next item
					End If
				Next index
				dc2.Save(outFileWord)
				System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(inpFileWord) With {.UseShellExecute = True})
				System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(outFileWord) With {.UseShellExecute = True})
			End If
		End Sub
	End Class
End Namespace

          

Download.


If you need a new code example or have a question: email us at support@sautinsoft.com or ask at Online Chat (right-bottom corner of this page) or use the Form below:



Questions and suggestions from you are always welcome!

We are developing .Net components since 2002. We know PDF, DOCX, RTF, HTML, XLSX and Images formats. If you need any assistance with creating, modifying or converting documents in various formats, we can help you. We will write any code example for you absolutely free.