Как конвертировать DOCX в HTML на C# и .NET

  1. Добавьте SautinSoft.Document из Nuget.
  2. Загрузите входной документ.
  3. Сохраните в формате HTML.

SautinSoft.Document может помочь Вашему приложению преобразовать документ из одного формата в другой.
Вам нужно будет только Load() документ и Save() в нужном формате:


            DocumentCore dc = DocumentCore.Load("...");
            dc.Save("....");

Полный код

using System.IO;
using SautinSoft.Document;

namespace Example
{
    class Program
    {
        static void Main(string[] args)
        {
            // Get your free 30-day key here:   
            // https://sautinsoft.com/start-for-free/

            ConvertFromFile();
            ConvertFromStream();
        }

        /// <summary>
        /// Convert DOCX to HTML (file to file).
        /// </summary>
		/// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-docx-to-html-in-csharp-vb.php
        /// </remarks>
        static void ConvertFromFile()
        {
            string inpFile = @"..\..\..\example.docx";
            string outFile = @"Result.html";

            DocumentCore dc = DocumentCore.Load(inpFile);
            dc.Save(outFile);

            // Open the result for demonstration purposes.
            System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile) { UseShellExecute = true });
        }

        /// <summary>
        /// Convert DOCX to HTML (using Stream).
        /// </summary>
		/// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-docx-to-html-in-csharp-vb.php
        /// </remarks>
        static void ConvertFromStream()
        {

            // We need files only for demonstration purposes.
            // The conversion process will be done completely in memory.
            string inpFile = @"..\..\..\example.docx";
            string outFile = @"ResultStream.html";
            byte[] inpData = File.ReadAllBytes(inpFile);
            byte[] outData = null;

            using (MemoryStream msInp = new MemoryStream(inpData))
            {

                // Load a document.
                DocumentCore dc = DocumentCore.Load(msInp, new DocxLoadOptions());

                // Save the document to HTML format.
                using (MemoryStream outMs = new MemoryStream())
                {
                    dc.Save(outMs, new HtmlFixedSaveOptions());
                    outData = outMs.ToArray();
                }
                // Show the result for demonstration purposes.
                if (outData != null)
                {
                    File.WriteAllBytes(outFile, outData);
                    System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(outFile) { UseShellExecute = true });
                }
            }
        }
    }
}

Download

Imports System
Imports System.IO
Imports SautinSoft.Document

Module Sample
    Sub Main()
        ConvertFromFile()
        ConvertFromStream()
    End Sub
    ''' Get your free 30-day key here:   
    ''' https://sautinsoft.com/start-for-free/
    ''' <summary>
    ''' Convert DOCX to HTML (file to file).
    ''' </summary>
    ''' <remarks>
    ''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-docx-to-html-in-csharp-vb.php
    ''' </remarks>
    Sub ConvertFromFile()
        Dim inpFile As String = "..\..\..\example.docx"
        Dim outFile As String = "Result.html"

        Dim dc As DocumentCore = DocumentCore.Load(inpFile)
        dc.Save(outFile)

        ' Open the result for demonstration purposes.
        System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(outFile) With {.UseShellExecute = True})
    End Sub

    ''' <summary>
    ''' Convert DOCX to HTML (using Stream).
    ''' </summary>
    ''' <remarks>
    ''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-docx-to-html-in-csharp-vb.php
    ''' </remarks>
    Sub ConvertFromStream()

        ' We need files only for demonstration purposes.
        ' The conversion process will be done completely in memory.
        Dim inpFile As String = "..\..\..\example.docx"
        Dim outFile As String = "ResultStream.html"
        Dim inpData() As Byte = File.ReadAllBytes(inpFile)
        Dim outData() As Byte = Nothing

        Using msInp As New MemoryStream(inpData)

            ' Load a document.
            Dim dc As DocumentCore = DocumentCore.Load(msInp, New DocxLoadOptions())

            ' Save the document to HTML format.
            Using outMs As New MemoryStream()
                dc.Save(outMs, New HtmlFixedSaveOptions())
                outData = outMs.ToArray()
            End Using
            ' Show the result for demonstration purposes.
            If outData IsNot Nothing Then
                File.WriteAllBytes(outFile, outData)
                System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(outFile) With {.UseShellExecute = True})
            End If
        End Using
    End Sub
End Module

Download


Если вам нужен пример кода или у вас есть вопрос: напишите нам по адресу [email protected] или спросите в онлайн-чате (правый нижний угол этой страницы) или используйте форму ниже:



Вопросы и предложения всегда приветствуются!

Мы разрабатываем компоненты .Net с 2002 года. Мы знаем форматы PDF, DOCX, RTF, HTML, XLSX и Images. Если вам нужна помощь в создании, изменении или преобразовании документов в различных форматах, мы можем вам помочь. Мы напишем для вас любой пример кода абсолютно бесплатно.