Как конвертировать HTML в текст на C# и .NET

  1. Добавьте SautinSoft.Document из Nuget.
  2. Загрузите входной документ.
  3. Сохраните в текстовый формат.

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("....");

SautinSoft.Document поддерживает форматы:

PDF DOCX RTF HTML Текст Изображения
Create/Read/Write Create/Read/Write Create/Read/Write Create/Read/Write Create/Read/Write Create/Read(OCR)/Write

Полный код

using System.IO;
using SautinSoft.Document;

namespace Example
{
    class Program
    {
        static void Main(string[] args)
        {
            // Get your free 100-day key here:   
            // https://sautinsoft.com/start-for-free/

            ConvertFromFile();
            ConvertFromStream();
        }

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

            DocumentCore dc = DocumentCore.Load(inpFile);
            dc.Save(outFile);
			
			// Important for Linux: Install MS Fonts
			// sudo apt install ttf-mscorefonts-installer -y

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

        /// <summary>
        /// Convert HTML to Text (using Stream).
        /// </summary>
		/// <remarks>
        /// Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-html-to-text-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.html";
            string outFile = @"ResultStream.txt";
            byte[] inpData = File.ReadAllBytes(inpFile);
            byte[] outData = null;

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

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

                // Save the document to Text format.
                using (MemoryStream outMs = new MemoryStream())
                {
                    dc.Save(outMs, new TxtSaveOptions() );
                    outData = outMs.ToArray();

			// Important for Linux: Install MS Fonts
			// sudo apt install ttf-mscorefonts-installer -y
                    
                }
                // 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.IO
Imports SautinSoft.Document

Namespace Example
	Friend Class Program
		Shared Sub Main(ByVal args() As String)
			ConvertFromFile()
			ConvertFromStream()
		End Sub
                ''' Get your free 100-day key here:   
                ''' https://sautinsoft.com/start-for-free/
		''' <summary>
		''' Convert HTML to Text (file to file).
		''' </summary>
		''' <remarks>
		''' Details: https://sautinsoft.com/products/document/help/net/developer-guide/convert-html-to-text-in-csharp-vb.php
		''' </remarks>
		Private Shared Sub ConvertFromFile()
			Dim inpFile As String = "..\..\..\example.html"
			Dim outFile As String = "Result.txt"

			Dim dc As DocumentCore = DocumentCore.Load(inpFile)
			dc.Save(outFile)
			
			' Important for Linux: Install MS Fonts
			' sudo apt install ttf-mscorefonts-installer -y

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

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

			' We need files only for demonstration purposes.
			' The conversion process will be done completely in memory.
			Dim inpFile As String = "..\..\..\example.html"
			Dim outFile As String = "ResultStream.txt"
			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 HtmlLoadOptions())

				' Save the document to Text format.
				Using outMs As New MemoryStream()
					dc.Save(outMs, New TxtSaveOptions())
					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 Class
End Namespace

Download

Если вам нужен пример кода или у вас есть вопрос: напишите нам по адресу support@sautinsoft.com 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.