Как загрузить PDF документ на C# и .NET

  1. Добавьте SautinSoft.Document из Nuget.
  2. Загрузите PDF-документ из файла или потока.
  1. Загрузить из файла: 
    
DocumentCore dc = DocumentCore.Load(@"d:\Book.pdf");
    Объект dc представляет собой документ "Book.pdf", загруженный в память. Формат файла определяется автоматически по расширению файла: ".pdf".

    После загрузки Вы получите документ, представленный в виде Tree Of Objects, где корневым узлом является класс DocumentCore.

    Чтобы гарантировать, что загружаемый контент действительно является PDF, и установить некоторые параметры загрузки, используя PdfLoadOptions в качестве второго параметра. 

    
DocumentCore dc = DocumentCore.Load(@"d:\Book.pdf", new PdfLoadOptions());
  2. Загрузка из потока: 
    
            // Assume that we already have a PDF document as bytes array.
            byte[] pdfBytes = null;
            // pdfBytes = ...

            DocumentCore dc = null;
            using (MemoryStream pdfStream = new MemoryStream(fileBytes))
            {
                // Specifying PdfLoadOptions we explicitly set that a loadable document is PDF.
                PdfLoadOptions pdfLO = new PdfLoadOptions()
                {
                    // 'false' - means to load vector graphics as is. Don't transform it to raster images.
                    RasterizeVectorGraphics = false,

                    // The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
                    // In case of 'true' the component will detect and recreate tables from graphic lines.
                    DetectTables = false,

                    // 'Disabled' - Never load embedded fonts in PDF. Use the fonts with the same name installed at the system or similar by font metrics.
					// 'Enabled' - Always load embedded fonts in PDF.
					// 'Auto' - Load only embedded fonts missing in the system. In other case, use the system fonts.
                    PreserveEmbeddedFonts = PropertyState.Auto,

                    // Load only the 1st page from the document.
                    PageIndex = 0,
                    PageCount = 1
                };

                // Load a PDF document from the MemoryStream.
                dc = DocumentCore.Load(pdfStream, new PdfLoadOptions());
            }
            // Here we can do with our document 'dc' anything we need.

Полный код

using System;
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/

            LoadPDFFromFile();
            //LoadPDFFromStream();
        }

        /// <summary>
        /// Loads a PDF document into DocumentCore (dc) from a file.
        /// </summary>
        /// <remarks>
        /// Details: https://www.sautinsoft.com/products/document/help/net/developer-guide/load-pdf-document-net-csharp-vb.php
        /// </remarks>
        static void LoadPDFFromFile()
        {
            string filePath = @"..\..\..\example.pdf";

            // The file format is detected automatically from the file extension: ".pdf".
            // But as shown in the example below, we can specify PdfLoadOptions as 2nd parameter
            // to explicitly set that a loadable document has PDF format.
            DocumentCore dc = DocumentCore.Load(filePath);

            if (dc != null)
                Console.WriteLine("Loaded successfully!");
			
			Console.ReadKey();			
        }

        /// <summary>
        /// Loads a PDF document into DocumentCore (dc) from a MemoryStream.
        /// </summary>
        /// <remarks>
        /// Details: https://www.sautinsoft.com/products/document/help/net/developer-guide/load-pdf-document-net-csharp-vb.php
        /// </remarks>
        static void LoadPDFFromStream()
        {
            // Assume that we already have a PDF document as bytes array.
            byte[] fileBytes = File.ReadAllBytes(@"..\..\..\example.pdf");

            DocumentCore dc = null;

            // Create a MemoryStream
            using (MemoryStream pdfStream = new MemoryStream(fileBytes))
            {
                // Specifying PdfLoadOptions we explicitly set that a loadable document is PDF.
                PdfLoadOptions pdfLO = new PdfLoadOptions()
                {
                    // 'false' - means to load vector graphics as is. Don't transform it to raster images.
                    RasterizeVectorGraphics = false,

                    // The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
                    // In case of 'true' the component will detect and recreate tables from graphic lines.
                    DetectTables = false,

                    // 'Disabled' - Never load embedded fonts in PDF. Use the fonts with the same name installed at the system or similar by font metrics.
					// 'Enabled' - Always load embedded fonts in PDF.
					// 'Auto' - Load only embedded fonts missing in the system. In other case, use the system fonts.
                    PreserveEmbeddedFonts = PropertyState.Auto,

                    // Load only the 1st page from the document.
                    PageIndex = 0,
                    PageCount = 1
                };

                // Load a PDF document from the MemoryStream.
                dc = DocumentCore.Load(pdfStream, new PdfLoadOptions());
            }
            if (dc != null)
                Console.WriteLine("Loaded successfully!");
			
			Console.ReadKey();			
        }
    }
}

Download

Imports System
Imports System.IO
Imports SautinSoft.Document

Module Sample
    Sub Main()
        LoadPDFFromFile()
        'LoadPDFFromStream()
    End Sub
    ''' Get your free 100-day key here:   
    ''' https://sautinsoft.com/start-for-free/
    ''' <summary>
    ''' Loads a PDF document into DocumentCore (dc) from a file.
    ''' </summary>
    ''' <remarks>
    ''' Details: https://www.sautinsoft.com/products/document/help/net/developer-guide/load-pdf-document-net-csharp-vb.php
    ''' </remarks>
    Sub LoadPDFFromFile()
        Dim filePath As String = "..\..\..\example.pdf"

        ' The file format is detected automatically from the file extension: ".pdf".
        ' But as shown in the example below, we can specify PdfLoadOptions as 2nd parameter
        ' to explicitly set that a loadable document has PDF format.
        Dim dc As DocumentCore = DocumentCore.Load(filePath)

        If dc IsNot Nothing Then
            Console.WriteLine("Loaded successfully!")
        End If

        Console.ReadKey()
    End Sub

    ''' <summary>
    ''' Loads a PDF document into DocumentCore (dc) from a MemoryStream.
    ''' </summary>
    ''' <remarks>
    ''' Details: https://www.sautinsoft.com/products/document/help/net/developer-guide/load-pdf-document-net-csharp-vb.php
    ''' </remarks>
    Sub LoadPDFFromStream()
        ' Assume that we already have a PDF document as bytes array.
        Dim fileBytes() As Byte = File.ReadAllBytes("..\..\..\example.pdf")

        Dim dc As DocumentCore = Nothing

        ' Create a MemoryStream
        Using pdfStream As New MemoryStream(fileBytes)

            ' Specifying PdfLoadOptions we explicitly set that a loadable document is PDF.
            Dim pdfLO As New PdfLoadOptions()
            With pdfLO
                .RasterizeVectorGraphics = False
                .DetectTables = False
                ' 'Disabled' - Never load embedded fonts in PDF. Use the fonts with the same name installed at the system or similar by font metrics.
                ' 'Enabled' - Always load embedded fonts in PDF.
                ' 'Auto' - Load only embedded fonts missing in the system. In other case, use the system fonts.
                .PreserveEmbeddedFonts = PropertyState.Auto
                .PageIndex = 0
                .PageCount = 1
            End With

            ' RasterizeVectorGraphics = False
            ' This means to load vector graphics as is. Don't transform it to raster images.

            ' DetectTables = False
            ' This means don't detect tables.
            ' The PDF format doesn't have real tables, in fact it's a set of orthogonal graphic lines.
            ' Set it to 'True' and the component will detect and recreate tables from graphic lines.

            ' Load a PDF document from the MemoryStream.
            dc = DocumentCore.Load(pdfStream, New PdfLoadOptions())
        End Using
        If dc IsNot Nothing Then
            Console.WriteLine("Loaded successfully!")
        End If

        Console.ReadKey()
    End Sub
End Module

Download

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