IronPDF対iTextSharp: C#でのPDFファイル読み込み

using IronPdf;

// Begin the comparison of IronPDF and iTextSharp for reading PDFs in C#
Console.WriteLine("Comparison of IronPDF And iTextSharp Read PDF Files in C#");

// Read PDF using IronPDF
ReadUsingIronPdf.Read();

public class ReadUsingIronPDF
{
    public static void Read()
    {
        // Specify the path to the PDF document
        string filename = "C:\\code\\articles\\ITextSharp\\ITextSharpIronPdfDemo\\Example.pdf";

        // Create a PDF Reader instance to read the PDF
        // IronPDF automatically handles various PDF versions and encryption
        var pdfReader = PdfDocument.FromFile(filename);

        // Extract all text from the PDF - maintains formatting and structure
        var allText = pdfReader.ExtractAllText();
        Console.WriteLine("------------------Text From PDF-----------------");
        Console.WriteLine(allText);
        Console.WriteLine("------------------Text From PDF-----------------");

        // Extract all images from the PDF - supports various image formats
        var allImages = pdfReader.ExtractAllImages();
        Console.WriteLine("------------------Image Count From PDF-----------------");
        Console.WriteLine($"Total Images = {allImages.Count()}");

        // Save extracted images if needed (production example)
        for (int i = 0; i < allImages.Count(); i++)
        {
            // allImages[i].SaveAs($"image_{i}.png");
        }
        Console.WriteLine("------------------Image Count From PDF-----------------");

        // Iterate through each page to extract text from them
        Console.WriteLine("------------------One Page Text From PDF-----------------");
        var pageCount = pdfReader.PageCount;
        for (int page = 0; page < pageCount; page++)
        {
            string text = pdfReader.ExtractTextFromPage(page);
            Console.WriteLine($"Page {page + 1} content:");
            Console.WriteLine(text);
        }

        // Additional IronPDF capabilities for production use
        // Extract form data
        var form = pdfReader.Form;
        if (form != null)
        {
            foreach (var field in form.Fields)
            {
                Console.WriteLine($"Form Field: {field.Name} = {field.Value}");
            }
        }

        // Access metadata
        Console.WriteLine($"Author: {pdfReader.MetaData.Author}");
        Console.WriteLine($"Title: {pdfReader.MetaData.Title}");
        Console.WriteLine($"Created: {pdfReader.MetaData.CreationDate}");
    }
}

Imports IronPdf

' Begin the comparison of IronPDF and iTextSharp for reading PDFs in C#
Console.WriteLine("Comparison of IronPDF And iTextSharp Read PDF Files in C#")

' Read PDF using IronPDF
ReadUsingIronPDF.Read()

Public Class ReadUsingIronPDF
    Public Shared Sub Read()
        ' Specify the path to the PDF document
        Dim filename As String = "C:\code\articles\ITextSharp\ITextSharpIronPdfDemo\Example.pdf"

        ' Create a PDF Reader instance to read the PDF
        ' IronPDF automatically handles various PDF versions and encryption
        Dim pdfReader = PdfDocument.FromFile(filename)

        ' Extract all text from the PDF - maintains formatting and structure
        Dim allText = pdfReader.ExtractAllText()
        Console.WriteLine("------------------Text From PDF-----------------")
        Console.WriteLine(allText)
        Console.WriteLine("------------------Text From PDF-----------------")

        ' Extract all images from the PDF - supports various image formats
        Dim allImages = pdfReader.ExtractAllImages()
        Console.WriteLine("------------------Image Count From PDF-----------------")
        Console.WriteLine($"Total Images = {allImages.Count()}")

        ' Save extracted images if needed (production example)
        For i As Integer = 0 To allImages.Count() - 1
            ' allImages(i).SaveAs($"image_{i}.png")
        Next
        Console.WriteLine("------------------Image Count From PDF-----------------")

        ' Iterate through each page to extract text from them
        Console.WriteLine("------------------One Page Text From PDF-----------------")
        Dim pageCount = pdfReader.PageCount
        For page As Integer = 0 To pageCount - 1
            Dim text As String = pdfReader.ExtractTextFromPage(page)
            Console.WriteLine($"Page {page + 1} content:")
            Console.WriteLine(text)
        Next

        ' Additional IronPDF capabilities for production use
        ' Extract form data
        Dim form = pdfReader.Form
        If form IsNot Nothing Then
            For Each field In form.Fields
                Console.WriteLine($"Form Field: {field.Name} = {field.Value}")
            Next
        End If

        ' Access metadata
        Console.WriteLine($"Author: {pdfReader.MetaData.Author}")
        Console.WriteLine($"Title: {pdfReader.MetaData.Title}")
        Console.WriteLine($"Created: {pdfReader.MetaData.CreationDate}")
    End Sub
End Class

using IronPdf;
using iText.Kernel.Pdf;
using iText.Kernel.Pdf.Canvas.Parser.Listener;
using iText.Kernel.Pdf.Canvas.Parser;
using iText.Kernel.Pdf.Xobject;

// Begin the comparison of IronPDF and iTextSharp for reading PDFs in C#
Console.WriteLine("Comparison of IronPDF And iTextSharp Read PDF Files in C#");

// Call method to read PDF using iTextSharp library
ReadUsingITextSharp.Read();

public class ReadUsingITextSharp
{
    public static void Read()
    {
        // Specify the path to the PDF document
        string pdfFile = "C:\\code\\articles\\ITextSharp\\ITextSharpIronPdfDemo\\Example.pdf";

        // Create a PDF Reader instance - more verbose than IronPDF
        PdfReader pdfReader = new PdfReader(pdfFile);

        // Initialize a new PDF Document - additional step required
        iText.Kernel.Pdf.PdfDocument pdfDocument = new iText.Kernel.Pdf.PdfDocument(pdfReader);

        // Extract text from all pages - more complex than IronPDF
        Console.WriteLine("------------------Text From PDF (iTextSharp)-----------------");
        for (int page = 1; page <= pdfDocument.GetNumberOfPages(); page++)
        {
            // Use a text extraction strategy to extract plain text from the PDF
            LocationTextExtractionStrategy strategy = new LocationTextExtractionStrategy();
            string pdfText = PdfTextExtractor.GetTextFromPage(pdfDocument.GetPage(page), strategy);
            Console.WriteLine($"Page {page} content:");
            Console.WriteLine(pdfText);
        }

        // Extract images - significantly more complex than IronPDF
        Console.WriteLine("------------------Images From PDF (iTextSharp)-----------------");
        int imageCount = 0;
        for (int pageNum = 1; pageNum <= pdfDocument.GetNumberOfPages(); pageNum++)
        {
            var page = pdfDocument.GetPage(pageNum);
            var resources = page.GetResources();
            var xobjects = resources.GetResource(PdfName.XObject);

            if (xobjects != null)
            {
                foreach (var key in xobjects.KeySet())
                {
                    var xobject = xobjects.GetAsStream(key);
                    if (xobject != null)
                    {
                        var pdfObject = xobjects.Get(key);
                        if (pdfObject.IsStream())
                        {
                            var stream = (PdfStream)pdfObject;
                            var subtype = stream.GetAsName(PdfName.Subtype);
                            if (PdfName.Image.Equals(subtype))
                            {
                                imageCount++;
                                // Extracting the actual image requires additional complex code
                            }
                        }
                    }
                }
            }
        }
        Console.WriteLine($"Total Images Found: {imageCount}");

        // Close the document - manual resource management required
        pdfDocument.Close();
        pdfReader.Close();
    }
}

Imports IronPdf
Imports iText.Kernel.Pdf
Imports iText.Kernel.Pdf.Canvas.Parser.Listener
Imports iText.Kernel.Pdf.Canvas.Parser
Imports iText.Kernel.Pdf.Xobject

' Begin the comparison of IronPDF and iTextSharp for reading PDFs in VB.NET
Console.WriteLine("Comparison of IronPDF And iTextSharp Read PDF Files in VB.NET")

' Call method to read PDF using iTextSharp library
ReadUsingITextSharp.Read()

Public Class ReadUsingITextSharp
    Public Shared Sub Read()
        ' Specify the path to the PDF document
        Dim pdfFile As String = "C:\code\articles\ITextSharp\ITextSharpIronPdfDemo\Example.pdf"

        ' Create a PDF Reader instance - more verbose than IronPDF
        Dim pdfReader As New PdfReader(pdfFile)

        ' Initialize a new PDF Document - additional step required
        Dim pdfDocument As New iText.Kernel.Pdf.PdfDocument(pdfReader)

        ' Extract text from all pages - more complex than IronPDF
        Console.WriteLine("------------------Text From PDF (iTextSharp)-----------------")
        For page As Integer = 1 To pdfDocument.GetNumberOfPages()
            ' Use a text extraction strategy to extract plain text from the PDF
            Dim strategy As New LocationTextExtractionStrategy()
            Dim pdfText As String = PdfTextExtractor.GetTextFromPage(pdfDocument.GetPage(page), strategy)
            Console.WriteLine($"Page {page} content:")
            Console.WriteLine(pdfText)
        Next

        ' Extract images - significantly more complex than IronPDF
        Console.WriteLine("------------------Images From PDF (iTextSharp)-----------------")
        Dim imageCount As Integer = 0
        For pageNum As Integer = 1 To pdfDocument.GetNumberOfPages()
            Dim page = pdfDocument.GetPage(pageNum)
            Dim resources = page.GetResources()
            Dim xobjects = resources.GetResource(PdfName.XObject)

            If xobjects IsNot Nothing Then
                For Each key In xobjects.KeySet()
                    Dim xobject = xobjects.GetAsStream(key)
                    If xobject IsNot Nothing Then
                        Dim pdfObject = xobjects.Get(key)
                        If pdfObject.IsStream() Then
                            Dim stream As PdfStream = CType(pdfObject, PdfStream)
                            Dim subtype = stream.GetAsName(PdfName.Subtype)
                            If PdfName.Image.Equals(subtype) Then
                                imageCount += 1
                                ' Extracting the actual image requires additional complex code
                            End If
                        End If
                    End If
                Next
            End If
        Next
        Console.WriteLine($"Total Images Found: {imageCount}")

        ' Close the document - manual resource management required
        pdfDocument.Close()
        pdfReader.Close()
    End Sub
End Class