C#/VB.NET: PDF 문서에서 텍스트 추출

PM> Install-Package Spire.PDF

using System;
    using System.IO;
    using Spire.Pdf;
    using Spire.Pdf.Texts;
    
    namespace ExtractTextFromPage
    {
        class Program
        {
            static void Main(string[] args)
            {
                //Create a PdfDocument object
                PdfDocument doc = new PdfDocument();
    
                //Load a PDF file
                doc.LoadFromFile(@"C:\Users\Administrator\Desktop\Terms of Service.pdf");
    
                //Get the second page
                PdfPageBase page = doc.Pages[1];
    
                //Create a PdfTextExtractot object
                PdfTextExtractor textExtractor = new PdfTextExtractor(page);
    
                //Create a PdfTextExtractOptions object
                PdfTextExtractOptions extractOptions = new PdfTextExtractOptions();
    
                //Set isExtractAllText to true
                extractOptions.IsExtractAllText = true;
    
                //Extract text from the page
                string text = textExtractor.ExtractText(extractOptions);
    
                //Write to a txt file
                File.WriteAllText("Extracted.txt", text);
            }
        }
    }

Imports System
    Imports System.IO
    Imports Spire.Pdf
    Imports Spire.Pdf.Texts
    
    Namespace ExtractTextFromPage
        Class Program
            Shared  Sub Main(ByVal args() As String)
                'Create a PdfDocument object
                Dim doc As PdfDocument =  New PdfDocument()
    
                'Load a PDF file
                doc.LoadFromFile("C:\Users\Administrator\Desktop\Terms of Service.pdf")
    
                'Get the second page
                Dim page As PdfPageBase =  doc.Pages(1)
    
                'Create a PdfTextExtractot object
                Dim textExtractor As PdfTextExtractor =  New PdfTextExtractor(page)
    
                'Create a PdfTextExtractOptions object
                Dim extractOptions As PdfTextExtractOptions =  New PdfTextExtractOptions()
    
                'Set isExtractAllText to true
                extractOptions.IsExtractAllText = True
    
                'Extract text from the page
                Dim text As String =  textExtractor.ExtractText(extractOptions)
    
                'Write to a txt file
                File.WriteAllText("Extracted.txt", text)
            End Sub
        End Class
    End Namespace

using Spire.Pdf;
    using Spire.Pdf.Texts;
    using System.IO;
    using System.Drawing;
    
    namespace ExtractTextFromRectangleArea
    {
        class Program
        {
            static void Main(string[] args)
            {
                //Create a PdfDocument object
                PdfDocument doc = new PdfDocument();
    
                //Load a PDF file
                doc.LoadFromFile(@"C:\Users\Administrator\Desktop\Terms of Service.pdf");
    
                //Get the second page
                PdfPageBase page = doc.Pages[1];
    
                //Create a PdfTextExtractot object
                PdfTextExtractor textExtractor = new PdfTextExtractor(page);
    
                //Create a PdfTextExtractOptions object
                PdfTextExtractOptions extractOptions = new PdfTextExtractOptions();
    
                //Set the rectangle area
                extractOptions.ExtractArea = new RectangleF(0, 0, 890, 170);
    
                //Extract text from the rectangle
                string text = textExtractor.ExtractText(extractOptions);
    
                //Write to a txt file
                File.WriteAllText("Extracted.txt", text);
            }
        }
    }

Imports Spire.Pdf
    Imports Spire.Pdf.Texts
    Imports System.IO
    Imports System.Drawing
    
    Namespace ExtractTextFromRectangleArea
        Class Program
            Shared  Sub Main(ByVal args() As String)
                'Create a PdfDocument object
                Dim doc As PdfDocument =  New PdfDocument()
    
                'Load a PDF file
                doc.LoadFromFile("C:\Users\Administrator\Desktop\Terms of Service.pdf")
    
                'Get the second page
                Dim page As PdfPageBase =  doc.Pages(1)
    
                'Create a PdfTextExtractot object
                Dim textExtractor As PdfTextExtractor =  New PdfTextExtractor(page)
    
                'Create a PdfTextExtractOptions object
                Dim extractOptions As PdfTextExtractOptions =  New PdfTextExtractOptions()
    
                'Set the rectangle area
                extractOptions.ExtractArea = New RectangleF(0, 0, 890, 170)
    
                'Extract text from the rectangle
                Dim text As String =  textExtractor.ExtractText(extractOptions)
    
                'Write to a txt file
                File.WriteAllText("Extracted.txt", text)
            End Sub
        End Class
    End Namespace

using System.IO;
    using Spire.Pdf;
    using Spire.Pdf.Texts;
    
    namespace SimpleExtraction
    {
        class Program
        {
            static void Main(string[] args)
            {
                //Create a PdfDocument object
                PdfDocument doc = new PdfDocument();
    
                //Load a PDF file
                doc.LoadFromFile(@"C:\Users\Administrator\Desktop\Invoice.pdf");
    
                //Get the first page
                PdfPageBase page = doc.Pages[0];
    
                //Create a PdfTextExtractor object
                PdfTextExtractor textExtractor = new PdfTextExtractor(page);
    
                //Create a PdfTextExtractOptions object
                PdfTextExtractOptions extractOptions = new PdfTextExtractOptions();
    
                //Set IsSimpleExtraction to true
                extractOptions.IsSimpleExtraction = true;
    
                //Extract text from the selected page
                string text = textExtractor.ExtractText(extractOptions);
    
                //Write to a txt file
                File.WriteAllText("Extracted.txt", text);
            }
        }
    }

Imports System.IO
    Imports Spire.Pdf
    Imports Spire.Pdf.Texts
    
    Namespace SimpleExtraction
        Class Program
            Shared  Sub Main(ByVal args() As String)
                'Create a PdfDocument object
                Dim doc As PdfDocument =  New PdfDocument()
    
                'Load a PDF file
                doc.LoadFromFile("C:\Users\Administrator\Desktop\Invoice.pdf")
    
                'Get the first page
                Dim page As PdfPageBase =  doc.Pages(0)
    
                'Create a PdfTextExtractor object
                Dim textExtractor As PdfTextExtractor =  New PdfTextExtractor(page)
    
                'Create a PdfTextExtractOptions object
                Dim extractOptions As PdfTextExtractOptions =  New PdfTextExtractOptions()
    
                'Set IsSimpleExtraction to true
                extractOptions.IsSimpleExtraction = True
    
                'Extract text from the selected page
                Dim text As String =  textExtractor.ExtractText(extractOptions)
    
                'Write to a txt file
                File.WriteAllText("Extracted.txt", text)
            End Sub
        End Class
    End Namespace