从PDF中提取文本在C#中：使用iTextSharp与IronPDF

using IronPdf;

// Load the PDF document
var pdf = PdfDocument.FromFile("invoice.pdf");

// Extract text from the PDF
string extractedText = pdf.ExtractAllText();

// Output the extracted text
Console.WriteLine(extractedText);

Imports IronPdf

' Load the PDF document
Private pdf = PdfDocument.FromFile("invoice.pdf")

' Extract text from the PDF
Private extractedText As String = pdf.ExtractAllText()

' Output the extracted text
Console.WriteLine(extractedText)

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

// Define the path to your PDF
string path = "sample.pdf";

// Open the PDF reader and document
using (PdfReader reader = new PdfReader(path))
using (PdfDocument pdf = new PdfDocument(reader))
{
    // Use a simple text extraction strategy
    var strategy = new SimpleTextExtractionStrategy();

    // Extract text from the first page
    string pageText = PdfTextExtractor.GetTextFromPage(pdf.GetPage(1), strategy);

    // Output the extracted text
    Console.WriteLine(pageText);
}

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

' Define the path to your PDF
Private path As String = "sample.pdf"

' Open the PDF reader and document
Using reader As New PdfReader(path)
Using pdf As New PdfDocument(reader)
	' Use a simple text extraction strategy
	Dim strategy = New SimpleTextExtractionStrategy()

	' Extract text from the first page
	Dim pageText As String = PdfTextExtractor.GetTextFromPage(pdf.GetPage(1), strategy)

	' Output the extracted text
	Console.WriteLine(pageText)
End Using
End Using

using IronPdf;

// Load the PDF document
var pdf = PdfDocument.FromFile("longPdf.pdf");

// Define the page numbers to extract text from
int[] pages = new[] { 2, 3, 4 };

// Extract text from the specified pages
var text = pdf.ExtractTextFromPages(pages);

// Output the extracted text
Console.WriteLine("Extracted text from pages 2, 3, and 4:\n" + text);

Imports Microsoft.VisualBasic
Imports IronPdf

' Load the PDF document
Private pdf = PdfDocument.FromFile("longPdf.pdf")

' Define the page numbers to extract text from
Private pages() As Integer = { 2, 3, 4 }

' Extract text from the specified pages
Private text = pdf.ExtractTextFromPages(pages)

' Output the extracted text
Console.WriteLine("Extracted text from pages 2, 3, and 4:" & vbLf & text)

using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
using System.IO;
using System.Text;

// Load the PDF document
PdfReader reader = new PdfReader("longPdf.pdf");
StringBuilder textBuilder = new StringBuilder();

// Extract text from pages 2–4
for (int i = 2; i <= 4; i++)
{
    string pageText = PdfTextExtractor.GetTextFromPage(reader, i, new LocationTextExtractionStrategy());
    textBuilder.AppendLine(pageText);
}

// Output the extracted text
Console.WriteLine(textBuilder.ToString());

// Close the PDF reader
reader.Close();

Imports iTextSharp.text.pdf
Imports iTextSharp.text.pdf.parser
Imports System.IO
Imports System.Text

' Load the PDF document
Private reader As New PdfReader("longPdf.pdf")
Private textBuilder As New StringBuilder()

' Extract text from pages 2–4
For i As Integer = 2 To 4
	Dim pageText As String = PdfTextExtractor.GetTextFromPage(reader, i, New LocationTextExtractionStrategy())
	textBuilder.AppendLine(pageText)
Next i

' Output the extracted text
Console.WriteLine(textBuilder.ToString())

' Close the PDF reader
reader.Close()

using IronPdf;

// Load the PDF
var pdf = PdfDocument.FromFile("sample.pdf");

// Extract all text from every page
string extractedText = pdf.ExtractAllText();

// Output the extracted text
Console.WriteLine(extractedText);

Imports IronPdf

' Load the PDF
Private pdf = PdfDocument.FromFile("sample.pdf")

' Extract all text from every page
Private extractedText As String = pdf.ExtractAllText()

' Output the extracted text
Console.WriteLine(extractedText)

using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
using System.IO;
using System.Text;

// Load the PDF
var reader = new PdfReader("sample.pdf");
StringBuilder text = new StringBuilder();

for (int i = 1; i <= reader.NumberOfPages; i++)
{
    text.Append(PdfTextExtractor.GetTextFromPage(reader, i));
}

// Output the extracted text
Console.WriteLine(text.ToString());

Imports iTextSharp.text.pdf
Imports iTextSharp.text.pdf.parser
Imports System.IO
Imports System.Text

' Load the PDF
Private reader = New PdfReader("sample.pdf")
Private text As New StringBuilder()

For i As Integer = 1 To reader.NumberOfPages
	text.Append(PdfTextExtractor.GetTextFromPage(reader, i))
Next i

' Output the extracted text
Console.WriteLine(text.ToString())