PDFから埋め込まれたテキストと画像を抽出する方法

using IronPdf;
using System.IO;

PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// Extract text
string text = pdf.ExtractAllText();

// Export the extracted text to a text file
File.WriteAllText("extractedText.txt", text);

Imports IronPdf
Imports System.IO

Private pdf As PdfDocument = PdfDocument.FromFile("sample.pdf")

' Extract text
Private text As String = pdf.ExtractAllText()

' Export the extracted text to a text file
File.WriteAllText("extractedText.txt", text)

using IronPdf;
using System.IO;
using System.Linq;

// Open PDF from file
PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// Extract text by lines
var lines = pdf.Pages[0].Lines;

// Extract text by characters
var characters = pdf.Pages[0].Characters;

File.WriteAllLines("lines.txt", lines.Select(l => $"at Y={l.Bottom:F2}: {l.Contents}"));

Imports IronPdf
Imports System.IO
Imports System.Linq

' Open PDF from file
Private pdf As PdfDocument = PdfDocument.FromFile("sample.pdf")

' Extract text by lines
Private lines = pdf.Pages(0).Lines

' Extract text by characters
Private characters = pdf.Pages(0).Characters

File.WriteAllLines("lines.txt", lines.Select(Function(l) $"at Y={l.Bottom:F2}: {l.Contents}"))

using IronPdf;

PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// Extract images
var images = pdf.ExtractAllImages();

for(int i = 0; i < images.Count; i++)
{
    // Export the extracted images
    images[i].SaveAs($"images/image{i}.png");
}

Imports IronPdf

Private pdf As PdfDocument = PdfDocument.FromFile("sample.pdf")

' Extract images
Private images = pdf.ExtractAllImages()

For i As Integer = 0 To images.Count - 1
	' Export the extracted images
	images(i).SaveAs($"images/image{i}.png")
Next i

using IronPdf;

PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// Extract text from page 1
string textFromPage1 = pdf.ExtractTextFromPage(0);

int[] pages = new[] { 0, 2 };

// Extract text from pages 1 & 3
string textFromPage1_3 = pdf.ExtractTextFromPages(pages);

Imports IronPdf

Private pdf As PdfDocument = PdfDocument.FromFile("sample.pdf")

' Extract text from page 1
Private textFromPage1 As String = pdf.ExtractTextFromPage(0)

Private pages() As Integer = { 0, 2 }

' Extract text from pages 1 & 3
Private textFromPage1_3 As String = pdf.ExtractTextFromPages(pages)