How to Extract Embedded Text and Images from PDFs

using IronPdf;
using System.IO;

// This code snippet demonstrates how to extract text from a PDF file and save it to a .txt file.

// Instantiate a PdfDocument object by loading a PDF file from the specified path.
PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

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

// Write the extracted text to a file named "extractedText.txt".
// If the file already exists, it will be overwritten.
File.WriteAllText("extractedText.txt", text);

Imports IronPdf

Imports System.IO



' This code snippet demonstrates how to extract text from a PDF file and save it to a .txt file.



' Instantiate a PdfDocument object by loading a PDF file from the specified path.

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



' Extract all text from the PDF document.

Private text As String = pdf.ExtractAllText()



' Write the extracted text to a file named "extractedText.txt".

' If the file already exists, it will be overwritten.

File.WriteAllText("extractedText.txt", text)

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

// Create a PDF document from the file located at "sample.pdf"
PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// Extract the lines of text from the first page of the PDF
var lines = pdf.Pages[0].Lines;

// Extract the individual characters of text from the first page
var characters = pdf.Pages[0].Characters;

// Write the extracted line information to "lines.txt".
// This includes the vertical position (Y coordinate) and the content of each line.
// The Y coordinate is formatted to two decimal places.
File.WriteAllLines("lines.txt", lines.Select(l => $"at Y={l.BoundingBox.Top:F2}: {l.Contents}"));

// Note: If you intend to use character extraction, you should handle the 'characters' variable accordingly.
// The 'characters' variable holds detailed character information, useful for operations like text search or
// individual character analysis.

Imports IronPdf

Imports System.IO

Imports System.Linq



' Create a PDF document from the file located at "sample.pdf"

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



' Extract the lines of text from the first page of the PDF

Private lines = pdf.Pages(0).Lines



' Extract the individual characters of text from the first page

Private characters = pdf.Pages(0).Characters



' Write the extracted line information to "lines.txt".

' This includes the vertical position (Y coordinate) and the content of each line.

' The Y coordinate is formatted to two decimal places.

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



' Note: If you intend to use character extraction, you should handle the 'characters' variable accordingly.

' The 'characters' variable holds detailed character information, useful for operations like text search or

' individual character analysis.

// Import the necessary IronPdf namespace for handling PDF documents
using IronPdf;

// Load the PDF document from a file
PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// Extract all images contained within the PDF document
var images = pdf.ExtractAllImages();

// Check if the "images" directory exists and create it if it does not
string directoryPath = "images";
if (!System.IO.Directory.Exists(directoryPath))
{
    System.IO.Directory.CreateDirectory(directoryPath);
}

// Loop through each extracted image and save it as a PNG file
for (int i = 0; i < images.Count; i++)
{
    // Save the extracted image to a specified directory with a unique file name
    // Use a numbered sequence to name each image based on its position in the list
    images[i].SaveAs($"{directoryPath}/image{i}.png");
}

' Import the necessary IronPdf namespace for handling PDF documents

Imports IronPdf



' Load the PDF document from a file

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



' Extract all images contained within the PDF document

Private images = pdf.ExtractAllImages()



' Check if the "images" directory exists and create it if it does not

Private directoryPath As String = "images"

If Not System.IO.Directory.Exists(directoryPath) Then

	System.IO.Directory.CreateDirectory(directoryPath)

End If



' Loop through each extracted image and save it as a PNG file

For i As Integer = 0 To images.Count - 1

	' Save the extracted image to a specified directory with a unique file name

	' Use a numbered sequence to name each image based on its position in the list

	images(i).SaveAs($"{directoryPath}/image{i}.png")

Next i

using IronPdf;

// This program demonstrates how to extract text from specific pages of a PDF document using IronPdf library.
//
// Note: Ensure that the IronPdf library is installed and referenced in your project.

// Load a PDF document from a given file path
PdfDocument pdf = PdfDocument.FromFile("sample.pdf");

// Extract text from the first page (Note: page index is zero-based, so index 0 refers to the first page)
string textFromPage1 = pdf.ExtractTextFromPage(0);

// Specify pages to extract text from, using zero-based indices
// In this example, we specify the first page (index 0) and the third page (index 2)
int[] pages = new[] { 0, 2 };

// Extract text from the specified pages (in this case, pages 1 and 3)
string textFromPage1_3 = pdf.ExtractTextFromPages(pages);

// (Optional) Output extracted texts to console for verification
Console.WriteLine("Text from Page 1:");
Console.WriteLine(textFromPage1);

Console.WriteLine("\nText from Pages 1 and 3:");
Console.WriteLine(textFromPage1_3);

Imports Microsoft.VisualBasic

Imports IronPdf



' This program demonstrates how to extract text from specific pages of a PDF document using IronPdf library.

'

' Note: Ensure that the IronPdf library is installed and referenced in your project.



' Load a PDF document from a given file path

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



' Extract text from the first page (Note: page index is zero-based, so index 0 refers to the first page)

Private textFromPage1 As String = pdf.ExtractTextFromPage(0)



' Specify pages to extract text from, using zero-based indices

' In this example, we specify the first page (index 0) and the third page (index 2)

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



' Extract text from the specified pages (in this case, pages 1 and 3)

Private textFromPage1_3 As String = pdf.ExtractTextFromPages(pages)



' (Optional) Output extracted texts to console for verification

Console.WriteLine("Text from Page 1:")

Console.WriteLine(textFromPage1)



Console.WriteLine(vbLf & "Text from Pages 1 and 3:")

Console.WriteLine(textFromPage1_3)