How to Read PDFs

using IronOcr;

// The IronTesseract class is the primary class from IronOCR used for performing OCR operations.
var ocrTesseract = new IronTesseract();

// Using statement ensures the OcrPdfInput object is disposed of after use,
// which helps in freeing up resources. This input represents a PDF file to be processed.
using (var pdfInput = new OcrPdfInput("Potter.pdf"))
{
    // Perform OCR on the PDF input. The Read method processes the given PDF and outputs the result.
    // OcrResult holds the extracted text and other metadata.
    OcrResult ocrResult = ocrTesseract.Read(pdfInput);

    // The extracted text can be accessed through ocrResult.Text
    // Uncomment the below line to output the recognized text to the console
    // Console.WriteLine(ocrResult.Text);
}

Imports IronOcr



' The IronTesseract class is the primary class from IronOCR used for performing OCR operations.

Private ocrTesseract = New IronTesseract()



' Using statement ensures the OcrPdfInput object is disposed of after use,

' which helps in freeing up resources. This input represents a PDF file to be processed.

Using pdfInput = New OcrPdfInput("Potter.pdf")

	' Perform OCR on the PDF input. The Read method processes the given PDF and outputs the result.

	' OcrResult holds the extracted text and other metadata.

	Dim ocrResult As OcrResult = ocrTesseract.Read(pdfInput)



	' The extracted text can be accessed through ocrResult.Text

	' Uncomment the below line to output the recognized text to the console

	' Console.WriteLine(ocrResult.Text);

End Using

// Import the necessary namespaces
using IronOcr;
using System.Collections.Generic;

// Instantiate IronTesseract as an OCR engine
var ocrTesseract = new IronTesseract();

// Create a list of page indices to specify which pages to process in the PDF.
// Example: Process only the first and third pages (0 and 2 based index).
var pageIndices = new List<int> { 0, 2 };

// Use a using statement to ensure the OcrPdfInput object is disposed of correctly.
// This object reads the specified PDF and allows specifying specific pages for OCR.
using (var pdfInput = new OcrPdfInput("Potter.pdf"))
{
    // Assign the page indices to the PageIndices property of the pdfInput object
    pdfInput.PageIndices = pageIndices;

    // Perform OCR on the specified pages of the PDF.
    // The Read method processes the input and returns an OcrResult object containing the recognized text.
    OcrResult ocrResult = ocrTesseract.Read(pdfInput);

    // Example: Output the recognized text (Add your own logic if necessary)
    // Uncomment the following line to print the recognized text to the console
    // Console.WriteLine(ocrResult.Text);
}

' Import the necessary namespaces

Imports IronOcr

Imports System.Collections.Generic



' Instantiate IronTesseract as an OCR engine

Private ocrTesseract = New IronTesseract()



' Create a list of page indices to specify which pages to process in the PDF.

' Example: Process only the first and third pages (0 and 2 based index).

Private pageIndices = New List(Of Integer) From {0, 2}



' Use a using statement to ensure the OcrPdfInput object is disposed of correctly.

' This object reads the specified PDF and allows specifying specific pages for OCR.

Using pdfInput = New OcrPdfInput("Potter.pdf")

	' Assign the page indices to the PageIndices property of the pdfInput object

	pdfInput.PageIndices = pageIndices



	' Perform OCR on the specified pages of the PDF.

	' The Read method processes the input and returns an OcrResult object containing the recognized text.

	Dim ocrResult As OcrResult = ocrTesseract.Read(pdfInput)



	' Example: Output the recognized text (Add your own logic if necessary)

	' Uncomment the following line to print the recognized text to the console

	' Console.WriteLine(ocrResult.Text);

End Using

using IronOcr;
using IronSoftware.Drawing; // Import the necessary namespace for Rectangle
using System;

// Initialize an instance of IronTesseract for performing OCR operations
var ocrTesseract = new IronTesseract();

// Define crop regions as rectangles where OCR should be performed
Rectangle[] scanRegions = { new Rectangle(550, 100, 600, 300) };

// Process the PDF file for OCR inside a using block to ensure proper resource management
using (var pdfInput = new OcrInput("Potter.pdf", scanRegions))
{
    // Read the specified regions of the PDF and perform OCR to extract text
    OcrResult ocrResult = ocrTesseract.Read(pdfInput);

    // Output the recognized text to the console
    Console.WriteLine(ocrResult.Text);
}

Imports IronOcr

Imports IronSoftware.Drawing ' Import the necessary namespace for Rectangle

Imports System



' Initialize an instance of IronTesseract for performing OCR operations

Private ocrTesseract = New IronTesseract()



' Define crop regions as rectangles where OCR should be performed

Private scanRegions() As Rectangle = { New Rectangle(550, 100, 600, 300) }



' Process the PDF file for OCR inside a using block to ensure proper resource management

Using pdfInput = New OcrInput("Potter.pdf", scanRegions)

	' Read the specified regions of the PDF and perform OCR to extract text

	Dim ocrResult As OcrResult = ocrTesseract.Read(pdfInput)



	' Output the recognized text to the console

	Console.WriteLine(ocrResult.Text)

End Using