Aspose.OCRでスキャンされたPDFからテキストを抽出する方法

PM> Install-Package Aspose.OCR

using Aspose.OCR;

OcrInput input = new OcrInput(InputType.PDF);
input.Add("contract.pdf");
input.Add("archive.pdf");
// Optionally specify page ranges:
// input.Add("report.pdf", startPage: 0, pagesCount: 5);

RecognitionSettings settings = new RecognitionSettings();
settings.Language = Language.English;

AsposeOcr ocr = new AsposeOcr();
List<RecognitionResult> results = ocr.Recognize(input, settings);

foreach (RecognitionResult result in results)
{
    Console.WriteLine(result.RecognitionText); // Show the text in console
    result.Save("output.txt", SaveFormat.Text); // Save as plain text
    result.Save("output.pdf", SaveFormat.Pdf); // Save as searchable PDF
}

try
{
    AsposeOcr ocr = new AsposeOcr();
    List<RecognitionResult> results = ocr.Recognize(input, settings);
    // Further processing...
}
catch (Exception ex)
{
    Console.WriteLine($"Error: {ex.Message}");
}

// Example: Add all scanned PDFs in a folder
foreach (string file in Directory.GetFiles("./pdfs", "*.pdf"))
{
    input.Add(file);
}

using Aspose.OCR;
using System;
using System.Collections.Generic;

class Program
{
    static void Main(string[] args)
    {
        try
        {
            OcrInput input = new OcrInput(InputType.PDF);
            input.Add("contract.pdf");
            input.Add("archive.pdf");

            RecognitionSettings settings = new RecognitionSettings();
            settings.Language = Language.English;

            AsposeOcr ocr = new AsposeOcr();
            List<RecognitionResult> results = ocr.Recognize(input, settings);

            foreach (RecognitionResult result in results)
            {
                Console.WriteLine(result.RecognitionText);
                result.Save("output.txt", SaveFormat.Text);
                result.Save("output.pdf", SaveFormat.Pdf);
            }
        }
        catch (Exception ex)
        {
            Console.WriteLine($"Error: {ex.Message}");
        }
    }
}

input.Add("archive.pdf", startPage: 5, pagesCount: 3);

foreach (RecognitionResult result in results)
{
    result.Save("output.docx", SaveFormat.Docx);
    result.Save("output.json", SaveFormat.Json);
}