請求書ラインアイテムと構造テーブルを抽出する方法

string invoiceFile = "invoice_with_items.pdf";

using Aspose.OCR;
InvoiceRecognitionSettings settings = new InvoiceRecognitionSettings();
settings.Language = Language.English;
AsposeOcr ocr = new AsposeOcr();
OcrInput input = new OcrInput(InputType.PDF);
input.Add(invoiceFile);
List<RecognitionResult> results = ocr.RecognizeInvoice(input, settings);
string fullText = results[0].RecognitionText;

// Example: Split into lines, then columns (simplified)
string[] lines = fullText.Split(new[] { '\n' }, StringSplitOptions.RemoveEmptyEntries);
foreach (var line in lines)
{
    if (Regex.IsMatch(line, @"\d+\s+[A-Za-z].*\s+\d+[.,]\d{2}")) // crude line item match
    {
        string[] columns = line.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries);
        // Map columns: SKU, description, qty, price, total, etc.
    }
}

using (var writer = new StreamWriter("invoice_lineitems.csv"))
{
    writer.WriteLine("SKU,Description,Qty,UnitPrice,Total");
    // Loop and write line items parsed above
}

using Aspose.OCR;
using System;
using System.IO;
using System.Text.RegularExpressions;
using System.Collections.Generic;

class Program
{
    static void Main(string[] args)
    {
        string invoiceFile = "invoice_with_items.pdf";
        InvoiceRecognitionSettings settings = new InvoiceRecognitionSettings();
        settings.Language = Language.English;
        AsposeOcr ocr = new AsposeOcr();
        OcrInput input = new OcrInput(InputType.PDF);
        input.Add(invoiceFile);
        List<RecognitionResult> results = ocr.RecognizeInvoice(input, settings);
        string fullText = results[0].RecognitionText;
        var lineItems = new List<string[]>();
        string[] lines = fullText.Split(new[] { '\n' }, StringSplitOptions.RemoveEmptyEntries);
        foreach (var line in lines)
        {
            if (Regex.IsMatch(line, @"\d+\s+[A-Za-z].*\s+\d+[.,]\d{2}"))
                lineItems.Add(line.Split(new[] { ' ' }, StringSplitOptions.RemoveEmptyEntries));
        }
        using (var writer = new StreamWriter("invoice_lineitems.csv"))
        {
            writer.WriteLine("SKU,Description,Qty,UnitPrice,Total");
            foreach (var item in lineItems)
                writer.WriteLine(string.Join(",", item));
        }
    }
}