如何在 .NET 中从 PDF 中提取结构数据和表格

using Aspose.Pdf.Plugins;
using System.IO;

string input = @"C:\Docs\financial-report.pdf";
var extractor = new TextExtractor();
var options = new TextExtractorOptions(TextExtractorOptions.TextFormattingMode.Pure);
options.AddInput(new FileDataSource(input));
string extracted = extractor.Process(options).ResultCollection[0].ToString();

// Simple parsing: Assume rows separated by '\n', columns by tabs or spaces
var rows = extracted.Split('\n');
using (var writer = new StreamWriter(@"C:\Docs\extracted-table.csv"))
{
    foreach (var row in rows)
    {
        var columns = row.Split(new[] {'\t', ' '}, StringSplitOptions.RemoveEmptyEntries);
        writer.WriteLine(string.Join(",", columns));
    }
}

using System.Text.Json;
var table = rows
    .Where(r => r.Trim().Length > 0)
    .Select(r => r.Split(new[] {'\t', ' '}, StringSplitOptions.RemoveEmptyEntries))
    .ToList();

File.WriteAllText(@"C:\Docs\extracted-table.json", JsonSerializer.Serialize(table));