C#實現從PDF中提取表格的方法詳解

using Spire.Pdf;
using Spire.Pdf.Utilities;
using System.IO;
using System.Text;

namespace ExtractTable
{
    class Program
    {
        static void Main(string[] args)
        {
            //範例化PdfDocument類的物件
            PdfDocument pdf = new PdfDocument();

            //載入PDF檔案
            pdf.LoadFromFile("程式語言1.pdf");

            //建立StringBuilder類的物件
            StringBuilder builder = new StringBuilder();

            //範例化PdfTableExtractor類的物件
            PdfTableExtractor extractor = new PdfTableExtractor(pdf);

            //宣告PdfTable類的表格陣列
            PdfTable[] tableLists;

            //遍歷PDF頁面
            for (int pageIndex = 0; pageIndex < pdf.Pages.Count; pageIndex++)
            {
                //從頁面提取表格
                tableLists = extractor.ExtractTable(pageIndex);

                //判斷表格列表是否為空
                if (tableLists != null && tableLists.Length > 0)
                {
                    //遍歷表格
                    foreach (PdfTable table in tableLists)
                    {
                        //獲取表格中的行和列數
                        int row = table.GetRowCount();
                        int column = table.GetColumnCount();

                        //遍歷表格行和列 
                        for (int i = 0; i < row; i++)
                        {
                            for (int j = 0; j < column; j++)
                            {
                                //獲取行和列中的文字
                                string text = table.GetText(i, j);

                                //寫入文字到StringBuilder容器
                                builder.Append(text + " ");
                            }
                            builder.Append("rn");
                        }
                    }
                }
            }

            //儲存提取的表格內容為txt檔案
            File.WriteAllText("提取表格.txt", builder.ToString());
        }
    }
}

Imports Spire.Pdf
Imports Spire.Pdf.Utilities
Imports System.IO
Imports System.Text

Namespace ExtractTable
  Class Program
    Private Shared Sub Main(args As String())
      '範例化PdfDocument類的物件
      Dim pdf As New PdfDocument()

      '載入PDF檔案
      pdf.LoadFromFile("程式語言1.pdf")

      '建立StringBuilder類的物件
      Dim builder As New StringBuilder()

      '範例化PdfTableExtractor類的物件
      Dim extractor As New PdfTableExtractor(pdf)

      '宣告PdfTable類的表格陣列
      Dim tableLists As PdfTable()

      '遍歷PDF頁面
      For pageIndex As Integer = 0 To pdf.Pages.Count - 1
        '從頁面提取表格
        tableLists = extractor.ExtractTable(pageIndex)

        '判斷表格列表是否為空
        If tableLists IsNot Nothing AndAlso tableLists.Length > 0 Then
          '遍歷表格
          For Each table As PdfTable In tableLists
            '獲取表格中的行和列數
            Dim row As Integer = table.GetRowCount()
            Dim column As Integer = table.GetColumnCount()

            '遍歷表格行和列 
            For i As Integer = 0 To row - 1
              For j As Integer = 0 To column - 1
                '獲取行和列中的文字
                Dim text As String = table.GetText(i, j)

                '寫入文字到StringBuilder容器
                builder.Append(text & Convert.ToString(" "))
              Next
              builder.Append(vbCr & vbLf)
            Next
          Next
        End If
      Next

      '儲存提取的表格內容為txt檔案
      File.WriteAllText("提取表格.txt", builder.ToString())
    End Sub
  End Class
End Namespace