C#实现从PDF中提取表格的方法详解

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

namespace ExtractTable
{
    class Program
    {
        static void Main(string[] args)
        {
            //实例化PdfDocument类的对象
            PdfDocument pdf = new PdfDocument();

            //加载PDF文档
            pdf.LoadFromFile("编程语言1.pdf");

            //创建StringBuilder类的对象
            StringBuilder builder = new StringBuilder();

            //实例化PdfTableExtractor类的对象
            PdfTableExtractor extractor = new PdfTableExtractor(pdf);

            //声明PdfTable类的表格数组
            PdfTable[] tableLists;

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

                //判断表格列表是否为空
                if (tableLists != null && tableLists.Length > 0)
                {
                    //遍历表格
                    foreach (PdfTable table in tableLists)
                    {
                        //获取表格中的行和列数
                        int row = table.GetRowCount();
                        int column = table.GetColumnCount();

                        //遍历表格行和列 
                        for (int i = 0; i < row; i++)
                        {
                            for (int j = 0; j < column; j++)
                            {
                                //获取行和列中的文本
                                string text = table.GetText(i, j);

                                //写入文本到StringBuilder容器
                                builder.Append(text + " ");
                            }
                            builder.Append("\r\n");
                        }
                    }
                }
            }

            //保存提取的表格内容为txt文档
            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())
      '实例化PdfDocument类的对象
      Dim pdf As New PdfDocument()

      '加载PDF文档
      pdf.LoadFromFile("编程语言1.pdf")

      '创建StringBuilder类的对象
      Dim builder As New StringBuilder()

      '实例化PdfTableExtractor类的对象
      Dim extractor As New PdfTableExtractor(pdf)

      '声明PdfTable类的表格数组
      Dim tableLists As PdfTable()

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

        '判断表格列表是否为空
        If tableLists IsNot Nothing AndAlso tableLists.Length > 0 Then
          '遍历表格
          For Each table As PdfTable In tableLists
            '获取表格中的行和列数
            Dim row As Integer = table.GetRowCount()
            Dim column As Integer = table.GetColumnCount()

            '遍历表格行和列 
            For i As Integer = 0 To row - 1
              For j As Integer = 0 To column - 1
                '获取行和列中的文本
                Dim text As String = table.GetText(i, j)

                '写入文本到StringBuilder容器
                builder.Append(text & Convert.ToString(" "))
              Next
              builder.Append(vbCr & vbLf)
            Next
          Next
        End If
      Next

      '保存提取的表格内容为txt文档
      File.WriteAllText("提取表格.txt", builder.ToString())
    End Sub
  End Class
End Namespace