C＃將pdf轉換為txt

Question

我熱烈歡迎...我有一個問題，我正在嘗試將PDF轉換為txt，但是我無法保存txt文件？ 有人請幫我嗎？

using System;
using System.Text;
using System.Windows.Forms;
using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
using System.IO;

namespace ZestawienieFaktur
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();

        }



        private void button1_Click(object sender, EventArgs e)
        {

            string[] filePaths = Directory.GetFiles(@"D:\\faktury\\", "*.pdf");

           foreach (string fp in filePaths)
            {
                ExtractTextFromPdf(fp);
            }

        }

        public static string ExtractTextFromPdf(string path)
        {
            using (PdfReader reader = new PdfReader(path))
            {
                StringBuilder text = new StringBuilder();

                for (int i = 1; i <= reader.NumberOfPages; i++)
                {
                    text.Append(PdfTextExtractor.GetTextFromPage(reader, i));
                }

                string lines = text.ToString();
                using (var file = new StreamWriter(@"D:\faktury\test1.txt"))
                {
                    file.WriteLine(lines);
                    file.Close();
                }


            }




        }

    }
}

在文件夾中，我有一些不同名稱的pdf文件。 而且我想將所有格式都轉換為txt格式。 謝謝...

Answer 1

您應該改為刪除return關鍵字，而僅返回void 。 它不執行的原因是因為它在return之后停止執行其余代碼。 更改為此：

public static void ExtractTextFromPdf(string path)
{
    using (PdfReader reader = new PdfReader(path))
    {
        StringBuilder text = new StringBuilder();

        for (int i = 1; i <= reader.NumberOfPages; i++)
        {
            text.Append(PdfTextExtractor.GetTextFromPage(reader, i));
        }
        string lines = "";
       using(var file = new StreamWriter(path2))
       {
          file.WriteLine(lines);
          file.Close();
       }      

    }
}

希望能幫助到你！

Answer 2

好的，謝謝朋友...

using System;
using System.Text;
using System.Windows.Forms;
using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
using System.IO;

namespace ZestawienieFaktur
{
    public partial class Form1 : Form
    {
        public Form1()
        {
            InitializeComponent();

        }



        private void button1_Click(object sender, EventArgs e)
        {

            string[] filePaths = Directory.GetFiles(@"D:\faktury\", "*.pdf");

           foreach (string fp in filePaths)
            {
                ExtractTextFromPdf(fp);
            }

        }

        public static string ExtractTextFromPdf(string path)
        {
            using (PdfReader reader = new PdfReader(path))
            {
                StringBuilder text = new StringBuilder();

                for (int i = 1; i <= reader.NumberOfPages; i++)
                {
                    text.Append(PdfTextExtractor.GetTextFromPage(reader, i));
                }

                string lines = text.ToString();
                using (var file = new StreamWriter(@"D:\faktury\test1.txt"))
                {
                    file.WriteLine(lines);
                    file.Close();
                }
                return lines; 
            }


        }




    }

    }