Question

我正在开发一个将pdf文档转换为excel文件的程序。有大约1000个pdf文件要转换。但是我在处理第234个文件时遇到了这个错误。这是重要的代码。

private void getFullFileContent()
    {
        Excel.Application objExcel = new Excel.Application();
        objExcel.Visible = true;
        Excel.Workbook objBook = objExcel.Workbooks.Add(System.Reflection.Missing.Value);
        Excel.Worksheet objSheet;

        Excel.Range objRange=null;

        DateTime endDate, startDate=System.DateTime.Now;



        string[] pdfFiles = Directory.GetFiles(folderBrowserDialog1.SelectedPath, "*.pdf");
        for (int i = 1; i <= pdfFiles.Length; i++)
        {
            objSheet = (Excel.Worksheet)objBook.Worksheets.get_Item(1);
            string bColumn = "B" + i,aColumn="A"+i;

            objRange = objSheet.get_Range(aColumn, System.Reflection.Missing.Value);
            objRange.set_Value(System.Reflection.Missing.Value, pdfFiles[i-1].Substring(pdfFiles[i-1].LastIndexOf('\\') + 1));
            objRange = objSheet.get_Range(bColumn, System.Reflection.Missing.Value);
            objRange.set_Value(System.Reflection.Missing.Value, ConvertPdfToText(pdfFiles[i - 1]));
            label4.Text = pdfFiles[i].Substring(pdfFiles[i].LastIndexOf('\\')+1);
            label6.Text = "Remaining File: "+(pdfFiles.Length - i).ToString();
            endDate = System.DateTime.Now;
            label5.Text = "Total time: " + (endDate - startDate).Hours.ToString() + ":" + (endDate - startDate).Minutes.ToString() + ":" + (endDate - startDate).Seconds.ToString();
            GC.Collect();
        }

        try
        {

              objBook.SaveAs("Training Data.xlsx");
              MessageBox.Show("Your PDF files converted and printed into \"Training Data.xlsx\"");
        }
        catch (Exception)
        {                
            throw;
        }



    }


   private string ConvertPdfToText(string path)
    {
        StringBuilder text = new StringBuilder();
        string fileName = path;
        string strFileContent = "";
        if (File.Exists(fileName))
        {
            PdfReader pdfReader = new PdfReader(fileName);

            for (int page = 1; page <= pdfReader.NumberOfPages; page++)
            {
                ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
                string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);

                currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
                text.Append(currentText);

                strFileContent += currentText;
            }
            pdfReader.Close();
        }
        return strFileContent;
    }

Answer 1

您的文件有多大？也许您可以尝试使用像RedGate Ants或JetBrains dotTrace这样的内存分析器来确定内存泄漏的位置（使用较小的批处理时）。

这段代码也可以在getFullFileContent（）的for循环之外：

objSheet = (Excel.Worksheet)objBook.Worksheets.get_Item(1)

将pdfs转换为excel 0x8007000E时出现内存不足错误（E_OUTOFMEMORY）

1 个答案: