0

pdfbox问题

我使用 pdfbox 将文本从 PDF 提取到我的richtextbox。

我不知道问题出在哪里,但有一些 PDF 很好,但有一些 PDF 会引发异常,例外情况是:

你调用的对象是空的。

这是我的代码:

using org.pdfbox.pdmodel;
using org.pdfbox.util;

private void pdfButton_Click(object sender, EventArgs e)
{
    OpenFileDialog openFD = new OpenFileDialog();
    openFD.FileName = "";
    openFD.InitialDirectory = "C:\\";
    openFD.Filter = "All PDF Files|*.PDF";
    openFD.Title = "Browse all PDF files";

    if (openFD.ShowDialog() == DialogResult.OK)
    {
        try
        {
            pdf_filename = Path.GetFileNameWithoutExtension(openFD.Filename);
            PDDocument pdfFile = PDDocument.load(openFD.Filename);

            PDFTextStripper pdfStripper = new PDFTextStripper();
            richtextBox1.Text = pdfStripper.getText(pdfFile);
            textBox1.Text = Path.GetFileName(openFD.Filename);
        }
        catch (Exception error)
        {
            MessageBox.Show(error.ToString());
        }
    }
}
4

1 回答 1

0

我使用 iTextSharp 解决了这个问题。这是我的同事建议的,我用 iTextSharp 更改了 PDFBox。

如果有人和我有同样的问题,这里的工作代码:

using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;


private void pdfButton_Click(object sender, EventArgs e)
{
    OpenFileDialog openFD = new OpenFileDialog();
    openFD.FileName = "";
    openFD.InitialDirectory = "C:\\";
    openFD.Filter = "All PDF Files|*.PDF";
    openFD.Title = "Browse all PDF files";

    if (openFD.ShowDialog() == DialogResult.OK)
    {
        try
        {
            pdf_filename = Path.GetFileNameWithoutExtension(openFD.Filename);

            richtextBox1.Text = ReadPdf(openFD.FileName);
            textBox1.Text = Path.GetFileName(openFD.Filename);
        }

        catch (Exception error)
        {
            MessageBox.Show(error.ToString());
        }

    }
}


private string ReadPdf(string filename)
{

    if (!File.Exists(filename)) return string.Empty;

    PdfReader reader = new PdfReader(filename);

    string text = string.Empty;

    for (int page = 1; page <= reader.NumberOfPages; page++)
    {

        text += PdfTextExtractor.GetTextFromPage(reader, page);

    }

    return text;
}
于 2012-09-03T04:45:34.717 回答