C#读取PDF、TXT内容

最新推荐文章于 2024-05-21 09:49:44 发布

王-大米

最新推荐文章于 2024-05-21 09:49:44 发布

阅读量8k

点赞数

分类专栏： C#

本文链接：https://blog.csdn.net/wk125570/article/details/73794257

版权

//读取PDF内容
private void button2_Click(object sender, EventArgs e)
        {
            label3.Text = OnCreated("D:\\aa.pdf");
        }

        private string OnCreated(string filepath)
        {
            try
            {
                string pdffilename = filepath;
                PdfReader pdfReader = new PdfReader(pdffilename);
                int numberOfPages = pdfReader.NumberOfPages;
                string text = string.Empty;

                for (int i = 1; i <= numberOfPages; ++i)
                {
                    iTextSharp.text.pdf.parser.ITextExtractionStrategy strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
                    text += iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfReader, i, strategy);
                }
                pdfReader.Close();

                return text;
            }
            catch (Exception e