C# 使用 iTextSharp 將 PDF 轉換成 TXT 文本

            var pdfReader = new PdfReader("xxx.pdf");
            
            StreamWriter output = new StreamWriter(new FileStream("處理結果.txt", FileMode.Create));

            int pageCount = pdfReader.NumberOfPages;
            for (int pg = 1; pg <= pageCount; pg++)
            {
                ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
                var value = PdfTextExtractor.GetTextFromPage(pdfReader, pg, strategy);
                value = value.Replace(" ", "");
                Console.WriteLine(value);
                output.Write(value);
            }

            output.Flush();
            output.Close();
            Console.Write("處理完畢");
            Console.ReadLine();

 

該方法讀出的漢字不會亂碼。