1             var pdfReader = new PdfReader("xxx.pdf"); 2              3             StreamWriter output = new StreamWriter(new FileStream("处理结果.txt", FileMode.Create)); 4  5             int pageCount = pdfReader.NumberOfPages; 6             for (int pg = 1; pg <= pageCount; pg++) 7             { 8                 ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy(); 9                 var value = PdfTextExtractor.GetTextFromPage(pdfReader, pg, strategy);10                 value = value.Replace(" ", "");11                 Console.WriteLine(value);12                 output.Write(value);13             }14 15             output.Flush();16             output.Close();17             Console.Write("处理完毕");18             Console.ReadLine();

 

该方法读出的汉字不会乱码。