将PDF文件拆分为多个文件-控制台c#

//在顶部使用块使用系统;使用先;使用Leadtools;使用Leadtools.Codecs;使用Leadtools.Pdf;使用Leadtools.Document;使用Leadtools.Document.Converter;使用Leadtools.Document.Writer;使用Leadtools.Ocr;

静态无效主要(字符串[]参数){试一试{SetLicense ();字符串multipageFile =@“C: \ LEADTOOLS22 \资源\ \ leadtools.pdf图像”；字符串_splitDir =@“C: \ LEADTOOLS22 \ Resources \ \分割图像pdf文档”；如果(! Directory.Exists (_splitDir)){Directory.CreateDirectory (_splitDir);｝SplitUsingRasterCodecs (multipageFile _splitDir);SplitUsingPDFFile (multipageFile _splitDir);SplitUsingLEADDocument (multipageFile _splitDir);｝抓(异常交货){Console.WriteLine (ex.ToString ());｝控制台。WriteLine (“按任意键退出。”);控制台。ReadKey (真正的);｝

静态无效SplitUsingRasterCodecs (字符串inputFile,字符串_directory){使用(RasterCodecs codecs =新RasterCodecs ()){codecs.Options.Pdf.InitialPath =@ " C: \ LEADTOOLS22 \ Bin \ Dotnet4 \ x64”；inttotalPages = codecs.GetTotalPages(inputFile);控制台。写($“SplitUsingRasterCodecs . .\nTotal pages: {totalPages}，分割页面:");为（intPage = 1;page <= totalPages;+ +页){控制台。写($“{页面}. .”);字符串outputFileName = $“{Path.GetFileNameWithoutExtension (inputFile)} _codecs_page{页面}. pdf”；字符串outputFile =路径。结合(_directory outputFileName);使用(RasterImage图像=编解码器。负载(inputFile、页面)编解码器。保存(image, outputFile, RasterImageFormat。RasPdfLzw, 0);｝Console.WriteLine ();｝｝

静态无效SplitUsingPDFFile (字符串inputFile,字符串_directory){PDFFile =新PDFFile (inputFile);inttotalPages = pdfFile.GetPageCount();控制台。写($“SplitUsingPDFFile . .\nTotal pages: {totalPages}，分割页面:");为（intPage = 1;page <= totalPages;+ +页){控制台。写($“{页面}. .”);字符串outputFileName = $“{Path.GetFileNameWithoutExtension (inputFile)} _pdfFile_page{页面}. pdf”；字符串outputFile =路径。结合(_directory outputFileName);pdfFile。ExtractPages(page, page, outputFile);｝Console.WriteLine ();｝

静态无效SplitUsingLEADDocument (字符串inputFile,字符串_directory){DocumentWriter =新DocumentWriter ();//可选:使用documentWriter.GetOptions()和documentWriter.SetOptions()修改PDF选项varcreateOptions =新CreateDocumentOptions ();LEADDocument inputDocument = DocumentFactory。LoadFromFile (inputFile新LoadDocumentOptions ());IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(ocrengintype . lead);ocrEngine。启动(零,零,零,@“C: \ LEADTOOLS22 \ Bin \常见\ OcrLEADRuntime”);控制台。写($“SplitUsingLEADDocument . .\nTotal pages: {inputDocument.Pages。Count}，分割页面:");foreach（varinputPage在inputDocument.Pages){LEADDocument pageDocument = DocumentFactory.Create(createOptions);pageDocument。AutoDisposeDocuments =真正的；pageDocument。Name =“VirtualPage”；pageDocument.Pages.Add (inputPage);docConverter =新DocumentConverter ();docConverter。SetOcrEngineInstance (ocrEngine假);docConverter.SetDocumentWriterInstance (documentWriter);intpage = inputDocument.Pages.IndexOf(inputPage) + 1;//(+ 1)，因为index是从零开始的控制台。写($“{页面}. .”);varjobData =新DocumentConverterJobData{文档= pageDocument，OutputDocumentFileName =路径。结合(_directory, $“{Path.GetFileNameWithoutExtension (inputFile)} _LeadDoc_page{页面}. pdf”)，DocumentFormat = DocumentFormat. pdf}；varjob = docConverter.Jobs.CreateJob(jobData);docConverter.Jobs.RunJob(工作);｝控制台。WriteLine (”“);ocrEngine.Shutdown ();｝

//下面的代码在Main方法中//注意PDFFile类不接受流输入字节[] multipageData = File.ReadAllBytes(multipageFile);使用(MemoryStream multipageStream =新MemoryStream (multipageData)){SplitUsingRasterCodecs (multipageStream);SplitUsingLEADDocument (multipageStream);｝静态无效SplitUsingRasterCodecs(流inputStream){使用(RasterCodecs codecs =新RasterCodecs ()){codecs.Options.Pdf.InitialPath =@ " C: \ LEADTOOLS22 \ Bin \ Dotnet4 \ x64”；inttotalPages = codecs.GetTotalPages(inputStream);控制台。写($“SplitUsingRasterCodecs . .\nTotal pages: {totalPages}，分割页面:");为（intPage = 1;page <= totalPages;+ +页){控制台。写($“{页面}. .”);使用(RasterImage图像=编解码器。负载(inputStream,页面))使用(MemoryStream outputStream =新MemoryStream ()){编解码器。保存(image, outputStream, RasterImageFormat。RasPdfLzw, 0);//使用包含拆分文件的输出内存流，在它被关闭并释放给下一页之前｝｝Console.WriteLine ();｝｝静态无效SplitUsingLEADDocument(流inputStream){DocumentWriter =新DocumentWriter ();//可选:使用documentWriter.GetOptions()和documentWriter.SetOptions()修改PDF选项varcreateOptions =新CreateDocumentOptions ();LEADDocument inputDocument = DocumentFactory。LoadFromStream (inputStream,新LoadDocumentOptions ());IOcrEngine ocrEngine = OcrEngineManager.CreateEngine(ocrengintype . lead);ocrEngine。启动(零,零,零,@“C: \ LEADTOOLS22 \ Bin \常见\ OcrLEADRuntime”);控制台。写($“SplitUsingLEADDocument . .\nTotal pages: {inputDocument.Pages。Count}，分割页面:");foreach（varinputPage在inputDocument.Pages){LEADDocument pageDocument = DocumentFactory.Create(createOptions);pageDocument。AutoDisposeDocuments =真正的；pageDocument。Name =“VirtualPage”；pageDocument.Pages.Add (inputPage);docConverter =新DocumentConverter ();docConverter。SetOcrEngineInstance (ocrEngine假);docConverter.SetDocumentWriterInstance (documentWriter);intpage = inputDocument.Pages.IndexOf(inputPage) + 1;//(+ 1)，因为index是从零开始的控制台。写($“{页面}. .”);varjobData =新DocumentConverterJobData{文档= pageDocument，OutputDocumentStream =新MemoryStream (),DocumentFormat = DocumentFormat. pdf，JobName =“LeadDoc_page”+页面}；varjob = docConverter.Jobs.CreateJob(jobData);docConverter.Jobs.JobCompleted += Jobs_JobCompleted;docConverter.Jobs.RunJob(工作);｝控制台。WriteLine (”“);ocrEngine.Shutdown ();｝私人静态无效Jobs_JobCompleted (对象sender, DocumentConverterJobEventArgs{MemoryStream outputStream = e.Job.JobData.OutputDocumentStream作为MemoryStream;//转换作业完成后，每个输出流将包含一个分割页//在释放和关闭之前使用流outputStream.Dispose ();outputStream.Close ();｝