使用Solid Framework可以很方便的已編程方式將PDF轉換成Word文件格式

首先準備一套Solid Framework

在Visual Studio中建立一個項目并引用SolidFramework.dll

添加命名空間 SolidFramework

using SolidFramework; using SolidFramework.Configuration; using SolidFramework.Converters; using SolidFramework.Converters.Plumbing;

前期準備, 設置路徑個許可證

string directoryName = Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location); char directorySeparatorChar = Path.DirectorySeparatorChar; string str = string.Concat(directoryName, directorySeparatorChar.ToString(), "SolidFramework");Installer.NativePlatformDirectory = str; Installer.ForceUnpack = false; License.Import("Solid Framework", "xxxx", "xxx", "xxxxxxxxxxxxxxx", "NOCALL");

初始化SolidFrame Pdf Converter

//Add the PDF file to convert pdfToWordConverter.AddSourceFile(path); //Settings pdfToWordConverter.ReconstructionMode = option.C_ReconstructionMode; pdfToWordConverter.DetectTables = option.Table_Detection; pdfToWordConverter.OutputType = WordDocumentType.DocX; pdfToWordConverter.HeaderAndFooterMode = option.C_HeaderAndFooterMode; pdfToWordConverter.ImageAnchoringMode=option.C_ImageAnchoringMode; pdfToWordConverter.OverwriteMode = SolidFramework.Plumbing.OverwriteMode.ForceOverwrite; pdfToWordConverter.KeepCharacterSpacing = false; FileInfo fileInfo = new FileInfo(path); pdfToWordConverter.TextRecoveryType = option.Recognize_Text; pdfToWordConverter.OutputDirectory= fileInfo.DirectoryName; pdfToWordConverter.SupportRightToLeftWritingDirection = true; pdfToWordConverter.DetectLists = true; pdfToWordConverter.DetectStyles = true; pdfToWordConverter.DetectToc = true; pdfToWordConverter.MarkupAnnotConversionType = MarkupAnnotConversionType.Never; pdfToWordConverter.TextRecoveryNseType = TextRecoveryNSE.Never;

OCR識別引擎， 這里使用內置引擎

pdfToWordConverter.TextRecoveryEngine = TextRecoveryEngine.SolidOCR;

一切就緒開始轉換

pdfToWordConverter.Convert(); ConversionStatus status = pdfToWordConverter.Results[0].Status;

關于ConversionStatus
ConversionStatus 定義了多種轉換狀態IO錯誤密碼錯誤等

public enum ConversionStatus{Success = 0,Canceled = 1,InternalError = 2,Unknown = 200,Fail = 3,BadData = 5,IOError = 6,IOFileLocked = 7,NotEnoughMemory = 9,FileHasCopyProtection = 10,InvalidPagesRange = 8,UnsupportedEncryptionHandler = 11,MissingCertificate = 12,OCRCanceled = 13,NoTablesToExtract = 0xF,NoImagesToExtract = 0x10,NoBppConversion = 150,NoGrayscale = 151,PSDUnsupportedMode = 152,PdfAError = 20,PdfAFatalError = 21,CanceledExists = 14,WrongPassword = 0x1F,NoUserNoOwner = 0x20,NoUserOwner = 33,UserNoOwner = 34,UserOwner = 35,InvalidLicense = 36,AlreadyLoaded = 30,UnavailableAction = 4}

關于輸出格式
pdfToWordConverter.OutputType = WordDocumentType.DocX;
可以是Doc或Docx

執行后
就可以將PDF轉換成Word了

總結

以上是生活随笔為你收集整理的使用.NET 将PDF转成Word的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。