c word转html标签原理,c# – 从Word文档转换为HTML

要将.docx文件转换为HTML格式,可以使用以下代码：

>添加对OpenXmlPowerTools.dll的引用

代码：

using OpenXmlPowerTools;

using DocumentFormat.OpenXml.Wordprocessing;

byte[] byteArray = File.ReadAllBytes(DocxFilePath);

using (MemoryStream memoryStream = new MemoryStream())

{

memoryStream.Write(byteArray,byteArray.Length);

using (WordprocessingDocument doc = WordprocessingDocument.Open(memoryStream,true))

{

HtmlConverterSettings settings = new HtmlConverterSettings()

{

PageTitle = "My Page Title"

};

XElement html = HtmlConverter.ConvertToHtml(doc,settings);

File.WriteAllText(HTMLFilePath,html.ToStringNewLineOnAttributes());

}

}