专业网站建设品牌,十四年专业建站经验,服务6000+客户--广州京杭网络
免费热线:400-683-0016      微信咨询  |  联系我们

C# Net 使用 openxml 提取word中的文本和图片并转为Html

当前位置:网站建设 > 技术支持
资料来源:网络整理       时间:2023/2/14 0:58:02       共计:3671 浏览

加入包:OpenXml

创建文件:Read.cs

复制下面全部代码到文件 Read.cs


using DocumentFormat.OpenXml; using DocumentFormat.OpenXml.Packaging; using DocumentFormat.OpenXml.Wordprocessing; using System; using System.Collections.Generic; using System.IO; using System.Text; using System.Xml; using System.Xml.Xsl;   namespace YCBX.Office.WordXml {     public class WordRead     {         public static List<string> ReadToHtml(string wordPathStr)         {             return ReadToHtml(new FileStream(wordPathStr, FileMode.Open));         }           public static List<string> ReadToHtml(Stream wordStream)         {             using (WordprocessingDocument doc = WordprocessingDocument.Open(wordStream, false))             {                 //XmlWriterSettings settings = new XmlWriterSettings() { OmitXmlDeclaration = true, ConformanceLevel = ConformanceLevel.Auto,DoNotEscapeUriAttributes=true};                 List<string> paragraphHtmls = new List<string>();                   MainDocumentPart mainPart = doc.MainDocumentPart;                 Body body = doc.MainDocumentPart.Document.Body;                   //段落                 foreach (var paragraph in body.Elements<Paragraph>())                 {                     StringBuilder paragraphHtml = new StringBuilder();                     //块                     foreach (var run in paragraph.ChildElements)                     {                         if (run is Run)                         {                             foreach (OpenXmlElement openXmlElement in run.Elements())                             {                                 //软回车                                 if (openXmlElement is Break br)                                 {                                     paragraphHtmls.Add(paragraphHtml.ToString());                                     paragraphHtml = new StringBuilder();                                 }                                 //文字块                                 else if (openXmlElement is Text text)                                 {                                     paragraphHtml.Append(text.Text);                                 }                                 //图像块                                 else if (openXmlElement is Drawing drawing)                                 {                                     //得到图像的内嵌ID(外嵌没做处理)                                     var inline = drawing.Inline;                                     var extent = inline.Extent;                                     var pic = inline.Graphic.GraphicData.GetFirstChild<DocumentFormat.OpenXml.Drawing.Pictures.Picture>();                                     var embed = pic.BlipFill.Blip.Embed.Value;                                       //得到图像流                                     var part = mainPart.GetPartById(embed);                                     var stream = part.GetStream();                                       //流转2进制                                     byte[] bytes = new byte[stream.Length];                                     stream.Read(bytes, 0, bytes.Length);                                       //2进制转base64                                     string imgHtml = $"<img width='{ImageExtent.EMU_TO_PX((decimal)extent.Cx.Value).ToString("0.")}' height='{ImageExtent.EMU_TO_PX((decimal)extent.Cy.Value).ToString("0.")}' src='data:{part.ContentType};base64," + Convert.ToBase64String(bytes) + "' />";                                     paragraphHtml.Append(imgHtml);                                 }                             }                         }                         //else if(run is DocumentFormat.OpenXml.Math.OfficeMath math)                         //{                         //    var x = new XmlDocument();                         //    x.LoadXml(math.OuterXml);                         //    using var ms = ConvertToMatchMl(x, settings);                         //    paragraphHtml.Append(ConvertToLatex(settings, ms));                         //}                     }                       paragraphHtmls.Add(paragraphHtml.ToString());                 }                   return paragraphHtmls;             }                      }           /// <summary>         /// 合并文档         /// </summary>         /// <param name="finalFile"></param>         /// <param name="files"></param>         public static void Combine(string finalFile, List<string> files)         {             if (files.Count < 2)             {                 return;             }             File.Copy(files[0], finalFile, true);             using (WordprocessingDocument doc = WordprocessingDocument.Open(finalFile, true))             {                 Body b = doc.MainDocumentPart.Document.Body;                 for (int i = 1; i < files.Count; i++)                 {                     using (WordprocessingDocument doc1 = WordprocessingDocument.Open(files[i], true))                     {                         foreach (var inst in doc1.MainDocumentPart.Document.Body.Elements())                         {                             b.Append(inst.CloneNode(true));                         }                     }                 }             }         }           private string ConvertToLatex(XmlWriterSettings settings, Stream ms)         {             var latexTransform = new XslCompiledTransform();             latexTransform.Load(Path.Combine(AppContext.BaseDirectory, "xsltml""mmltex.xsl"), new XsltSettings(true,true),new XmlUrlResolver() );             using var la = new MemoryStream();             latexTransform.Transform(new XmlTextReader(ms), XmlWriter.Create(la, settings));             la.Seek(0, SeekOrigin.Begin);             StreamReader sr = new StreamReader(la, Encoding.UTF8);             return sr.ReadToEnd();         }           private Stream ConvertToMatchMl(XmlDocument xmlDocument, XmlWriterSettings settings)         {             var ms = new MemoryStream();             var xslTransform = new XslCompiledTransform();             xslTransform.Load(Path.Combine(AppContext.BaseDirectory, "xsltml""OMML2MML.XSL"));             xslTransform.Transform(xmlDocument, XmlWriter.Create(ms, settings));             ms.Seek(0, SeekOrigin.Begin);             return ms;         }     } }

创建文件:ImageExtent.cs

复制下面全部代码到文件 ImageExtent.cs

using System; using System.Collections.Generic; using System.Text;   namespace YCBX.Office.WordXml {     /// <summary>     /// 图像长度单位转换     /// </summary>     public class ImageExtent     {         private const decimal CM_TO_PX = 96M;         private const decimal INCH_TO_CM = 2.54M;         /// <summary>         /// 厘米到EMU(English Metric Unit)         /// </summary>         private const decimal CM_TO_EMU = 360000M;           /// <summary>         /// EMU(English Metric Unit) 到像素(px)         /// </summary>         /// <param name="EMU"></param>         public static decimal EMU_TO_PX(decimal EMU)         {             return EMU / CM_TO_EMU / INCH_TO_CM * CM_TO_PX;         }     } }

调用方法:

1 var sss = new Read().ParagraphHtmlAll("1.docx");

word文件中为:

 

 

创建一个test.html,将代码放在<body></body>中,查看效果为:

 

 

完成

 

版权说明:
本网站凡注明“广州京杭 原创”的皆为本站原创文章,如需转载请注明出处!
本网转载皆注明出处,遵循行业规范,如发现作品内容版权或其它问题的,请与我们联系处理!
欢迎扫描右侧微信二维码与我们联系。
·上一条:C#微信开发之旅(九):JSAPI支付(V3) | ·下一条:C#Word转Html的类

Copyright © 广州京杭网络科技有限公司 2005-2025 版权所有    粤ICP备16019765号 

广州京杭网络科技有限公司 版权所有