使用openxml提取word中的文本和图片

使用 openXml 提取 word 中的 Text 和 Drawing

使用 openXml 将 word 中的文本和图片转为Html

使用 openXml 将 word 中的 文本 和 图片 转为 Html

注:只支持内嵌,不支持公式

------------------------------------------------

---------------文章最后为效果------------

------------------------------------------------

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 Read

{

public List ParagraphHtmlAll(string wordPathStr)

{

return ParagraphHtmlAll(new FileStream(wordPathStr, FileMode.Open));

}

public List ParagraphHtmlAll(Stream wordStream)

{

using (WordprocessingDocument doc = WordprocessingDocument.Open(wordStream, false))

{

//XmlWriterSettings settings = new XmlWriterSettings() { OmitXmlDeclaration = true, ConformanceLevel = ConformanceLevel.Auto,DoNotEscapeUriAttributes=true};

List paragraphHtmls = new List();

MainDocumentPart mainPart = doc.MainDocumentPart;

Body body = doc.MainDocumentPart.Document.Body;

//段落

foreach (var paragraph in body.Elements())

{

StringBuilder paragraphHtml = new StringBuilder();

//块

foreach (var run in paragraph.ChildElements)

{

if (run is Run)

{

foreach (OpenXmlElement openXmlElement in run.Elements())

{

//文字块

if (openXmlElement is Text)

{

Text text = openXmlElement as Text;

paragraphHtml.Append(text.Text);

}

//图像块

else if (openXmlElement is Drawing)

{

Drawing drawing = openXmlElement as 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();

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 = $"";

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;

}

}

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

{

///

/// 图像长度单位转换

///

public class ImageExtent

{

private const decimal CM_TO_PX = 96M;

private const decimal INCH_TO_CM = 2.54M;

///

/// 厘米到EMU(English Metric Unit)

///

private const decimal CM_TO_EMU = 360000M;

///

/// EMU(English Metric Unit) 到像素(px)

///

///

public static decimal EMU_TO_PX(decimal EMU)

{

return EMU / CM_TO_EMU / INCH_TO_CM * CM_TO_PX;

}

}

}

调用方法:

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

word文件中为:

f084bee82afdfc4169cf819c7a275ea3.png

创建一个test.html,将代码放在

中,查看效果为:

138a112fbdb67fac16e559992df70001.png

完成

来源:https://www.cnblogs.com/ping9719/archive/2020/03/11/12462478.html

Logo

魔乐社区(Modelers.cn) 是一个中立、公益的人工智能社区,提供人工智能工具、模型、数据的托管、展示与应用协同服务,为人工智能开发及爱好者搭建开放的学习交流平台。社区通过理事会方式运作,由全产业链共同建设、共同运营、共同享有,推动国产AI生态繁荣发展。

更多推荐