使用openxml提取word中的文本和圖片並轉為Html

使用openxml提取word中的文本和圖片

使用 openXml 提取 word 中的 Text 和 Drawing

使用 openXml 將 word 中的文本和圖片轉為Html

使用 openXml 將 word 中的 文本 和 圖片 轉為 Html

註：只支持內嵌，不支持公式

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

---------------文章最後為效果------------

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

加入包：OpenXml

創建文件：Read.cs

複製下麵全部代碼到文件 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<string> ParagraphHtmlAll(string wordPathStr)
        {
            return ParagraphHtmlAll(new FileStream(wordPathStr, FileMode.Open));
        }

        public List<string> ParagraphHtmlAll(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();
                    //塊
                    foreach (var run in paragraph.ChildElements)
                    {
                        if (run is Run)
                        {
                            foreach (OpenXmlElement openXmlElement in run.Elements())
                            {
                                //文字塊
                                if (openXmlElement is Text)
                                {
                                    Text text = openXmlElement as Text;

                                    paragraphHtml.Append(text.Text);
                                }
                                //圖像塊
                                else if (openXmlElement is Drawing)
                                {
                                    Drawing drawing = openXmlElement as Drawing;

                                    //得到圖像的內嵌ID（外嵌沒做處理）
                                    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;

                                    //得到圖像流
                                    var part = mainPart.GetPartById(embed);
                                    var stream = part.GetStream();

                                    //流轉2進位
                                    byte[] bytes = new byte[stream.Length];
                                    stream.Read(bytes, 0, bytes.Length);

                                    //2進位轉base64
                                    string imgHtml = $"<img style='width:{ImageExtent.EMU_TO_PX((decimal)extent.Cx.Value).ToString("0.")}px;height:{ImageExtent.EMU_TO_PX((decimal)extent.Cy.Value).ToString("0.")}px' 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;
            }
            
        }
        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;
        }
    }
}

創建文件：ImageExtent.cs

複製下麵全部代碼到文件 ImageExtent.cs

using System;
using System.Collections.Generic;
using System.Text;

namespace YCBX.Office.WordXml
{
    /// <summary>
    /// 圖像長度單位轉換
    /// </summary>
    public class ImageExtent
    {
        private const decimal CM_TO_PX = 96M;
        private const decimal INCH_TO_CM = 2.54M;
        /// <summary>
        /// 釐米到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;
        }
    }
}

調用方法：

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

word文件中為：

創建一個test.html，將代碼放在<body></body>中，查看效果為：

完成