.NET word内容转换成HTML

最新推荐文章于 2023-04-26 14:18:00 发布

weixin_34297300

最新推荐文章于 2023-04-26 14:18:00 发布

阅读量123

点赞数

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/yinchengliang/archive/2012/08/23/2651923.html

本文介绍了一种使用C#从Word文档中提取全文内容的方法，并将其转换为HTML格式保存。此方法涉及利用Microsoft Office Interop Word组件打开指定路径的.doc文件，读取其内容并转换为字符串，再将文档另存为HTML格式。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

using System.IO;
using Word = Microsoft.Office.Interop.Word;

public static string getWordFulltext(string WordFilePath, string docId)
        {
            string docText = "";
            try
            {
                if (File.Exists(WordFilePath) && docId != "" && WordFilePath.EndsWith(".doc"))
                {

                    Word.Application wordApp = new Word.Application();
                    object Source = WordFilePath;
                    string SaveHtmlPath = HttpContext.Current.Server.MapPath("UploadHTML") + "\\" + docId + ".html";
                    object Target = SaveHtmlPath;
                    object Unknown = Type.Missing;
                    object readOnly = true;
                    Word.Document doc = wordApp.Documents.Open(ref Source, ref Unknown, ref readOnly, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown);
                    docText = doc.Content.Text.ToString();
                    object format = Word.WdSaveFormat.wdFormatHTML;
                    doc.SaveAs(ref Target, ref format, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown, ref Unknown);
                    doc.Close(ref Unknown, ref Unknown, ref Unknown);
                    wordApp.Quit(ref Unknown, ref Unknown, ref Unknown);

}

            }
            catch { }
            return docText;
        }

转载于:https://www.cnblogs.com/yinchengliang/archive/2012/08/23/2651923.html