c#把word文档转换为html页面

时间:2022-11-11 21:53:16

首先找到一个引用,这个引用2015上的vs都有的,诺,就是这个!

using Microsoft.Office.Interop.Word

首选准备好你的word这里做测试呢 就在项目里面创建一个文件夹,给你要转换的word放到里面,

其次copy下面这段方法到你的项目里面

 1         private string GetPathByDocToHTML(string strFile)
 2         {
 3             if (string.IsNullOrEmpty(strFile))
 4             {
 5                 return "0";//没有文件
 6             }
 7 
 8             Microsoft.Office.Interop.Word.ApplicationClass word = new Microsoft.Office.Interop.Word.ApplicationClass();
 9             Type wordType = word.GetType();
10             Microsoft.Office.Interop.Word.Documents docs = word.Documents;
11 
12             // 打开文件  
13             Type docsType = docs.GetType();
14 
15             object fileName = strFile;
16 
17             Microsoft.Office.Interop.Word.Document doc = (Microsoft.Office.Interop.Word.Document)docsType.InvokeMember("Open",
18             System.Reflection.BindingFlags.InvokeMethod, null, docs, new Object[] { fileName, true, true });
19 
20             // 转换格式,另存为html  
21             Type docType = doc.GetType();
22             //给文件重新起名
23             string filename = System.DateTime.Now.Year.ToString() + System.DateTime.Now.Month.ToString() + System.DateTime.Now.Day.ToString() +
24             System.DateTime.Now.Hour.ToString() + System.DateTime.Now.Minute.ToString() + System.DateTime.Now.Second.ToString();
25 
26             string strFileFolder = "/html/";
27             DateTime dt = DateTime.Now;
28             //以yyyymmdd形式生成子文件夹名
29             string strFileSubFolder = dt.Year.ToString();
30             strFileSubFolder += (dt.Month < 10) ? ("0" + dt.Month.ToString()) : dt.Month.ToString();
31             strFileSubFolder += (dt.Day < 10) ? ("0" + dt.Day.ToString()) : dt.Day.ToString();
32             string strFilePath = strFileFolder + strFileSubFolder + "/";
33             // 判断指定目录下是否存在文件夹,如果不存在,则创建 
34             if (!Directory.Exists(Server.MapPath(strFilePath)))
35             {
36                 // 创建up文件夹 
37                 Directory.CreateDirectory(Server.MapPath(strFilePath));
38             }
39 
40             //被转换的html文档保存的位置 
41             // HttpContext.Current.Server.MapPath("html" + strFileSubFolder + filename + ".html")
42             string ConfigPath = Server.MapPath(strFilePath + filename + ".html");
43             object saveFileName = ConfigPath;
44 
45             /*下面是Microsoft Word 9 Object Library的写法,如果是10,可能写成: 
46               * docType.InvokeMember("SaveAs", System.Reflection.BindingFlags.InvokeMethod, 
47               * null, doc, new object[]{saveFileName, Word.WdSaveFormat.wdFormatFilteredHTML}); 
48               * 其它格式: 
49               * wdFormatHTML 
50               * wdFormatDocument 
51               * wdFormatDOSText 
52               * wdFormatDOSTextLineBreaks 
53               * wdFormatEncodedText 
54               * wdFormatRTF 
55               * wdFormatTemplate 
56               * wdFormatText 
57               * wdFormatTextLineBreaks 
58               * wdFormatUnicodeText 
59             */
60             docType.InvokeMember("SaveAs", System.Reflection.BindingFlags.InvokeMethod,
61             null, doc, new object[] { saveFileName, Microsoft.Office.Interop.Word.WdSaveFormat.wdFormatFilteredHTML });
62 
63             //docType.InvokeMember("SaveAs", System.Reflection.BindingFlags.InvokeMethod,
64             //  null, doc, new object[] { saveFileName, Microsoft.Office.Interop.Word.WdSaveFormat.wdFormatFilteredHTML }); 
65 
66             //关闭文档  
67             docType.InvokeMember("Close", System.Reflection.BindingFlags.InvokeMethod,
68             null, doc, new object[] { null, null, null });
69 
70             // 退出 Word  
71             wordType.InvokeMember("Quit", System.Reflection.BindingFlags.InvokeMethod, null, word, null);
72             //转到新生成的页面  
73             //return ("/" + filename + ".html");
74 
75             //转化HTML页面统一编码格式
76             TransHTMLEncoding(ConfigPath);
77 
78             return (strFilePath + filename + ".html");
79         }
80         private void TransHTMLEncoding(string strFilePath)
81         {
82             try
83             {
84                 System.IO.StreamReader sr = new System.IO.StreamReader(strFilePath, Encoding.GetEncoding(0));
85                 string html = sr.ReadToEnd();
86                 sr.Close();
87                 html = System.Text.RegularExpressions.Regex.Replace(html, @"<meta[^>]*>", "<meta http-equiv=Content-Type content='text/html; charset=gb2312'>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
88                 System.IO.StreamWriter sw = new System.IO.StreamWriter(strFilePath, false, Encoding.Default);
89 
90                 sw.Write(html);
91                 sw.Close();
92             }
93             catch (Exception ex)
94             {
95                 Page.ClientScript.RegisterStartupScript(Page.ClientScript.GetType(), "myscript", "<script>alert('" + ex.Message + "')</script>");
96             }
97         }

其实是两个方法。

为了测试呢 你需要随便弄个地方调用这个这个方法

string strWord = Server.MapPath("/wordpath/thisisword.doc");
GetPathByDocToHTML(strWord);

就是这个,需要把你的word传进去,当然你可以写在Page_Load里面,测试用运行之后打开你的项目找到你保存的位置就行了。