# clean HTML code from a word html

## 1. HtmlRuleSanitizer (Nuget)
#### (可考慮使用)
open-source (MIT)
Nuget: https://www.nuget.org/packages/Vereyon.Web.HtmlSanitizer
Github: https://github.com/Vereyon/HtmlRuleSanitizer

使用方法:

using Vereyon.Web;
var sanitizer = HtmlSanitizer.SimpleHtml5Sanitizer();
string cleanHtml = sanitizer.Sanitize(dirtyHtml)

參考圖片：

參考文章：
https://stackoverflow.com/questions/2806678/programmatically-clean-word-generated-html-while-preserving-styles

## 2. Cleaning Word's Nasty HTML (function)
#### (*候選)
透過正則表達式處理，沒有使用其他新的dll

static void Main(string[] args)
{
    if (args.Length == 0 || String.IsNullOrEmpty(args[0]))
    {
        Console.WriteLine("No filename provided.");
        return;
    }
    string filepath = args[0];
    if (Path.GetFileName(filepath) == args[0])
    {
        filepath = Path.Combine(Environment.CurrentDirectory, filepath);
    }
    if (!File.Exists(args[0]))
    {
        Console.WriteLine("File doesn't exist.");
    }
    string html = File.ReadAllText(filepath);
    Console.WriteLine("input html is " + html.Length + " chars");
    html = CleanWordHtml(html);
    html = FixEntities(html);
    filepath = Path.GetFileNameWithoutExtension(filepath) + ".modified.htm";
    File.WriteAllText(filepath, html);
    Console.WriteLine("cleaned html is " + html.Length + " chars");
}

static string CleanWordHtml(string html)
{
    StringCollection sc = new StringCollection();
    
    // get rid of unnecessary tag spans (comments and title)
    sc.Add(@"<!--(w|W)+?-->");
    sc.Add(@"<title>(w|W)+?</title>");
    
    // Get rid of classes and styles
    sc.Add(@"s?class=w+");
    sc.Add(@"s+style='[^']+'");
    
    // Get rid of unnecessary tags
    sc.Add(@"<(meta|link|/?o:|/?style|/?div|/?std|/?head|/?html|body|/?body|/?span|![)[^>]*?>");
    
    // Get rid of empty paragraph tags
    sc.Add(@"(<[^>]+>)+&nbsp;(</w+>)+");
    
    // remove bizarre v: element attached to <img> tag
    sc.Add(@"s+v:w+=""[^""]+""");
    
    // remove extra lines
    sc.Add(@"(nr){2,}");
    
    foreach (string s in sc)
    {
        html = Regex.Replace(html, s, "", RegexOptions.IgnoreCase);
    }
    return html;
}

static string FixEntities(string html)
{
    NameValueCollection nvc = new NameValueCollection();
    nvc.Add(""", "&ldquo;");
    nvc.Add(""", "&rdquo;");
    nvc.Add("–", "&mdash;");
    foreach (string key in nvc.Keys)
    {
        html = html.Replace(key, nvc[key]);
    }
    return html;
}

參考文章：
https://blog.codinghorror.com/cleaning-words-nasty-html
## 3. 正則表達式 function
也可參考：https://gist.github.com/SamWM/1716310

public string CleanHtml(string html)
    {
        //Cleans all manner of evils from the rich text editors in IE, Firefox, Word, and Excel
        // Only returns acceptable HTML, and converts line breaks to <br />
        // Acceptable HTML includes HTML-encoded entities.

        html = html.Replace("&" + "nbsp;", " ").Trim(); //concat here due to SO formatting
        // Does this have HTML tags?

        if (html.IndexOf("<") >= 0)
        {
            // Make all tags lowercase
            html = Regex.Replace(html, "<[^>]+>", delegate(Match m){
                return m.ToString().ToLower();
            });
            // Filter out anything except allowed tags
            // Problem: this strips attributes, including href from a
            // http://stackoverflow.com/questions/307013/how-do-i-filter-all-html-tags-except-a-certain-whitelist
            string AcceptableTags = "i|b|u|sup|sub|ol|ul|li|br|h2|h3|h4|h5|span|div|p|a|img|blockquote";
            string WhiteListPattern = "</?(?(?=" + AcceptableTags + @")notag|[a-zA-Z0-9]+)(?:\s[a-zA-Z0-9\-]+=?(?:([""']?).*?\1?)?)*\s*/?>";
            html = Regex.Replace(html, WhiteListPattern, "", RegexOptions.Compiled);
            // Make all BR/br tags look the same, and trim them of whitespace before/after
            html = Regex.Replace(html, @"\s*<br[^>]*>\s*", "<br />", RegexOptions.Compiled);
        }


         // No CRs
         html = html.Replace("\r", "");
         // Convert remaining LFs to line breaks
         html = html.Replace("\n", "<br />");
         // Trim BRs at the end of any string, and spaces on either side
         return Regex.Replace(html, "(<br />)+$", "", RegexOptions.Compiled).Trim();
    }

## 4. ASPOSE 無法做到clean word html code

##