HTML冗余代码清除.docxVIP

/// summary /// 清理 Word 生成的冗余HTML /// /summary /// param name=html/param /// returns/returns public 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|/?st\d|/?head|/?html|body|/?body|/?span|!\[)[^]*?); sc.Add(@(meta|link|/?o:|/?style|/?font|/?strong|/?st\d|/?head|/?html|body|/?body|/?span|!\[)[^]*?); // Get rid of empty paragraph tags sc.Add(@([^]+)+ (/\w+)+); // remove bizarre v: element attached to img tag sc.Add(@\s+v:\w+=[^]+); // remove extra lines sc.Add(@(\n\r){2,}); foreach (string s in sc) { html = Regex.Replace(html, s, , RegexOptions.IgnoreCase); } return html; } ================================================================================ 从 word 粘贴时冗余 HTML 代码过滤增强版 后台日志编辑默认的编辑器貌似不支持从word 粘贴功能，无奈换上了最新的kindeditor3.5.1，过滤功能很强大。赞！不过还是剩下一些没用的span/span。吃流量，不环保。自己动手增强了一把，做法如下，感兴趣的也可以照此自己改改这一块（改之前务必备份原来的文件！！！）： 1、kindeditor.js（3.5.1 版）的 3236 行，“//add start”和“//add end”之间是我加的代码。 KE.plugin[wordpaste] = KE.plugin[wordpaste] = { click : function(id) { KE.util.selection(id); this.dialog = new KE.dialog({ id : id, cmd : wordpaste, file : wordpaste.html, width : 450, height : 300, loadingMode : true, title : KE.lang[wordpaste], yesButton : KE.lang[yes], noButton : KE.lang[no] 14. }); 15. this.dialog.show(); 16. }, exec : function(id) { var dialogDoc = KE.util.getIframeDoc(this.dialog.iframe); var wordIframe = KE.$(wordIframe, dialogDoc); var str = KE.util.getIframeDoc(wordIframe).body.innerHTML; str = str.replace(/meta(\n|.)*?/ig, ); 22. str = str.replace(/!(\n|.)*?/ig, ); 23. str = str.replace(/style[^]*(\n|.)*?\/style/ig, ); 24. str = str.replace(/script[^]*(\n|.)*?\/script/ig, ); 25. str = str.replace(/w:[^]+(\n|.)*?\/w:[^]+/ig, ); 26. str = str.replace(/xml(\n|.)*?\