常用正则表达式

1、从Xml中提取Encoding值的
<\?xml\s+[^>]*Encoding=('|")?(?<Encoding>[^>\s'"]*)('|")?[^>]*> 

2、过滤所有HTML标签取纯文本

Code
/**//// <summary>
        /// 过滤所有HTML标签取纯文本
        /// </summary>
        /// <param name="html"></param>
        /// <returns></returns>
        public static string FilterHTMLTags(string html)
        {
            html = html.Replace("\n\r", " ").Replace("\r\n", " ").Replace("\n", " ").Replace("\r", " ").Replace("\t", "    ");

            Regex regex1 = new Regex(@"<[\s]*?script[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?script[\s]*?>", RegexOptions.IgnoreCase);
            Regex regex2 = new Regex(@"<[\s]*?style[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?style[\s]*?>", RegexOptions.IgnoreCase);
            Regex regex3 = new Regex(@"<[^>]+>", RegexOptions.IgnoreCase);
            //Regex regex7 = new Regex(@"<[\s]*?style[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?style[\s]*?>", RegexOptions.IgnoreCase);

            html = regex1.Replace(html, string.Empty);                      //过滤<script></script>标记           
            html = regex2.Replace(html, string.Empty);                      //过滤<style> 里面的内容 
            html = regex3.Replace(html, string.Empty);                      //过滤<> 里面的内容 
            return html;
        }

3、过滤不安全的HTML脚本

Code
/**//// <summary>
        /// 正则表达式过滤不安全的HTML脚本 
        /// </summary>
        /// <param name="html">输入的Html</param>
        /// <returns>过滤净化后的Html</returns>
        public static string Wipescript(string html)
        {
            Regex regex1 = new Regex(@"<[\s]*?script[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?script[\s]*?>", RegexOptions.IgnoreCase);

            Regex regex2 = new Regex(@"</?form[^>]*>", RegexOptions.IgnoreCase);
            Regex regex3 = new Regex(@"<[\s]*?style[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?style[\s]*?>", RegexOptions.IgnoreCase);
            html = regex1.Replace(html, ""); //过滤<script></script>标记 
            html = regex2.Replace(html, "");
            html = regex3.Replace(html, "");
            return html;
        }

4、取所有src链接
(\ssrc=)(?<url>[^>\s]*)  

5、取所有图片链接地址

Code
 /**//// <summary>
        /// 获取HTML中所有图片的地址
        /// </summary>
        /// <param name="html">原HTML</param>
        /// <returns>HashTable 所有图片链接</returns>
        public static Hashtable GetImg(string html)
        {
            MatchCollection mm = Regex.Matches(html, @"<img\s+[^>]*src=\s*('|"")*(?<url>[^>\s'""]*)('|"")*[^>]*>", RegexOptions.IgnoreCase | RegexOptions.IgnorePatternWhitespace);           

            int i = 0;
            bool blnRepeat;
            Hashtable htb = new Hashtable();

            if (mm != null)
            {
                foreach (Match ss in mm)
                {
                    if (i == 0)
                    {
                        i++;
                        htb.Add(0, ss.Groups["url"].Value);
                    }
                    else
                    {
                        blnRepeat = false;
                        foreach (DictionaryEntry de in htb)
                        {
                            if (ss.Groups["url"].Value.ToLower() == de.Value.ToString().ToLower())
                            {
                                blnRepeat = true;
                                break;
                            }
                        }
                        if (blnRepeat == false)
                        {
                            htb.Add(i, ss.Groups["url"].Value);
                            i++;
                        }
                    }
                }
            }

            return htb;
        }

 6、高亮显示文本内容

Code
/**//// <summary>
        /// 将文本标记为高亮
        /// </summary>
        /// <param name="textToShow">要显示的文本</param>
        /// <param name="keysString">高亮匹配的关键字串(逗号分隔)</param>
        /// <returns>返回高亮标记后的文本</returns>
        public static string MarkHightLightText(string textToShow, string keysString)
        {
            string[] strAkeys = keysString.Split(new char[] { ',', '，' }, StringSplitOptions.RemoveEmptyEntries);
            foreach (string keyString in strAkeys)
            {
                System.Text.RegularExpressions.MatchCollection m = Regex.Matches(textToShow, keyString, RegexOptions.IgnoreCase);//忽略大小写搜索字符串中的关键字
                for (int j = 0; j < m.Count; j++)//循环在匹配的子串前后插东东
                {

                    //j×31为插入html标签使pain字符串增加的长度:
                    textToShow = textToShow.Insert((m[j].Index + keyString.Length + j * 31), "</span>");//关键字后插入html标签
                    textToShow = textToShow.Insert((m[j].Index + j * 31), "<span class=\"Highlight\">");//关键字前插入html标签
                }
            }
            return textToShow;     
        }

         

7、在页面头部找feed链接

<link[^>]+href=\s*(?:'(?<href>[^']+)'|""(?<href>[^""]+)""|(?<href>[^>\s]+))\s*[^>]*>

例:

Code
/**//// <summary>
        /// 在Html中找Feed地址
        /// </summary>
        /// <param name="strHtml">可能包含Feed地址的Html</param>
        /// <returns></returns>
        public static string GetFeedAddressInHtml(string strHtml)
        {
            string strFeedAddress = string.Empty;
            try
            {
                if (strHtml != string.Empty)
                {
                    int intHeaderEndIndex = strHtml.ToLower().IndexOf("</head>");
                    if (intHeaderEndIndex > -1)
                    {
                        // 截取头部代码
                        string strHeader = strHtml.Substring(0, strHtml.ToLower().IndexOf("</head>"));

                        string strRegex = @"<link[^>]+href=\s*(?:'(?<href>[^']+)'|""(?<href>[^""]+)""|(?<href>[^>\s]+))\s*[^>]*>";
                        MatchCollection results = Regex.Matches(strHeader, strRegex);

                        foreach (Match res in results)
                        {
                            string strFeed = res.Groups["href"].Value.Replace("\"", string.Empty).Trim();
                            string strExtend = strFeed.Substring(strFeed.LastIndexOf('.') + 1, strFeed.Length - strFeed.LastIndexOf('.') - 1);

                            if (_blackExtendNameString.IndexOf("," + strExtend.Trim().ToLower() + ",") >= 0)
                            {
                                continue;
                            }
                            else
                            {
                                strFeedAddress = strFeed;
                                break;
                            }
                        }
                    }
                }
            }
            catch (Exception ex)
            {
                Log.Write("在Html中查找Feed地址出错");
                Log.Write(ex);                
            }            
            
            return strFeedAddress;
        }

         

8、分离Url参数和锚点

Code
Regex rex = new Regex("#.+");
                MatchCollection mct = rex.Matches(Request.QueryString["idx"]);
                string strAnchor = mct == null ? string.Empty : mct.Count == 0 ? string.Empty : mct[0].Value.Trim();
                string strIdx = rex.Replace(Request.QueryString["idx"], ""); 

9、过滤unicode编码

     \&\#\d*;

 

附：C#中调用正则表达式匹配的代码示例

Code
MatchCollection results = Regex.Matches(strHtml, @"<\?xml\s+[^>]*Encoding=('|"")?(?<Encoding>[^>\s'""]*)('|"")?[^>]*>", RegexOptions.IgnoreCase | RegexOptions.IgnorePatternWhitespace);

 

 foreach (Match res in results)
 {
     strEncoding = res.Groups["Encoding"].Value;
 }