c# 网站生成静态页面

在一些需要经常更新页面数据的网站中，一般访问量不是很大的都直接发布的是带后台代码，每次访问都是有数据库交互的。但是一旦访问量增加了，那么这些服务器开销变成本就要考虑进来了，像一些文章，后台编辑后，文章内容存入数据库，如果1000人访问，如果还是每次取数据库，那这1000次的io访问就显得比较大了，一个好的方法就是，文章确定之后，做成静态页面，而这个做的方法由程序来做，就是递归遍历整个网站，将网站内容都访问一遍，然后生成这些页面的静态文本页面，在将这些页面发布，这样对浏览者而言，他看到的还是同一个地址，同一份文章，只是这份是静态的而言。这样就提升了网站的效率节约了资源；

下面附上一份C#遍历网站内容，然后生成内容页面代码；

private ArrayList htmlCreatedList = new ArrayList();

        /// <summary>
        /// 递归实现页面静态化功能
        /// </summary>
        /// <param name="urlString">要访问的页面链接地址</param>
        public void SaveHtmlCode(string urlString)
        {
            if (htmlCreatedList.Contains(urlString))
            {
                return;
            }
            string htmlCode = GetHtmlCodeFromUrl(urlString);
            string htmlPath = urlString.ToPhysicalPath();
            string direcHtmlPath = Path.GetDirectoryName(htmlPath);
            if (!Directory.Exists(direcHtmlPath))
            {
                Directory.CreateDirectory(direcHtmlPath);
            }
            File.WriteAllText(htmlPath, htmlCode);
            htmlCreatedList.Add(urlString);
            var urlList = GetUrlLinkFromHtmlCode(htmlCode);
            string urlTemp = string.Empty;
            foreach (string url in urlList)
            {
                urlTemp = url;
                urlTemp = Regex.Replace(urlTemp, "href\s*=\s*", "");
                urlTemp = urlTemp.Replace(""", "");
                urlTemp = urlTemp.Replace("\", "/");
                urlTemp = WebConfigInfo.UrlPrefix + urlTemp;
                SaveHtmlCode(urlTemp);
            }
        }

        /// <summary>
        /// 通过HttpWebRequest页面链接的html代码
        /// </summary>
        /// <param name="urlString">页面链接地址</param>
        /// <returns>页面链接对应的html代码</returns>
        private string GetHtmlCodeFromUrl(string urlString)
        {
            HttpWebRequest hwRequest = (HttpWebRequest)WebRequest.Create(urlString);
            hwRequest.UserAgent = "User-Agent:Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705";
            hwRequest.Accept = "*/*";
            hwRequest.KeepAlive = true;
            hwRequest.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5");
            HttpWebResponse hwResponse = (HttpWebResponse)hwRequest.GetResponse();
            Stream streamResponse = hwResponse.GetResponseStream();
            StreamReader readerOfStream = new StreamReader(streamResponse, System.Text.Encoding.GetEncoding("utf-8"));
            string strHtml = readerOfStream.ReadToEnd();
            readerOfStream.Close();
            streamResponse.Close();
            hwResponse.Close();
            return strHtml;
        }

        ///<summary>
        ///正则表达式匹配出html代码中的超链接
        ///</summary>
        ///<param name="htmlCode">要找出超链接的html代码</param>
        ///<returns></returns>
        private IEnumerable<string> GetUrlLinkFromHtmlCode(string htmlCode)
        {
            string strRegex = "href\s*=\s*(?:["'](?<1>[^"'.#:]*)["'])";
            Regex r = new Regex(strRegex, RegexOptions.IgnoreCase);
            MatchCollection ms = r.Matches(htmlCode);
            IEnumerable<string> listUrl = from Match cc in ms select cc.ToString().Replace("&", "&");
            return listUrl.Distinct();
        }
    }

给string 扩展了一个方法。

public static string ToPhysicalPath(this string urlString)
       {
           System.Uri uri = new System.Uri(urlString);
           string htmlPath = string.Format("{0}\Html\{1}\", System.Web.HttpContext.Current.Request.PhysicalApplicationPath, uri.AbsolutePath);
           string[] querys = uri.Query.Split(new char[] { '?', '&', '=' }, StringSplitOptions.RemoveEmptyEntries);
           htmlPath += string.Join(string.Empty, querys);
           htmlPath += querys.Length.Equals(0) ? "Index.html" : ".html";
           htmlPath = htmlPath.Replace("/", "\");
           htmlPath = htmlPath.Replace("\\", "\");
           return htmlPath;
       }