C#网站生成静态页面的实例讲解

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();
    }
  }

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;
    }