Asp.Net MVC页面静态化功能实现二：用递归算法来实现

上一篇提到采用IHttpModule来实现当用户访问网站的时候，通过重新定义Response.Filter来实现将返回给客户端的html代码保存，以便用户下一次访问是直接访问静态页面。

Asp.Net MVC页面静态化功能实现一：利用IHttpModule，摒弃ResultFilter

后来想到可以通过WebRequest获取html代码，然后采用递归算法来实现。基本实现思路如下：

通过WebRequest获取超链接地址返回的html代码，并保存；然后正则表达式匹配html代码中所有的超链接href=""里面地址信息； 循坏超链接地址，然后再递归WebRequest获取html代码

实现代码如下：

public class HtmlPageHelper
{
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 = GetHtmlPathFromUrl(urlString);
string direcHtmlPath = Path.GetDirectoryName(htmlPath);
if (!Directory.Exists(direcHtmlPath))
{
Directory.CreateDirectory(direcHtmlPath);
}
File.WriteAllText(htmlPath, htmlCode);
htmlCreatedList.Add(urlString);

ArrayList 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>
/// 分析页面链接地址，生成静态页面保存的物理路径
/// </summary>
/// <param name="urlString">页面链接地址</param>
/// <returns>静态页面保存的物理路径</returns>
private string GetHtmlPathFromUrl(string urlString)
{
Uri uri = new Uri(urlString);
string filePath = HttpContext.Current.Request.PhysicalApplicationPath + "Html" + uri.AbsolutePath + "\\";
string[] querys = uri.Query.Split(new char[] { '?', '&', '=' }, StringSplitOptions.RemoveEmptyEntries);
foreach (string query in querys)
{
filePath += query;
}
filePath += querys.Length.Equals(0) ? "Index.html" : ".html";
filePath = filePath.Replace("/", "\\");
filePath = filePath.Replace("\\\\", "\\");
return filePath;
}

/// <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 ArrayList GetUrlLinkFromHtmlCode(string htmlCode)
{
ArrayList aList = new ArrayList();
string strRegex = "href\\s*=\\s*(?:[\"'](?<1>[^\"'.#:]*)[\"'])";
Regex r = new Regex(strRegex, RegexOptions.IgnoreCase);
MatchCollection m = r.Matches(htmlCode);
for (int i = 0; i <= m.Count - 1; i++)
{
string strNew = m[i].ToString().Replace("amp;", "");
if (!aList.Contains(strNew))
{
aList.Add(strNew);
}
}
return aList;
}
}