Asp.net 資料擷取基類(遠程抓取,分解,儲存,匹配)
詳細參考地址:http://www.opent.cn/article.asp?id=5
#region 日期隨機函數
/**********************************
* 函數名稱:DateRndName
* 功能說明:日期隨機函數
* 參 數:ra:隨機數
* 調用樣本:
* GetRemoteObj o = new GetRemoteObj();
* Random ra = new Random();
* string s = o.DateRndName(ra);
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 日期隨機函數
/// </summary>
/// <param name="ra">隨機數</param>
/// <returns></returns>
public string DateRndName(Random ra)
{
DateTime d = DateTime.Now;
string s = null, y, m, dd, h, mm, ss;
y = d.Year.ToString();
m = d.Month.ToString();
if (m.Length < 2) m = "0" + m;
dd = d.Day.ToString();
if (dd.Length < 2) dd = "0" + dd;
h = d.Hour.ToString();
if (h.Length < 2) h = "0" + h;
mm = d.Minute.ToString();
if (mm.Length < 2) mm = "0" + mm;
ss = d.Second.ToString();
if (ss.Length < 2) ss = "0" + ss;
s += y + m + dd + h + mm + ss;
s += ra.Next(100, 999).ToString();
return s;
}
#endregion
#region 取得檔案尾碼
/**********************************
* 函數名稱:GetFileExtends
* 功能說明:取得檔案尾碼
* 參 數:filename:檔案名稱
* 調用樣本:
* GetRemoteObj o = new GetRemoteObj();
* string url = @"http://www.baidu.com/img/logo.gif";
* string s = o.GetFileExtends(url);
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 取得檔案尾碼
/// </summary>
/// <param name="filename">檔案名稱</param>
/// <returns></returns>
public string GetFileExtends(string filename)
{
string ext = null;
if (filename.IndexOf('.') > 0)
{
string[] fs = filename.Split('.');
ext = fs[fs.Length - 1];
}
return ext;
}
#endregion
#region 擷取遠程檔案原始碼
/**********************************
* 函數名稱:GetRemoteHtmlCode
* 功能說明:擷取遠程檔案原始碼
* 參 數:Url:遠程url
* 調用樣本:
* GetRemoteObj o = new GetRemoteObj();
* string url = @"http://www.baidu.com";
* string s = o.GetRemoteHtmlCode(url);
* Response.Write(s);
* o.Dispose();
* ********************************/
/// <summary>
/// 擷取遠程檔案原始碼
/// </summary>
/// <param name="url">遠程url</param>
/// <returns></returns>
public string GetRemoteHtmlCode(string Url)
{
string s = "";
MSXML2.XMLHTTP _xmlhttp = new MSXML2.XMLHTTPClass();
_xmlhttp.open("GET", Url, false, null, null);
_xmlhttp.send("");
if (_xmlhttp.readyState == 4)
{
s = System.Text.Encoding.Default.GetString((byte[])_xmlhttp.responseBody);
}
return s;
}
#endregion
取得頁面HTML代碼的例子上面已經給出不少了
下面的代碼是使用Regex取得HTML中內容的代碼
Regex regex1 = new Regex(this.NameKey, RegexOptions.Singleline | RegexOptions.IgnoreCase );
MatchCollection collection1 = regex1.Matches(this.ArtHtml);
if (collection1.Count>0)
{
result=collection1[0].Result("${title}");
}