Excel Vba 正則URL協議、網域名稱、連接埠號碼、頁面路徑

開啟Excel,Shift + F11 開啟VBA編輯器，注意高度時必須先儲存，否則會提示無法高度外部程式。

Sub RegexURL()

Dim url As String
Dim regex As Object
url = "http://www.baidu.com/a/b/index.html"
Set regex = CreateObject("vbscript.regexp")
regex.Global = True
regex.Pattern = "(\w+)://([^/:]+)(:\d*)?([^# ]*)"
MsgBox regex.Replace(url, "使用協議/主網域名稱/連接埠號碼/頁面：[$1],[$2],[$3],[$4]")

End Sub

            Regex reg = new Regex(@"(\w+):\/\/([^/:]+)(:\d*)?([^# ]*)");

            List<string> items = new List<string>() { 
"http://www.baidu.com",
"http://www.baidu.com/index.html",
"http://www.fengcao.baidu.cn/index/index.html",
"ftp://www.baidu.cn/index/index.html",
"ftp://www.baidu.com.cn",
"http://www.net.cn",
            };

            StringBuilder sb = new StringBuilder ();
foreach (string item in items)
            { 
foreach(Match match in reg.Matches(item))
                {
//for(int i=0;i<match.Groups.Count ;i++)
//{
//sb.Append(match.Groups[2]);
                    MessageBox.Show(GetServerDomain(match.Groups[2].ToString ()));
//}
                }
                sb.AppendLine("--");
            }

string result = sb.ToString();

       public bool IsNumeric(string str)
        {
try { int i = Convert.ToInt32(str); return true; }
catch { return false; }
        }

public string GetServerDomain(string url)
        {
string str = url.ToLower();//此處擷取值轉換為小寫
            if (str.IndexOf('.') > 0)
            {
string[] strArr = str.Split('.');
string lastStr = strArr.GetValue(strArr.Length - 1).ToString();
if (IsNumeric(lastStr)) //如果最後一位是數字，那麼說明是IP地址
                {
return str.Replace(".", ""); //替換.為純數字輸出 
                }
else //否則為網域名稱
                {
string[] domainRules = ".com.cn|.net.cn|.org.cn|.gov.cn|.com|.net|.cn|.org|.cc|.me|.tel|.mobi|.asia|.biz|.info|.name|.tv|.hk|.公司|.中國|.網路".Split('|');
string findStr = string.Empty;
string replaceStr = string.Empty;
string returnStr = string.Empty;
for (int i = 0; i < domainRules.Length; i++)
                    {
if (str.EndsWith(domainRules[i].ToLower())) //如果最後有找到匹配項
                        {
                            findStr = domainRules[i].ToString(); //www.eieboom.com
                            replaceStr = str.Replace(findStr, ""); //將匹配項替換為空白，便於再次判斷
                            if (replaceStr.IndexOf('.') > 0) //存在次層網域或者三級，比如：www.eieboom
                            {
string[] replaceArr = replaceStr.Split('.'); // www eieboom
                                returnStr = replaceArr.GetValue(replaceArr.Length - 1).ToString() + findStr;
return returnStr;
                            }
else //eieboom
                            {
                                returnStr = replaceStr + findStr; //串連起來輸出為：eieboom.com
                                return returnStr;
                            };
                        }
else
                        { returnStr = str; }
                    }
return returnStr;
                }
            }
else
            {
return str;
            }
        }