'正則表達式的核心是設置對比的規則,也就是設置Pattern屬性,而組成這些規則除了字符本身以外,是具有特定含義的符號。
'下面介紹的是正規表達式中常用符號的第一部分。
'\號
'1.放在不便書寫的字符前面,如換行符(\r),回車符(\n),制表符(\t),\自身(\\)
'2.放在有特殊意義字符的前面,表示它自身,"\$","\^","\."
'3.放在可以匹配多個字符的前面
'\d 0~9的數字
'\w 任意一個字母或數字或下划線,也就是 A~Z,a~z,0~9,_ 中任意一個
'\s 包括空格、制表符、換頁符等空白字符的其中任意一個
'以上改為大寫時,為相反的意思,如\D 表示非數字類型
Sub t1()
Dim regx As New RegExp
Dim sr
sr = "AE45B646C"
With regx
.Global = True
.Pattern = "\d" '排除非數字
Debug.Print .Replace(sr, "")
End With
End Sub
'.(點)
'可以匹配除換行符以外的所有字符
也是一個點位符 \.
'+號
'+表示一個字符可以有任意多個重復的。但至少有一個
Sub t11()
Dim regx As New RegExp
Dim sr
sr = "A234CA7A"
With regx
.Global = True
.Pattern = "A\d+"
Debug.Print .Replace(sr, "")
End With
End Sub
'{}號
'可以設置重復次數
'1 {n} 重復n次
Sub t16()
Dim regx As New RegExp
Dim sr
sr = "A234CA7A67"
With regx
.Global = True
.Pattern = "\d{5}" '連續5個數字
Debug.Print .Replace(sr, "")
End With
End Sub
'2 {m,n}最小重復m次,最多重復n次
Sub t22()
Dim regx As New RegExp
Dim sr
sr = "A234CA7A6789"
With regx
.Global = True
.Pattern = "\d{4,5}" '連續兩個數字或連續三個數字
Debug.Print .Replace(sr, "")
End With
End Sub
'3 {m,} 最少重復m次,相當於+
Sub t23()
Dim regx As New RegExp
Dim sr
sr = "A2348t6CA7A67"
With regx
.Global = True
.Pattern = "\d{2,}" '連續兩個數字或連續三個數字
Debug.Print .Replace(sr, "")
End With
End Sub
'* 可以出現0等任意次 相當於 {0,},比如:"\^*b"可以匹配 "b","^^^b"...
' ?
'1 匹配表達式0次或者1次,相當於 {0,1},比如:"a[cd]?"可以匹配 "a","ac","ad"
Sub t24()
Dim regx As New RegExp
Dim sr
sr = "A23.48CA7A6..7"
With regx
.Global = True
.Pattern = "\d+\.?\d+" '最多連續1個
Debug.Print .Replace(sr, "")
End With
End Sub
'2 利用+?的格式可以分段匹配
Sub t87()
Dim regex As New RegExp
Dim sr, mat, m
sr = "<td><p>aa</p></td> <td><p>bb</p></td>"
With regex
.Global = True
.Pattern = "<td>.*?</td>"
Set mat = .Execute(sr)
For Each m In mat
Debug.Print m
Next m
End With
End Sub
Sub t88()
Dim regex As New RegExp
Dim sr, mat, m
sr = " aba aca ada "
With regex
.Global = True
.Pattern = "\s.+?\s"
Set mat = .Execute(sr)
For Each m In mat
Debug.Print m
Next m
End With
End Sub