vba-正则表达式2（常用符号）
'正则表达式的核心是设置对比的规则，也就是设置Pattern属性，而组成这些规则除了字符本身以外，是具有特定含义的符号。
'下面介绍的是正规表达式中常用符号的第一部分。
'\号
'1.放在不便书写的字符前面,如换行符(\r),回车符(\n),制表符(\t),\自身(\\)
'2.放在有特殊意义字符的前面,表示它自身,"\$","\^","\."
'3.放在可以匹配多个字符的前面
'\d 0~9的数字
'\w 任意一个字母或数字或下划线，也就是 A~Z,a~z,0~9,_ 中任意一个
'\s 包括空格、制表符、换页符等空白字符的其中任意一个
'以上改为大写时,为相反的意思,如\D 表示非数字类型
Sub t1()
Dim regx As New RegExp
Dim sr
sr = "AE45B646C"
With regx
.Global = True
.Pattern = "\d" '排除非数字
Debug.Print .Replace(sr, "")
End With
End Sub
'.(点)
'可以匹配除换行符以外的所有字符
也是一个点位符 \.
'+号
'+表示一个字符可以有任意多个重复的。但至少有一个
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
'{}号
'可以设置重复次数
'1 {n} 重复n次
Sub t16()
Dim regx As New RegExp
Dim sr
sr = "A234CA7A67"
With regx
.Global = True
.Pattern = "\d{5}" '连续5个数字
Debug.Print .Replace(sr, "")
End With
End Sub
'2 {m,n}最小重复m次,最多重复n次
Sub t22()
Dim regx As New RegExp
Dim sr
sr = "A234CA7A6789"
With regx
.Global = True
.Pattern = "\d{4,5}" '连续两个数字或连续三个数字
Debug.Print .Replace(sr, "")
End With
End Sub
'3 {m,} 最少重复m次,相当于+
Sub t23()
Dim regx As New RegExp
Dim sr
sr = "A2348t6CA7A67"
With regx
.Global = True
.Pattern = "\d{2,}" '连续两个数字或连续三个数字
Debug.Print .Replace(sr, "")
End With
End Sub
'* 可以出现0等任意次 相当于 {0,}，比如："\^*b"可以匹配 "b","^^^b"...
' ?
'1 匹配表达式0次或者1次，相当于 {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+" '最多连续1个
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
