当前位置: 首页 > 图文教程 > 网络编程 > 正则表达式 > 截字符串 去除HTML标记
正则表达式 中的 截字符串 去除HTML标记
出处:互联网 整理: 软晨网(RuanChen.com) 发布: 2009-09-13 浏览: 107 ::
收藏到网摘:
n/a
<%
'**************************************************
'函数名:gotTopic
'作 用:截字符串,汉字一个算两个字符,英文算一个字符
'参 数:str ----原字符串
' strlen ----截取长度
'返回值:截取后的字符串
'**************************************************
function gotTopic(str,strlen)
if str="" then
gotTopic=""
exit function
end if
dim l,t,c, i
str=replace(replace(replace(replace(str," "," "),""",chr(34)),">",">"),"<","<")
str=replace(str,"?","")
l=len(str)
t=0
for i=1 to l
c=Abs(Asc(Mid(str,i,1)))
if c>255 then
t=t+2
else
t=t+1
end if
if t>=strlen then
gotTopic=left(str,i) & "…"
exit for
else
gotTopic=str
end if
next
gotTopic=replace(replace(replace(replace(gotTopic," "," "),chr(34),"""),">",">"),"<","<")
end function
'=========================================================
'函数:RemoveHTML(strHTML)
'功能:去除HTML标记
'参数:strHTML --要去除HTML标记的字符串
'=========================================================
Function RemoveHTML(strHTML)
Dim objRegExp, Match, Matches
Set objRegExp = New Regexp
objRegExp.IgnoreCase = True
objRegExp.Global = True
'取闭合的<>
objRegExp.Pattern = "<.+?>"
'进行匹配
Set Matches = objRegExp.Execute(strHTML)
' 遍历匹配集合,并替换掉匹配的项目
For Each Match in Matches
strHtml=Replace(strHTML,Match.Value,"")
Next
RemoveHTML=strHTML
Set objRegExp = Nothing
set Matches=nothing
End Function
%>