正则替换 html

正则替换 html
2010年11月16日
  protected string str = "sdasasdsdd
sdsaaassss
说是道 ";
  protected void Page_Load(object sender, EventArgs e)
  {
  //string regexstr = @"]*>"; //去除所有的标签
  //@"]*?>.*?" //去除所有脚本,中间部分也删除
  // string regexstr = @"]*>"; //去除图片的正则
  // string regexstr = @""; //去除所有标签,只剩br
  // string regexstr = @"]*?>.*?"; //去除table里面的所有内容
  string regexstr = @""; //去除所有标签,只剩img,br,p
  str = Regex.Replace(str, regexstr, string.Empty, RegexOptions.IgnoreCase);
  } function ExecReg(re, content)
  Dim myRegExp, ResultString
  Set myRegExp =New RegExp
  myRegExp.Global =True
  myRegExp.Pattern = re
  ResultString = myRegExp.Replace(content, "")
  ExecReg = ResultString
  end function
  function DecodeFilter(html)
  html =LCase(html)
  ' 去除所有客户端脚本javascipt,vbscript,jscript,js,vbs,event, html = ExecReg("]*>", html)
  html = ExecReg("(javascript|jscript|vbscript|vbs):", html)
  html = ExecReg("on(mouse|exit|error|click|key)", html)
  html = ExecReg("", html)
  ' 去除表格
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  ' 去除样式类class=""
  html = ExecReg("(]+) class=[^ |^>]*([^>]*>)", html)
  ' 去除样式style=""
  html = ExecReg("(]+) style=""[^""]*""([^>]*>)", html)
  ' 去除XML
  html = ExecReg("]*>", html)
  ' 去除命名空间
  html = ExecReg("]*>", html)
  ' 去除字体
  html = ExecReg("]*>", html)
  ' 去除字幕
  html = ExecReg("]*>", html)
  ' 去除对象
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  html = ExecReg("]*>", html)
  DecodeFilter= html
  end function
  function nohtml(str)
  dim re
  Set re=new RegExp
  re.IgnoreCase =true
  re.Global=True
  re.Pattern="(\)"
  str=re.replace(str," ")
  re.Pattern="(\)"
  str=re.replace(str," ")
  str=replace(str," ","")
  str=replace(str," ","")
  nohtml=str
  set re=nothing
  end function
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值