//去除指定字符串中的HTML标签相关代码函数
private static string RemoveHtml(string strContent, string strTagName)
{
string pattern = "";
string strResult = "";
Regex exp;
MatchCollection matchList;
//去掉所有两个标记的内容,保留和代码中间的代码
pattern = "])*>";
exp = new Regex(pattern, RegexOptions.IgnoreCase | RegexOptions.Multiline | RegexOptions.IgnorePatternWhitespace);
matchList = exp.Matches(strContent);
foreach (Match match in matchList)
{
if (match.Value.Length > 0)
{
strResult = match.Value;
strContent = strContent.Replace(strResult, "");
}
}
pattern = "" + strTagName + "([^>])*>";
exp = new Regex(pattern, RegexOptions.IgnoreCase | RegexOptions.Multiline | RegexOptions.IgnorePatternWhitespace);
matchList = exp.Matches(strContent);
foreach (Match match in matchList)
{
if (match.Value.Length > 0)
{
strResult = match.Value;
strContent = strContent.Replace(strResult, "");
}
去掉所有和两个标记之间的全部内容
pattern = "])*>.*?" + strTagName + "([^>])*>";
exp = new Regex(pattern, RegexOptions.IgnoreCase | RegexOptions.Multiline | RegexOptions.IgnorePatternWhitespace);
matchList = exp.Matches(strContent);
foreach (Match match in matchList)
{
if (match.Value.Length > 0)
{
strResult = match.Value;
strContent = strContent.Replace(strResult, "");
}
}
}
return strContent;
}