去除指定字符串中的HTML标签

最新推荐文章于 2023-04-18 00:20:46 发布

fzuwcb

最新推荐文章于 2023-04-18 00:20:46 发布

阅读量855

点赞数

分类专栏： .net 文章标签： html regex string

本文链接：https://blog.csdn.net/fzuwcb/article/details/5168786

版权

.net 专栏收录该内容

1 篇文章 0 订阅

订阅专栏

//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<a></a>两个标记的内容,保留<a>和</a>代码中间的代码
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, "");

}
}
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<a></a>和两个标记之间的全部内容
pattern = "<" + strTagName + "([^>])*>.*?</" + 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;
}