java/android 正則表示式去除所有HTML標籤
阿新 • • 發佈:2019-01-07
protected string str = "<table><tr><td>sdasasdsdd</td></tr></table><br><p>sds</p><img id='img1' src='http://www.baidu.com/img/baidu_logo.gif' width='100' height='50' alt=''>aaassss<br><img src='http://www.baidu.com/img/baidu_logo.gif' width='100' height='50' alt=''> 說是道 ";
protected void Page_Load(object sender, EventArgs e)
{
//string regexstr = @"<[^>]*>"; //去除所有的標籤
//@"<script[^>]*?>.*?</script >" //去除所有指令碼,中間部分也刪除
// string regexstr = @"<img[^>]*>"; //去除圖片的正則
// string regexstr = @"<(?!br).*?>"; //去除所有標籤,只剩br
// string regexstr = @"<table[^>]*?>.*?</table>"; //去除table裡面的所有內容
string regexstr = @"<(?!img|br|p|/p).*?>"; //去除所有標籤,只剩img,br,p
str = Regex.Replace(str, regexstr, string.Empty, RegexOptions.IgnoreCase);
}