import java.util.regex.Matcher;
import java.util.regex.Pattern;
private String cleanHtmlTags(String htmlText)
{
if (StringUtils.isEmpty(htmlText))
{
return "";
}
htmlText = htmlText.replaceAll(" ", " "); // 过滤html标签
String regEx_html = "<[^>]+>";
String regEx_td = "<[td]+>";
String regEx_tr = "<[tr]+>";
Pattern p_html = Pattern.compile(regEx_td, Pattern.CASE_INSENSITIVE);
Matcher m_html = p_html.matcher(htmlText);
htmlText = m_html.replaceAll(" "); // td替换成空格
p_html = Pattern.compile(regEx_tr, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlText);
htmlText = m_html.replaceAll("\n"); // tr替换成换行
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlText);
htmlText = m_html.replaceAll(""); // 过滤html标签
return htmlText;
}
去除String中的html标签,并对<td><tr>进行替换
猜你喜欢
转载自blog.csdn.net/VeastLee/article/details/82665987
今日推荐
周排行