一、去掉html
public static String delHTMLTag(String htmlStr) {
String regEx_script = "<script[^>]*?>[\\s\\S]*?<\\/script>"; //定义script的正则表达式
String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; //定义style的正则表达式
String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式
Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
Matcher m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); //过滤script标签
Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
Matcher m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); //过滤style标签
Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
Matcher m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); //过滤html标签
return htmlStr.trim().replace(" ", ""); //返回文本字符串
}
二、截取摘要
public R Edit(Article m) {
//判断概述
if (m.getSummary() == null || m.getSummary().length() == 0) {
String str = uTableUtils.delHTMLTag(m.getContent());
int strlen = 100;
if (str.length() < 100)
strlen = str.length();
m.setSummary(str.substring(0, strlen));
}
saveOrUpdate(m);
return R.ok("成功");
}