如題:
/**
* 去除html格式,提取文字信息
*/
public static String getContent(String content){
if(StringUtil.isNull(content)){
return "";
}
String txtcontent = setTextAreaHtml(content).replaceAll("</?[^>]+>", ""); //剔出<html>的標籤
txtcontent = txtcontent.replaceAll("<a>\\s*|\t|\r|\n</a>", "");//去除字符串中的空格,回車,換行符,製表符
return txtcontent;
}
public static String setTextAreaHtml(String content){
return content.replaceAll("<", "<").replaceAll("gt;", ">").replaceAll("&", "&").replaceAll(""", "\"").replaceAll("'", "'").replaceAll(" "," ");
}