public String delHTMLTag(String htmlStr) {
String regEx_style = "<style[^>]*?>[\\s\\S]*?<\\/style>"; //定義style的正則表達式
String regEx_html = "<[^>]+>"; //定義HTML標簽的正則表達式
Pattern p_style = Pattern.compile(regEx_style, Pattern.CASE_INSENSITIVE);
Matcher m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); //過濾style標簽
Pattern p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
Matcher m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); //過濾html標簽
htmlStr = htmlStr.replace(" ", "");
htmlStr = htmlStr.replaceAll("\\s*|\t|\r|\n", "");
htmlStr = htmlStr.replace("“", "");
htmlStr = htmlStr.replace("”", "");
htmlStr = htmlStr.replaceAll(" ", "");
return htmlStr.trim(); //返回文本字符串
}