去除html代码中的标签
public static String htmlText(String inputString) {
String htmlStr = inputString; //含html标签的字符串
String textStr ="";
java.util.regex.Pattern p_script;
java.util.regex.Matcher m_script;
java.util.regex.Pattern p_style;
java.util.regex.Matcher m_style;
java.util.regex.Pattern p_html;
java.util.regex.Matcher m_html;
java.util.regex.Pattern p_nbsp;
java.util.regex.Matcher m_nbsp;
java.util.regex.Pattern p_r;
java.util.regex.Matcher m_r;
java.util.regex.Pattern p_n;
java.util.regex.Matcher m_n;
try {
String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; //定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script> }
String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; //定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style> }
String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式
String regEx_nbsp = " "; //定义 标签的正则表达式
String regEx_r = "\r"; //定义 标签的正则表达式
String regEx_n = "\n"; //定义 标签的正则表达式
p_script = Pattern.compile(regEx_script,Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); //过滤script标签
p_style = Pattern.compile(regEx_style,Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); //过滤style标签
p_html = Pattern.compile(regEx_html,Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); //过滤html标签
p_nbsp = Pattern.compile(regEx_nbsp,Pattern.CASE_INSENSITIVE);
m_nbsp = p_nbsp.matcher(htmlStr);
htmlStr = m_nbsp.replaceAll(""); //过滤
// p_r = Pattern.compile(regEx_r, Pattern.CASE_INSENSITIVE);
// m_r = p_r.matcher(htmlStr);
// htmlStr = m_r.replaceAll("");//过滤\r
//
// p_n = Pattern.compile(regEx_n, Pattern.CASE_INSENSITIVE);
// m_n = p_n.matcher(htmlStr);
// htmlStr = m_n.replaceAll("");//过滤\n
textStr = htmlStr;
}catch(Exception e) {
}
return textStr;
}