使用正则表达式过滤
/**
* 定义script的正则表达式
*/
private static final String REGEX_SCRIPT = "<script[^>]*?>[\\s\\S]*?<\\/script>";
/**
* 定义style的正则表达式
*/
private static final String REGEX_STYLE = "<style[^>]*?>[\\s\\S]*?<\\/style>";
/**
* 定义HTML标签的正则表达式
*/
private static final String REGEX_HTML = "<[^>]+>";
/**
* 定义空格回车换行符
*/
private static final String REGEX_SPACE = "\\s*|\t|\r|\n";
public static String delHTMLTag(String htmlStr) {
// 过滤script标签
Pattern p_script = Pattern.compile(REGEX_SCRIPT, Pattern.CASE_INSENSITIVE);
Matcher m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll("");
// 过滤style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html标签
Pattern p_html = Pattern.compile(REGEX_HTML, Pattern.CASE_INSENSITIVE);
Matcher m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll("");
// 过滤空格回车标签
Pattern p_space = Pattern.compile(REGEX_SPACE, Pattern.CASE_INSENSITIVE);
Matcher m_space = p_space.matcher(htmlStr);
htmlStr = m_space.replaceAll("");
return htmlStr.trim(); // 返回文本字符串
}
将包含html标签的string直接调用delHTMLTag方法即可去处标签