注：這是Java正則表達式去除html標簽方法。
private
static
final
String regEx_script =
"<script[^>]*?>[\\s\\S]*?<\\/script>"
;
// 定義script的正則表達式
private
static
final
String regEx_style =
"<style[^>]*?>[\\s\\S]*?<\\/style>"
;
// 定義style的正則表達式
private
static
final
String regEx_html =
"<[^>]+>"
;
// 定義HTML標簽的正則表達式
private
static
final
String regEx_space =
"\\s*|\t|\r|\n"
;
// 定義空格回車換行符
private
static
final
String regEx_w =
"<w[^>]*?>[\\s\\S]*?<\\/w[^>]*?>"
;
//定義所有w標簽
/**
* @param htmlStr
* @return 刪除Html標簽
* @author LongJin
*/
public
static
String delHTMLTag(String htmlStr) {
Pattern p_w = Pattern.compile(regEx_w, Pattern.CASE_INSENSITIVE);
Matcher m_w = p_w.matcher(htmlStr);
htmlStr = m_w.replaceAll(
""
);
// 過濾script標簽
Pattern p_script = Pattern.compile(regEx_script, Pattern.CASE_INSENSITIVE);
Matcher m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(
""
);
// 過濾script標簽
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
Pattern p_space = Pattern.compile(regEx_space, Pattern.CASE_INSENSITIVE);
Matcher m_space = p_space.matcher(htmlStr);
htmlStr = m_space.replaceAll(
""
);
// 過濾空格回車標簽
htmlStr = htmlStr.replaceAll(
" "
,
""
);
//過濾
return
htmlStr.trim();
// 返回文本字符串
}