/**
* 去掉文本中的html標籤
*
* @param inputString
* @return
*/
public static String html2Text(String inputString) {
if (StringUtils.isEmpty(inputString)) {
return null;
}
String htmlStr = inputString;
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_html1;
java.util.regex.Matcher m_html1;
try {
String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; // 定義script的正則表達式{或<script[^>]*?>[\\s\\S]*?<\\/script>
// }
String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; // 定義style的正則表達式{或<style[^>]*?>[\\s\\S]*?<\\/style>
// }
String regEx_html = "<[^>]+>"; // 定義HTML標籤的正則表達式
String regEx_html1 = "<[^>]+";
p_script = Pattern.compile(regEx_script,
Pattern.CASE_INSENSITIVE);
m_script = p_script.matcher(htmlStr);
htmlStr = m_script.replaceAll(""); // 過濾script標籤
p_style = Pattern
.compile(regEx_style, Pattern.CASE_INSENSITIVE);
m_style = p_style.matcher(htmlStr);
htmlStr = m_style.replaceAll(""); // 過濾style標籤
p_html = Pattern.compile(regEx_html, Pattern.CASE_INSENSITIVE);
m_html = p_html.matcher(htmlStr);
htmlStr = m_html.replaceAll(""); // 過濾html標籤
p_html1 = Pattern
.compile(regEx_html1, Pattern.CASE_INSENSITIVE);
m_html1 = p_html1.matcher(htmlStr);
htmlStr = m_html1.replaceAll(""); // 過濾html標籤
textStr = htmlStr;
// 替換&nbsp;
textStr = textStr.replaceAll("&", "").replaceAll("nbsp;", "");
} catch (Exception e) {
System.err.println("Html2Text: " + e.getMessage());
}
return textStr;// 返回文本字符串
}