java正则匹配非html字符串_java正则表达式去除html中所有的标签和特殊HTML字符（以开头的）...

cons.utils;importjava.io.BufferedReader;importjava.io.FileNotFoundException;importjava.io.FileReader;importjava.io.IOException;importjava.util.regex.Pattern;public classReduceHtml2Text {/*** 删除Html标签

*@paraminputString

*@return

*/

public staticString removeHtmlTag(String inputString) {if (inputString == null)return null;

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_special;

java.util.regex.Matcher m_special;try{//定义script的正则表达式{或

String regEx_script = "<[\s]*?script[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?script[\s]*?>";//定义style的正则表达式{或

String regEx_style = "<[\s]*?style[^>]*?>[\s\S]*?<[\s]*?\/[\s]*?style[\s]*?>";//定义HTML标签的正则表达式

String regEx_html = "<[^>]+>";//定义一些特殊字符的正则表达式 如：

String regEx_special = "\&[a-zA-Z]{1,10};";

p_script=pile(regEx_script, Pattern.CASE_INSENSITIVE);

m_script=p_script.matcher(htmlStr);

htmlStr= m_script.replaceAll(""); //过滤script标签

p_style =pile(regEx_style, Pattern.CASE_INSENSITIVE);

m_style=p_style.matcher(htmlStr);

htmlStr= m_style.replaceAll(""); //过滤style标签

p_html =pile(regEx_html, Pattern.CASE_INSENSITIVE);

m_html=p_html.matcher(htmlStr);

htmlStr= m_html.replaceAll(""); //过滤html标签

p_special =pile(regEx_special, Pattern.CASE_INSENSITIVE);

m_special=p_special.matcher(htmlStr);

htmlStr= m_special.replaceAll(""); //过滤特殊标签

textStr =htmlStr;

}catch(Exception e) {

e.printStackTrace();

}return textStr;//返回文本字符串

}/*** 测试用的main函数

*@paramargs*/

public static voidmain(String[] args) {

StringBuffer sb= newStringBuffer();try{

FileReader fr= new FileReader("D:/test.html");

BufferedReader br= newBufferedReader(fr);

String s= "";while((s = br.readLine())!=null){

sb.append(s);

}

}catch(FileNotFoundException e) {//TODO Auto-generated catch block

e.printStackTrace();

}catch(IOException e) {//TODO Auto-generated catch block

e.printStackTrace();

}

String ssss=ReduceHtml2Text.removeHtmlTag(sb.toString());

System.out.println(ssss);

}

}