TA的每日心情 | 开心
2021-3-12 23:18 |
|---|
签到天数: 2 天 [LV.1]初来乍到
|
|
[code][/code]
package string;
import java.util.regex.Pattern;
/**
* 截取HTML代码
*
* @author YangJunping
* @date 2010-7-15
*/
public class Html2Text {
public static void main(String[] args) {
StringBuffer htmlStr = new StringBuffer();
htmlStr.append("<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">")
.append("<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en"><head><title>aaa</title><mce:script type="text/javascript"></mce:script>")
.append("<link href="static_files/help.css" mce_href="static_files/help.css" rel="stylesheet" type="text/css" media="all" />")
.append("</head><body><ul><li>XXXX</li></ul></body></html>");
System.out.println(Html2Text(htmlStr.toString()));
}
public static String Html2Text(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_html1;
java.util.regex.Matcher m_html1;
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_html1 = "<[^>]+";
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_html1 = Pattern.compile(regEx_html1, Pattern.CASE_INSENSITIVE);
m_html1 = p_html1.matcher(htmlStr);
htmlStr = m_html1.replaceAll(""); // 过滤html标签
textStr = htmlStr;
} catch (Exception e) {
System.err.println("Html2Text: " + e.getMessage());
}
return textStr;// 返回文本字符串
}
}
运行:
C:work>java Html2Text
aaaXXXX |
|
|手机版|Java学习者论坛
( 声明：本站资料整理自互联网，用于Java学习者交流学习使用，对资料版权不负任何法律责任，若有侵权请及时联系客服屏蔽删除 )
发表于 2014-10-28 23:58:46