url特殊字符转义及解决方法
Posted
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了url特殊字符转义及解决方法相关的知识，希望对你有一定的参考价值。
做页面开发的时候有时候，会使用JavaScript的escape()，encodeURIComponent(),encodeURI ()这三个函数进行URL编码,防止特殊字符接收不到。
解决方法：就是把客服端中带有特殊字符的参数替换成另一些代替的参数，如下所示
1、+ URL 中+号表示空格 %2B
2、空格 URL中的空格可以用+号或者编码 %20
3、 / 分隔目录和子目录 %2F
4、 ? 分隔实际的 URL 和参数 %3F
5、 % 指定特殊字符 %25
6、# 表示书签 %23
7、 & URL 中指定的参数间的分隔符 %26
8、 = URL 中指定参数的值 %3D
1.使用encodeURLComponent传递参数
这是所需要传递的参数
<a href="javascript:video(0);"onclick="javascript:URLencode(‘${classify.name }‘);">${classify.name }</a></li>
解决方式如下
<script> function URLencode(sStr) { sStr = escape(escape(sStr)); location.href="http://passport.baidu.com/?logout&aid=7&u=‘+encodeURIComponent("http://cang.baidu.com/bruce42")+); } </script>
2. 进行URL跳转的时候整体使用encodeURL
<script> function URLencode(sStr) { Location.href=encodeURI("http://cang.baidu.com/do/s?word=百度&ct=21"); } </script>
3.js使用数据时可以用escape(个人用的比较多)编码功能比较强大（个人觉得）
Javascript中的escape()是将中文按ISO-8859-1字符集进行URL编码的，那样通过 request.getParameter()是能直接获取到请求参数的，但后来的Javascript将escape()换成了Unicode字符集编 码，如此一来，在JSP和Servlet中就没法直接拿到请求参数了，而且此时的request获得的参数值都是空值，
首先对中文字符进行两次escape()编码，如要传参数name，值为“黄修群”，则url的格式为….name=escape(escape(“黄修群”))，这样后台获取的数据就是经过就是经过浏览器解码一次后的参数，所以需要自己写一个，工具类解码，
下面是具体例子
jsp代码
<a href="javascript:video(0);" onclick="javascript:URLencode(‘${classify.name }‘);">${classify.name }</a>
js代码
function URLencode(sStr) {
sStr = escape(escape(sStr));
location.href="${pageContext.request.contextPath }/classify/queryClassify?c="+sStr;
}
由于取到的参数是经过u9EC4%u4FEE%u7FA4这样格式的，没办法用常规的URLDecoder.decode()来进行解码，下面一个大牛写的一个工具类，我直接拿来使用了。直接调用unescape（）就可以解码了。
package com.cn.imax.util; /** * JavaScript escape/unescape 编码的 Java 实现 */ public class Escape { private final static String[] hex = { "00","01","02","03","04","05","06","07","08","09","0A","0B","0C","0D","0E","0F", "10","11","12","13","14","15","16","17","18","19","1A","1B","1C","1D","1E","1F", "20","21","22","23","24","25","26","27","28","29","2A","2B","2C","2D","2E","2F", "30","31","32","33","34","35","36","37","38","39","3A","3B","3C","3D","3E","3F", "40","41","42","43","44","45","46","47","48","49","4A","4B","4C","4D","4E","4F", "50","51","52","53","54","55","56","57","58","59","5A","5B","5C","5D","5E","5F", "60","61","62","63","64","65","66","67","68","69","6A","6B","6C","6D","6E","6F", "70","71","72","73","74","75","76","77","78","79","7A","7B","7C","7D","7E","7F", "80","81","82","83","84","85","86","87","88","89","8A","8B","8C","8D","8E","8F", "90","91","92","93","94","95","96","97","98","99","9A","9B","9C","9D","9E","9F", "A0","A1","A2","A3","A4","A5","A6","A7","A8","A9","AA","AB","AC","AD","AE","AF", "B0","B1","B2","B3","B4","B5","B6","B7","B8","B9","BA","BB","BC","BD","BE","BF", "C0","C1","C2","C3","C4","C5","C6","C7","C8","C9","CA","CB","CC","CD","CE","CF", "D0","D1","D2","D3","D4","D5","D6","D7","D8","D9","DA","DB","DC","DD","DE","DF", "E0","E1","E2","E3","E4","E5","E6","E7","E8","E9","EA","EB","EC","ED","EE","EF", "F0","F1","F2","F3","F4","F5","F6","F7","F8","F9","FA","FB","FC","FD","FE","FF" }; private final static byte[] val = { 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F, 0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F }; public static String escape(String s) { StringBuffer sbuf = new StringBuffer(); int len = s.length(); for (int i = 0; i < len; i++) { int ch = s.charAt(i); if (ch == ‘ ‘) { // space : map to ‘+‘ sbuf.append(‘+‘); } else if (‘A‘ <= ch && ch <= ‘Z‘) { // ‘A‘..‘Z‘ : as it was sbuf.append((char)ch); } else if (‘a‘ <= ch && ch <= ‘z‘) { // ‘a‘..‘z‘ : as it was sbuf.append((char)ch); } else if (‘0‘ <= ch && ch <= ‘9‘) { // ‘0‘..‘9‘ : as it was sbuf.append((char)ch); } else if (ch == ‘-‘ || ch == ‘_‘ // unreserved : as it was || ch == ‘.‘ || ch == ‘!‘ || ch == ‘~‘ || ch == ‘*‘ || ch == ‘/‘ || ch == ‘(‘ || ch == ‘)‘) { sbuf.append((char)ch); } else if (ch <= 0x007F) { // other ASCII : map to %XX sbuf.append(‘%‘); sbuf.append(hex[ch]); } else { // unicode : map to %uXXXX sbuf.append(‘%‘); sbuf.append(‘u‘); sbuf.append(hex[(ch >>> 8)]); sbuf.append(hex[(0x00FF & ch)]); } } return sbuf.toString(); } public static String unescape(String s) { StringBuffer sbuf = new StringBuffer(); int i = 0; int len = s.length(); while (i < len) { int ch = s.charAt(i); if (ch == ‘+‘) { // + : map to ‘ ‘ sbuf.append(‘ ‘); } else if (‘A‘ <= ch && ch <= ‘Z‘) { // ‘A‘..‘Z‘ : as it was sbuf.append((char)ch); } else if (‘a‘ <= ch && ch <= ‘z‘) { // ‘a‘..‘z‘ : as it was sbuf.append((char)ch); } else if (‘0‘ <= ch && ch <= ‘9‘) { // ‘0‘..‘9‘ : as it was sbuf.append((char)ch); } else if (ch == ‘-‘ || ch == ‘_‘ // unreserved : as it was || ch == ‘.‘ || ch == ‘!‘ || ch == ‘~‘ || ch == ‘*‘ || ch == ‘/‘ || ch == ‘(‘ || ch == ‘)‘) { sbuf.append((char)ch); } else if (ch == ‘%‘) { int cint = 0; if (‘u‘ != s.charAt(i+1)) { // %XX : map to ascii(XX) cint = (cint << 4) | val[s.charAt(i+1)]; cint = (cint << 4) | val[s.charAt(i+2)]; i+=2; } else { // %uXXXX : map to unicode(XXXX) cint = (cint << 4) | val[s.charAt(i+2)]; cint = (cint << 4) | val[s.charAt(i+3)]; cint = (cint << 4) | val[s.charAt(i+4)]; cint = (cint << 4) | val[s.charAt(i+5)]; i+=5; } sbuf.append((char)cint); } i++; } return sbuf.toString(); } public static void main(String[] args) { // String stest = "数据库"; // System.out.println(stest); // System.out.println(escape(stest)); // System.out.println(unescape(escape(stest))); } }
注意：+字符好像没有被编译（可能我水平不够吧）所以接收参数的时候这样出来一下
c = c.replaceAll(" ", "%2B");
c = Escape.unescape(c);
这样就解码成功了
以上是关于url特殊字符转义及解决方法的主要内容，如果未能解决你的问题，请参考以下文章
url 中的特殊字符 % # & = ? / + 无法被后端解析问题分析及解决方法