我还编写了一个基于 rfc1738 和 rfc3986 的 URL 验证函数来检查 http 和 https url。我尽量保持这个module化,所以它可以更好地维护和适应自己的要求。
一行中的 RegExp 显示在本文末尾。
RegExp 接受带有一些国际域或 IPv4 号码的 HTTP 和 HTTPS URL。尚不支持 IPv6。
window.isValidURL = (function() {// wrapped in self calling function to prevent global pollution
//URL pattern based on rfc1738 and rfc3986
var rg_pctEncoded = "%[0-9a-fA-F]{2}";
var rg_protocol = "(http|https):\\/\\/";
var rg_userinfo = "([a-zA-Z0-9$\\-_.+!*'(),;:&=]|" + rg_pctEncoded + ")+" + "@";
var rg_decOctet = "(25[0-5]|2[0-4][0-9]|[0-1][0-9][0-9]|[1-9][0-9]|[0-9])"; // 0-255
var rg_ipv4address = "(" + rg_decOctet + "(\\." + rg_decOctet + "){3}" + ")";
var rg_hostname = "([a-zA-Z0-9\\-\\u00C0-\\u017F]+\\.)+([a-zA-Z]{2,})";
var rg_port = "[0-9]+";
var rg_hostport = "(" + rg_ipv4address + "|localhost|" + rg_hostname + ")(:" + rg_port + ")?";
// chars sets
// safe = "$" | "-" | "_" | "." | "+"
// extra = "!" | "*" | "'" | "(" | ")" | ","
// hsegment = *[ alpha | digit | safe | extra | ";" | ":" | "@" | "&" | "=" | escape ]
var rg_pchar = "a-zA-Z0-9$\\-_.+!*'(),;:@&=";
var rg_segment = "([" + rg_pchar + "]|" + rg_pctEncoded + ")*";
var rg_path = rg_segment + "(\\/" + rg_segment + ")*";
var rg_query = "\\?" + "([" + rg_pchar + "/?]|" + rg_pctEncoded + ")*";
var rg_fragment = "\\#" + "([" + rg_pchar + "/?]|" + rg_pctEncoded + ")*";
var rgHttpUrl = new RegExp(
"^"
+ rg_protocol
+ "(" + rg_userinfo + ")?"
+ rg_hostport
+ "(\\/"
+ "(" + rg_path + ")?"
+ "(" + rg_query + ")?"
+ "(" + rg_fragment + ")?"
+ ")?"
+ "$"
);
// export public function
return function (url) {
if (rgHttpUrl.test(url)) {
return true;
} else {
return false;
}
};
})();
正则表达式在一行中:
var rg = /^(http|https):\/\/(([a-zA-Z0-9$\-_.+!*'(),;:&=]|%[0-9a-fA-F]{2})+@)?(((25[0-5]|2[0-4][0-9]|[0-1][0-9][0-9]|[1-9][0-9]|[0-9])(\.(25[0-5]|2[0-4][0-9]|[0-1][0-9][0-9]|[1-9][0-9]|[0-9])){3})|localhost|([a-zA-Z0-9\-\u00C0-\u017F]+\.)+([a-zA-Z]{2,}))(:[0-9]+)?(\/(([a-zA-Z0-9$\-_.+!*'(),;:@&=]|%[0-9a-fA-F]{2})*(\/([a-zA-Z0-9$\-_.+!*'(),;:@&=]|%[0-9a-fA-F]{2})*)*)?(\?([a-zA-Z0-9$\-_.+!*'(),;:@&=\/?]|%[0-9a-fA-F]{2})*)?(\#([a-zA-Z0-9$\-_.+!*'(),;:@&=\/?]|%[0-9a-fA-F]{2})*)?)?$/;