如何检查给定的字符串是否是有效的URL地址?
我对正则表达式的知识是基本的，不允许我从我已经在网上看到的数百个正则表达式中进行选择。
当前回答
function validateURL(textval) {
var urlregex = new RegExp(
"^(http|https|ftp)\://([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*$");
return urlregex.test(textval);
}
匹配 http://site.com/dir/file.php?var=moo | ftp://user:pass@site.com:21/file/dir
Non-Matches site。com | http://site.com/dir//
其他回答
感谢@eyelidlessness提供了非常彻底(尽管很长)的基于RFC的正则表达式。
然而，对于那些使用EICMAScript / JavaScript / Apps Script的人来说，它不起作用。以下是他的答案的精确副本，可以与这些问题一起工作(以及一个代码片段，例如-整洁的新功能!):
regEx_valid_URL = /^[a-z](?:[-a-z0-9\+\.])*:(?:\/\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:])*@)?(?:\[(?:(?:(?:[0-9a-f]{1,4}:){6}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|::(?:[0-9a-f]{1,4}:){5}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){4}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,1}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){3}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,2}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:){2}(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,3}[0-9a-f]{1,4})?::[0-9a-f]{1,4}:(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,4}[0-9a-f]{1,4})?::(?:[0-9a-f]{1,4}:[0-9a-f]{1,4}|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3})|(?:(?:[0-9a-f]{1,4}:){0,5}[0-9a-f]{1,4})?::[0-9a-f]{1,4}|(?:(?:[0-9a-f]{1,4}:){0,6}[0-9a-f]{1,4})?::)|v[0-9a-f]+\.[-a-z0-9\._~!\$&'\(\)\*\+,;=:]+)\]|(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])(?:\.(?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])){3}|(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=])*)(?::[0-9]*)?(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))*)*|\/(?:(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))*)*)?|(?:(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))+)(?:\/(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@]))*)*|(?!(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@])))(?:\?(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@])|[\uE000-\uF8FF}\uF0000-\uFFFFD\u100000-\u10FFFD\/\?])*)?(?:\#(?:(?:%[0-9a-f][0-9a-f]|[-a-z0-9\._~\uA0}-\uD7FF}\uF900-\uFDCF}\uFDF0}-\uFFEF}\u10000-\u1FFFD\u20000-\u2FFFD\u30000-\u3FFFD\u40000-\u4FFFD\u50000-\u5FFFD\u60000-\u6FFFD\u70000-\u7FFFD\u80000-\u8FFFD\u90000-\u9FFFD\uA0000-\uAFFFD\uB0000-\uBFFFD\uC0000-\uCFFFD\uD0000-\uDFFFD\uE1000-\uEFFFD!\$&'\(\)\*\+,;=:@])|[\/\?])*)?$/i; checkedURL = RegExp(regEx_valid_URL).exec('gopher://example.somewhere.university/'); if (checkedURL != null) { console.log('The URL ' + checkedURL + ' is valid'); }
对我来说，URL的最佳正则表达式是:
"(([\w]+:)?//)?(([\d\w]|%[a-fA-F\d]{2,2})+(:([\d\w]|%[a-fA-f\d]{2,2})+)?@)?([\d\w][-\d\w]{0,253}[\d\w]\.)+[\w]{2,4}(:[\d]+)?(/([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)*(\?(&?([-+_~.\d\w]|%[a-fA-f\d]{2,2})=?)*)?(#([-+_~.\d\w]|%[a-fA-f\d]{2,2})*)?"
我无法找到我正在寻找的正则表达式，所以我修改了一个正则表达式来满足我的要求，显然现在它似乎工作得很好。我的要求是:
匹配带有协议的url (www.gooogle.com) 使用查询参数和路径匹配url (http://subdomain.web-site.com/cgi-bin/perl.cgi?key1=value1&key2=value2e) 不要匹配有不可接受字符的url(例如。' '£)，例如:(www.google.com/somthing"/somethingmore)
以下是我的想法，任何建议都很感激:
@Test
public void testWebsiteUrl(){
String regularExpression = "((http|ftp|https):\\/\\/)?[\\w\\-_]+(\\.[\\w\\-_]+)+([\\w\\-\\.,@?^=%&:/~\\+#]*[\\w\\-\\@?^=%&/~\\+#])?";
assertTrue("www.google.com".matches(regularExpression));
assertTrue("www.google.co.uk".matches(regularExpression));
assertTrue("http://www.google.com".matches(regularExpression));
assertTrue("http://www.google.co.uk".matches(regularExpression));
assertTrue("https://www.google.com".matches(regularExpression));
assertTrue("https://www.google.co.uk".matches(regularExpression));
assertTrue("google.com".matches(regularExpression));
assertTrue("google.co.uk".matches(regularExpression));
assertTrue("google.mu".matches(regularExpression));
assertTrue("mes.intnet.mu".matches(regularExpression));
assertTrue("cse.uom.ac.mu".matches(regularExpression));
assertTrue("http://www.google.com/path".matches(regularExpression));
assertTrue("http://subdomain.web-site.com/cgi-bin/perl.cgi?key1=value1&key2=value2e".matches(regularExpression));
assertTrue("http://www.google.com/?queryparam=123".matches(regularExpression));
assertTrue("http://www.google.com/path?queryparam=123".matches(regularExpression));
assertFalse("www..dr.google".matches(regularExpression));
assertFalse("www:google.com".matches(regularExpression));
assertFalse("https://www@.google.com".matches(regularExpression));
assertFalse("https://www.google.com\"".matches(regularExpression));
assertFalse("https://www.google.com'".matches(regularExpression));
assertFalse("http://www.google.com/path'".matches(regularExpression));
assertFalse("http://subdomain.web-site.com/cgi-bin/perl.cgi?key1=value1&key2=value2e'".matches(regularExpression));
assertFalse("http://www.google.com/?queryparam=123'".matches(regularExpression));
assertFalse("http://www.google.com/path?queryparam=12'3".matches(regularExpression));
}
下面的正则表达式适用于我:
(http(s)?:\/\/.)?(ftp(s)?:\/\/.)?(www\.)?[-a-zA-Z0-9@:%._\+~#=]{0,256}\.[a-z]
{2,6}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)
匹配:
https://google.com t.me https://t.me ftp://google.com http://sm.tj http://bro.tj t.me/rshss https:google.com www.cool.com.au http://www.cool.com.au http://www.cool.com.au/ersdfs http://www.cool.com.au/ersdfs?dfd=dfgd@s=1 http://www.cool.com:81/index.html
这里有一个很好的规则，它涵盖了所有可能的情况:端口，参数等等
/(https?:\/\/(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\.)+[a-z0-9][a-z0-9-]{0,61}[a-z0-9])(:?\d*)\/?([a-z_\/0-9\-#.]*)\??([a-z_\/0-9\-#=&]*)/g
推荐文章
- 关于数据库，每个开发人员应该知道些什么?
- Java中的正则表达式命名组
- 使用正则表达式搜索和替换Visual Studio代码
- 使用split("|")按管道符号拆分Java字符串
- 哪个HTTP状态代码表示“尚未准备好，稍后再试”?
- 当内存不足导致抛出OutOfMemoryError时会发生什么?
- 替换字符串中第一次出现的模式
- “\d”在正则表达式中是数字吗?
- 如何从URL获取参数与JSP
- 从集合中随机选取一个元素
- 如何检查一行是否为空白使用正则表达式
- RegEx以确保字符串至少包含一个小写字符、大写字符、数字和符号
- URL从Java中的类路径加载资源
- 就地基数排序
- Java Regex捕获组
