Iphone NSRegularExpression验证URL

我在一个网站上找到了这个正则表达式。据说这是最好的URL验证表达式，我同意。迭戈·佩里尼创造了它

我面临的问题是，当尝试将它与

objective-C

结合使用以检测字符串上的URL时。我尝试过使用诸如

NSRegularExpressionAnchorsMatchLines

、

NSRegularExpressionIgnoreMetacharacters

等选项，但仍然没有成功

对于

Objective-C

，表达式的格式是否不正确？我错过什么了吗？有什么想法吗

我也尝试过John Gruber的正则表达式，但由于一些无效的URL，它失败了

        Regular Expression                                  Explanation of expression                      

 ^                                                  match at the beginning
//Protocol identifier
(?:
    (?:https?|ftp                                   http, https or ftp
    ):\\/\\/                                        ://
)?                                                  optional
// User:Pass authentication
(?:
    ^\\s+                                           non white spaces, 1 or more times
    (?:
        :^\\s*                                      : non white spaces, 0 or more times, optionally
    )?@                                             @
)?                                                  optional
//Private IP Addresses                              ?! Means DO NOT MATCH ahead. So do not match any of the following
(?:
    (?!10                                           10                                                          10.0.0.0 - 10.999.999.999
        (?:
            \\.\\d{1,3}                             . 1 to 3 digits, three times
        ){3}
    )
    (?!127                                          127                                                         127.0.0.0 - 127.999.999.999
        (?:
            \\.\\d{1,3}                             . 1 to 3 digits, three times
        ){3}
    )
    (?!169\\.254                                    169.254                                                     169.254.0.0 - 169.254.999.999
        (?:
            \\.\\d{1,3}                             . 1 to 3 digits, two times
        ){2}
    )
    (?!192\\.168                                    192.168                                                     192.168.0.0 - 192.168.999.999
        (?:
            \\.\\d{1,3}                             . 1 to 3 digits, two times
        ){2}
    )
    (?!172\\.                                       172.                                                        172.16.0.0 - 172.31.999.999
        (?:                                                                                                             
            1[6-9]                                  1 followed by any number between 6 and 9
            |                                       or
            2\\d                                    2 and any digit
            |                                       or
            3[0-1]                                  3 followed by a 0 or 1
        )
        (?:
            \\.\\d{1,3}                             . 1 to 3 digits, two times
        ){2}
    )
    //First Octet IPv4                              // match these. Any non network or broadcast IPv4 address
    (?:
        [1-9]\\d?                                   any number from 1 to 9 followed by an optional digit        1 - 99
        |                                           or
        1\\d\\d                                     1 followed by any two digits                                100 - 199
        |                                           or
        2[01]\\d                                    2 followed by any 0 or 1, followed by a digit               200 - 219
        |                                           or
        22[0-3]                                     22 followed by any number between 0 and 3                   220 - 223
    )
    //Second and Third Octet IPv4
    (?:
        \\.                                         .
        (?:
            1?\\d{1,2}                              optional 1 followed by any 1 or two digits                  0 - 199
            |                                       or
            2[0-4]\\d                               2 followed by any number between 0 and 4, and any digit     200 - 249
            |                                       or
            25[0-5]                                 25 followed by any numbers between 0 and 5                  250 - 255
        )
    ){2}                                            two times
    //Fourth Octet IPv4
    (?:
        \\.                                         .
        (?:
            [1-9]\\d?                               any number between 1 and 9 followed by an optional digit    1 - 99
            |                                       or
            1\\d\\d                                 1 followed by any two digits                                100 - 199
            |                                       or
            2[0-4]\\d                               2 followed by any number between 0 and 4, and any digit     200 - 249
            |                                       or
            25[0-4]                                 25 followed by any number between 0 and 4                   250 - 254
        )
    )
    //Host name
    |                                               or                  
    (?:
        (?:
            [a-z\u00a1-\uffff0-9]+-?                any letter, digit or character one or more times with optional -
        )*                                          zero or more times
        [a-z\u00a1-\uffff0-9]+                      any letter, digit or character one or more times
    )
    //Domain name
    (?:
        \\.                                         .
        (?:
            [a-z\u00a1-\uffff0-9]+-?                any letter, digit or character one or more times with optional -
        )*                                          zero or more times
        [a-z\u00a1-\uffff0-9]+                      any letter, digit or character one or more times
    )*                                              zero or more times
    //TLD identifier
    (?:
        \\.                                         .
        (?:
            [a-z\u00a1-\uffff]{2,}                  any letter, digit or character more than two times
        )
    )
)
//Port number
(?:
    :\\d{2,5}                                       : followed by any digit, two to five times, optionally
)?              
//Resource path
(?:
    \\/[^\\s]*                                      / followed by an optional non space character, zero or more times
)?                                                  optional
$                                                  match at the end

编辑 我想我忘了说我在下面的代码中使用了这个表达式：（部分代码）

我错过什么了吗

你错过了为你做这件事的内在因素。有一个方便的对象叫做。您创建它是为了寻找某些数据“类型”（比如说），然后要求它提供其属性

是我找到的最好的URL验证正则表达式，我的问题中对此进行了解释。它已经格式化为可在Objective-C上使用。但是，将其与

NSRegularExpression

一起使用会给我带来各种各样的问题，包括我的应用程序崩溃

RegexKitLite

在处理它时没有问题。我不知道这是一个大小限制还是一些标志没有设置。 我的最终代码如下所示：

//First I take the string and put every word in an array, then I match every word with the regular expression
NSArray *splitIntoWordsArray = [textToMatch componentsSeparatedByCharactersInSet:[NSCharacterSet whitespaceAndNewLineCharacterSet]];
NSMutableString *htmlString = [NSMutableString stringWithString:textToMatch];
for (NSString *theText in splitIntoWordsArray){
    NSEnumerator *matchEnumerator = [theText matchEnumeratorWithRegex:theRegularExpressionString];
    for (NSString *temp in matchEnumerator){
        [htmlString replaceOccurrencesOfString:temp withString:[NSString stringWithFormat:@"<a href=\"%@\">%@</a>", temp, temp] options:NSLiteralSearch range:NSMakeRange(0, [htmlString length])];
    }
}
[htmlString replaceOccurrencesOfString:@"\n" withString:@"<br />" options:NSLiteralSearch range:NSMakeRange(0, htmlString.length)];
//embed the text on a webView as HTML
[webView loadHTMLString:[NSString stringWithFormat:embedHTML, [mainFont fontName], [mainFont pointSize], htmlString] baseURL:nil];

希望这对将来的人有帮助

正则表达式有时会导致应用程序挂起，因此我决定使用gruber的正则表达式修改以识别不带协议或www部分的url：

(?i)\\b((?:[a-z][\\w-]+:(?:/{1,3}|[a-z0-9%])|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}/?)(?:[^\\s()<>]+|\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\))*(?:\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]{};:'\".,<>?«»“”‘’])*)

（a）以下以下：：：{{1,3}[a-z0-10-10-9%[a-z0-10-9%[a-z0-10-9%[a-z0-10-9-9%[a-10.5.以下：：，（a）两个（a-a-a-a-z[a-a-z[[a-a-z[[[[a-a-z[[[[[a-a-z[[[a-z[[[[[[[a-a-a-a-z[[[[[[[[[[[[[a-a-a-a-z[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[[w-[w[w[w-[w-[w-[[[[[[[[[[[[[[[[[[[[[[[[[[w-[^\\s`！（）\\[\]{}；：'\''，«»'''.''）*）

---

感谢Dave的快速回答。我以前尝试过，但它无法识别某些URL，如.asia、.info等。这就是URL格式不正确的原因。这就是我使用正则表达式的原因。使用在线测试仪，它可以通过协议部分检测healthyhomes.asia或info.info。2017更新：刚刚检查了NSData探测器。

info.info

现在可以工作了，但是

healthyhomes.asia

仍然不能工作。

www.google.c

可以工作。不知道Safari（iOS和桌面）是如何工作的如果

Foundation

的

NSDataDetector

不支持这样的URL，则可以访问

healthyhomes.asia

。您更新的gruber代码很好，但它与“google.com”不匹配-它与“google.comm”和“google.co.uk”匹配“-知道如何调整吗？老兄，非常感谢正则表达式。真是太神奇了。

//First I take the string and put every word in an array, then I match every word with the regular expression
NSArray *splitIntoWordsArray = [textToMatch componentsSeparatedByCharactersInSet:[NSCharacterSet whitespaceAndNewLineCharacterSet]];
NSMutableString *htmlString = [NSMutableString stringWithString:textToMatch];
for (NSString *theText in splitIntoWordsArray){
    NSEnumerator *matchEnumerator = [theText matchEnumeratorWithRegex:theRegularExpressionString];
    for (NSString *temp in matchEnumerator){
        [htmlString replaceOccurrencesOfString:temp withString:[NSString stringWithFormat:@"<a href=\"%@\">%@</a>", temp, temp] options:NSLiteralSearch range:NSMakeRange(0, [htmlString length])];
    }
}
[htmlString replaceOccurrencesOfString:@"\n" withString:@"<br />" options:NSLiteralSearch range:NSMakeRange(0, htmlString.length)];
//embed the text on a webView as HTML
[webView loadHTMLString:[NSString stringWithFormat:embedHTML, [mainFont fontName], [mainFont pointSize], htmlString] baseURL:nil];

NSError *error = NULL;
NSRegularExpression *expression = [NSRegularExpression regularExpressionWithPattern:@"(?i)(?:(?:https?):\\/\\/)?(?:\\S+(?::\\S*)?@)?(?:(?:[1-9]\\d?|1\\d\\d|2[01]\\d|22[0-3])(?:\\.(?:1?\\d{1,2}|2[0-4]\\d|25[0-5])){2}(?:\\.(?:[1-9]\\d?|1\\d\\d|2[0-4]\\d|25[0-4]))|(?:(?:[a-z\\u00a1-\\uffff0-9]+-?)*[a-z\\u00a1-\\uffff0-9]+)(?:\\.(?:[a-z\\u00a1-\\uffff0-9]+-?)*[a-z\\u00a1-\\uffff0-9]+)*(?:\\.(?:[a-z\\u00a1-\\uffff]{2,})))(?::\\d{2,5})?(?:\\/[^\\s]*)?" options:NSRegularExpressionCaseInsensitive error:&error];
if (error)
    NSLog(@"error");
NSString *someString = @"This is a sample of a sentence with a URL http://. http://.. http://../ http://? http://?? http://??/ http://# http://-error-.invalid/ http://-.~_!$&'()*+,;=:%40:80%2f::::::@example.com within it.";
NSRange range = [expression rangeOfFirstMatchInString:someString options:NSMatchingCompleted range:NSMakeRange(0, [someString length])];
if (!NSEqualRanges(range, NSMakeRange(NSNotFound, 0))){
    NSString *match = [someString substringWithRange:range];
    NSLog(@"%@", match);
}   
else {
    NSLog(@"no match");
}

(?i)\\b((?:[a-z][\\w-]+:(?:/{1,3}|[a-z0-9%])|www\\d{0,3}[.]|[a-z0-9.\\-]+[.][a-z]{2,4}/?)(?:[^\\s()<>]+|\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\))*(?:\\(([^\\s()<>]+|(\\([^\\s()<>]+\\)))*\\)|[^\\s`!()\\[\\]{};:'\".,<>?«»“”‘’])*)