储9369 发表于 2016-6-11 07:19:47

万能Url正则表达式[http,ftp,news,telnet.....]——史上最全Url正则表达式(基于RFC1738‏

  文章来源:http://www.pin5i.com/showtopic-25932.html
  
  由于工作需要写了一个包括所有Url的正则表达式,用来验证返回的Url是否符合RFC1738规定。

有兴趣的同学可以去看RFC1378关于Url部分的介绍(http://www.ietf.org/rfc/rfc1738.txt),本文中的代码是按其规定编写的。

在没有了解RFC1738的时候,一直以为Url的正则表达式很简单,没想到Url有这么多分类,更没想到一个普通的http的正则表达式也不是那么简单。

以下是我搜到的关于http的正则表达式:

[*]http://([\w-]+\.)+[\w-]+(/[\w- ./?%&=]*)?

复制代码
  当然这已经满足大部分人的需求了,但是如果需要严格的验证的话还是要符合RFC1738了。

Url包括Http,Ftp,News,Nntpurl,Telnet,Gopher,Wais,Mailto,File,Prosperurl和Otherurl。

呵呵,废话不多说了,上代码

[*]#region Http
[*]            string lowalpha = @"";
[*]            string hialpha = @"";
[*]            string alpha = String.Format(@"({0}|{1})", lowalpha, hialpha);
[*]            string digit = @"";
[*]            string safe = @"(\$|-|_|\.|\+)";
[*]            string extra = @"(!|\*|'|\(|\)|,)";
[*]            string hex = String.Format(@"({0}|A|B|C|D|E|F|a|b|c|d|e|f)", digit);
[*]            string escape = String.Format(@"(%{0}{0})", hex);
[*]            string unreserved = String.Format(@"({0}|{1}|{2}|{3})", alpha, digit, safe, extra);
[*]            string uchar = String.Format(@"({0}|{1})", unreserved, escape);
[*]            string reserved = @"(;|/|\?|:|@|&|=)";
[*]            string xchar = String.Format(@"({0}|{1}|{2})", unreserved, reserved, escape);
[*]            string digits = String.Format(@"({0}+)", digit);
[*]            string alphadigit = String.Format(@"({0}|{1})", alpha, digit);
[*]            string domainlabel = String.Format(@"({0}|{0}({0}|-)*{0})", alphadigit);
[*]            string toplabel = String.Format(@"({0}|{0}({1}|-)*{1})", alpha, alphadigit);
[*]            string hostname = String.Format(@"(({0}\.)*{1})", domainlabel, toplabel);
[*]            string hostnumber = String.Format(@"{0}\.{0}\.{0}\.{0}", digits);
[*]            string host = String.Format(@"({0}|{1})", hostname, hostnumber);
[*]            string port = digits;
[*]            string hostport = String.Format(@"({0}(:{1}){{0,1}})", host, port);
[*]            string hsegment = String.Format(@"(({0}|;|:|@|&|=)*)", uchar);
[*]            string search = String.Format(@"(({0}|;|:|@|&|=)*)", uchar);
[*]            string hpath = String.Format(@"{0}(/{0})*", hsegment);
[*]            string httpurl = String.Format(@"http://{0}(/{1}(\?{2}){{0,1}}){{0,1}}", hostport, hpath, search);
[*]            #endregion

复制代码

[*]#region Ftp
[*]            string user = String.Format(@"(({0}|;|\?|&|=)*)", uchar);
[*]            string password = String.Format(@"(({0}|;|\?|&|=)*)", uchar);
[*]            string login = String.Format(@"(({0}(:{1}){{0,1}}@){{0,1}}{2})", user, password, hostport);
[*]            string fsegment = String.Format(@"(({0}|\?|:|@|&|=)*)", uchar);
[*]            string ftptype = @"(A|I|D|a|i|d)";
[*]            string fpath = String.Format(@"({0}(/{0})*)", fsegment);
[*]            string ftpurl = String.Format(@"ftp://{0}(/{1}(;type={2}){{0,1}}){{0,1}}", login, fpath, ftptype);
[*]            #endregion

复制代码

[*]#region News
[*]            string group = String.Format(@"({0}({0}|{1}|-|\.|\+|_)*)", alpha, digit);
[*]            string article = String.Format(@"(({0}|;|/|\?|:|&|=)+@{1})", uchar, host);
[*]            string grouppart = String.Format(@"(\*|{0}|{1})", group, article);
[*]            string newsurl = String.Format(@"(news:{0})", grouppart);
[*]            #endregion

复制代码

[*]#region Nntpurl
[*]            string nntpurl = String.Format(@"nntp://{0}/{1}(/{2}){{0,1}}", hostport, group, digits);
[*]            #endregion

复制代码

[*]#region Telnet
[*]            string telneturl = String.Format(@"telnet://{0}/{{0,1}}", login);
[*]            #endregion

复制代码

[*]#region Gopher
[*]            string gtype = xchar;
[*]            string selector = String.Format(@"({0}*)", xchar);
[*]            string gopherplus_string = String.Format(@"({0}*)", xchar);
[*]            string gopherurl = String.Format(@"gopher://{0}(/({1}({2}(%09{3}(%09{4}){{0,1}}){{0,1}}){{0,1}}){{0,1}}){{0,1}}", hostport, gtype, selector, search, gopherplus_string);
[*]            #endregion

复制代码

[*]#region Wais
[*]            string database = String.Format(@"({0}*)", uchar);
[*]            string wtype = String.Format(@"({0}*)", uchar);
[*]            string wpath = String.Format(@"({0}*)", uchar);
[*]            string waisdatabase = String.Format(@"(wais://{0}/{1})", hostport, database);
[*]            string waisindex = String.Format(@"(wais://{0}/{1}\?{2})", hostport, database, search);
[*]            string waisdoc = String.Format(@"(wais://{0}/{1}/{2}/{3})", hostport, database, wtype, wpath);
[*]            string waisurl = String.Format(@"{0}|{1}|{2}", waisdatabase, waisindex, waisdoc);
[*]            #endregion

复制代码

[*]#region Mailto
[*]            string encoded822addr = String.Format(@"({0}+)", xchar);
[*]            string mailtourl = String.Format(@"mailto:{0}", encoded822addr);
[*]            #endregion

复制代码

[*]#region File
[*]            string fileurl = String.Format(@"file://({0}{{0,1}}|localhost)/{1}", host, fpath);
[*]            #endregion

复制代码

[*]#region Prosperourl
[*]            string fieldname = String.Format(@"({0}|\?|:|@|&)", uchar);
[*]            string fieldvalue = String.Format(@"({0}|\?|:|@|&)", uchar);
[*]            string fieldspec = String.Format(@"(;{0}={1})", fieldname, fieldvalue);
[*]            string psegment = String.Format(@"(({0}|\?|:|@|&|=)*)", uchar);
[*]            string ppath = String.Format(@"({0}(/{0})*)", psegment);
[*]            string prosperourl = String.Format(@"prospero://{0}/{1}({2})*", hostport, ppath, fieldspec);
[*]            #endregion

复制代码

[*]#region Otherurl
[*]            //otherurl equal genericurl
[*]            string urlpath = String.Format(@"(({0})*)", xchar);
[*]            string scheme = String.Format(@"(({0}|{1}|\+|-|\.)+)", lowalpha, digit);
[*]            string ip_schemepar = String.Format(@"(//{0}(/{1}){{0,1}})", login, urlpath);
[*]            string schemepart = String.Format(@"(({0})*|{1})", xchar, ip_schemepar);
[*]            string genericurl = String.Format(@"{0}:{1}", scheme, schemepart);
[*]            string otherurl = genericurl;
[*]            #endregion

复制代码
  有了Pattern剩下的就简单多了,无非就是正则表达式的验证了,以Http为例:

Http的pattern为string httpurl,假设要验证的Url为url,所以验证url的代码如下:

[*]Regex regex = new Regex(httpurl);
[*]bool isMatchHttp = regex.IsMatch(url);

复制代码
  
页: [1]
查看完整版本: 万能Url正则表达式[http,ftp,news,telnet.....]——史上最全Url正则表达式(基于RFC1738‏