返回列表 回复 发帖

[转帖]最复杂全面的从文本文件中取 URL 的正则

  1. $string =~ s< (?:http://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\. )*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+) ){3}))(?::(?:\d+))?)(?:/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F \d]{2}))|[;:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{ 2}))|[;:@&=])*))*)(?:\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{ 2}))|[;:@&=])*))?)?)|(?:ftp://(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(? :%[a-fA-F\d]{2}))|[;?&=])*)(?::(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a- fA-F\d]{2}))|[;?&=])*))?@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|- )*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(? :\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?))(?:/(?:(?:(?:(?:[a-zA-Z\d$\-_.+! *'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'() ,]|(?:%[a-fA-F\d]{2}))|[?:@&=])*))*)(?:;type=[AIDaid])?)?)|(?:news:(?: (?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;/?:&=])+@(?:(?:( ?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[ a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3})))|(?:[a-zA-Z]( ?:[a-zA-Z\d]|[_.+-])*)|\*))|(?:nntp://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[ a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d ])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:[a-zA-Z](?:[a-zA-Z \d]|[_.+-])*)(?:/(?:\d+))?)|(?:telnet://(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+ !*'(),]|(?:%[a-fA-F\d]{2}))|[;?&=])*)(?::(?:(?:(?:[a-zA-Z\d$\-_.+!*'() ,]|(?:%[a-fA-F\d]{2}))|[;?&=])*))?@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a -zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d] )?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?))/?)|(?:gopher://(?:(?: (?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?: (?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+ ))?)(?:/(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))(?:(?:(?:[ a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))*)(?:%09(?:(?:(?:[a-zA -Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;:@&=])*)(?:%09(?:(?:[a-zA-Z\d$ \-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))*))?)?)?)?)|(?:wais://(?:(?:(?: (?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?: [a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))? )/(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)(?:(?:/(?:(?:[a-zA -Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)/(?:(?:[a-zA-Z\d$\-_.+!*'(),]|( ?:%[a-fA-F\d]{2}))*))|\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d] {2}))|[;:@&=])*))?)|(?:mailto:(?:(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:% [a-fA-F\d]{2}))+))|(?:file://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d] |-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?: (?:\d+)(?:\.(?:\d+)){3}))|localhost)?/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'() ,]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|( ?:%[a-fA-F\d]{2}))|[?:@&=])*))*))|(?:prospero://(?:(?:(?:(?:(?:[a-zA-Z \d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-) *[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:(?:(?:(? :[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a- zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*))*)(?:(?:;(?:(?:(?:[ a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&])*)=(?:(?:(?:[a-zA-Z\d $\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&])*)))*)|(?:ldap://(?:(?:(?:(?: (?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?: [a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))? ))?/(?:(?:(?:(?:(?:(?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]) )|(?:%20))+|(?:OID|oid)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%2 0)*)=(?:(?:%0[Aa])?(?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F \d]{2}))*))(?:(?:(?:%0[Aa])?(?:%20)*)\+(?:(?:%0[Aa])?(?:%20)*)(?:(?:(? :(?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID |oid)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa]) ?(?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)))*)(?:( ?:(?:(?:%0[Aa])?(?:%20)*)(?:[;,])(?:(?:%0[Aa])?(?:%20)*))(?:(?:(?:(?:( ?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID|o id)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])?( ?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*))(?:(?:(?: %0[Aa])?(?:%20)*)\+(?:(?:%0[Aa])?(?:%20)*)(?:(?:(?:(?:(?:[a-zA-Z\d]|%( ?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID|oid)\.(?:(?:\d+)(?: \.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])?(?:%20)*))?(?:(?:[a -zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)))*))*(?:(?:(?:%0[Aa])?(?:%2 0)*)(?:[;,])(?:(?:%0[Aa])?(?:%20)*))?)(?:\?(?:(?:(?:(?:[a-zA-Z\d$\-_.+ !*'(),]|(?:%[a-fA-F\d]{2}))+)(?:,(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-f A-F\d]{2}))+))*)?)(?:\?(?:base|one|sub)(?:\?(?:((?:[a-zA-Z\d$\-_.+!*'( ),;/?:@&=]|(?:%[a-fA-F\d]{2}))+)))?)?)?)|(?:(?:z39\.50[rs])://(?:(?:(? :(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(? :[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+)) ?)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+)(?:\+(?:(?: [a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+))*(?:\?(?:(?:[a-zA-Z\d$\-_ .+!*'(),]|(?:%[a-fA-F\d]{2}))+))?)?(?:;esn=(?:(?:[a-zA-Z\d$\-_.+!*'(), ]|(?:%[a-fA-F\d]{2}))+))?(?:;rs=(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA -F\d]{2}))+)(?:\+(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+))*) ?))|(?:cid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&= ])*))|(?:mid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@ &=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=] )*))?)|(?:vemmi://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z \d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:.(?:\d+)){3}))(?::(?:\d+))?)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a -fA-F\d]{2}))|[/?:@&=])*)(?:(?:;(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a -fA-F\d]{2}))|[/?:@&])*)=(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d ]{2}))|[/?:@&])*))*))?)|(?:imap://(?:(?:(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+ !*'(),]|(?:%[a-fA-F\d]{2}))|[&=~])+)(?:(?:;[Aa][Uu][Tt][Hh]=(?:\*|(?:( ?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~])+))))?)|(?:(?:;[ Aa][Uu][Tt][Hh]=(?:\*|(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2 }))|[&=~])+)))(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[ &=~])+))?))@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d]) ?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?: \d+)){3}))(?::(?:\d+))?))/(?:(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?: %[a-fA-F\d]{2}))|[&=~:@/])+)?;[Tt][Yy][Pp][Ee]=(?:[Ll](?:[Ii][Ss][Tt]| [Ss][Uu][Bb])))|(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2})) |[&=~:@/])+)(?:\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[ &=~:@/])+))?(?:(?:;[Uu][Ii][Dd][Vv][Aa][Ll][Ii][Dd][Ii][Tt][Yy]=(?:[1- 9]\d*)))?)|(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~ :@/])+)(?:(?:;[Uu][Ii][Dd][Vv][Aa][Ll][Ii][Dd][Ii][Tt][Yy]=(?:[1-9]\d* )))?(?:/;[Uu][Ii][Dd]=(?:[1-9]\d*))(?:(?:/;[Ss][Ee][Cc][Tt][Ii][Oo][Nn ]=(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~:@/])+)))?)) )?)|(?:nfs:(?:(?://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA- Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?: \.(?:\d+)){3}))(?::(?:\d+))?)(?:(?:/(?:(?:(?:(?:(?:[a-zA-Z\d\$\-_.!~*' (),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d\$\-_.!~*'(), ])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?)))?)|(?:/(?:(?:(?:(?:(?:[a-zA-Z\d \$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d\$-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?))|(?:(?:(?:(?:(?:[a-zA- Z\d\$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d \$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?))) ><<a href = "$1">$1</a>>gx;
复制代码

                     我是一个呼吸着现在的空气而生活在过去的人
               这样的注定孤独,孤独的身处闹市却犹如置身于荒漠
                                     我已习惯了孤独,爱上孤独
                                 他让我看清了自我,还原了自我
                             让我再静静的沉思中得到快乐和满足
                                   再孤独的世界里我一遍又一遍
                                   不厌其烦的改写着自己的过去
                                             延伸到现在与未来
                                       然而那只是泡沫般的美梦
                                 产生的时刻又伴随着破灭的到来
                         在灰飞烟灭的瞬间我看到的是过程的美丽
                                      而不是结果的悲哀。。。
返回列表