(?:http://(?:(?:(?:(?:(?:a-zA-Zd?). )(?:a-zA-Z?))|(?:(?:d+)(?:.(?:d+) ){3}))(?::(?:d+))?)(?:/(?:(?:(?:(?:[a-zA-Zd$-.+!'(),]|(?:%[a-fA-F d]{2}))|[;:@&=]))(?:/(?:(?:(?:[a-zA-Zd$-.+!'(),]|(?:%[a-fA-Fd]{ 2}))|[;:@&=]))))(?:?(?:(?:(?:[a-zA-Zd$-.+!'(),]|(?:%[a-fA-Fd]{ 2}))|[;:@&=])))?)?)|(?:ftp://(?:(?:(?:(?:(?:[a-zA-Zd$-.+!'(),]|(? :%[a-fA-Fd]{2}))|[;?&=]))(?::(?:(?:(?:[a-zA-Zd$-_.+!'(),]|(?:%[a- fA-Fd]{2}))|[;?&=])))?@)?(?:(?:(?:(?:(?:a-zA-Zd?).)* (...)

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

URLs parsen 🙂