TITLE

A Perl 6 module to find all the URL's in a set of text.


SUBTITLE

head

By default it will match domain names
that use unicode characters such as http://правительство.рф. To only match ASCII domains use the
:ascii option. It will also find URL's that end in one of the restricted characters, so
`https://www.google.com, ` will pull out `https://www.google.com`. It will find all the URL's in a
text by default, or you can specify a maximum number with the :limit option. By default it will
only find http, https, ftp, git and ssh schemes, but you can specify `:any<1>` to match any schemes
with legal characters..


para


my token anyprotocol {   <[ a..z A..Z ]> <[ a..z A..Z 0..9 . + - ]>+  }
my token protocol    {:i [http|https|ftp|git|ssh]                     }
my token baseascii   {   [ <[a..z A..Z 0..9 \- . ]> ]+                }
my token base        {   [ <:Number + :Letter + [ . - ]> ]+           }
my token protected   {   <[ $ + ! * ( ) , . ; ? @ = % & # " ' ]>      }
my token allowed     {   \S                                           }
my regex term        {   <allowed>+ <!after <protected>>              }
my token after       {   '/' <term>                                   }

#| Accepts a string and returns a list of URL's. Optionally you can specify a limit to the number
#| of URL's returned, or whether you want to only match URL's with ASCII domain names: :ascii<1>
#| Matches only http https ftp git and ssh schemes by default. To match any scheme, use :any<1>
sub find-urls ( Str $string, Num :$limit? is copy, :$ascii?, :$any? ) is export returns List  {
    $limit = ∞ if ! $limit.defined;
    my $base     = $ascii ?? &baseascii   !! &base;
    my $protocol = $any   ?? &anyprotocol !! &protocol;

    my $url-regex = regex { <$protocol> '://' <$base> [<after>+]? '/'?  };
    $string.comb($url-regex, $limit).List;
}



Samantha McVey (samcv) samantham@posteo.net


AUTHOR

This is free software; you can redistribute it and/or modify it under
the Artistic License 2.0.


LICENSE

root

README

React

=begin React :component<HeaderCol> :id<menu> 
=para L<Documentation|/doc/introduction>
=para L<Modules| /mods>
=para L<Examples| file:../examples/index.podlite>
=para L<Download |file:../download/index.podlite>
=para L<About|file:../about/index.podlite>
=para 🔍 K<⌘K>/K<ctrl-K>
=end React


=begin React :component<HeaderCol> :id<footer>  
=begin nested :!nested
=item1 B<Language>
    =item2 L<Get started|file:../getting-started/getting-started.podlite>
    =item2 L<Why Raku?|/doc/language/faq#Why-should-I-learn-Raku-What's-so-great-about-it>
    =item2 L<Try Raku|https://glot.io/new/raku>
    =item2 L<Raku cheat sheet|https://github.com/Raku/mu/blob/master/docs/Perl6/Cheatsheet/cheatsheet.txt>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<Raku on Exercism|https://exercism.org/tracks/raku>
    =item2 L<Wikipedia|https://en.wikipedia.org/wiki/Raku_(programming_language)>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>

=end nested
=begin nested :!nested

=item1 B<L<Documentation|/doc>>
    =item2 L<Getting started, Migration guides from other languages, & Tutorials | file:../doc/introduction.podlite>
    =item2 L<Language References|file:../doc/reference.podlite>
    =item2 L<Type Reference| file:../doc/types.podlite>
    =item2 L<Miscellaneous| file:../doc/miscellaneous.podlite>
    =item2 L<FAQs (Frequently Asked Questions)|/doc/language/faq>
    =item2 L<Community|/doc/language/community>
    =item2 L<The list of all documents|file:../doc/index.podlite>

=item1 B<Resources>
    =item2 L<The Raku Guide|https://raku.guide/>
    =item2 L<Books |https://perl6book.com/>
    =item2 L<Rosetta Code | https://www.raku.org/community/rosettacode>

=end nested
=begin nested :!nested

=item1 B<Resoures>
    =item2 L<Download | file:../download/index.podlite>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>

=item1 B<Learning>
    =item2 L<The Raku Guide|https://raku.guide/>
    =item2 L<Wikibook |https://en.wikibooks.org/wiki/Raku_Programming>
    =item2 L<Books |https://perl6book.com/>
    =item2 L<Rosetta Code | https://www.raku.org/community/rosettacode>
    =item2 L<Learn Raku in Y minutes|https://learnxinyminutes.com/docs/raku/>
    =item2 L<Golfing |https://github.com/AlexDaniel/raku-golf-cheatsheet>
=end nested
=begin nested :!nested

=item1 B<Explore>
    =item2 L<Raku Blog Aggregator|https://planet.raku.org/>
    =item2 L<Rakudo Weekly|https://rakudoweekly.blog/>
    =item2 L<The Weekly Challenge |https://perlweeklychallenge.org/>
    =item2 L<Raku Advent Calendar|https://raku-advent.blog/>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>
    =item2 L<empty|#>

=end nested
=end React


=begin React :component<CookieConsent> :id<CookieConsent> :buttonCaption("Got it!")
=para
This website uses cookies for analytics.
=end React


URL::Find

DESCRIPTION

AUTHOR

LICENSE