use strict;
my $str = '###################
# bug cases
https://www.catho.com.br/educacao/busca/em-em-em-em-extrema-mg
https://www.catho.com.br/educacao/busca/em-extrema-mg
https://www.catho.com.br/educacao/busca/em-mextrema-mg
https://www.catho.com.br/educacao/busca-curso-admin/usp/em-mextrema-mg
https://www.catho.com.br/educacao/busca-curso-admin/em-mextrema-mg
https://www.catho.com.br/educacao/busca-admin/em-mextrema-mg
#####################
// without term or filters
https://www.catho.com.br/educacao/busca
https://www.catho.com.br/educacao/busca/
###################
// with term or match but no filters
https://www.catho.com.br/educacao/busca-curso-design-industrial
https://www.catho.com.br/educacao/busca-curso-design-industrial/
https://www.catho.com.br/educacao/busca-de%20csign-industrial
https://www.catho.com.br/educacao/busca-de%20csign-industrial/
https://www.catho.com.br/educacao/busca-design-industrial
https://www.catho.com.br/educacao/busca-design-industrial/
###################
// without term but with provider
https://www.catho.com.br/educacao/busca/centro-universitario-senac
https://www.catho.com.br/educacao/busca/centro-universitario-senac/
// without term but with location
https://www.catho.com.br/educacao/busca/em-sao-paolo
https://www.catho.com.br/educacao/busca/em-sao-paolo/
// without term but with provider & location
https://www.catho.com.br/educacao/busca/centro-universitario-senac/em-sao-paolo
https://www.catho.com.br/educacao/busca/centro-universitario-senac/em-sao-paolo/
###################
// with term & provider
https://www.catho.com.br/educacao/busca-design-industrial/centro-universitario-senac
https://www.catho.com.br/educacao/busca-design-industrial/centro-universitario-senac/
// with term & location
https://www.catho.com.br/educacao/busca-design-industrial/em-sao-paolo
https://www.catho.com.br/educacao/busca-design-industrial/em-sao-paolo/
// with term & provider & location
https://www.catho.com.br/educacao/busca-design-industrial/centro-universitario-senac/em-sao-paolo
https://www.catho.com.br/educacao/busca-design-industrial/centro-universitario-senac/em-sao-paolo/
###################
// with match & provider
https://www.catho.com.br/educacao/busca-curso-design-industrial/centro-universitario-senac
https://www.catho.com.br/educacao/busca-curso-design-industrial/centro-universitario-senac/
// with match & location
https://www.catho.com.br/educacao/busca-curso-design-industrial/em-sao-paolo
https://www.catho.com.br/educacao/busca-curso-design-industrial/em-sao-paolo/
// with match & provider & location
https://www.catho.com.br/educacao/busca-curso-design-industrial/centro-universitario-senac/em-sao-paolo
https://www.catho.com.br/educacao/busca-curso-design-industrial/centro-universitario-senac/em-sao-paolo/';
my $regex = qr/educacao\/busca-?([\w%-]+)?\/?(?!em-)([\w%-]+)?\/?(em-)?([\w%-]+)?\/?/p;
if ( $str =~ /$regex/g ) {
print "Whole match is ${^MATCH} and its start/end positions can be obtained via \$-[0] and \$+[0]\n";
# print "Capture Group 1 is $1 and its start/end positions can be obtained via \$-[1] and \$+[1]\n";
# print "Capture Group 2 is $2 ... and so on\n";
}
# ${^POSTMATCH} and ${^PREMATCH} are also available with the use of '/p'
# Named capture groups can be called via $+{name}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Perl, please visit: http://perldoc.perl.org/perlre.html