use strict;
my $str = '#Fields: date time cs-ip cs-method cs-uri sc-status sc-bytes time-taken cs(Referer) cs(User-Agent) cs(Cookie) x-custom ghostip cache_status x-wafinfo
2023-11-17 07:33:55 217.165.96.151 GET /www.argos.co.uk/assets/common/polyfills/3.0.17/polyfills-request-idle-callback.min.js 200 1400 22 "https://www.argos.co.uk/product/4660185?cjdata=MXxOfDB8WXww&$ja=tsid%3A11674%7Cprd%3A100072047&utm_source=Skimlinks&utm_medium=affiliates&utm_campaign=Argos+Deep+Generator+AID-+DO+NOT+CHANGE&utm_content=10830324&utm_custom1=100072047&utm_custom2=Other&cmpid=cojun&cjevent=a61535ab851b11ee8392ee230a1cb82a&dclid=CLv4hcTCyoIDFe9C9ggdWDMACA" "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1" "akaas_arg_uk_global=1707982435~rv=34~id=e302e31ea1f9450e13700fd5beee9884" "-" 2.21.231.4 1 "1111_3104||"
2023-11-17 07:33:55 217.165.96.151 GET /www.argos.co.uk/assets/common/vendor/5.0.17/commonvendor-react.min.js 200 56746 23 "https://www.argos.co.uk/product/4660185?cjdata=MXxOfDB8WXww&$ja=tsid%3A11674%7Cprd%3A100072047&utm_source=Skimlinks&utm_medium=affiliates&utm_campaign=Argos+Deep+Generator+AID-+DO+NOT+CHANGE&utm_content=10830324&utm_custom1=100072047&utm_custom2=Other&cmpid=cojun&cjevent=a61535ab851b11ee8392ee230a1cb82a&dclid=CLv4hcTCyoIDFe9C9ggdWDMACA" "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6_1 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1" "akaas_arg_uk_global=1707982435~rv=34~id=e302e31ea1f9450e13700fd5beee9884" "-" 2.21.231.4 1 "1111_3104||"';
my $regex = qr/^(?P<date>\d{4}-\d+-\d+)\s+(?P<time>\d+:\d+:\d+)\s+(?P<ip>\d{1,3}.\d{1,3}.\d{1,3}.\d{1,3})\s+(?P<method>\w+)\s+(?P<uri>\/.*)\s+(?P<status>\d+)\s+(?P<bytes>\d+)\s+(?P<referer>\".*\")\s+(?P<useragent>\".*\")\s+(?P<cookie>\".*\")\s+(?P<custom>\".*\")\s+(?P<ghostip>\d{1,3}.\d{1,3}.\d{1,3}.\d{1,3})\s+(?P<cache>\d)\s+(?P<wafinfo>\".*\")$/mp;
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