use strict; use warnings; my $log_line = '67.60.185.31 - - [14/Jan/2008:02:25:54 -0800] "GET /display.cgi?2643943|3334115 HTTP/1.1" 200 55 "-" "Mozilla/5.0 (Macintosh; U; Intel Mac OS X; en-us) AppleWebKit/523.10.6 (KHTML, like Gecko)" "67.60.185.31"'; my $ip_address = qr{ \d{1,3} (?: \. \d{1,3} ){3} }xms; my $log_pattern = qr{ ( $ip_address ) \s \S+ # user name \s \S+ # user group? \s \[ ( \d\d / # day (?: Jan | Feb | Mar | Apr | May | Jun | Jul | Aug | Sep | Oct | Nov | Dec ) # month / \d{4} # year : \d\d : \d\d : \d\d # time \s+ \S+ # timezone ) \] \s \" ( [A-Z]+ ) # method (GET, POST) \s+ ( \S+ ) \? ( \S+ ) # URL parts \s+ HTTP/( 1\.\d ) # protocol version \" \s ( \d+ ) # response code \s+ ( \d+ ) # bytes of response \s \" ( .* ) \" # referrer \s \" ( .* ) \" # user agent \s+ \" ( $ip_address ) \" }xms; my @fields = ( $log_line =~ /$log_pattern/ ); print "$_\n" for @fields;