use strict;
my $str = '190.2.7.178 - - [21/Dec/2011:05:47:03 +0000] "GET /gnu3/index.php?doc=../../../../../../../proc/self/environ%00 HTTP/1.1" 404 273 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:04 +0000] "GET /gnu/index.php?doc=../../../../../../../proc/self/environ%00 HTTP/1.1" 404 271 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:04 +0000] "GET /phpgwapi/setup/tables_update.inc.php?appdir=../../../../../../../proc/self/environ%00 HTTP/1.1" 404 286 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:05 +0000] "GET /forum/install.php?phpbb_root_dir=../../../../../../../proc/self/environ%00 HTTP/1.1" 404 274 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:06 +0000] "GET /includes/calendar.php?phpc_root_path=../../../../../../../proc/self/environ%00 HTTP/1.1" 404 275 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:06 +0000] "GET /includes/setup.php?phpc_root_path=../../../../../../../proc/self/environ%00 HTTP/1.1" 404 273 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:07 +0000] "GET /inc/authform.inc.php?path_pre=../../../../../../../proc/self/environ%00 HTTP/1.1" 404 275 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:07 +0000] "GET /include/authform.inc.php?path_pre=../../../../../../../proc/self/environ%00 HTTP/1.1" 404 278 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:08 +0000] "GET /index.php?nic=../../../../../../../proc/self/environ%00 HTTP/1.1" 200 4399 "-" "<?php system(\\"id\\"); ?>"
190.2.7.178 - - [21/Dec/2011:05:47:11 +0000] "GET /index.php?sec=../../../../../../../proc/self/environ%00 HTTP/1.1" 200 4399 "-" "<?php system(\\"id\\"); ?>"
123.125.71.79 - - [28/Apr/2012:08:12:57 +0100] "GET /robots.txt HTTP/1.1" 404 268 "-" "Mozilla/5.0 (compatible; Baiduspider/2.0; +http://www.baidu.com/search/spider.html)"
157.56.95.126 - - [28/Apr/2012:10:23:02 +0100] "GET /robots.txt HTTP/1.1" 404 268 "-" "msnbot/2.0b (+http://search.msn.com/msnbot.htm)"
157.56.95.126 - - [28/Apr/2012:10:23:02 +0100] "GET / HTTP/1.1" 200 4399 "-" "msnbot/2.0b (+http://search.msn.com/msnbot.htm)"
110.75.173.193 - - [28/Apr/2012:11:57:26 +0100] "GET / HTTP/1.1" 200 4399 "-" "Yahoo! Slurp China"';
my $regex = qr/(?x)^
(?P<remote_host>\S+) \s+ # host %h
\S+ \s+ # indent %l (unused)
(?P<remote_user>\S+) \s+ # user %u
\[(?P<time_received>.*?)\] \s+ # time %t
"(?P<request>.*?)" \s+ # request "%r"
(?P<status>[0-9]+) \s+ # status %>s
(?P<response_bytes_clf>\S+) (?:\s+ # size %b (careful, can be '-')
"(?P<referrer>[^"?\s]*[^"]*)" \s+ # referrer "%{Referer}i"
"(?P<user_agent>.*? )" (?:\s+ # user agent "%{User-agent}i"
"[^"]*" )?)? # optional argument (unused)
$/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