use strict;
my $str = 'Name|COL
San Diego|\'https://foo.com/energy_docs/tyv/2004/019787_S30_gasTOC.cfm https://foo.com/energy_docs/tyv/99/19787s022_gas.pdf https://foo.com/energy_docs/tyv/2000/19787s021_gas.pdf https://foo.com/energy_docs/tyv/2000/19787-s017_report.pdf https://foo.com/energy_docs/tyv/99/293-_9302SDFS 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/99/19787-s018_gas.pdf https://foo.com/energy_docs/tyv/2000/19787-s017_report.pdf https://foo.com/energy_docs/tyv/98/019787-S16_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/97/019787-S15_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/97/019787-S14_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/97/19787-S013_gas.pdf https://foo.com/energy_docs/tyv/96/019787-S12_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/96/019787-S11_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/96/019787-S10_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S9_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S8_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/96/19-787s007_Amlodipine.cfm https://foo.com/energy_docs/tyv/pre96/019787-S6_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S5_gas 2.5 KM, 5.0 KM, & 10.0 KM GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S4_gas GAS_TPC.cfm https://foo.com/energy_docs/tyv/pre96/019787-S3_gas_toc.cfm https://foo.com/energy_docs/tyv/pre96/019787-S2_gas GAS_TPC.cfm\'
Washington|\'https://foo.com/energy_docs/a32/2007/022136.cfm\'
Texas|\'https://foo.com/energy/29380/no_ant/USA/2/2007.pdf\'';
my $regex = qr/(\bhttp.*?\.pdf\b)/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