#!/web/perl use strict; $|++; use LWP::Simple; -d "RESULTS" or mkdir "RESULTS", 0755 or die "cannot mkdir RESULTS: $!"; my $all_model_index = get "http://sportsillustrated.cnn.com/2012_swimsuit/models/"; while ($all_model_index =~ m{"(/2012[^"]+/)"}g) { doit("$1"); } doit("/2012_swimsuit/painting/$_/") for qw(alex-morgan natalie-coughlin natalie-gulbis); exit 0; my %done; sub doit { my $base = shift; return if $done{$base}++; print "$base =>\n"; # (print "[TEMP SKIPPED]", "\n"), return unless $base =~ /paint/; my $model_index = get "http://sportsillustrated.cnn.com/$base/index2.html"; unless ($model_index) { $model_index = get "http://sportsillustrated.cnn.com/$base/"; } while ($model_index =~ m{(\w+)\.html.*?\"(http://i.cdn.turner.com/si/pr/subs/swimsuit/images/.*?[\w.\-]+)_t.jpg\"}g) { my $url = "$2.jpg"; my $file = "RESULTS/$1.jpg"; if (-e $file) { print "$url => $file: "; print "skip\n"; } else { print "$url => $file: "; print mirror($url, $file), "\n"; } } }