#!/usr/bin/perl -w # Print all dlib urls that aren't article urls use strict; open(URLS, "urls_by_article_complete.txt") || die($!); while (my $line = ) { # Ignore article urls next if ($line !~ m|^\t|); chomp($line); my ($url) = $line =~ /^\t(.+)/; print "$url\n" if ($url =~ m|^http://www.dlib.org|); } close URLS;