#!/usr/bin/perl -w
use strict;
use HTML::TreeBuilder;
my $data = <<'EOF';
EOF
# This list of URLs to omit is case-insensitive.
my %omit = map {lc($_),1} qw(
http://www.cnn.com/WEATHER/index.html
ftp://DEBIAN.SECSUP.ORG/PUB/LINUX/DEBIAN/README
);
print "\nParsing with HTML::TreeBuilder...\n";
my $tree = HTML::TreeBuilder->new;
$tree->parse($data);
$tree->eof();
for (@{ $tree->extract_links('a') }) {
my($real_url, $element, $attr, $tag) = @$_;
if( $omit{ lc($real_url) } ) {
print "Skip this url: $real_url\n";
next;
}
print "Good URL: $real_url\n";
}
$tree = $tree->delete;
print "\nParsing with regex...\n";
my @tags = ($data =~ m{()}ig );
foreach my $url (@tags) {
my ($real_url) = ( $url=~ m{}i )
or die "URL '$url' failed pattern match";
if( $omit{ lc($real_url) } ) {
print "Skip this url: $real_url\n";
next;
}
print "Good URL: $real_url\n";
}