use strict; use warnings; use diagnostics; use XML::RSS::Tools; # Parse the content use HTML::Entities; use HTML::LinkExtor; # Extract the links use HTML::Entities; # "fix" any entities use LWP::UserAgent; # Change the UserAgent my $rss = $ARGV[0]; my $rss_feed = XML::RSS::Tools->new( auto_wash => 1, debug => 1); my $ua = LWP::UserAgent->new; my $request = HTTP::Request->new(GET => $rss); my $response = $ua->request($request); my $status = $response->status_line; my $type = $response->header('Content-Type'); my $content = $response->content; $content =~ s,\cM,,g; $content =~ s,—,--,g; $content =~ s,\x92,',g; $rss_feed->rss_string("$content"); $rss_feed->xsl_file('atom03.xsl'); $rss_feed->transform; my $parsed = encode_entities($rss_feed->as_string); my $decoded = decode_entities($parsed); print "$decoded";