#! /usr/bin/perl use strict; use warnings; use Data::Dumper; use HTML::TreeBuilder; # meteoalarm.html contains the source of your link open my $fh, q{<}, q{meteoalarm.html} or die qq{cant open file to read: $!\n}; my $content = do{local $/; <$fh>}; my $data = _parse_details($content); print Dumper $data; sub _parse_details { my $content =shift; my (%data); my $p = HTML::TreeBuilder->new_from_content( $content ); $data{fullname} = $p->look_down( _tag => q{h1} )->as_text; my @warnbox_divs = $p->look_down( _tag => q{div}, class => qr/warnbox wb\d/ ); for my $div (@warnbox_divs) { my ($as_txt); my @info_divs = $div->look_down( _tag => q{div}, class => q{info} ); $as_txt = $info_divs[0]->as_text; my ($from, $until) = $as_txt =~ /valid from (.*) Until (.*)$/; $as_txt = $info_divs[1]->as_text; my ($warning, $level) = $as_txt =~ /([^\s]+)\s+Awareness Level:\s+(.*)/; my $text = $div->look_down( _tag => q{div}, class => q{text} )->as_text; $data{warnings}{$warning} = { level => $level, from => $from, until => $until, text => $text, }; } return \%data; }