use strict;
use warnings;
use LWP::Simple;
use LWP::UserAgent;
use HTML::TokeParser::Simple;
my $ua = LWP::UserAgent->new( );
my $text = do_GET_TXT("http://www.spacex.com/webcast");
print $text;
sub do_GET_TXT {
my ($url)=@_;
print "Downloading and reading HTML $url...\n";
my $response = $ua->get($url);
if ($response->is_error) {
$response->code;
}
else{
my $HTML = $response->decoded_content();
my @text;
require HTML::TokeParser::Simple;
my $p = HTML::TokeParser::Simple->new(\$HTML);
while ( my $token = $p->get_token ) {
next unless $token->is_text;
my $out = $token->as_is;
$out =~ s/^\s+/\n/;
push (@text, $out);
}
my $text = join("", @text);
#some heuristics
$text =~ s/\n+/\n/g;
$text =~ s/\n(\d+\.)\n/$1\t/g;
$text =~ s/(\(\d+\))\n/$1\t/g;
$text =~ s/([a-z]\))\n/$1\t/g;
return $text;
}
}
####
my $dom = Mojo::DOM->new($HTML);
my $text = $dom->all_text();
##
##
my $dom = Mojo::DOM->new($HTML);
my $text = $dom->at('body')->all_text();