use GT::HTML::LinkExtractor;
my $extractor = new GT::HTML::LinkExtractor(
wanted_urls => [@GT::HTML::LinkExtractor::URL_ALL],
wanted_images => ['http://', 'https://'],
get_images => 1,
get_text => 1,
follow_base => 1,
base => 'http://somedomain.com'
);
$extractor->extract( $html ); # Extract from a string
$extractor->extract_from_file( "/path/to/html.htm" ); # extract from file
$extractor->extract_from_uri( "http://www.yahoo.com";, "http://www.gossamer-threads.com"; ); # extract from uri my $links = $extractor->links;

<a href="http://link"; class="MyClass">text<img src="http://image"; alt="My Alt Tag">more text</a>

{
href => "http://link";,
class => "MyClass"
content => [
"text",
{
src => "http://image";,
alt => "My Alt Tag,
},
"more text"
]
}