Many of the tools used to parse HTML use
HTML::Parser under the hood, and it is worthwhile knowing how it works. This script gathers up all the content of each list item, including other elements, into a variable. When it meets the closing list item tag, you can do what you need to the content before printing it out.
use HTML::Parser;
my $inside_li = 0;
my $list_item = '';
sub start {
my ($tag, $text) = @_;
if ($inside_li) {
$list_item .= $text;
return;
}
if ($tag eq 'li') {
$inside_li = 1;
}
print $text;
};
sub text {
my ($text) = @_;
if ($inside_li) {
$list_item .= $text;
return;
}
print $text;
};
sub end {
my ($tag, $text) = @_;
if ($tag eq 'li') {
$inside_li = 0;
# do things to <li> content
$list_item =~ s/^\s+//;
print $list_item;
$list_item = '';
}
if ($inside_li) {
$list_item .= $text;
return;
}
print $text;
};
my $parser = HTML::Parser->new(
api_version => 3,
start_h => [\&start, "tagname, text"],
text_h => [\&text, "text"],
end_h => [\&end, "tagname, text"],
default_h => [\&text, "text"],
);
$parser->parse_file(\*DATA);