Atom Feed for Chatterbox 60

#!/usr/bin/env perl

use HTML::HTML5::Parser;
use Object::Tap -package => 'XML::Atom::Base';
use XML::Atom::Feed;
use XML::Atom::Entry;
use XML::Atom::Person;
use XML::LibXML 2.00;

my $list = HTML::HTML5::Parser
    -> new
    -> parse_file('http://mini-cb60.datenzoo.de/', { ignore_http_respo
+nse_code => 1 })
    -> getElementsByTagName('dl')
    -> get_node(1);

my $feed = XML::Atom::Feed->new;
$feed->title('PerlMonks Chatterbox');
$feed->id('tag:buzzword.org.uk,2012:perlmonks:chatterbox');

my $dt;
foreach my $node ($list->getChildrenByTagName('*'))
{
    ($dt = $node) && next if $node->tagName eq 'dt';

    $feed->add_entry(
        XML::Atom::Entry->new->tap(
            title  => [ $node->textContent ],
            id     => [ join ':', $feed->id, $dt->{id} ],
            author => [
                XML::Atom::Person->new->tap(
                    name => [ $dt->getElementsByTagName('a')->get_node
+(1)->textContent ],
                    uri  => [
                        'http://www.perlmonks.org/'.
                        $dt->getElementsByTagName('a')->get_node(1)->{
+href}
                    ],
                )
            ],
            published => [
                $dt->getElementsByTagName('small')->get_node(1)->textC
+ontent,
            ],
        )
    );
}

print $feed->as_xml;
[download]

Fixing up the datetimes to meet the Atom 1.0 spec is left as an exercise for the reader.

perl -E'sub Monkey::do{say$_,for@_,do{($monkey=[caller(0)]->[3])=~s{::}{ }and$monkey}}"Monkey say"->Monkey::do'

Comment on Atom Feed for Chatterbox 60 Download Code

Replies are listed 'Best First'.

Re: Atom Feed for Chatterbox 60
by mje (Curate) on Oct 15, 2012 at 13:16 UTC

Thanks tobyink. I had to make a slight change for behind a proxy server:

my $ua = LWP::UserAgent->new;
$ua->env_proxy;

my $list = HTML::HTML5::Parser
    -> new
    -> parse_file('http://mini-cb60.datenzoo.de/', { ignore_http_respo
+nse_code => 1, user_agent => $ua })
    -> getElementsByTagName('dl')
    -> get_node(1);
[download]

Also, HTML::HTML5::Parser failed its tests for me. When I looked at the test results I saw other people/smokers had hit this too so I reported it at 07ua.t fails.

[reply]
[d/l]


We don't bite newbies here... much
	PerlMonks