Dan’s Blog

## (C) 2007 Dan Check
##
## This script is free software; you can redistribute it and/or modify
## it under the terms of the GNU General Public License as published by
## the Free Software Foundation; either version 2, or (at your option)
## any later version.
##
## This script is distributed in the hope that it will be useful,
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.
##
## You may have received a copy of the GNU General Public License
## along with this script; see the file COPYING. If not, write to the
## Free Software Foundation, Inc., 59 Temple Place - Suite 330,
## Boston, MA 02111-1307, USA.

use strict;
use warnings;
use LWP;
use XML::RSS;
use Date::Format;
use HTML::TreeBuilder;

# Create an XML RSS object
my $rss = new XML::RSS (version => ‘2.0′);
$rss->channel(title => ‘Heck\’s Kitchen’,
link => ‘http://jennymiller.com/’,
language => ‘en’,
description => ‘The dramatic lives of trapeze artists, a clown, and an elephant trainer against a background of circus spectacle.’,
copyright => ‘Copyright 2007, jennymiller.com’,
managingEditor => ‘katspank@gmail.com’,
webMaster => ‘katspank@gmail.com’
);
$rss->add_module(prefix=>’content’, uri=>’http://purl.org/my/rss/module/’);
# pubDate => ‘Thu, 23 Aug 1999 07:00:00 GMT’,
# lastBuildDate => ‘Thu, 23 Aug 1999 16:20:26 GMT’,

# create a new browser
my $browser = LWP::UserAgent->new;

# Set browser headers
$browser->default_headers->push_header(’User-Agent’ => ‘Mozilla/5.0 (Macintosh; U; Intel Mac OS X; en-US; rv:1.8.1.6) Gecko/20070725 Firefox/2.0.0.6′);
$browser->default_headers->push_header(’Accept’ => ‘text/xml,application/xml,application/xhtml+xml,text/html,text/plain,image/png,*/*’);
$browser->default_headers->push_header(’Accept-Language’ => ‘en-us,en’);
$browser->default_headers->push_header(’Accept-Charset’ => ‘ISO-8859-1,utf-8′);

my $url = “http://www.jennymiller.com/”;

# Create a cookie jar
$browser->cookie_jar({});

# Get the login page
my $response = $browser->get($url);
unless($response->is_success) {
warn “Couldn’t get $url: “, $response->status_line, “\n”;
die;
}

# create a tree
my $tree = HTML::TreeBuilder->new;
$tree->parse($response->content);
$tree->eof;

my @out;
# we want entry and menu classes
foreach my $item (
$tree->look_down(’_tag’, ‘div’,
sub {
return if !$_[0]->attr(’class’) && !$_[0]->attr(’id’);
return unless (($_[0]->attr(’class’) && $_[0]->attr(’class’) =~ /^entry$/) || ($_[0]->attr(’id’) && $_[0]->attr(’id’) =~ /^menu$/));
# print “Got ” . $_[0]->as_text . “\n”;
my @c = $_[0];
}
)) {
my $item_tree = HTML::TreeBuilder->new;
$item_tree->parse($item->as_HTML);
$item_tree->eof;
# Grab the first h3 as the title
my $date_tree = $item_tree->look_down(’_tag’, ‘h3′);
my $title_tree = $item_tree->look_down(’_tag’, ‘h1′);
my $date = time2str(”%b %d, %Y”, time);
if ($date_tree) {
$date = $date_tree->as_text;
}
# Default the title to LOOK, for the links section
my $title = “LOOK!”;
if ($title_tree) {
$title = $title_tree->as_text;
}
$rss->add_item(title => $title,
link => “http://jennymiller.com/”,
guid => $date,
description => “< ![CDATA[" . $item->as_HTML . “]]>”

);
}

$tree->delete;

$rss->{output} = ‘2.0′;
$rss->save(’./jloreview.com/hk/rss.xml’);