NRC ENR Atom feed generator

nrc-atom.pl

#!/usr/local/bin/perl -T

#NRC ENR Atom feed generator
#Kurt Raschke
#[email protected]

#Resources:
#http://linuxgazette.net/108/oregan2.html
#http://linuxgazette.net/109/oregan.html
#http://ttul.org/repos/cpan/trunk/Kwiki-Atom/lib/Kwiki/Atom.pm
#http://japhy.perlmonk.org/sexeger/sexeger.html
#http://www.ahinea.com/en/tech/perl-unicode-struggle.html

#Copyright (c) 2005 Kurt Raschke

#Permission is hereby granted, free of charge, to any person obtaining a
#copy of this software and associated documentation files (the "Software"),
#to deal in the Software without restriction, including without limitation
#the rights to use, copy, modify, merge, publish, distribute, sublicense,
#and/or sell copies of the Software, and to permit persons to whom the
#Software is furnished to do so, subject to the following conditions:

#The above copyright notice and this permission notice shall be included in
#all copies or substantial portions of the Software.

#THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
#IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
#FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
#THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
#LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
#FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
#DEALINGS IN THE SOFTWARE.

use strict;
use XML::Atom::Feed;
use XML::Atom::Entry;
use XML::Atom::Link;
use XML::Atom::Person;
use XML::Atom::Content;
use LWP::Simple;
use HTML::Entities;
use HTML::TokeParser::Simple;
use HTML::TableExtract;
use DateTime;
use Encode;
use Cache::FileCache;
use CGI qw/:standard/;
use CGI::Carp qw(fatalsToBrowser);

binmode(STDOUT, ":encoding(UTF-8)");

my $cache = new Cache::FileCache({"namespace" => "nrc-atom", "default_expires_in" => 3600});
$cache->Purge();

my $url = "http://www.nrc.gov/reading-rm/doc-collections/event-status/event/en.html";

if (my $purl = param('url'))
{
	if ( $purl =~ /^http:\/\/www.nrc.gov\/reading-rm\/doc-collections\/event-status\/event(.*)/)
	{
		$url = $purl;
	}
	else
	{
		die "The URL parameter given ($purl) is invalid and will not be parsed.";
	}
}

my $feed = $cache->get($url);

if (not defined $feed) {
	my $page = get($url);
	$page = Encode::decode('iso-8859-1', $page);
	$feed = parsepage($page);
	$cache->set($url,$feed);
}

print "Content-Type: application/atom+xml\r\n\r\n";

print $feed;


sub parsepage
{

	my $toparse = shift(@_);

	my $atom = XML::Atom::Feed->new;
	my $entry;
	my $stream = HTML::TokeParser::Simple->new(\$toparse);
	my $tag;
	$atom->title('NRC: Current Event Notification Report');
	$atom->tagline('Event Notification Report from the U.S. Nuclear Regulatory Commission Operations Center');
	my $link = XML::Atom::Link->new;
	$link->type('text/html');
	$link->rel('alternate');
	$link->href($url);
	$atom->add_link($link);
	$atom->version('0.3');
	$atom->modified(DateTime->now()->iso8601().'Z');

	while ($tag = $stream->get_tag('a'))
	{
		next unless $tag->return_attr("name") =~ /en\d{5}/;
		my $enrid = $tag->return_attr("name");
		#print $tag->return_attr("name");
		$tag = $stream->get_tag('table');
		my $content_st = "";
		
		until ($tag->is_tag('a'))
		{
			$content_st .= $tag->as_is;
			$tag = $stream->get_token;
			next;
		}
		
		$stream->unget_token($tag);
		
		
		#caution, ugly code ahead.
		$content_st = scalar reverse($content_st);
		$content_st =~ s/^(.*?)>ELBAT\/</>ELBAT\/</ms;
		$content_st = scalar reverse($content_st);
		#end ugly code zone.
		
		
		my $toptable = $content_st;
		
		my $author_st = $toptable;
		$author_st =~ /.*NRC Notified By: (.*)<BR>/;
		$author_st = $1;
		
		my $author = XML::Atom::Person->new;
		$author->name($author_st);
		
		my $date = $toptable;
		$date =~ /.*Notification Date: (.*)\/(.*)\/(.*)<BR>/;
		my $month = $1;
		my $day = $2;
		my $year = $3;
		
		my $time = $toptable;
		$time =~ /.*Notification Time: (.*):(.*)<BR>/;
		my $hour = $1;
		my $minute = $2;
		
		my $dt = DateTime->new( year   => $year,
								month  => $month,
								day    => $day,
								hour   => $hour,
								minute => $minute,
								second => 0,
								time_zone => 'America/New_York',
								);
		
		$dt->set_time_zone('UTC');
		
		
		my $te = new HTML::TableExtract();
		$te->parse($content_st);
		my @tc = $te->tables();
		my $count = @tc;
		my @ts = $te->table(0,$count-1);	
		my @rows = $ts[0]->rows;
		my @lines = split("\n",$rows[0][0]);
		chop $lines[0];
		my $title = $lines[0];
		
		my $en = $enrid;
		
		$en =~ s/en(\d{5})/EN #$1/;
			
		my $entry = XML::Atom::Entry->new;
		$entry->title($en.": ".$title);
		my $itemlink = XML::Atom::Link->new;
		$itemlink->type('text/html');
		$itemlink->rel('alternate');
		$itemlink->href($url.'#'.$enrid);
		$entry->add_link($itemlink);
		$entry->author($author);
		
		my $tagd = DateTime->now();

		$tagd = $tagd->ymd('-');
		
		$entry->id('tag:nrc.gov,'.$tagd.':'.$enrid);
		$entry->issued($dt->iso8601().'Z');
		$entry->modified($dt->iso8601().'Z');
		
		
		my $content = XML::Atom::Content->new;
		my $text = ($content->LIBXML) ? 'XML::LibXML::Text' : 'XML::XPath::Node::Text';
		my $elem = $content->elem;
		$content->type('text/html');
		$elem->appendChild($text->new($content_st));
		$elem->setAttribute('mode', 'escaped');	
		$entry->content($content);
		
		$atom->add_entry($entry);
		
	}

	return $atom->as_xml;
}