#!/usr/bin/perl -w

use strict;

use XML::RSS::SimpleGen;

my $VERSION=0.01;

my $LIVE=1;

my $url         = "http://cpanratings.perl.org/";

######################################################
# set those variables
my $local_rss   = "/web/infotree/rss/cpanratings.rss"; 
my $webmaster   = 'me@localhost';
######################################################

my $local_cache = "cpanratings.html";

my $rss = XML::RSS::SimpleGen->new( $url, "CPAN Ratings", "Ratings and Reviews for CPAN");
$rss->language( 'en' );
$rss->webmaster( $webmaster );
$rss->twice_daily();
$rss->item_limit( 25);

if( $LIVE)
  { $rss->get_url( $url ); }
else
  { open( my $html, '<', $local_cache) or die "$!";
    local undef $/;
    $_=<$html>;
  }

while( m{<h3>\s*
         <a \s+ href="([^"]*)">([^<]*)</a> # $1: module URL, $2: module name
         \s*\(([^\(]*)\)                   # $3: version
         \s*<img.*?alt="(\d) \s stars?">   # $4: rating
         \s*</h3>
         \s*<p>\s*
         (.*?)                             # $5: text (first line)
         (\s*<br \s* />.*?)?               # $6: more lines
         \s*</p>
         \s*<p>
         \s*<a[^>]*>([^<]*)</a>            # $7: author
         .*?                               # date, unused for now
         \s*<br \s* />
         \s*\(<a \s+ href="/([^"]*)"       # $8: url
         }xgs
     )
  { my( $module_url, $module_name, $module_version, $rating, $text, $more, $author, $review_url)
      = ($1, $2, $3, $4, $5, $6, $7, $8);
    my $url= "http://cpanratings.perl.org/$review_url";
    my $title= "$module_name ($module_version): $rating stars - by $author";
    my $descr= $text;
    if( $more) { $descr=~ s{\s*\.*\s*$}{ ...}; }
    $rss->item( $url, $title, $descr);
    unless( $LIVE) { warn "title: '$title' - url: '$url' - descr: '$descr'\n"; }
  }

$rss->save( $local_rss, 5);           # the 5 means that the script will scream if the RSS does not change for 5 days in a row

exit;

__END__

=head1 NAME

  gen_rss_cpanratings - generate an RSS feed for CPAN Ratings

=head1 SYNOPSYS

set the top variables, then run the script from cron twice a day

=head1 REQUIREMENTS

Perl 5, 

XML::RSS::SimpleGen

=head1 LICENSE

This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.

=head1 AUTHOR

Michel Rodriguez <mirod@xmltwig.com>