simplify.pl

   1 #! /usr/bin/perl
   2 # Copyright (C) 2003, 2004  Alex Schroeder <alex@emacswiki.org>
   3 #
   4 # This program is free software; you can redistribute it and/or modify
   5 # it under the terms of the GNU General Public License as published by
   6 # the Free Software Foundation; either version 2 of the License, or
   7 # (at your option) any later version.
   8 #
   9 # This program is distributed in the hope that it will be useful,
  10 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12 # GNU General Public License for more details.
  13 #
  14 # You should have received a copy of the GNU General Public License
  15 # along with this program; if not, write to the
  16 #    Free Software Foundation, Inc.
  17 #    59 Temple Place, Suite 330
  18 #    Boston, MA 02111-1307 USA
  19
  20 use CGI qw/:standard/;
  21 use CGI::Carp qw(fatalsToBrowser);
  22 use XML::RSS;
  23 use LWP::UserAgent;
  24 use encoding 'utf8';
  25
  26 my $wikins = 'http://purl.org/rss/1.0/modules/wiki/';
  27 my $rdfns = 'http://www.w3.org/1999/02/22-rdf-syntax-ns#';
  28 my $output = '0.91';
  29
  30 if (not param('url')) {
  31   print header(),
  32     start_html('RSS Simplification'),
  33     h1('RSS Simplification'),
  34     p('Translates any RSS feed to Really Simple Syndication ', $output,
  35       'It understands ModWiki, and will use wiki:diff as the link,',
  36       'and it will add dc:contributor to the description.'),
  37     start_form(-method=>'GET'),
  38     p('RSS feed: ', textfield('url', '', 70)),
  39     p(submit()),
  40     end_form(),
  41     end_html();
  42   exit;
  43 }
  44
  45 print header(-type=>'text/plain; charset=UTF-8');
  46 my $rss = new XML::RSS(output=>$output);
  47 my $ua = new LWP::UserAgent;
  48 my $request = HTTP::Request->new('GET', param('url'));
  49 my $response = $ua->request($request);
  50 my $data = $response->content;
  51 eval {
  52   local $SIG{__DIE__} = sub { parse_rss3(); }; # parsing errors -> try RSS 3.0!
  53   $rss->parse($data);
  54   munge_rss();
  55 };
  56
  57 sub munge_rss {
  58   foreach my $i (@{$rss->{items}}) {
  59     if ($i->{dc}->{contributor}) {
  60       if ($i->{description}) {
  61         $i->{description} = $i->{description} . ' -- ' . $i->{dc}->{contributor};
  62       } else {
  63         $i->{description} = '-- ' .$i->{dc}->{contributor};
  64       }
  65     }
  66     if ($i->{$wikins}->{diff}) {
  67       $i->{link} = $i->{$wikins}->{diff};
  68     }
  69   }
  70   print $rss->as_string();
  71 }
  72
  73 # perl simplify.pl 'url=http://localhost/cgi-bin/wiki.pl?search=foo%3braw=1'
  74
  75 sub parse_rss3 {
  76   $rss->add_module(
  77     prefix => 'wiki',
  78     uri    => 'http://purl.org/rss/1.0/modules/wiki/'
  79   );
  80   my @entries = ();
  81   foreach my $entry (split(/\n\n+/, $data)) {
  82     my %entry = ();
  83     while ($entry =~ /(\S+?): (.*?)(?=\n[^\t]|\Z)/sg) {
  84       my ($key, $value) = ($1, $2);
  85       $value =~ s/\n\t/\n/g;
  86       $entry{$key} = $value if $value;
  87     }
  88     push(@entries, \%entry);
  89   }
  90   # the first entry is the channel
  91   my %entry = %{shift(@entries)};
  92   $rss->channel(%entry);
  93   # the rest are items
  94   while (@entries) {
  95     my %entry = %{shift(@entries)};
  96     my %dc = (date        => $entry{'last-modified'},
  97               contributor => $entry{generator},);
  98     my %wiki = (size      => $entry{size},);
  99     $entry{dc} = %dc;
 100     $entry{wiki} = %wiki;
 101     for my $key qw(last-modified generator size) { delete $entry{$key}; }
 102     $rss->add_item(%entry);
 103   }
 104   print $rss->as_string();
 105 }