moin-search.pl

   1 #! /usr/bin/perl
   2 # Copyright (C) 2003  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 LWP::UserAgent;
  23
  24 if (not param('url')) {
  25   print header(),
  26     start_html('MoinMoin Search RSS 3.0'),
  27     h1('MoinMoin Search RSS 3.0'),
  28     p('Translates a MoinMoin Search result into RSS 3.0 usable by Oddmuse.'),
  29     start_form(-method=>'GET'),
  30     p('Search URL: ', textfield('url'), submit()),
  31     end_form(),
  32     end_html();
  33   exit;
  34 }
  35
  36 print header(-type=>'text/plain; charset=UTF-8');
  37
  38 my $ua = new LWP::UserAgent;
  39 my $request = HTTP::Request->new('GET', param('url'));
  40 my $response = $ua->request($request);
  41 my $data = $response->content;
  42
  43 $data =~ /\<title\>([^<]*)/i;
  44 print "title: $1\n" if $1;
  45 print "link: " . param('url') . "\n\n";
  46
  47 $data =~ /\<ul\>((.*\n)*.*)\<\/ul\>/i;
  48
  49 foreach $item (split(/\<li\>/i, $1)) {
  50   next unless $item =~ /\<a[^>]*\>([^<]+)/i;
  51   print "title: $1\n";
  52   $desc = '';
  53   while ($item =~ m/\<font[^>]*\>((.*?\n)*?.*?)\<\/font\>/gi) {
  54     $word = $1;
  55     $word =~ s/^\.\.\.\S+/\.\.\./;
  56     $word =~ s/\S+\.\.\.$/\.\.\./;
  57     $desc .= $word . ' ';
  58   }
  59   if ($desc) {
  60     $desc =~ s/\<\/?b\>//gi;
  61     $desc =~ s/[\r\n\t]+/ /g;
  62     $desc =~ s/\.\.\. \.\.\./\.\.\./g;
  63     print "description: $desc\n";
  64   }
  65   print "\n";
  66 }