This file is indexed.

/usr/share/perl5/WWW/Search/WashPost.pm is in libwww-search-perl 2.51.30-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
# $Id: WashPost.pm,v 2.83 2009/05/02 19:26:53 Martin Exp $

=head1 NAME

WWW::Search::WashPost - WWW::Search backend for searching www.washingtonpost.com

=head1 SYNOPSIS

  use WWW::Search;
  my $oSearch = new WWW::Search('WashPost');
  my $sQuery = WWW::Search::escape_query("japan prime minister");
  $oSearch->native_query($sQuery);
  while (my $oResult = $oSearch->next_result())
    { print $oResult->url, "\n"; }

=head1 DESCRIPTION

This class is a specialization of WWW::Search.  It handles making and
interpreting searches on news at The Washington Post
F<http://www.washingtonpost.com>.

This class exports no public interface; all interaction should
be done through L<WWW::Search> objects.

=head1 NOTES

In the resulting WWW::SearchResult objects,
the following elements will be set (in addition to the usual title, description, etc.):

=over

=item source

Something like "Post" or a certain "Edition".

=item location

The page number of the print edition, e.g. "E05".

=item category

The type of item found, either "Article" or "Photo".

=item seller

The author or photographer.

=back

=head1 SEE ALSO

To make new backends, see L<WWW::Search>.

=head1 CAVEATS

This backend (and all its subclasses) only searches news stories from
the last 14 days.
(This is a restriction on the Washington Post website that we can not avoid.)

=head1 BUGS

Please tell the author if you find any!

=head1 AUTHOR

Martin Thurn <mthurn@cpan.org>

=head1 LICENSE

Copyright (C) 1998-2009 Martin 'Kingpin' Thurn

This software is released under the same license as Perl itself.

=cut

package WWW::Search::WashPost;

use strict;

use URI;
use base 'WWW::Search';
use WWW::SearchResult;

our
$VERSION = do { my @r = (q$Revision: 2.83 $ =~ /\d+/g); sprintf "%d."."%03d" x $#r, @r };
our $MAINTAINER = 'Martin Thurn <mthurn@cpan.org>';

sub _native_setup_search
  {
  my ($self, $sQuery, $native_options_ref) = @_;

  $self->{_debug} = $native_options_ref->{'search_debug'};
  $self->{_debug} = 2 if ($native_options_ref->{'search_parse_debug'});
  $self->{_debug} ||= 0;

  # washingtonpost.com does not let us change this:
  my $DEFAULT_HITS_PER_PAGE = 10;
  $self->{'_hits_per_page'} = $DEFAULT_HITS_PER_PAGE;
  # $self->timeout(120);  # use this if website is slow

  # Use this if website refuses robots:
  $self->user_agent('non-robot');
  # Use this if website mucks up page format depending on browser:
  $self->{'agent_name'} = 'Mozilla/4.76';

  $self->{_next_to_retrieve} = 0;
  $self->{'_num_hits'} = 0;
  # This is the result page number:
  $self->{_washpost_cp} = 1;
  if (!defined($self->{_options}))
    {
    # As of 2004-05-22, URL is http://www.washingtonpost.com/ac2/wp-dyn/Search?tab=article_tab&adv=a&keywords=japan&source=APOnline
    # As of 2007-05, full URL is http://www.washingtonpost.com/ac2/wp-dyn/NewsSearch?sa=as&sd=&ed=&sb=-1&x=0&y=0&st=treasure&blt=&fa_1_pagenavigator=&fa_1_sourcenavigator="The+Washington+Post"&daterange=0&specificMonth=5&specificDay=18&specificYear=2007&FromRangeMonth=3&FromRangeDay=19&FromRangeYear=2007&ToRangeMonth=5&ToRangeDay=18&ToRangeYear=2007&sb2=1
    # As of 2007-05, simplest URL is http://www.washingtonpost.com/ac2/wp-dyn/NewsSearch?sa=as&st=treasure&fa_1_sourcenavigator="The+Washington+Post"
    $self->{_options} = {
                         'search_url' => 'http://www.washingtonpost.com/ac2/wp-dyn/NewsSearch',
                         'sa' => 'as',
                         'st' => $sQuery,
                         'fa_1_sourcenavigator' => q'"The+Washington+Post"',
                        };
    } # if
  my $options_ref = $self->{_options};
  if (defined($native_options_ref))
    {
    # Copy in new options.
    foreach (keys %$native_options_ref)
      {
      $options_ref->{$_} = $native_options_ref->{$_};
      } # foreach
    } # if

  # Finally, figure out the url.
  $self->{_next_url} = $self->{_options}{'search_url'} .'?'. $self->hash_to_cgi_string($options_ref);
  } # _native_setup_search

sub _preprocess_results_page_OFF
  {
  my $self = shift;
  my $sPage = shift;
  print STDERR $sPage if (2 < $self->{_debug});
  return $sPage;
  } # _preprocess_results_page

my $WS = q{[\t\r\n\240\ ]};

sub _parse_tree
  {
  my $self = shift;
  my $oTree = shift;
  my $hits_found = 0;
  # Look for the total hit count:
  my @aoSPANcount = $oTree->look_down(
                                      _tag => 'div',
                                      class => 'redBlock',
                                     );
 COUNT_SPAN_TAG:
  foreach my $oSPAN (@aoSPANcount)
    {
    if (ref $oSPAN)
      {
      my $sSPAN = $oSPAN->as_text;
      print STDERR " DDD   try SPANcount == $sSPAN\n" if 2 <= $self->{_debug};
      if ($sSPAN =~ m!([0-9,]+)$WS+results!i)
        {
        my $sCount = $1;
        print STDERR " DDD     raw    count == $sCount\n" if 2 <= $self->{_debug};
        $sCount =~ s!,!!g;
        # print STDERR " DDD     cooked count == $sCount\n" if 2 <= $self->{_debug};
        $self->approximate_result_count($sCount);
        last COUNT_SPAN_TAG;
        } # if
      } # if
    } # foreach COUNT_SPAN_TAG
  # $oTree->objectify_text;

  # Find all the results:
  my @aoSPAN = $oTree->look_down(
                                 _tag => 'div',
                                 class => 'resultBlock',
                                );
 SPAN_TAG:
  foreach my $oSPAN (@aoSPAN)
    {
    next SPAN_TAG unless ref $oSPAN;
    print STDERR " DDD   try oSPAN ===", $oSPAN->as_HTML, "===\n" if (2 <= $self->{_debug});
    my $oDIVheadline = $oSPAN->look_down('_tag' => 'h2',
                                        );
    next SPAN_TAG unless ref $oDIVheadline;
    my $oA = $oDIVheadline->look_down('_tag' => 'a');
    next SPAN_TAG unless ref $oA;
    my $sURL = $oA->attr('href');
    my $sTitle = _strip($oA->as_text);
    print STDERR " DDD     found <A>, url=$sURL=\n" if (2 <= $self->{_debug});
    print STDERR " DDD              title=$sTitle=\n" if (2 <= $self->{_debug});
    $oA->detach;
    $oA->delete;
    my $hit = new WWW::SearchResult;
    $hit->add_url($sURL);
    $hit->title($sTitle);
    my $oDIVdate = $oSPAN->look_down('_tag' => 'p',
                                     class => 'kicker');
    if (ref($oDIVdate))
      {
      my $s = $oDIVdate->as_text;
      print STDERR " DDD   raw date (kicker) =$s=\n" if 2 <= $self->{_debug};
      if ($s =~ m/(.+)\ \|\ (.+)/x)
        {
        my $sType = $1;
        $hit->category($sType);
        my $sDate = $2;
        $hit->change_date($sDate);
        } # if
      $oDIVdate->detach;
      $oDIVdate->delete;
      } # if
    my $oDIVdesc = $oSPAN->look_down('_tag' => 'p',
                                     class => 'teaser');
    if (ref($oDIVdesc))
      {
      $hit->description($oDIVdesc->as_text);
      $oDIVdesc->detach;
      $oDIVdesc->delete;
      } # if
    my $oDIVbyline = $oSPAN->look_down('_tag' => 'p',
                                       class => 'stamp',
                                      );
    my $sByline = '';
    if (ref($oDIVbyline))
      {
      $sByline = $oDIVbyline->as_text;
      } # if
    else
      {
      $sByline = $oSPAN->as_text;
      }
    print STDERR " DDD     try sByline ==$sByline==\n" if 2 <= $self->{_debug};
    if ($sByline =~ m!\((.+)\)!)
      {
      $hit->source($1);
      } # if
    if ($sByline =~ m/\A(.+), (\S+)/)
      {
      $hit->seller($1);
      $hit->location($2);
      }
    if ($sByline =~ m/\b([A-Z]{1,2}[0-9]{1,3})\b/)
      {
      $hit->location($1);
      }
    push(@{$self->{cache}}, $hit);
    $self->{'_num_hits'}++;
    $hits_found++;
    } # foreach SPAN_TAG

  # The next-page link uses JavaScript to fill-in and submit the form.
  # In order to do it mechanically, we need to keep track of what page
  # we're on and put that number in cp, along with sa=np

  # Find the next link, if any:
  my $oDiv = $oTree->look_down('_tag', 'div',
                               class => 'pagination',
                              );
  goto SKIP_NEXT_LINK if (! ref $oDiv);
  my @aoAnext = $oDiv->look_down(_tag => 'a');
  my $oAnext = pop @aoAnext;
  goto SKIP_NEXT_LINK if (! ref($oAnext));
  goto SKIP_NEXT_LINK if ($oAnext->as_text ne 'Next>');
  $self->{_options}->{sa} = 'np';
  $self->{_options}->{cp} = ++$self->{_washpost_cp};
  $self->{_next_url} = $self->{_options}{'search_url'} .'?'. $self->hash_to_cgi_string($self->{_options});
 SKIP_NEXT_LINK:
  return $hits_found;
  } # _parse_tree


sub _strip
  {
  my $s = shift;
  $s =~ s!\A$WS+!!x;
  $s =~ s!$WS+\Z!!x;
  return $s;
  } # _strip


sub _octalize
  {
  my $s = shift;
  return sprintf "\\%.3lo" x length($s), unpack("C*", $s);
  } # _octalize

1;

__END__