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
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
|
use Carp qw(carp croak);
use HTML::Form;
use WWW::Mechanize;
use HTML::TokeParser;
use HTTP::Request::Common;
use LWP::UserAgent;
$WWW::Search::Pagesjaunes::VERSION = '0.13';
sub ROOT_URL() { 'http://www.pagesjaunes.fr' }
sub new {
my $class = shift;
my $self = {};
my $ua = shift() || WWW::Mechanize->new(
env_proxy => 1,
keep_alive => 1,
timeout => 10,
agent => "Firefox",
);
$self->{ua} = $ua;
$self->{limit} = 1000;
$self->{fast} = 0;
$self->{error} = 1;
$self->{lang} = 'FR';
$self->{activite}='plombier';
$self->{departement}='idf';
#'recouvrements commerciaux et autres'
bless( $self, $class );
}
sub agent {
my $self = shift;
if ( $_[0] ) {
my $old = $self->{ua};
$self->{ua} = $_[0];
return $old;
}
else {
return $self->{ua};
}
}
sub find {
my $self = shift;
my %opt = @_;
my $p = $self->{activite} ? 'j' : 'b';
# Make the first request to pagesjaunes.fr
$self->{URL} = ROOT_URL . "/p$p.cgi";
if ( $self->{fast} ) {
$self->{req} = POST(
$self->{URL},
[
faire => 'decode_input_image',
DEFAULT_ACTION => $p . 'f_inscriptions_req',
lang => $self->{lang},
pays => 'FR',
srv => uc("p$p"),
TYPE_RECHERCHE => 'ZZZ',
input_image => '',
FRM_ACTIVITE => $p eq 'j' ? $self->{activite} : undef,
FRM_NOM => $opt{nom},
FRM_PRENOM => $p eq 'b' ? $opt{prenom} : undef,
FRM_ADRESSE => $opt{adresse},
FRM_LOCALITE => $opt{localite},
FRM_DEPARTEMENT => $opt{departement},
'${p}F_INSCRIPTIONS_REQ.x' => 100,
'${p}F_INSCRIPTIONS_REQ.y' => 1,
]);
}
else {
my $req = $self->{ua}->get($self->{URL});
if ( !$req->content || !$req->is_success ) {
croak('Error while retrieving the HTML page');
}
my @forms = HTML::Form->parse( $req->content, $self->{URL} );
# BooK finds the form by grepping thru all of them, instead
# of limiting ourselves to the first and second form.
my ($form) = grep { $_->find_input('lang') } @forms;
eval {
# HTML::Form complains when you change hidden fields values.
local $^W;
$form->value( 'lang', $self->{lang} );
$form->value( 'FRM_ACTIVITE', $self->{activite} ) if $self->{activite};
$form->value( 'FRM_NOM', $opt{nom} );
$form->value( 'FRM_PRENOM', $opt{prenom} ) if !$self->{activite};
$form->value( 'FRM_ADRESSE', $opt{adresse} );
$form->value( 'FRM_LOCALITE', $opt{localite} );
$form->value( 'FRM_DEPARTEMENT', $self->{departement} );
};
croak "Cannot fill the pagesjaunes request form. try with the 'fast' option\n" if $@;
$self->{limit} = $opt{limit} || $self->{limit};
$self->{req} = $form->click;
}
return $self;
}
sub results {
my $self = shift;
my $result_page = $self->{ua}->request( $self->{req} )->content;
my $parser = HTML::TokeParser->new( \$result_page );
# All the <br> tags are transformed to '§¤§', to separate
# multiple phone numbers
$parser->{textify} = {
'br' => sub() { '§¤§' }
};
my @results;
if ( $self->{limit} == 0 ) {
$self->{has_more} = 0;
return @results;
}
# XXX This is a really crude parsing of the data, but it seems to
# get the job done.
#
# <table class="fdcadreinscr">
# <tr>
# <td>
# <table class="fdinscr">
# <tr class="fdrsinscr">
# <td class="txtrsinscr">Name</td>
# <td class="txtrsinscr" align=right> </td>
# </tr>
# <tr valign="top">
# <td class="txtinscr">Address</td>
# <td align="right" class=txtinscr nowrap>(télécopie)? Phone</td>
# </tr>
# </table>
# </td>
# </tr>
# </table>
#
$self->{has_more} = 0;
while ( my $token = $parser->get_tag("table") ) {
next
unless $token->[1]
&& $token->[1]{class}
&& $token->[1]{class} eq 'fdinscr';
{ # We're inside an entry table
$parser->get_tag("td"); # The first <td> is the name
my $name = _trim( $parser->get_trimmed_text('/td') );
$parser->get_tag("td"); # The second <td> is ignored
$parser->get_tag("td"); # The third <td> is the address
my $address = _trim( $parser->get_trimmed_text('/td') );
$address =~ s/\W*\|.*$//g;
$parser->get_tag("td"); # The fourth <td> is the phone number
my $phone = _trim( $parser->get_trimmed_text('/td') );
my @phones = map { _trim($_); s/\.(\s*\d)/$1/; $_ } split(/§¤§/, $phone);
# The fifth <td> tag is either the mail or the descr, depending
# on the class
my @emails = ('');
my $tag = $parser->get_tag("td");
if ( $tag->[1]{class} && $tag->[1]{class} eq 'txtinscr'){
my $email = _trim( $parser->get_trimmed_text('/td') );
@emails = map { _trim($_); s/Mail\s*:\s*//; $_ } split(/§¤§/, $email);
}
push(
@results,
WWW::Search::Pagesjaunes::Entry->new(
$name, $address, [ @phones ], [ @emails ]#, $website
)
);
return @results if --$self->{limit} == 0;
}
}
# XXX - The form is sometimes commented??
$result_page =~ s/<!-- (<form id="form_jauge_none")/$1/;
# We select the form by its id attribute "form_jauge_none".
my @forms = grep {
$_->attr("id") && $_->attr("id") eq "form_jauge_none" }
HTML::Form->parse( $result_page, $self->{URL} );
# Print the $result for see the content
my $DATA= "./debug.txt";
open (DATA, ">$DATA")or die "Cannot open $DATA for write :$!";
print DATA $result_page;
close DATA;
unless (@forms) {
$self->{has_more} = 0;
return;
}
# Affectation of the form in the scalar $form_jauge_none.
my $form_jauge_none = shift @forms;
# Identification of the values.
$self->{last_rep} = $form_jauge_none->value("LAST_REP_PRINT_NONE");
$self->{first_rep} = $form_jauge_none->value("FIRST_REP_PRINT_NONE");
$self->{nb_rep} = $form_jauge_none->value("NB_REP_TOTAL_NONE");
if ( $self->{last_rep} <= $self->{nb_rep} ) {
$self->{first_rep} += 10;
$self->{last_rep} += 10;
{
local $^W;
$form_jauge_none->value( 'FIRST_REP_PRINT_NONE', $self->{first_rep} );
$form_jauge_none->value( 'LAST_REP_PRINT_NONE', $self->{last_rep} );
}
#warn "** there's more $$self{first_rep}..$$self{last_rep} of $$self{nb_rep}\n";
$self->{has_more} = 1;
$self->{req} = $form_jauge_none->click();
}
# If there was no result, we look for an error message in the HTML page
if ( !@results && $self->{error} ) {
$parser = HTML::TokeParser->new( \$result_page );
while ( my $token = $parser->get_tag("font") ) {
next
unless $token->[1]
&& $token->[1]{color}
&& $token->[1]{color} eq '#ff0000';
$parser->{textify} = {
'br' => sub() { " " }
};
carp _trim( $parser->get_trimmed_text('/font') ) . "\n";
}
}
wantarray ? @results : $results[0];
}
sub _trim {
$_[0] =~ s/\xa0/ /g; # Transform the into whitespace
$_[0] =~ s/^\s*|\s*$//g;
$_[0] =~ s/\s+/ /g;
$_[0];
}
sub limit {
my $self = shift;
$self->{limit} = $_[0] || $self->{limit};
}
sub has_more { $_[0]->{has_more} }
package WWW::Search::Pagesjaunes::Entry;
# The entry object is a blessed array with the following indices:
# 0 - Name
# 1 - Address
# 2 - Arrayref of phone numbers
# 3 - E-mail (pj)
# 4 - Notes (pj)
# 5 - Website (pj)
sub new {
my $class = shift;
bless [ @_ ], $class
}
sub name { $_[0]->[0] }
sub address { $_[0]->[1] }
sub phone { $_[0]->[2] }
sub email { $_[0]->[3] }
#sub website { $_[0]->[4] }
sub entry {
# Name Address First email Phones
$_[0]->[0], $_[0]->[1], $_[0]->[3]->[0], @{ @{ $_[0] }[2] }#, $_[0]->[4],
}
1;
__END__
=pod
=head1 NAME
WWW::Search::Pagesjaunes - Lookup phones numbers from www.pagesjaunes.fr
=head1 SYNOPSIS
use WWW::Search::Pagesjaunes;
my $pj = new WWW::Search::Pagesjaunes;
$pj->find( activite => "Plombier", localite => "Paris" );
do {
print $_->entry . "\n" foreach ($pj->results);
} while $pj->has_more;
=head1 DESCRIPTION
The WWW::Search::Pagesjaunes provides name, phone number and addresses of French
telephone subscribers by using the L<http://www.pagesjaunes.fr>
directory.
=head1 METHODS
Two classes are used in this module, a first one (WWW::Search::Pagesjaunes) to do the
fetching and parsing, and the second one and a second one
(WWW::Search::Pagesjaunes::Entry) holding the entry infos.
Here are the methods for the main WWW::Search::Pagesjaunes module:
=over 4
=item new()
The constructor accept an optional LWP::UserAgent as argument, if you want to
provide your own.
=item find( %request )
Here are the values for the %request hash that are understood. They
each have two name, the first is the french one and the second is the
english one:
=over 4
=item nom / name
Name of the person you're looking for.
=item activite / business
Business type of the company you're looking for. Note that if this
field is filled, the module searches in the yellow pages.
=item localite / town
Name of the town you're searching in.
=item prenom / firstname
First name of the person you're looking for. It is not set if you set the
'activite' field.
=item departement / district
Name or number of the Département or Région you're searching in.
=back
=item results()
Returns an array of WWW::Search::Pagesjaunes::Entry containing the first matches of the
query.
=item limit($max_number_of_entries)
Set the maximum number of entries returned. Default to 50.
=item has_more()
If the query leads to more than a few results, the field has_more is set. You
can then call the results() method again to fetch the datas.
=back
The WWW::Search::Pagesjaunes::Entry class has six methods:
=over 4
=item new($name, $address, $phone, $fax)
Returns a new WWW::Search::Pagesjaunes::Entry.
=item name
Returns the name of the entry.
=item address
Returns the address of the entry.
=item phone
Returns the phone number of the entry.
=item is_fax
Returns true if the phone number is a fax one, false otherwise. Note
that currently, this method always returns 0.
=item entry($separator)
Returns the concatenation of the name and the phone number, separated by
" - ". You can specify your own separator as first argument.
=back
=head1 BUGS
The phone numbers are sometimes not correctly parsed, esp. when one
entry has several phone numbers.
If you found a bug and want to report it or send a patch, you are
encouraged to use the CPAN Request Tracker interface:
L<https://rt.cpan.org/NoAuth/Dists.html?Queue=WWW-Search-Pagesjaunes>
=head1 COPYRIGHT
Please read the Publisher information of L<http://www.pagesjaunes.fr> available at the following URL:
L<http://www.pagesjaunes.fr/pj.cgi?html=commun/avertissement.html&lang=en>
WWW::Search::Pagesjaunes is Copyright (C) 2002, Briac Pilpré
This module is free software; you can redistribute it or modify it under the
same terms as Perl itself.
=head1 AUTHOR
Briac Pilpré <briac@cpan.org>
=cut |
