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
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
| #!/usr/bin/perl -w
eval 'exec /usr/bin/perl -w -S $0 ${1+"$@"}'
if 0; # not running under some shell
=head1 NAME
tv_grab_fr - Grab TV listings for France.
=head1 SYNOPSIS
To configure: tv_grab_fr --configure [--config-file FILE] [--gui OPTION]
To grab listings: tv_grab_fr [--output FILE] [--quiet]
Slower, detailed grab: tv_grab_fr --slow [--output FILE] [--days N] [--offset N] [--quiet]
Help: tv_grab_fr --help
=head1 DESCRIPTION
Output TV listings for several channels available in France (Hertzian,
Cable/satellite, Canal+ Sat, TPS). The data comes from
telepoche.guidetele.com. The default is to grab as many days as possible
from the current day onwards. By default the program description are
not downloaded, so if you want description and ratings, you should
active the --slow option.
B<--configure> Grab channels informations from the website and ask for
channel type and names.
B<--gui OPTION> Use this option to enable a graphical interface to be used.
OPTION may be 'Tk', or left blank for the best available choice.
Additional allowed values of OPTION are 'Term' for normal terminal output
(default) and 'TermNoProgressBar' to disable the use of Term::ProgressBar.
B<--output FILE> write to FILE rather than standard output.
B<--days N> grab N days starting from today, rather than as many as
possible. Due to the website organization, the speed is exactly the
same, whatever the number of days is until you activate the --slow
option. So this option is ignored if --slow is not also given.
B<--offset N> start grabbing N days from today, rather than starting
today. N may be negative. Due to the website organization, N cannot
be inferior to -1. As with --days, this is only useful for limiting
downloads in --slow mode.
B<--slow> Get additional information from the website, like program
description, reviews and credits.
B<--quiet> suppress the progress messages normally written to standard
error.
B<--help> print a help message and exit.
=head1 SEE ALSO
L<xmltv(5)>
=head1 AUTHOR
Sylvain Fabre, centraladmin@lahiette.com
with some patches from :
- Francois Gouget, fgouget@free.fr
- Niel Markwick, nielm@bigfoot.com
=cut
# Todo: perhaps we should internationalize messages and docs?
use XMLTV::Usage <<END
$0: get French television listings in XMLTV format
To configure: tv_grab_fr --configure [--config-file FILE]
To grab listings: tv_grab_fr [--output FILE] [--quiet]
Slower, detailed grab: tv_grab_fr --slow [--output FILE] [--days N] [--offset N] [--quiet]
END
;
use warnings;
use strict;
use XMLTV::Version '$Id: tv_grab_fr,v 1.20 2005/04/13 19:37:37 reudeudeu Exp $ ';
use Getopt::Long;
use HTML::TreeBuilder;
use HTML::Entities; # parse entities
use IO::File;
use URI;
use Date::Manip;
use XMLTV;
use XMLTV::Memoize;
use XMLTV::Ask;
use XMLTV::ProgressBar;
use XMLTV::Mode;
use XMLTV::Config_file;
use XMLTV::DST;
use XMLTV::Get_nice;
# Force the infamous delay value to 0
$XMLTV::Get_nice::Delay = 1;
#***************************************************************************
# Main declarations
#***************************************************************************
my $GRID_BASE_URL = 'http://telepoche.guidetele.com/gtv/grille?openagent&d=2&h=6&b=';
my $GRID_BY_CHANNEL = 'http://telepoche.guidetele.com/gtv/semaine?openagent&c=';
my $SHEET_URL = "http://telepoche.guidetele.com/fiche/emi_";
my $ROOT_URL = "http://telepoche.guidetele.com";
my $LANG = "fr";
my $MAX_STARS = 4;
my $MAX_RETRY = 5;
my $VERSION = "130405-01";
# Temporary avoid XML warnings (to be investigated)
no warnings;
# Grid id defined by the website according to channel types (needed to build the URL)
my %GridType = ( "HERTZIENNE" => "EMWD-66DGBM",
"TNT" => "EMWD-6B2HZ3",
"CABLE/SAT" => "EMWD-66DGCT",
"TPS" => "EMWD-66DJQG",
"CANAL SAT" => "EMWD-66DJEA",
"FREEBOX" => "EMWD-66DJXL",
"ETRANGERES" => "EMWD-66DJAL" );
# Slot of hours according to the website (needed to build the URL)
my @offsets = (2, 3, 4, 5, 6, 7);
#***************************************************************************
# Global variables allocation according to options
#***************************************************************************
XMLTV::Memoize::check_argv('get_page_aux');
my ($opt_days, $opt_help, $opt_output, $opt_offset, $opt_gui, $opt_quiet, $opt_list_channels, $opt_config_file, $opt_configure, $opt_slow, $opt_licons);
$opt_quiet = 0;
# The website is able to store up to nine days from now
my $default_opt_days = 9;
$opt_output = '-'; # standard output
GetOptions('days=i' => \$opt_days,
'help' => \$opt_help,
'output=s' => \$opt_output,
'offset=i' => \$opt_offset,
'quiet' => \$opt_quiet,
'configure' => \$opt_configure,
'config-file=s' => \$opt_config_file,
'gui:s' => \$opt_gui,
'list-channels' => \$opt_list_channels,
'slow' => \$opt_slow
)
or usage(0);
#***************************************************************************
# Options processing, warnings, checks and default parameters
#***************************************************************************
die 'Number of days must not be negative' if (defined $opt_days && $opt_days < 0);
die 'Cannot get more than one day before current day' if (defined $opt_offset && $opt_offset < -1);
usage(1) if $opt_help;
XMLTV::Ask::init($opt_gui);
if (not $opt_slow) {
# Certain options are ignored in fast mode.
my %slow_options = (days => $opt_days,
offset => $opt_offset,
);
foreach (sort keys %slow_options) {
if (defined $slow_options{$_}) {
say <<END
In normal, fast grabbing mode all days are fetched at once, so the
--$_ option does nothing. The option is useful only for reducing
the extra downloads caused by --slow mode.
END
;
}
}
$opt_days = $default_opt_days;
$opt_offset = 0;
}
else {
# The options can be used, but we default them if not set.
$opt_offset = 0 if not defined $opt_offset;
$opt_days = $default_opt_days if not defined $opt_days;
}
if ( (($opt_offset + $opt_days) > $default_opt_days) or ($opt_offset > $default_opt_days) ) {
$opt_days = $default_opt_days - $opt_offset;
if ($opt_days < 0) {
$opt_offset = 0;
$opt_days = $default_opt_days;
}
say <<END
The website does not handle more than $default_opt_days days.
So the grabber is now configure with --offset $opt_offset --days $opt_days
END
;
}
#***************************************************************************
# Last init before doing real work
#***************************************************************************
my %results;
my $lastdaysoffset = $opt_offset + $opt_days - 1;
# Now detects if we are in configure mode
my $mode = XMLTV::Mode::mode('grab', # default
$opt_configure => 'configure',
$opt_list_channels => 'list-channels');
# File that stores which channels to download.
my $config_file = XMLTV::Config_file::filename($opt_config_file, 'tv_grab_fr', $opt_quiet);
#***************************************************************************
# Sub sections
#***************************************************************************
sub get_channels( $ );
sub process_channel_grid_page( $$$$ );
sub debug_print( $ );
# Set this to 1 of you debug strings
my $DEBUG_FR = 0;
# Internal debug functions
sub debug_print( $ ) {
my $str = shift;
if ($DEBUG_FR) { print $str; }
}
# Get a page using this agent.
sub get_page( $ ) {
my $url = shift;
# For Memoize s sake make extra sure of scalar context
#return scalar get_page_aux($url);
#return get_nice($url);
return scalar get_page_aux($url);
}
# Curious function to deal with the Get_nice API which does not offer an internal retry mode.
# Awful, but it seems to work.
# It works well, and it is mandatory with the telepoche website... Sorry for the ugly code...
sub get_page_aux {
my $url = shift;
my $retry = $MAX_RETRY;
my $got;
my $sleep = 0;
GET:
# Sleep 1 second after 1 pass
sleep $sleep;
$sleep = 1;
# Call the get_nice API
eval { $got = get_nice($url) };
# Then check the return string of the get_nice function
goto GET if $@ and $@ =~ /could not fetch/ and --$retry;
die "Can\'t download $url !!! Check you internet connection." if $retry == 0;
return $got;
}
sub xmlencoding {
# encode for xml
$_[0] =~ s/</</g;
$_[0] =~ s/>/>/g;
$_[0] =~ s/&/\%26/g;
return $_[0];
}
my $warned_bad_chars;
my $warned_unicode_chars;
sub tidy {
# clean bad characters from HTML
for (my $s = shift) {
tr/\205//d;
tr/\222/''/;
s/\234/oe/g;
s/−/ /g;
# Remove nasty caracters, thanks to nielm
s/“|”|&\#8219;|&\#8220;|&\#x201[89];/"/g;
s/‘|’|&\#8217;|&\#8218;|&\#x201[cdCD];/\'/g;
s/&\#8230;|&\#x202[4-7];/.../g;
s/&\#821[0123];|&\#x201[2-5];/-/g;
s/Œ/OE/g;
s/œ/oe/g;
s/œ/oe/g;
if ( s/(&\#[0-9]{4,};)//g ) {
print STDERR "removing unknown UNICODE characters: '$1'\n" unless $warned_unicode_chars++;
}
if ( s/(&\#x[0-9a-zA-Z]{3,};)//g ) {
print STDERR "removing unknown UNICODE characters: '$1'\n" unless $warned_unicode_chars++;
}
# Not strictly a bad character but it does get in the way.
s/ / /g;
tr/\240/ /;
tr/\t/ /;
if (s/([^\012\015\040-\176\240-\377])//g) {
print STDERR "removing bad characters: '$1'" unless $warned_bad_chars++;
}
return $_;
}
}
#***************************************************************************
# Configure mode
#***************************************************************************
if ($mode eq 'configure') {
XMLTV::Config_file::check_no_overwrite($config_file);
open(CONF, ">$config_file") or die "Cannot write to $config_file: $!";
# Get a list of available channels, according to the grid type
my @gts = sort keys %GridType;
my @gtnames = map { $GridType{$_} } @gts;
my @gtqs = map { "Get channels type : $_?" } @gts;
my @gtwant = ask_many_boolean(1, @gtqs);
my $bar = new XMLTV::ProgressBar('getting channel lists',
scalar grep { $_ } @gtwant)
if not $opt_quiet;
my %channels_for;
foreach my $i (0 .. $#gts) {
my ($gt, $gtw, $gtname) = ($gts[$i], $gtwant[$i], $gtnames[$i]);
next if not $gtw;
my %channels = get_channels( $gtname );
die 'No channels could be found' if not %channels;
$channels_for{$gt} = \%channels;
update $bar if not $opt_quiet;
}
$bar->finish() if not $opt_quiet;
my %asked;
foreach (@gts) {
my $gtw = shift @gtwant;
my $gtname = shift @gtnames;
if ($gtw) {
my %channels = %{$channels_for{$_}};
say "Channels for $_";
# Ask about each channel (unless already asked).
my @chs = grep { not $asked{$_}++ } sort keys %channels;
my @names = map { $channels{$_}{name} } @chs;
my @qs = map { "add channel $_?" } @names;
my @want = ask_many_boolean(1, @qs);
foreach (@chs) {
my $w = shift @want;
warn("cannot read input, stopping channel questions"), last if not defined $w;
# Print a config line, but comment it out if channel not wanted.
print CONF '#' if not $w;
print CONF "channel $_ $channels{$_}{name};$channels{$_}{icon}\n";
}
}
}
close CONF or warn "cannot close $config_file: $!";
say("Finished configuration.");
exit();
}
#***************************************************************************
# Check mode checking and get configuration file
#***************************************************************************
die if $mode ne 'grab' and $mode ne 'list-channels';
my @config_lines;
if ($mode eq 'grab') {
@config_lines = XMLTV::Config_file::read_lines($config_file);
}
#***************************************************************************
# Prepare the XMLTV writer object
#***************************************************************************
my %w_args;
if (defined $opt_output) {
my $fh = new IO::File(">$opt_output");
die "cannot write to $opt_output: $!" if not defined $fh;
$w_args{OUTPUT} = $fh;
}
$w_args{encoding} = 'ISO-8859-1';
my $writer = new XMLTV::Writer(%w_args);
$writer->start
({ 'source-info-url' => 'http://telepoche.guidetele.com/',
'source-data-url' => 'http://telepoche.guidetele.com/',
'generator-info-name' => 'XMLTV',
'generator-info-url' => 'http://membled.com/work/apps/xmltv/',
});
#***************************************************************************
# List channels only case
#***************************************************************************
if ($opt_list_channels) {
# Get a list of available channels, according to the grid type
my @gts = sort keys %GridType;
my @gtnames = map { $GridType{$_} } @gts;
my @gtqs = map { "List channels for grid : $_?" } @gts;
my @gtwant = ask_many_boolean(1, @gtqs);
foreach (@gts) {
my $gtw = shift @gtwant;
my $gtname = shift @gtnames;
if ($gtw) {
say "Now getting grid : $_ \n";
my %channels = get_channels( $gtname );
die 'no channels could be found' if (scalar(keys(%channels)) == 0);
foreach my $ch_did (sort(keys %channels)) {
my $ch_xid = "C".$ch_did."telepoche.com";
$writer->write_channel({ id => $ch_xid,
'display-name' => [ [ $channels{$ch_did}{name} ] ],
'icon' => [{src=>$ROOT_URL.$channels{$ch_did}{icon}}] });
}
}
}
$writer->end();
exit();
}
#***************************************************************************
# Now the real grabbing work
#***************************************************************************
die if $mode ne 'grab';
#***************************************************************************
# Build the working list of channel name/channel id
#***************************************************************************
my (%channels, $chicon, $chid, $chname);
my $line_num = 1;
foreach (@config_lines) {
++ $line_num;
next if not defined;
# Here we store the Channel name with the ID in the config file, as the XMLTV id = Website ID
if (/^channel:?\s+(\S+)\s+([^\#]+);([^\#]+)/) {
$chid = $1;
$chname = $2;
$chicon = $3;
$chname =~ s/\s*$//;
$channels{$chid} = {'name'=>$chname, 'icon'=>$chicon};
} else {
warn "$config_file:$line_num: bad line $_\n";
}
}
#***************************************************************************
# Now process the days by getting the main grids.
#***************************************************************************
my @to_get;
warn "No working channels configured, so no listings\n" if not %channels;
my $script_duration = time();
# The website stores channel information by hour area for a whole week !
foreach $chid (sort keys %channels) {
$writer->write_channel({ id => "C".$chid.".telepoche.com", 'display-name' => [[$channels{$chid}{name}]], 'icon' => [{src=>$ROOT_URL.$channels{$chid}{icon}}]});
foreach (@offsets) {
my $url = $GRID_BY_CHANNEL . "$chid&h=$_";
push @to_get, [ $url, $chid, $_ ];
}
}
my $bar = new XMLTV::ProgressBar('getting listings', scalar @to_get) if not $opt_quiet;
Date_Init("TZ=UTC");
foreach (@to_get) {
my ($url, $chid, $slot) = @$_;
#my $th = threads->new(\&process_channel_grid_page, $writer, $chid, $url, $slot);
#$th->join();
process_channel_grid_page($writer, $chid, $url, $slot);
update $bar if not $opt_quiet;
}
$writer->end();
$bar->finish() if not $opt_quiet;
# Print the duration
$script_duration = time() - $script_duration;
print STDERR "Grabber process finished in " . $script_duration . " seconds.\n" if not $opt_quiet;
#***************************************************************************
# Specific functions for grabbing information
#***************************************************************************
sub get_channels( $ ) {
my $gridid = shift;
my %channels;
my $url = $GRID_BASE_URL.$gridid;
my $t = HTML::TreeBuilder->new;
$t->parse(tidy(get_page($url)));
$t->eof;
debug_print( "URL : " . $url ."\n");
foreach my $cellTree ( $t->look_down( "_tag", "td", "width", "50", "height", "62" ) ) {
my $chid = $cellTree->look_down( "_tag", "a", 'href', '#' )->attr('onclick');
if ( $chid =~ /goChaine\('(.*)','(.*)',''\);/ ) {
$chid = $1;
my $imgCell = $cellTree->look_down( "_tag", "img" );
my $chname = $imgCell->attr('src');
$chname =~ s/\/c_img\/chaine\///;
$chname =~ s/\.gif//;
debug_print "Found channel : $chid - " . $chname . "\n";
$channels{$chid} = {'name' => $chname, 'icon' => $imgCell->attr('src') };
}
}
$t->delete(); undef $t;
return %channels;
}
sub process_channel_grid_page( $$$$ ) {
my ($writer, $chid, $url, $slot) = @_;
my ($genre, $showview, $hours, $starthour, $endhour, $date, $dateindex) = 0;
my ($title, $subgenre, $footext, $star_rating, $datecreate) = 0;
# Get the current page
my $t = HTML::TreeBuilder->new;
debug_print("Now getting page : " . $url . "\n");
$t->parse(tidy(get_page($url)));
$t->eof;
# Reset some working variables
my $cont = 0;
my $nbloop = 0;
# The process the page ...
# Each day is encapsulated in a table with the following parameters :
foreach my $tableTree ($t->look_down('_tag', 'table', 'width', '532', 'bgcolor', '#ffffff') ) {
# The new website display 2 times this table before real content table, so skip to tables occurence...
$cont += 1;
next if ($cont < 3);
# Get the list of rows of the table
my @dateRowTab = $tableTree->content_list();
# Now loop thru rows
foreach my $dateRow (@dateRowTab) {
# First row is the date
my $dateTree = $dateRow->look_down('_tag', 'td', 'width', '50');
my ($day, $month) = split (/\//,$dateTree->as_text); #PROBLEME ICI
$date = ParseDate("$month/$day/".UnixDate(DateCalc("today","+$nbloop days"),"%Y"));
$dateindex = UnixDate($date, "%Y%m%d");
# We need to limit the number of days fetched in slow
# mode, but in fast mode no limit is needed since
# there is a single fetch for all days.
if ($opt_slow) {
next if Date_Cmp($dateindex, UnixDate(DateCalc("today", "+$opt_offset days"),"%Y%m%d")) < 0;
next if Date_Cmp($dateindex, UnixDate(DateCalc("today", "+$lastdaysoffset days"),"%Y%m%d")) > 0;
}
$nbloop += 1;
# Then the program information
my $tabDay = $dateRow->look_down('_tag', 'td', 'width', '480', 'height', '62' );
foreach my $progTree ($tabDay->look_down('_tag', 'a', 'onMouseout', 'hidemenu()') ) {
my $text = $progTree->as_text();
my $line = $progTree->attr('onMouseover');
$line =~ (!m/drc\(([^""]+)\)/);
$line =~ m/\'(.*)\',\'(.*)\'/;
$title = $2;
my $mydata = $1;
next if ( $title eq 'Fin des programmes');
($hours, $genre, $showview) = split (/<br>/, $mydata);
next if ( !$hours );
# Process the title, sometimes a showview field is shown
$title =~ s/^\d{7,8} //;
$title =~ s/\\//g;
if ($title =~ s/\s*([*]+)\s*$//) {
my $n = length $1;
if (0 < $n and $n <= $MAX_STARS) {
$star_rating = $n;
} elsif ($MAX_STARS < $n) {
warn "too many stars ($n), expected at most $MAX_STARS\n";
} else { die }
}
die if $title =~ /[*]$/;
my ($language, $subtitles_language);
for ($title) {
s/\s+$//;
if (s/\s+\(VO\)$//) {
# Version originale - language is unknown but not
# French. There is no way to represent this in
# the DTD.
#
}
elsif (s/\s+\(VO sous-titr.e\)$//) {
# Language unknown, but we know it has French
# subtitles.
#
$subtitles_language = 'fr';
}
elsif (s/\s+\(VF\)$//) {
# Version francaise. The title may or may not be
# translated.
#
$language = 'fr';
}
}
# At this point, $title contains title and subtitle (if any),
# separated by a '-'. We will try to split off the subtitle
# further down
# Process hours, there are like HHhMM
($starthour, $endhour) = split("-", $hours);
$starthour =~ s/h//g
or die "Cannot detect start hour from website : $starthour \n";
$endhour =~ s/h//g
or die "Cannot detect end hour from website : $endhour \n";
# Process the start/stop dates
my $start = $dateindex.$starthour."00";
my $stop = $dateindex.$endhour."00";
# Dummy site : the slot 0-4 of day n is in fact the slot 0-4 for day n+1
if ( $slot == 7 ) {
my $myslot = substr($starthour, 0, 2);
die if not $start;
$start = &UnixDate(&DateCalc($start, "+1 day"), "%Y%m%d%H%M%S")
if ($myslot >= 0 && $myslot < 4);
die 'could not add one day to start time' if not $start;
$stop = &UnixDate(&DateCalc($stop, "+1 day"), "%Y%m%d%H%M%S");
die 'could not add one day to stop time' if not $stop;
}
# Last check to see if start > stop
if ( Date_Cmp($start, $stop) > 0 ) {
$stop = &UnixDate(&DateCalc($stop, "+1 day"), "%Y%m%d%H%M%S");
die 'could not add one day to stop time' if not $stop;
}
# Now set the proper timezone (WT/ST) according to current date
die if not $start; die if not $stop;
$start = utc_offset( $start, "+0100");
$stop = utc_offset( $stop , "+0100");
# Now use the utf8 conversion (???)
utf8::encode($title) if (utf8::is_utf8($title) );
my %prog = (channel => "C".$chid.".telepoche.com",
title => [ [ $title ] ], # lang unknown
start => $start,
stop => $stop
);
debug_print("Found title : $title - $start - $stop \n");
$prog{'star-rating'} = [ "$star_rating/$MAX_STARS" ]
if defined $star_rating;
for ($language) { $prog{language} = [ $_ ] if defined }
for ($subtitles_language) {
$prog{subtitles} = [ { type => 'onscreen',
language => [ $_ ] } ]
if defined;
}
# Sometimes the genre is not set, so replace it by the showview field
if (defined $genre and $genre =~ m/Showview : /) {
$showview = $genre;
undef $genre;
}
# Process the genre, subgenre and date if defined
if (defined $genre ) {
($genre, $datecreate) = split("-", $genre);
($genre, $subgenre) = split(",", $genre);
for ($genre) { s/^\s+//; s/\s+$// }
if (defined $subgenre) {
for ($subgenre) { s/^\s+//; s/\s+$// }
# utf8 conversion...
utf8::encode($genre) if (utf8::is_utf8($genre));
utf8::encode($subgenre) if (utf8::is_utf8($subgenre));
$prog{category} = [ [ xmlencoding($genre), $LANG ], [ xmlencoding($subgenre), $LANG ] ];
} else {
$prog{category} = [ [ xmlencoding($genre), $LANG ] ];
}
if (defined $datecreate) {
for ($datecreate) { s/^\s+//; s/\s+$// }
$prog{date} = $datecreate ;
}
}
# Process the showview field
if ( defined $showview ) {
$showview =~ s/Showview : //;
for ($showview) { s/^\s+//; s/\s+$// }
$prog{showview} = $showview;
}
# Variables needed for the detailed information parsing
my ($idesc, $tdesc, $imgdesc);
# Now get program description if the longlisting option is set
if ( $opt_slow && $progTree->attr('class') eq 'fiche' ) {
my $id = $progTree->attr('onclick');
my @desc;
$id =~ /fiche\('(\d+)'\)/
or die "expected fiche(x), got: $id";
$id = $1;
debug_print("Calling sheet URL : " . $SHEET_URL . $id . "\n");
my $tfic = HTML::TreeBuilder->new;
$tfic->parse(tidy(get_page($SHEET_URL . $id)));
$tfic->eof;
# This page's title tag contains the program title without
# the sub-title. Use it to separate the two.
my $ttitle;
if ( $ttitle = $tfic->look_down('_tag', 'title') ) {
my $htmltitle=$ttitle->as_text();
if ($title =~ s/^\Q$htmltitle\E\s+-\s+//) {
$prog{'title'} = [ [ $htmltitle ] ];
$prog{'sub-title'} = [ [ $title ] ];
}
}
# Get the duration and the year
my ($length, $hour, $min, $year);
if ( $tdesc = $tfic->look_down('_tag', 'td', 'width', '250', 'class', 'txt') ) {
$length = $tdesc->as_text();
if ( $length =~ s/ Durée : (\d+)h(\d+) AM - (\d+)// ) {
$hour = $1; $min = $2; $year = $3;
# guidetele.com si full of bugs ...
$hour = $hour - 12 if ($hour >= 12);
$prog{'length'} = ($hour * 3600) + ($min * 60);
$prog{'date'} = $year;
}
}
# Now get descriptions, summary, advices, actors and director
my ($resume, $histoire, $avis);
my ($nextIsResume,$nextIsHistory,$nextIsAvis,$nextIsDirector) = (0,0,0,0);
my (@director, @actor);
if ( $tdesc = $tfic->look_down('_tag', 'td', 'width', '396') ) {
# Detect actors
foreach my $actorcell ($tdesc->look_down('_tag', 'td', 'class', 'disActeur') ) {
push @actor, tidy($actorcell->as_text());
}
my @children = $tdesc->content_list();
foreach my $desc (@children) {
# Remove leading and trailing spaces
$desc =~ s/^ ://;
$desc =~ s/ $//;
if ($nextIsDirector == 1 ) {
push @director, tidy($desc);
$nextIsDirector = 0;
debug_print "FOUND DIRECTOR : " . tidy($desc) . " - $title - $id\n";
}
if ($nextIsResume == 1) {
warn "RESUME seen twice\n" if defined $resume;
$resume = tidy($desc);
$nextIsResume = 0;
debug_print "FOUND RESUME : $resume \n";
}
if ($nextIsHistory == 1 ) {
warn "HISTOIRE seen twice\n" if defined $histoire;
$histoire = tidy($desc);
$nextIsHistory = 0;
debug_print "FOUND HISTOIRE : $histoire \n";
}
if ($nextIsAvis == 1 ) {
warn "AVIS seen twice\n" if defined $avis;
$avis = tidy($desc);
$nextIsAvis = 0;
debug_print "FOUND AVIS : $avis \n";
}
if ( ref($desc) ) {
$nextIsResume = 1 if ( $desc->as_text() eq "RESUME" );
$nextIsHistory = 1 if ( $desc->as_text() eq "HISTOIRE" );
$nextIsAvis = 1 if ( $desc->as_text() eq "AVIS" );
$nextIsDirector = 1 if ($desc->as_text eq "Réalisateur" );
}
}
}
# RESUME is main definition, HISTOIRE shorter.
foreach ($resume, $histoire) {
push @{$prog{desc}}, [ $_, $LANG ] if defined and length;
}
# Add AVIS to the main description, or make a new desc
# for it if there are none.
if (defined $avis and length($avis) ) {
if ($prog{desc}) {
$prog{desc}->[0]->[0] .= "Critique : " . $avis;
} else {
push @{$prog{desc}}, [ $avis, $LANG ];
}
}
if ($idesc = $tfic->look_down('_tag', 'table', 'width', '190', 'height', '100%') ) {
if ($tdesc = $idesc->look_down('_tag', 'td', 'valign', 'top', 'align', 'center' ) ) {
if ($imgdesc = $tdesc->look_down('_tag', 'img') ) {
$prog{icon} = [ {'src' => $ROOT_URL.$imgdesc->attr('src') } ];
}
}
}
# Now push the credits section, if exists
$prog{credits}{director } = \@director if @director;
$prog{credits}{actor} = \@actor if @actor;
} else {
# The text for the <a> tag contains the title without the
# sub-title so we can use that to separate the two. However
# the text for the <a> tag may have been truncated so it
# fits the slot on the page. Also some titles may contain
# a ' - '. Still the heuristic works very well.
my $subtitle;
if ($text =~ s/\.\.\.$//) {
if ($title =~ s/^\Q$text\E([^-]+)\s+-\s+//) {
$prog{'title'} = [ [ "$text$1" ] ];
$prog{'sub-title'} = [ [ $title ] ];
}
}
elsif ($title =~ s/^\Q$text\E\s+-\s+//) {
$prog{'title'} = [ [ $text ] ];
$prog{'sub-title'} = [ [ $title ] ];
}
}
if ( !$results{$prog{start}.$chid} ) {
$results{$prog{start}.$chid} = "1";
$writer->write_programme(\%prog);
}
}
}
}
$t->delete(); undef $t;
} |
probleme avec script perl grab_tv_fr.pl
Répondre avec citation
Partager