This file is indexed.

/usr/bin/tv_grab_uk_tvguide is in xmltv-util 0.5.67-0.1.

This file is owned by root:root, with mode 0o755.

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
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
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
#!/usr/bin/perl -w

eval 'exec /usr/bin/perl -w -S $0 ${1+"$@"}'
    if 0; # not running under some shell
#
# Copyright G. Westcott - February 2013
#
# This code is distributed under the GNU General Public License v2 (GPLv2) .
#
#   For extended help information run
#         tv_grab_uk_tvguide  --info
# 

my $_version 	= '$Id: tv_grab_uk_tvguide,v 1.16 2015/06/29 16:38:09 knowledgejunkie Exp $';


eval 'exec /usr/bin/perl -w -S $0 ${1+"$@"}'
    if 0; # not running under some shell

use Data::Dumper;

use strict;
use warnings;
use XMLTV::ProgressBar;
use XMLTV::Options qw/ParseOptions/;
use XMLTV::Configure::Writer;
use XMLTV::Supplement 0.005065 qw/SetSupplementRoot GetSupplementDir GetSupplementLines/;
use XMLTV::Get_nice qw/get_nice_tree/;

use File::Path;
use POSIX qw(strftime);
use DateTime;
use Date::Parse;
#v1.3: use DateTime::Format::DateParse;
use Encode;
use URI::Escape;

use HTTP::Cache::Transparent;


#require HTTP::Cookies;
#my $cookies = HTTP::Cookies->new;
#$XMLTV::Get_nice::ua->cookie_jar($cookies);


# Although we use HTTP::Cache::Transparent, this undocumented --cache
# option for debugging is still useful since it will _always_ use a
# cached copy of a page, without contacting the server at all.
#
use XMLTV::Memoize; XMLTV::Memoize::check_argv('XMLTV::Get_nice::get_nice_aux');

use subs qw(debug warning);
my $warnings = 0;

# ------------------------------------------------------------------------------------------------------------------------------------- #
# Grabber details
my $VERSION 								= $_version;
my $GRABBER_NAME 						= 'tv_grab_uk_tvguide';
my $GRABBER_DESC 						= 'UK - TV Guide (tvguide.co.uk)';
my $GRABBER_URL 						= 'http://wiki.xmltv.org/index.php/XMLTVProject';
my $ROOT_URL                = 'http://my.tvguide.co.uk/';
my $SOURCE_NAME							= 'TV Guide UK';
my $SOURCE_URL							= 'http://my.tvguide.co.uk/';
#
my $generator_info_name 		= $GRABBER_NAME;
my $generator_info_url 			= $GRABBER_URL;
my $source_info_name				= $SOURCE_NAME;
my $source_info_url					= $SOURCE_URL;



# ------------------------------------------------------------------------------------------------------------------------------------- #
# Use XMLTV::Options::ParseOptions to parse the options and take care of the basic capabilities that a tv_grabber should
my ($opt, $conf) = ParseOptions({ 
			grabber_name 			=> $GRABBER_NAME,
			capabilities 			=> [qw/baseline manualconfig apiconfig cache/],
			stage_sub 				=> \&config_stage,
			listchannels_sub 	=> \&fetch_channels,
			version 					=> $VERSION,
			description 			=> $GRABBER_DESC,
			extra_options			=> [qw/nodetailspage/],
});

#print Dumper($conf); exit;

# any overrides?
if (defined( $conf->{'generator-info-name'} )) { $generator_info_name = $conf->{'generator-info-name'}->[0]; }
if (defined( $conf->{'generator-info-url'} ))  { $generator_info_url  = $conf->{'generator-info-url'}->[0]; }
if (defined( $conf->{'source-info-name'} )) 	 { $source_info_name 		= $conf->{'source-info-name'}->[0]; }
if (defined( $conf->{'source-info-url'} ))  	 { $source_info_url 		= $conf->{'source-info-url'}->[0]; }



# ------------------------------------------------------------------------------------------------------------------------------------- #
# Initialise the web page cache
init_cachedir( $conf->{cachedir}->[0] );
HTTP::Cache::Transparent::init( { 
    BasePath => $conf->{cachedir}->[0],
    NoUpdate => 60*60,			# cache time in seconds
		MaxAge => 24,						# flush time in hours
    Verbose => $opt->{debug},
} );


# ------------------------------------------------------------------------------------------------------------------------------------- #
# Check we have all our required conf params
config_check();

# Load the conf file containing mapped channels and categories information
my %mapchannelhash;
my %mapcategoryhash;
loadmapconf();
#print Dumper(\%mapchannelhash, \%mapcategoryhash); exit;



# ------------------------------------------------------------------------------------------------------------------------------------- #
# Progress Bar :)
my $bar = new XMLTV::ProgressBar({
  name => "Fetching listings",
  count => (scalar @{$conf->{channel}}) * ($opt->{days} + 1)		# +1 added for the extra day necessary for <06:00 programmes
}) unless ($opt->{quiet} || $opt->{debug});



# ------------------------------------------------------------------------------------------------------------------------------------- #
# Data store before being written as XML
my $programmes = ();
my $channels = ();

# Get the schedule(s) from TV Guide
fetch_listings();

# print Dumper($programmes);

# Progress Bar
$bar->finish() && undef $bar if defined $bar;



# ------------------------------------------------------------------------------------------------------------------------------------- #
# Filter out programmes outside of requested period (see man page)
my %w_args;
if (($opt->{offset} != 0) || ($opt->{days} != -999)) {
  $w_args{offset} = $opt->{offset};
  $w_args{days} = ($opt->{days} == -999) ? 100 : $opt->{days};
  $w_args{cutoff} = '000000';			# e.g. '060000'
}



# ------------------------------------------------------------------------------------------------------------------------------------- #
# Generate the XML
my $encoding = 'UTF-8';
my $credits = { 'generator-info-name' => $generator_info_name,
								'generator-info-url' 	=> $generator_info_url,
								'source-info-name' 		=> $source_info_name,
								'source-info-url' 		=> $source_info_url };
	
XMLTV::write_data([ $encoding, $credits, $channels, $programmes ], %w_args);
# Finished!



# ------------------------------------------------------------------------------------------------------------------------------------- #
# Signal that something went wrong if there were warnings.
exit(1) if $warnings;

# All data fetched ok.
debug "Exiting without warnings.";
exit(0);


# #############################################################################
# # THE MEAT #####################################################################
# ------------------------------------------------------------------------------------------------------------------------------------- #

sub fetch_listings {
		# Fetch listings per channel
		
		foreach my $channel_id (@{$conf->{channel}}) {
			# Officially:
			# http://www.tvguide.co.uk/channellisting.asp?cTime=3%2F19%2F2013+06%3A00%3A00+&ch=857&go=go
			# But this works too:
			# http://www.tvguide.co.uk/channellisting.asp?ch=86&cTime=3/18/2013
			
			my $baseurl = $ROOT_URL.'channellisting.asp';
			
			# Now grab listings for each channel on each day, according to the options in $opt
			#
			# tvguide runs from 06:00 so we need to get the previous day as well just for any programmes after midnight
			#
			for (my $i=($opt->{offset} -1); $i < ($opt->{offset} + $opt->{days}); $i++) {
				my $theday = DateTime->today->add (days => $i)->set_time_zone('Europe/London');
			
				# Construct the listings url
				my $url = $baseurl . '?ch=' . $channel_id . '&cTime=' . uri_escape( $theday->strftime('%m/%d/%Y 00:00:00') );
				#debug "Fetching: $url";

				# If we need to map the fetched channel_id to a different value
				my $xmlchannel_id = $channel_id;
				if (defined(&map_channel_id)) { $xmlchannel_id = map_channel_id($channel_id); }
				
				# Fetch the page
				my $tree = XMLTV::Get_nice::get_nice_tree($url);
				# $tree->dump; exit;

				# Scrub the page
				if ($tree) {
					my $channelname = $tree->look_down('_tag' => 'option', 'value' => $channel_id);
					$channelname = $channelname->as_text;
					
					# 	<table border="0" cellpadding="0" style="background:black;border-collapse: collapse;background-image: url(http://i.g8.tv/HighlightImages/Large/);background-repeat: no-repeat;" width="677">

					my @shows = $tree->look_down('_tag' => 'table', 'border' => '0', 'cellpadding' => '0', 'style' => qr/background:\s*black;border-collapse:\s*collapse;/);
					
					if (@shows) {
						foreach my $show (@shows) {
							#		$show->dump;
							
							# are we processing yesterday's schedule? (see above)
							if ($i == ($opt->{offset} -1)) {
								my $showstart = $show->look_down('_tag' => 'span', 'class' => 'tvchannel');
								my ($h, $i, $a) = $showstart->as_text =~ /(\d*):(\d*)\s*(am|pm)/;
								# 2014-04-02  see note below
								if (!defined $a) {
									$showstart = $show->look_down('_tag' => 'span', 'class' => 'season');
									($h, $i, $a) = $showstart->as_text =~ /(\d*):(\d*)\s*(am|pm)/;
								}
								if ($a eq 'am' && ($h < 6 || $h == 12)) {
									# continue processing of pre-6am programme
								} else {
									next;
								}
								$showstart = $h = $i = $a = undef;
							}
							
							my %prog = ();
								
							my $showtime;
							
							# see if we have a details page
							#		<a href="javascript:popup(151361219);" ...
							#		http://www.tvguide.co.uk/detail.asp?id=151451760
							# 2013-12-14 site changed
							#    <a href="javascript:popupshow('http://www.tvguide.co.uk/detail/1889599/94819598/saturday-kitchen-live');" target="_blank" ...
							# 2014-04-02 site changed
							#    <a href="http://www.tvguide.co.uk/detail/138990373/88745969/breakfast" target="_blank"...
							# 2014-11-26 site changed
							#    <a href="http://watch.tvguide.co.uk/engage/2057116/103685857-fake_britain" target="_blank"...
							# 2014-12-03 site changed
							#  my $webdetails = $show->look_down('_tag' => 'a', 'href' => qr/javascript:popup/);
							# 2014-12-03 The new website seems a bit flakey with these details pages, often returning a 500 Server Error
							#    Here's an option to disable the details pages  (  --nodetailspage )
							# 2014-12-24 site changed
							#  my $webdetails = $show->look_down('_tag' => 'a', 'href' => qr/\/engage\//);
							#
						if (!$opt->{nodetailspage}) {
							
							my $webdetails = $show->look_down('_tag' => 'a', 'href' => qr/\/detail\//);
							my $href = $webdetails->attr('href');
							#    my ($id) = $href =~ /javascript:popup\((\d*)\);/;
							#    $url = $ROOT_URL . 'detail.asp?id=' . $id;
							#    my ($url) = $href =~ /javascript:popupshow\('(.*)'\);/;
							my ($url) = $href;
							#debug "Fetching: $url";

							# Fetch the page
							my $treedetail = XMLTV::Get_nice::get_nice_tree($url);
							
							my $showdetail = $treedetail->look_down('_tag' => 'div', 'id' => 'content-engage');						
							#	$showdetail->dump;
							
							if ($showdetail) {
								# Details page contains Director names and a better list of Actors
								
								if ( my ($cast) = $showdetail->look_down('_tag' => 'div', 'class' => qr/castoverlay/) ) {
								
									# Get the cast and extract them into a new tree
									my @lis = $cast->look_down('_tag' => 'li');		
								
									LOOP:
									foreach my $person (@lis) {
										#    <div>Don Sharp </div><div class="partname">Director</div>
										#    <div>Antonio Banderas</div>  <div class='partname' >Ahmed Ibn Fahdlan</div>
										#
										my ($name, $role);
										if ( my ($_name) = $person->look_down('_tag' => 'div') ) {
											$name = $_name->as_text;
										}
										if ( my ($_role) = $person->look_down('_tag' => 'div', 'class' => 'partname') ) {
											$role = $_role->as_text;
										}
										#	drop the "Executive Director" & "Executive Producer"   - any others we should drop?
										next LOOP  if ( $role =~ /^(Executive Director|Executive Producer)/ );

										# map the website role to an xmltv role
										my %xmltvroles = ( 'Director'=>'director', 'Producer'=>'producer', 'Series Producer'=>'producer', 'Writer'=>'writer', 'Co-Director'=>'director', 'Presenter'=>'presenter', 'Commentator'=>'commentator', 'Guest'=>'guest' );
										
										my $credit;
										if (exists $xmltvroles{$role}) {
											$credit = $xmltvroles{$role};
								} else {
											$credit = 'actor';
								}
								
										if ($credit eq 'actor' && defined $role) {
											push @{$prog{'credits'}{$credit}}, [ encode('utf-8', $name), encode('utf-8', $role) ];
										} else {
											push @{$prog{'credits'}{$credit}}, encode('utf-8', $name);
								}
								
								}
								
									
									# removed after site changed 2014-11-26
									if (0) {  my ($treespans);
									
								#	rating 		i.e. "Certificate"
								my $showcertificate = $treespans->look_down('_tag' => 'span', 'class' => 'tvchannel', sub { $_[0]->as_text =~ /Certificate/ } );
								if ($showcertificate) {
									$showcertificate = $showcertificate->right;
									if ($showcertificate->tag eq 'span' && $showcertificate->attr('class') eq 'programmetext') {
										if ($showcertificate->as_text) {
											$prog{'rating'} = [[ $showcertificate->as_text, 'BBFC' ]]
										}
									}
									$showcertificate->detach;
								}
								
								
								# start and stop time (actually an optional DTD element)
								#		<span class="datetime">10:00am-11:50am <span class=programmetext> (1 hour 50 minutes)</span> Wed 20 Mar</span>
								# (use the Date provided to avoid issues with the site running from 06:00-06:00)
								#
								# Note site displays stop time wrong on GMT/BST changeover, e.g.:
								#			12:45am-1:10am (25 minutes) Sun 31 Mar
								# 	this should be 12:45am-2:10am (BST)
								# 	this makes $showtime->set barf on "invalid local time for date in timezone"
								#
								my $showtimes = $treedetail->look_down('_tag' => 'span', 'class' => 'datetime');
								if ($showtimes) {
									my ($h, $i, $a, $h2, $i2, $a2, $dt) = $showtimes->as_text =~ /(\d*):(\d*)(am|pm)(?:-(\d*):(\d*)(am|pm))?\s*(?:\(.*\))?\s*(.*)$/;
									if ($dt && $dt !~ /\D\D\D\s\d\d?\s\D\D\D/) {
										my @thedt = localtime(time);	# ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst)
										my ($yr1, $yr2) = ($thedt[5]+1900, $thedt[5]+1900);
										if ($thedt[4] == 11) { $yr2++; }
										if ($thedt[4] == 0) { $yr1--; }
										SWITCH: {
											$dt =~ 'Christmas\s+Eve' 		&& do { $dt = '24 Dec '.$yr1; last SWITCH; };
											$dt =~ 'Christmas\s+Day' 		&& do { $dt = '25 Dec '.$yr1; last SWITCH; };
											$dt =~ 'Boxing\s+Day' 			&& do { $dt = '26 Dec '.$yr1; last SWITCH; };
											$dt =~ 'New\s+Years\s+Eve' 	&& do { $dt = '31 Dec '.$yr1; last SWITCH; };
											$dt =~ 'New\s+Years\s+Day' 	&& do { $dt = '1 Jan ' .$yr2; last SWITCH; };
											undef $dt;
										}
									}
									if ($dt) {
										 #v1.3: $showtime = DateTime::Format::DateParse->parse_datetime( $dt, 'Europe/London' );
										 
										 # workaround for bug in Date::Time::str2time() which generates wrong dates for future months when no year is given
										 #		https://rt.cpan.org/Public/Bug/Display.html?id=92611
										 $dt .= ' '.( (localtime(time))[5]+1900 )  if $dt !~ /(19|20)\d\d/;
									
										 $showtime = DateTime->from_epoch( epoch=>str2time( $dt, 'Europe/London' ) )->set_time_zone('Europe/London');
									} else {
										 $showtime = $theday->clone;
									}
									$h  += 12 if $a  eq 'pm' && $h   < 12;		# e.g. 12:30pm means 12:30 !
									$h  -= 12 if $a  eq 'am' && $h  == 12;		# e.g. 12:30am means 00:30 !
									$h2 += 12 if $a2 eq 'pm' && $h2  < 12;	
									$h2 -= 12 if $a2 eq 'am' && $h2 == 12;	
									$showtime->set(hour => $h, minute => $i, second => 0);
									$prog{'start'} = $showtime->strftime("%Y%m%d%H%M%S %z");
									if (defined $h2 && $h2 >= 0) {
										$showtime->add (days => 1) if $h2 < $h; 
										# see note above re errors with GMT/BST transition
										eval {				# try
											$showtime->set(hour => $h2, minute => $i2, second => 0);
											$prog{'stop'} = $showtime->strftime("%Y%m%d%H%M%S %z");
										} or do {			# catch
											# no output prog 'stop' time
										}
									} else {
										# no output prog 'stop' time
									}
								}
								
									}
									
									
									undef @lis;
								
								}
							}	# end showdetail
						}
								
								
							# channel
							$prog{'channel'} = $xmlchannel_id;
							
							# title (mandatory)
							#		<span class="programmeheading">Baywatch</span>
							my $showtitle = $show->look_down('_tag' => 'span', 'class' => 'programmeheading');
							$prog{'title'} = [[ encode('utf-8', $showtitle->as_text), 'en' ]];
							$showtitle->detach;
							
							
							# Note: <span class="tvchannel"> is used by StartTime then SubTitle then Category then Subtitles/B&W/etc
							
							# start (mandatory)
							#		<span class="tvchannel">3:00pm </span>
							# (don't add it even we already have it from the detail page but we still need to delete it from the tree)

							# @ 2014-04-02 the site has changed to 
							#                         <span class="season">6:00 am </span>
							# but this just doesn't sound right to me (i.e. I think it might change again), so let's try both ways
							#
							my $showstart = $show->look_down('_tag' => 'span', 'class' => 'tvchannel');
							if (!$prog{'start'}) {
								my ($h, $i, $a) = $showstart->as_text =~ /(\d*):(\d*)\s*(am|pm)/;
								if (!defined $a) {
									$showstart = $show->look_down('_tag' => 'span', 'class' => 'season');
									($h, $i, $a) = $showstart->as_text =~ /(\d*):(\d*)\s*(am|pm)/;
								}
								$h += 12 if $a eq 'pm' && $h  < 12;		# e.g. 12:30pm means 12:30 !
								$h -= 12 if $a eq 'am' && $h == 12;		# e.g. 12:30am means 00:30 !
								$showtime = $theday->clone;
								$showtime->set(hour => $h, minute => $i, second => 0);
								$showtime->add (days => 1) if ($h < 6);		# site runs from 06:00-06:00 so anything <06:00 is for tomorrow
								$prog{'start'} = $showtime->strftime("%Y%m%d%H%M%S %z");
								# no prog 'stop' time available
							}
							$showstart->detach;
							
							# category
							#		<span class="tvchannel">Category </span><span class="programmetext">General Movie/Drama</span>
							my $showcategory = $show->look_down('_tag' => 'span', 'class' => 'tvchannel', sub { $_[0]->as_text =~ /Category/ } );
							if ($showcategory) {
								$showcategory = $showcategory->right;
								my @showcategory = split(/\//, $showcategory->as_text);
								my @showcategories = ();
								foreach my $category (@showcategory) {
									# category translation?
									if (defined(&map_category)) { $category = map_category($category); }
									if ($category =~ /\|/) { 
										foreach my $cat (split(/\|/, $category)) { push @showcategories, $cat unless grep(/$cat/, @showcategories); }
									} elsif ($category ne '') {
										push @showcategories, $category unless grep(/$category/, @showcategories);
									}
								}
								foreach my $category (@showcategories) {
									push @{$prog{'category'}}, [ encode('utf-8', $category), 'en' ];
								}
								$showcategory->left->detach;
							}
							
							# desc
							#		<span class="programmetext">Dissolving bikinis cause a stir on the beach</span>
							my $showdesc = $show->look_down('_tag' => 'span', 'class' => 'programmetext');
							if ($showdesc) {
								$showdesc = $showdesc->as_text;
								$showdesc .= '.' if ( (length $showdesc) && (substr $showdesc,-1,1 ne '.') );	# addend a fullstop
								if (length $showdesc) {
									$prog{'desc'} = [[ encode('utf-8', $showdesc), 'en' ]];
								}
							}

							# year
							# 	strip this off the title e.g. "A Useful Life (2010)"
							my ($showyear) = $prog{'title'}->[0][0] =~ /.*\((\d\d\d\d)\)$/;
							if ($showyear) {
								$prog{'date'} = $showyear;
								# assume anything with a year is a film - add Films category group
								push @{$prog{'category'}}, [ 'Films', 'en' ];
							}
							
							# flags
							# 		<span class='tvchannel'>(Subtitles)</span> <span class='tvchannel'>(Black &amp; White)</span>
							my $showflags = $show->look_down('_tag' => 'span', 'class' => 'tvchannel', sub { $_[0]->as_text =~ /Subtitles/ } );
							if ($showflags) {
								push @{$prog{'subtitles'}}, {'type' => 'teletext'};
								$showflags->detach;
							}
							#$showflags = $show->look_down('_tag' => 'span', 'class' => 'tvchannel', sub { $_[0]->as_text =~ /Audio Described/ } );
							#if ($showflags) {
							#	push @{$prog{'subtitles'}}, {'type' => 'deaf-signed'};    <-- Audio Described is not deaf-signed
							#	$showflags->detach;
							#}
							$showflags = $show->look_down('_tag' => 'span', 'class' => 'tvchannel', sub { $_[0]->as_text =~ /Repeat/ } );
							if ($showflags) {
	#	push @{$prog{'previously-shown'}}, {};
								$prog{'previously-shown'} = {};
								$showflags->detach;
							}
							my $showvideo = $show->look_down('_tag' => 'span', 'class' => 'tvchannel', sub { $_[0]->as_text =~ /Black & White/ } );
							if ($showvideo) {
								$prog{'video'}->{'colour'} = '0';
								$showvideo->detach;
							}
							#if ($showflags && $showflags->as_text =~ '\[REP\]') {
							#	push @{$prog{'previously-shown'}}, {};
							#}
							$showflags = $show->look_down('_tag' => 'span', 'class' => 'tvchannel', sub { $_[0]->as_text =~ /Interactive/ } );
							if ($showflags) {
								# no flag in DTD for this
								$showflags->detach;
							}
						
						
							# episode number
							# 	<span class="season">Season 2 </span> <span class="season">Episode 3 of 22</span>
							my @showepisode = $show->look_down('_tag' => 'span', 'class' => 'season');
							my $showepisode;
							foreach my $el (@showepisode) { 
								$showepisode .= $el->as_text;
							}
							if ($showepisode) {
								my ($showsxx, $showexx, $showeof) = ( $showepisode =~ /^(?:(?:Series|Season) (\d+)(?:[., :]+)?)?(?:Episode (\d+)(?: of (\d+))?)?/ );
								# scan the description for any "Part x of x." info
								my ($showpxx, $showpof) = ('', '');
								($showpxx, $showpof) = ( $showdesc =~ /Part (one|two|three|four|five|six|seven|eight|nine|\d+)(?: of (one|two|three|four|five|six|seven|eight|nine|\d+))?/ ) if ($showdesc);
								my $showepnum = make_ns_epnum($showsxx, $showexx, $showeof, $showpxx, $showpof);
								if ($showepnum && $showepnum ne '...') {
									$prog{'episode-num'} = [[ $showepnum, 'xmltv_ns' ]];
								}
								#debug "--$showepnum-- ".$showepisode->as_text;
							}
							
							# episode title
							# 	<span class="tvchannel">The Fabulous Buchannon Boys</span>
							my $showeptitle = $show->look_down('_tag' => 'span', 'class' => 'tvchannel');
							if ($showeptitle) {
							  if ($showeptitle->as_text =~ /\(?Premiere\)?/) {
									$prog{'premiere'} = [];
							  } else {									
								$prog{'sub-title'} = [[ encode('utf-8', $showeptitle->as_text), 'en' ]];
								}
								$showeptitle->detach;
							}
						
							# director						
							# never seen one but let's assume they're in the description
							if (!$prog{'credits'}->{'director'}) {
								if ($showdesc) {
									my ($directors) = ( $showdesc =~ /(?:Directed by|Director) ([^\.]*)\.?/ );
									if ($directors) {
										$directors =~ s/ (with|and) /,/ig;
										$directors =~ s/ (singer|actor|actress) //ig;			# strip these words
										$directors =~ s/,,/,/g;	# delete empties
										$directors = encode('utf-8', $directors);	# encode names into utf-8
										#debug $directors;
										my @directors = split(/,/, $directors);
										s{^\s+|\s+$}{}g foreach @directors;	# strip leading & trailing spaces
										$prog{'credits'}->{'director'} = \@directors  if (scalar @directors > 0);
									}
								}
							}
							
							# actors
							# these are buried in the description  :-(
							if (!$prog{'credits'}->{'actor'}) {			
								if ($showdesc) {
									my ($actors) = ( $showdesc =~ /(?:starring)([^\.]*)\.?/i );
									if ($actors) {
										$actors =~ s/ (also|starring|with|and) /,/ig;		# may be used to separate names
										$actors =~ s/ (singer|actor|actress) //ig;			# strip these words
										$actors =~ s/,,/,/g;	# delete empties
										$actors = encode('utf-8', $actors);	# encode names into utf-8
										#debug $actors;
										my @actors = split(/,/, $actors);
										s{^\s+|\s+$}{}g foreach @actors;	# strip leading & trailing spaces
										$prog{'credits'}->{'actor'} = \@actors  if (scalar @actors > 0);
									}
								}
							}
							
							# rating
							#		<span class="programmetext">Rating<br></span><span class="programmeheading">3.9</span>
							my $showrating = $show->look_down('_tag' => 'span', 'class' => 'programmetext', sub { $_[0]->as_text =~ /Rating/ } );
							if ($showrating) {
								$showrating = $showrating->right;
								$showrating = $showrating->right if ($showrating->tag eq 'br');
								if ($showrating->tag eq 'span' && $showrating->attr('class') eq 'programmeheading') {
									if ($showrating->as_text) {
										$prog{'star-rating'} =  [ $showrating->as_text . '/10' ];
									}
								}
							}
							
				
							# debug Dumper \%prog;
							push(@{$programmes}, \%prog);
						}
						

					} else {
						# no schedule found
						warning 'No schedule found';
					}
					
					undef @shows;
					
					# Add to the channels hash
					$channels->{$channel_id} = { 'id'=> $xmlchannel_id , 'display-name' => [[$channelname, 'en']]  };

				} else {
					# tree conversion failed
					warning 'Could not parse the page';
				}

				$bar->update if defined $bar;
			}
		}
}


# #############################################################################
# # THE VEG ######################################################################
# ------------------------------------------------------------------------------------------------------------------------------------- #

sub make_ns_epnum {
		# Convert an episode number to its xmltv_ns compatible - i.e. reset the base to zero
		# Input = series number, episode number, total episodes,  part number, total parts,
		#  e.g. "1, 3, 6, 2, 4" >> "0.2/6.1/4",    "3, 4" >> "2.3."
		#
		my ($s, $e, $e_of, $p, $p_of) = @_;
		#	debug Dumper(@_);

		# "Part x of x" may contaain integers or words (e.g. "Part 1 of 2", or "Part one")
		$p = text_to_num($p) if defined $p;
		$p_of = text_to_num($p_of) if defined $p_of;
		
		# re-base the series/episode/part numbers
		$s-- if (defined $s && $s > 0);
		$e-- if (defined $e && $e > 0);
		$p-- if (defined $p && $p > 0);
		
		# make the xmltv_ns compliant episode-num
		my $episode_ns = '';
		$episode_ns .= $s if defined $s;
		$episode_ns .= '.';
		$episode_ns .= $e if defined $e;
		$episode_ns .= '/'.$e_of if defined $e_of;
		$episode_ns .= '.';
		$episode_ns .= $p if defined $p;
		$episode_ns .= '/'.$p_of if defined $p_of;
		
		#debug "--$episode_ns--";
		return $episode_ns;
}
	
sub text_to_num {
		# Convert a word number to int e.g. 'one' >> '1'
		#
		my ($text) = @_;
		if ($text !~ /^[+-]?\d+$/) {	# standard test for an int
			my %nums = (one => 1, two => 2, three => 3, four => 4, five => 5, six => 6, seven => 7, eight => 8, nine => 9);
			return $nums{$text} if exists $nums{$text};
		}
		return $text
}

sub map_channel_id {
		# Map the fetched channel_id to a different value (e.g. our PVR needs specific channel ids)
		# mapped channels should be stored in a file called  tv_grab_uk_guardian.map.conf
		# containing lines of the form:  map==fromchan==tochan  e.g. 'map==5-star==5STAR'
		#
		my ($channel_id) = @_;
		my $mapchannels = \%mapchannelhash;
		if (%mapchannelhash && exists $mapchannels->{$channel_id}) { 
			return $mapchannels->{$channel_id} ; 
		}
		return $channel_id;
}

sub map_category {
		# Map the fetched category to a different value (e.g. our PVR needs specific genres)
		# mapped categories should be stored in a file called  tv_grab_uk_guardian.map.conf
		# containing lines of the form:  cat==fromcategory==tocategory  e.g. 'cat==General Movie==Film'
		#
		my ($category) = @_;
		my $mapcategories = \%mapcategoryhash;
		if (%mapcategoryhash && exists $mapcategories->{$category}) { 
			return $mapcategories->{$category} ; 
		}
		return $category;
}

sub loadmapconf {
		# Load the conf file containing mapped channels and categories information
		# 
		# This file contains 2 record types:
		# 	lines starting with "map" are used to 'translate' the incoming channel id to those required by your PVR
		#			e.g. 	map==dave==DAVE     will output "DAVE" in your XML file instead of "dave"
		# 	lines starting with "cat" are used to translate categories (genres) in the incoming data to those required by your PVR
		# 		e.g.  cat==Science Fiction==Sci-fi			will output "Sci-Fi" in your XML file instead of "Science Fiction"
		# 
		my $mapchannels = \%mapchannelhash;
		my $mapcategories = \%mapcategoryhash;
		#		
		my $supplementdir = $ENV{XMLTV_SUPPLEMENT} || GetSupplementDir();
		SetSupplementRoot($supplementdir);
		my $lines = GetSupplementLines($GRABBER_NAME, $GRABBER_NAME . '.map.conf');
		foreach my $line (@$lines) { 
				my ($type, $mapfrom, $mapto, $trash) = $line =~ /^(.*)==(.*)==(.*?)([\s\t]*#.*)?$/;
				SWITCH: {
						lc($type) eq 'map' && do { $mapchannels->{$mapfrom} = $mapto; last SWITCH; };
						lc($type) eq 'cat' && do { $mapcategories->{$mapfrom} = $mapto; last SWITCH; };
					warning "Unknown type in map file: \n $line";
				}
			}
		# debug Dumper ($mapchannels, $mapcategories);
}

sub fetch_channels {
	my ($opt, $conf) = @_;
  
	# Fetch channels via a dummy call to BBC1 listings
	#		http://www.tvguide.co.uk/channellisting.asp?ch=86&cTime=
	my $channel_list = $ROOT_URL.'channellisting.asp?ch=86&cTime=';

  my $result;
  my $channels = {};

  my $bar = new XMLTV::ProgressBar({
    name => "Fetching channels",
    count => 1
  }) unless ($opt->{quiet} || $opt->{debug});

  # Get the page containing the list of channels 
  my $tree = XMLTV::Get_nice::get_nice_tree($channel_list);
	#		$tree->dump;
  my $_channels = $tree->look_down('_tag' => 'select', 'name' => 'ch');
	my @channels = $_channels->look_down('_tag' => 'option');
			#		debug $_channels->as_HTML;
			#		foreach  my $xchannel (@channels) { debug $xchannel->as_HTML; }

  $bar->update() && $bar->finish && undef $bar if defined $bar;

  $bar = new XMLTV::ProgressBar({
    name => "Parsing result",
    count => scalar @channels
  }) unless ($opt->{quiet} || $opt->{debug});

  # Browse through the downloaded list of channels and map them to a hash XMLTV::Writer would understand
  foreach my $channel (@channels) {
    if ($channel->as_text) {
      my ($id) = $channel->attr('value');
			my ($url) = 'channellisting.asp?ch=' . $channel->attr('value');
			my ($name) = $channel->as_text;

      $channels->{"$id"} = {
        id => "$id",
        'display-name' => [[ encode('utf-8', $name), 'en' ]],
        url => [ $ROOT_URL.$url ]
      };

    }

    $bar->update() if defined $bar;
  }

  $bar->finish() && undef $bar if defined $bar;

  # Notifying the user :)
  $bar = new XMLTV::ProgressBar({
    name => "Reformatting",
    count => 1
  }) unless ($opt->{quiet} || $opt->{debug});

  # Let XMLTV::Writer format the results as a valid xmltv file
  my $writer = new XMLTV::Writer(OUTPUT => \$result, encoding => 'utf-8');
  $writer->start({'generator-info-name' => $generator_info_name});
  $writer->write_channels($channels);
  $writer->end();

  $bar->update() && $bar->finish() if defined $bar;

  return $result;
}

sub config_stage {
		my( $stage, $conf ) = @_;
		die "Unknown stage $stage" if $stage ne "start";

		my $result;
		my $writer = new XMLTV::Configure::Writer( OUTPUT => \$result, encoding => 'utf-8' );
		$writer->start( { grabber => $GRABBER_NAME } );
		$writer->write_string( {
				id => 'cachedir', 
				title => [ [ 'Directory to store the cache in', 'en' ] ],
				description => [ 
				 [ $GRABBER_NAME.' uses a cache with files that it has already '. 
					 'downloaded. Please specify where the cache shall be stored. ', 
					 'en' ] ],
				default => get_default_cachedir(),
		 } );

		$writer->end( 'select-channels' );

		return $result;
}

sub config_check {
		if (not defined( $conf->{cachedir} )) {
				print STDERR "No cachedir defined in configfile " . 
										 $opt->{'config-file'} . "\n" .
										 "Please run the grabber with --configure.\n";
				exit 1;
		}

		if (not defined( $conf->{'channel'} )) {
				print STDERR "No channels selected in configfile " .
										 $opt->{'config-file'} . "\n" .
										 "Please run the grabber with --configure.\n";
				exit 1;
		}
}

sub get_default_dir {
    my $winhome = $ENV{HOMEDRIVE} . $ENV{HOMEPATH} 
			if defined( $ENV{HOMEDRIVE} ) 
					and defined( $ENV{HOMEPATH} ); 
    
    my $home = $ENV{HOME} || $winhome || ".";
    return $home;
}

sub get_default_cachedir {
    return get_default_dir() . "/.xmltv/cache";
}

sub init_cachedir {
    my( $path ) = @_;
    if( not -d $path ) {
        mkpath( $path ) or die "Failed to create cache-directory $path: $@";
    }
}

sub debug ( $$ ) {
    my( $message, $nonewline ) = @_;
    print STDERR $message if $opt->{debug};
    print STDERR "\n" if $opt->{debug} && (!defined $nonewline || $nonewline != 1);
}

sub warning ( $ ) {
    my( $message ) = @_;
    print STDERR $message . "\n";
    $warnings++;
}

if (0) {		# not used
sub initialise_ua {
	my $cookies = HTTP::Cookies->new;
	#my $ua = LWP::UserAgent->new(keep_alive => 1);
	my $ua = LWP::UserAgent->new;
	# Cookies
	$ua->cookie_jar($cookies);
	# Define user agent type
	$ua->agent('Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US)');
	# Define timouts
	$ua->timeout(240);
	# Use proxy if set in http_proxy etc.
	$ua->env_proxy;
	
	return $ua;
}
}

# #############################################################################

__END__

=pod

=head1 NAME

B<tv_grab_uk_tvguide> - Grab TV listings for UK from the TV Guide UK website.

=head1 DESCRIPTION

Output TV listings in XMLTV format for many channels available in UK.
The data come from tvguide.co.uk

First you must run B<tv_grab_uk_tvguide --configure> to choose which channels
you want to receive.

Then running B<tv_grab_uk_tvguide> with no arguments will get a listings in XML
format for the channels you chose for available days including today.

=head1 OPTIONS

Please see B<tv_grab_uk_tvguide --help>

=head1 INSTALLATION

The file F<tv_grab_uk_tvguide.map.conf> has two purposes.  Firstly you can map the channel ids used by the site into something more meaningful to your PVR. E.g.

      map==74==BBC 1	

will change "74" to "BBC 1" in the output XML.

Note: the lines are of the form "map=={channel id}=={my name}".

The second purpose is to likewise translate genre names.  So if your PVR doesn"t have a category for "Science Fiction" but uses "Sci-fi" instead, then you can specify

      cat==Science Fiction==Sci-fi

and the output XML will have "Sci-fi".


IMPORTANT: the downloaded "tv_grab_uk_tvguide.map.conf" contains example lines to illustrate the format - you should edit this file to suit your own purposes!

=head1 ERROR HANDLING

If the grabber fails to download data for some channel on a specific day, 
it will print an errormessage to STDERR and then continue with the other
channels and days. The grabber will exit with a status code of 1 to indicate 
that the data is incomplete. 

=head1 ENVIRONMENT VARIABLES

The environment variable HOME can be set to change where configuration
files are stored. All configuration is stored in $HOME/.xmltv/. On Windows,
it might be necessary to set HOME to a path without spaces in it.

=head1 SUPPORTED CHANNELS

For information on supported channels, see http://tvguide.co.uk/

=head1 XMLTV VALIDATION

B<tv_validate_grabber> may report an error similar to:

      "Line 5 Invalid channel-id BBC 1"
	
This is a because ValidateFile.pm insists the channel-id adheres to RFC2838 despite the xmltv.dtd only saying "preferably" not "SHOULD".  
(Having channel ids of the form "bbc1.bbc.co.uk" will be rejected by many PVRs since they require the data to match their own list.)

It may also report:

      "tv_sort failed on the concatenated data. Probably due to overlapping data between days."
	
Both these errors can be ignored.

=head1 DISCLAIMER

The TV Guide website"s license for these data does not allow non-personal use.

Certainly any commercial use of listings data obtained by using this grabber will breach copyright law, but if you are just using the data for your own personal use then you are probably fine.

By using this grabber you aver you are using the listings data for your own personal use only and you absolve the author(s) from any liability under copyright law or otherwise.

=head1 AUTHOR

Geoff Westcott. This documentation and parts of the code
based on various other tv_grabbers from the XMLTV-project.

=head1 SEE ALSO

L<xmltv(5)>.

=cut


To Do
=====

1.  Improve the progress bar update frequency
2.  Add actor 'character' attribute
3.  Currently only does Actor, Director, Producer, Writer - does anyone actually use any of the others present in the DTD?