/usr/bin/tv_grab_na_dtv is in xmltv-util 0.5.69-1.
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 | #!/usr/bin/perl -w
=pod
=head1 NAME
tv_grab_na_dtv - Grab TV listings from DirecTV.
=head1 SYNOPSIS
tv_grab_na_dtv --help
tv_grab_na_dtv --configure [--config-file FILE]
tv_grab_na_dtv [--config-file FILE]
[--days N] [--offset N] [--processes N]
[--output FILE] [--quiet] [--debug]
tv_grab_na_dtv --list-channels [--config-file FILE]
[--output FILE] [--quiet] [--debug]
=head1 DESCRIPTION
Output TV and listings in XMLTV format from directv.com.
First you must run B<tv_grab_na_dtv --configure> to choose which stations
you want to receive.
Then running B<tv_grab_na_dtv> with no arguments will get listings for the
stations you chose for five days including today.
=head1 OPTIONS
B<--configure> Prompt for which stations to download and write the
configuration file.
B<--config-file FILE> Set the name of the configuration file, the
default is B<~/.xmltv/tv_grab_na_dtv.conf>. This is the file written by
B<--configure> and read when grabbing.
B<--output FILE> When grabbing, write output to FILE rather than
standard output.
B<--days N> When grabbing, grab N days rather than 5.
B<--offset N> Start grabbing at today + N days.
B<--processes N> Number of processes to run to fetch program details.
8 is a good number to try. You could try more with plenty of CPU and
bandwidth. More processes will reduce the time it takes to fetch your
listings. But be warned, the benefit might not be as much as you think,
and the more processes you initiate the more you are making it obvious
you are scraping and more likely to get banned by the source site.
A 'fast' website scraper is an oxymoron!
B<--quiet> Only print error-messages on STDERR.
B<--debug> Provide more information on progress to stderr to help in
debugging.
B<--list-channels> Output a list of all channels that data is available
for. The list is in xmltv-format.
B<--capabilities> Show which capabilities the grabber supports.
B<--version> Show the version of the grabber.
B<--help> Print a help message and exit.
=head1 ERROR HANDLING
If the grabber fails to download data, it will print an error message to
STDERR and then exit with a status code of 1 to indicate that the data is
missing.
=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.
TEMP or TMP, if present, will override the directory used to contain temporary
files. Default is "/tmp", so under Windows one of these is required.
=head1 CREDITS
Grabber written Rod Roark (http://www.sunsetsystems.com/),
Modified by Adam Lewandowski (adam@alewando.com) (January 2011, October 2014)
to account for DirecTV site/API changes.
=head1 BUGS
Like any screen-scraping grabber, this one will break regularly as the web site
changes, and you should try to fetch a new one from the project's repository.
At some point the breakage might not be fixable or it may be that nobody wants
to fix it. Sane people should use Schedules Direct instead.
=cut
use strict;
use XMLTV::Configure::Writer;
use XMLTV::Options qw/ParseOptions/;
use LWP::UserAgent;
use HTTP::Cookies;
use DateTime;
use JSON::PP;
use Errno qw(EAGAIN);
use URI;
use URI::Escape;
######################################################################
# Globals #
######################################################################
# This is the number of concurrent processes for scraping and parsing
# program details. 8 is a good number to try. You could try more with
# plenty of CPU and bandwidth. More processes will reduce the time it
# takes to fetch your listings.
# But be warned, the benefit might not be as much as you think,
# and the more processes you initiate the more you are making it obvious
# you are scraping and more likely to get banned by the source site.
# A 'fast' website scraper is an oxymoron!
#
# Set default to 1 so the xmltv.exe does NOT use perl fork
my $MAX_PROCESSES = 1;
my $VERBOSE = 0;
my $DEBUG = 0;
my $TMP_FILEBASE = $ENV{TEMP} || $ENV{TMP} || '/tmp';
$TMP_FILEBASE .= '/na_dtv_';
my $queue_filename = "$TMP_FILEBASE" . "q";
my $SITEBASE = "http://www.directv.com";
# URL for grabbing channel list
my $CHANNEL_LIST_URL = "$SITEBASE/json/channels";
# URL for schedule data
my $SCHEDULE_URL = "$SITEBASE/json/channelschedule";
# Each program ID will be appended to this URL to get its details.
my $DETAILS_URL = "$SITEBASE/json/program/flip";
my $XML_PRELUDE =
'<?xml version="1.0" encoding="ISO-8859-1"?>' . "\n"
. '<!DOCTYPE tv SYSTEM "xmltv.dtd">' . "\n"
. '<tv source-info-url="http://www.directv.com/" source-info-name="DirecTV" '
. 'generator-info-name="XMLTV" generator-info-url="http://www.xmltv.org/">'
. "\n";
my $XML_POSTLUDE = "</tv>\n";
# Global stuff shared by the parent and child processes.
my $browser;
my $fhq;
my $proc_number;
# Default to EST, will read from config file later
my $timeZone;
# This hash will contain accumulated channel and program information.
# Key is channel number, value is (a reference to) a hash of channel data
# derived from JSON data returned by DirecTV. Useful keys include:
# chNum, chCall, chName, chLogoUrl, chId
my %ch = ();
######################################################################
# Main logic starts here #
######################################################################
# prepare_queue creates the "queue file" of tasks for the child
# processes. It always writes channel XML to stdout.
if ( &prepare_queue() ) {
# Reopen the queue file so the child processes will share its handle.
open $fhq, "< $queue_filename";
binmode $fhq;
if ( $MAX_PROCESSES == 1 ) {
# Don't create any child processes - do it ourself
$proc_number = 0;
&child_logic();
} else {
# Create the children.
for ( $proc_number = 0 ; $proc_number < $MAX_PROCESSES ; ++$proc_number ) {
my $pid = fork;
if ($pid) {
# We are the parent. Keep on trucking.
}
elsif ( defined $pid ) {
# We are a child. Do juvenile stuff and then terminate.
exit &child_logic();
}
else {
# We are the parent and something is wrong. If we have at least one
# child process already started, then go with what we have.
if ( $proc_number > 0 ) {
$MAX_PROCESSES = $proc_number;
last;
}
# Otherwise retry if possible, or die if not.
if ( $! == EAGAIN ) {
print STDERR "Temporary fork failure, will retry.\n" if ($VERBOSE);
sleep 5;
--$proc_number;
}
else {
die "Fork failed: $!\n";
}
}
}
if ($VERBOSE) {
print STDERR "Started $MAX_PROCESSES processes to fetch and parse schedule and program data.\n";
}
# This would be a good place to implement a progress bar. Just enter a
# loop that sleeps for a few seconds, gets the $fhq seek pointer value,
# and writes the corresponding percentage completion.
# Wait for all the children to finish.
while ( wait != -1 ) {
# Getting here means that a child finished.
}
}
print STDERR "Done. Writing results and cleaning up.\n" if ($VERBOSE);
close $fhq;
unlink $queue_filename;
my @cdata = ();
# Open all data files and read the first program of each.
for ( my $procno = 0 ; $procno < $MAX_PROCESSES ; ++$procno ) {
my $fname = "$TMP_FILEBASE" . $procno;
my $fh;
open $fh, "< $fname" or die "Cannot open $fname: $!\n";
$cdata[$procno] = [];
$cdata[$procno][0] = $fh;
&read_queue( \@cdata, $procno );
}
# Merge the files and print their XML program data.
my $lastkey = "";
while (1) {
my $plow = 0;
# Get the next program, ordering chronologically within channel.
for ( my $procno = 0 ; $procno < $MAX_PROCESSES ; ++$procno ) {
$plow = $procno if ( $cdata[$procno][1] lt $cdata[$plow][1] );
}
last if ( $cdata[$plow][1] eq 'ZZZZ' );
if ( $lastkey eq $cdata[$plow][1] ) {
# There seems to be some race condition in my test setup's OS that
# allows two child processes to grab the same qfile entry.
# This is an attempt to work around it. -- Rod
print STDERR "Skipping duplicate: $lastkey" if ($VERBOSE);
}
else {
print $cdata[$plow][2];
$lastkey = $cdata[$plow][1];
}
&read_queue( \@cdata, $plow );
}
# Close and delete the temporary files.
for ( my $procno = 0 ; $procno < $MAX_PROCESSES ; ++$procno ) {
close $cdata[$procno][0];
unlink "$TMP_FILEBASE" . $procno;
}
}
print $XML_POSTLUDE;
exit 0;
######################################################################
# General Subroutines #
######################################################################
sub getBrowser {
my ($conf) = @_;
my $ua = LWP::UserAgent->new;
# Cookies
my $cookies = HTTP::Cookies->new;
$ua->cookie_jar($cookies);
my $zip = $conf->{zip}[0];
$cookies->set_cookie(0, 'dtve-prospect-zip', "$zip", '/', 'www.directv.com');
# Define user agent type
$ua->agent('Mozilla/5.0 (Linux) XmlTv');
# Define timouts
$ua->timeout(240);
# Use proxy if set in http_proxy etc.
$ua->proxy( [ 'http', 'https' ], $conf->{proxy}->[0] )
if $conf->{proxy}->[0];
if ($DEBUG && $VERBOSE) {
$ua->add_handler("request_send", sub { print "Request:\n"; shift->dump; return });
$ua->add_handler("response_done", sub { print "Response:\n"; shift->dump; return });
}
return $ua;
}
# For escaping characters not valid in xml. More needed here?
sub xmltr {
my $txt = shift;
$txt =~ s/&/&/g;
$txt =~ s/</</g;
$txt =~ s/>/>/g;
$txt =~ s/\"/"/g;
return $txt;
}
######################################################################
# Subroutines for the Parent Process #
######################################################################
# Read one queue entry from the file created by the specified process.
sub read_queue {
my ( $cdata, $procno ) = @_;
$cdata->[$procno][2] = '';
my $line = readline $cdata->[$procno][0];
if ( defined $line ) {
$cdata->[$procno][1] = $line;
while (1) {
$line = readline $cdata->[$procno][0];
last unless ( defined $line );
$cdata->[$procno][2] .= $line;
last if ( $line =~ /<\/programme>/i );
}
}
else {
# At EOF set the key field to a special value that sorts last.
$cdata->[$procno][1] = 'ZZZZ';
}
}
# For sorting %ch by its (channel number) key:
sub numerically { $a cmp $b }
# This is what the main process does first. Variables in here will
# go nicely out of scope before the child processes are started.
sub prepare_queue {
my ( $opt, $conf ) = ParseOptions(
{
grabber_name => "tv_grab_na_dtv",
capabilities => [qw/baseline manualconfig tkconfig apiconfig/],
stage_sub => \&config_stage,
listchannels_sub => \&list_channels,
version =>
'$Id: tv_grab_na_dtv,v 1.24 2016/11/23 19:41:36 knowledgejunkie Exp $',
description => "North America using www.directv.com",
extra_options => [qw/procs=i processes=i/], # allow 'procs' as a synonym for 'processes'
defaults => {'procs'=>0, 'processes'=>'0'}
}
);
# If we get here, then we are generating data normally.
# Get max( $MAX_PROCESSES, --procs, --processes )
$MAX_PROCESSES = ($MAX_PROCESSES, $opt->{procs})[$MAX_PROCESSES < $opt->{procs}];
$MAX_PROCESSES = ($MAX_PROCESSES, $opt->{processes})[$MAX_PROCESSES < $opt->{processes}];
$VERBOSE = !$opt->{quiet};
$DEBUG = $opt->{debug};
$timeZone = $conf->{timezone}[0];
$timeZone = "America/New_York" if !$timeZone; # Default to EST
$browser = getBrowser($conf);
# Populate %ch hash
&scrape_channel_list( $browser, $conf->{zip}[0], $conf->{channel}, \%ch );
print $XML_PRELUDE;
# Write XML for channels, and total the number of program IDs.
foreach my $channel_number ( sort numerically keys %ch ) {
print &channel_xml( $channel_number, 0, \%ch );
}
# Write all of the program IDs with their channel IDs and start times
# to a temporary file. This file will later be read by child processes.
my $startDate = DateTime->now;
$startDate->set_time_zone($timeZone);
$startDate->set(hour => 0, minute => 0, second => 0);
# Add offset to start date
$startDate -> add(days => $opt->{offset});
open $fhq, "> $queue_filename";
binmode $fhq;
foreach my $channel_number ( sort numerically keys %ch ) {
my %channel_data = %{ $ch{$channel_number} };
my $channel_name = $channel_data{chName};
my $channel_id = &rfc2838( $channel_number, $channel_name );
# Write queue entry for each channel and day
# Queue file contains two fields: channel_number day(Mon Oct 13 2014 16:00:00 GMT-0400)
for ( my $day = 0 ; $day < $opt->{days} ; $day++ ) {
my $queueDate = $startDate->clone();
$queueDate->add(days => $day);
# my $date = $queueDate->ymd;
my $date = $queueDate->strftime("%a %d %b %Y %H:%M:%S GMT%z");
# Fixed-length records make life easier. See comments in child_logic.
printf $fhq "%-6s %10s\n", $channel_number, $date;
}
}
close $fhq;
}
# Create a channel ID.
sub rfc2838 {
my ( $cnum, $cname ) = @_;
my $num = $cnum;
my $extra = "";
if($cnum =~ /^(\d+)(-.*)/) {
$num = $1;
$extra = $2;
}
my $id = sprintf('%04s%s.directv.com', $num, $extra );
return $id;
}
# This gets channels and program IDs for the one 2-hour time slot from
# the designated URL.
sub scrape_channel_list {
my ( $browser, $zip, $channels, $ch ) = @_;
print STDERR "Getting channel list\n" if ($DEBUG);
my $resp = $browser->get($CHANNEL_LIST_URL);
my $json = $resp->content();
my $data = decode_json $json;
# Check status code
if ( !$data->{success} ) {
print STDERR "Error getting channel list: " . $data->{errorMessage} . "\n";
exit 1;
}
# Populate %ch hash for selected channels
my @channels = @{ $data->{channels} };
for my $chanRef (@channels) {
my %chanData = %{$chanRef};
my $channel_number = $chanData{chNum};
my $channel_name = $chanData{chName};
# Handle channels with both HD and SD versions (ie: 0756-1.directv.com)
# Usually only seen on sports subscriptions where some games are not available in HD
# (ie: NBA League Pass, MLS, etc)
my $dual;
if($channel_name =~ /${channel_number}-1/ && $chanData{chHd}) {
$dual=1;
}
my $channel_id = &rfc2838( $channel_number, $channel_name );
# If channels were passed, skip those not listed.
if ($channels) {
next unless grep /^$channel_id$/, @$channels;
}
# Add to ch hash
$ch->{$channel_number} = $chanRef if !$ch->{$channel_number};
if($dual) {
$ch->{$channel_number}->{dual} = 1;
}
}
}
# Invoked by ParseOptions for configuration.
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 => 'tv_grab_na_dtv' } );
# Entering a zip code will cause local channels to be included, if
# available.
$writer->write_string(
{
id => 'zip',
title => [ [ 'Zip Code', 'en' ] ],
description =>
[ [ 'Enter your zip code to include local channels.', 'en' ] ],
}
);
# Timezone is needed to adjust the UTC times provided by DirecTV to local time
my @timezones = DateTime::TimeZone->names_in_country("US");
$writer->start_selectone( {
id => 'timezone',
title => [ [ 'Time Zone', 'en' ], ],
description => [ [ 'The timezone that you live in.', 'en' ], ],
} );
foreach my $tz (@timezones) {
$writer->write_option( {
value=>$tz,
text=> => [ [ $tz, 'en' ], ]
} );
}
$writer->end_selectone();
$writer->end('select-channels');
return $result;
}
# Invoked by ParseOptions when it wants the list of all channels.
sub list_channels {
my ( $conf, $opt ) = @_;
$VERBOSE = !$opt->{quiet};
my $browser = getBrowser($conf);
&scrape_channel_list( $browser, $conf->{zip}[0], $conf->{channel}, \%ch );
my $xml = $XML_PRELUDE;
foreach my $channel_number ( sort numerically keys %ch ) {
$xml .= &channel_xml( $channel_number, 1, \%ch );
}
$xml .= $XML_POSTLUDE;
return $xml;
}
# Create XML for the designated channel.
sub channel_xml {
my ( $channel_number, $setup, $ch ) = @_;
my %channel_data = %{ $ch->{$channel_number} };
my $channel_name = $channel_data{chName};
my $channel_id = &rfc2838( $channel_number, $channel_name );
my $xml = " <channel id=\"$channel_id\">\n";
if ($setup) {
# At --configure time the user will want to see channel numbers.
$xml .=
" <display-name>$channel_number "
. &xmltr($channel_name)
. "</display-name>\n";
} else {
$xml .=
" <display-name>"
. &xmltr($channel_name)
. "</display-name>\n"
. " <display-name>$channel_number</display-name>\n";
}
$xml .= " </channel>\n";
return $xml;
}
######################################################################
# Subroutines for the Child Processes #
######################################################################
# Top-level logic for child processes.
sub child_logic {
my $fname = "$TMP_FILEBASE" . $proc_number;
my $fh;
open $fh, "> $fname" or die "Cannot create $fname: $!";
# Here we use low-level I/O to read the shared queue file, so that seek
# pointer sharing will work properly. We expect the sysreads to be atomic.
while (1) {
my $line = '';
my $readlen = sysread $fhq, $line, 41;
last unless ($readlen);
print STDERR "Process $proc_number Queue entry:$line" if ($DEBUG);
# Queue line format (%-6s %10s)
if ( $line =~ /^([0-9-]+)\s+(.*)$/ ) {
my $channel_number = $1;
my $day = $2;
print $fh &scrape_channel_day( $browser, $channel_number, $day );
}
else {
# Errors here might mean that seek pointer sharing is broken.
print STDERR "Process $proc_number: input syntax error: '$line'\n";
}
}
close $fh;
return 0;
}
# Parse a date from either ISO-8601 or RFC-822 format
sub parseDate {
my ($input) = @_;
if ($input =~ /^\d{4}-/) {
# Format 2012-01-09T04:00:00.000+0000
my ($y,$m,$d,$h,$min,$s,$z) = $input =~ /(\d{4})-(\d{2})-(\d{2})T(\d{2}):(\d{2}):(\d{2})(?:\.\d{3}([+-]\d+))?/;
#print "parsed '$input' into $y, $m, $d, $h, $min, $s, $z\n";
my $date = DateTime->new(
year => $y,
month => $m,
day => $d,
hour => $h,
minute => $min,
second => $s || 0,
nanosecond => 0,
time_zone => $z || '-0400',
);
$date->set_time_zone($timeZone);
return $date;
}
if ($input =~ /^\w{3} /) {
# Format: Sun 19 Oct 2014 00:00:00 GMT-0400
my ($dow, $d, $m, $y, $h, $min, $s, $z) = $input =~ /(\w{3}) (\d{2}) (\w{3}) (\d{4}) (\d{2}):(\d{2}):(\d{2}).*([+-]\d{4})/;
#print "parsed '$input' into " . ($y,$m, $d, $h, $min, $s, $z) . "\n";
my %mon2num = qw(
Jan 1 Feb 2 Mar 3 Apr 4 May 5 Jun 6
Jul 7 Aug 8 Sep 9 Oct 10 Nov 11 Dec 12
);
my $date = DateTime->new(
year => $y,
month => $mon2num{$m},
day => $d,
hour => $h,
minute => $min,
second => $s,
nanosecond => 0,
time_zone => $z,
);
$date->set_time_zone($timeZone);
return $date;
}
}
sub printDate {
my ($dt) = @_;
#Format 20120109233500 -0500
my $str = $dt->strftime("%Y%m%d%H%M%S ") . DateTime::TimeZone->offset_as_string($dt->offset);
return $str;
}
# Check that the start date is on the requested day (after adjusting to the specified timezone)
sub checkStartDate {
my ($day, $startDt) = @_;
#my $cmpDay = $startDt->ymd;
return $startDt->ymd eq $day->ymd;
}
# This generates XML for the designated channel on the designated day
sub scrape_channel_day {
my ( $browser, $channel_number, $day ) = @_;
print STDERR "Retrieving schedule info for channel $channel_number on $day\n" if ($VERBOSE);
my $shortNum = $channel_number;
$shortNum =~ s/(\d+)-.*/$1/;
#Get channel schedule data for the specified day from the DirecTV JSON URL
my $starttime = $day;
my $blockduration = 24;
my $url = URI->new($SCHEDULE_URL);
#TODO: Include chIds parameter (comma-sep list of channel IDs corresponding to channel numbers)
$url->query_form('channels' => $shortNum, 'startTime' => $starttime, 'hours' => $blockduration);
my $resp = $browser->get($url);
my $json = $resp->content();
# Parse JSON
my $data = decode_json $json;
# Check status code
if ( $data->{errors} ) {
my $msg = "";
foreach my $err (@{$data->{errors}}) {
$msg .= $err->{text};
$msg .= "\n";
}
print STDERR
"Error getting schedule data for channel $channel_number on $day:\n$msg";
exit 1;
}
my $output = "";
if( ref($data->{schedule}) eq 'ARRAY' && @{ $data->{schedule}} ) {
my @schedules = @{ @{ $data->{schedule}}[0]->{schedules} };
foreach my $prog (@schedules) {
# Skip if program does not start on the target date (ie: started the previous day)
my $startDate = parseDate($prog->{airTime});
$prog->{startDt} = $startDate;
if (!checkStartDate(parseDate($day), parseDate($prog->{airTime}) )) {
print STDERR "Skipping program $prog->{programID} because it doesn't start on $day: $prog->{airTime}\n" if ($DEBUG);
next;
}
# Get program details
$output .= &scrape_program_details( $browser, $channel_number, $prog );
}
}
return $output;
}
sub scrape_program_details {
my ( $browser, $channel_number, $program_data ) = @_;
# Get what we can from the JSON structure
my $program_id = $program_data->{programID};
my $title = $program_data->{title};
#my $subtitle = $program_data->{episodeTitle};
my $start = $program_data->{airTime};
my $length = $program_data->{duration};
my $hd = $program_data->{hd};
return "" if $program_id eq "-1";
# Append '-1' to channel number if this is an HD broadcast on a dual-numbered channel
# This is how the channel is entered mannualy on the receiver
if($ch{$channel_number}->{dual} && $hd) {
$channel_number .= "-1";
}
my $channel_id = &rfc2838($channel_number);
# Calculate stop time
my $startDate = $program_data->{startDt};
my $stopDate = $startDate->clone();
$stopDate->add(minutes => $length);
# Get program details page
my $programDetailsUrl = $DETAILS_URL . "/${program_id}";
print STDERR "Retrieving details for program id $program_id: $programDetailsUrl\n" if ($DEBUG);
my $resp = $browser->get( $programDetailsUrl );
if(! $resp->is_success()) {
print STDERR "Error getting program details for $program_id: " . $resp->status_line() . "\n";
return "";
}
# my $detailContent = $resp->content();
# my $parser = HTML::TokeParser->new( \$detailContent );
my $detail_js = decode_json $resp->content();
my $detail = $detail_js->{"programDetail"};
# Extract program details
my $subtitle = $detail->{episodeTitle};
my $desc = $detail->{description};
my $rating = $detail->{rating};
my $releaseDate = $detail->{releaseYear};
my $star_rating = $detail->{starRatingNum};
# Generate program XML
my $xml = "";
# A "header" line is written before each program's XML for sorting
# when the files from the children are merged.
$xml .= "$channel_number $startDate\n";
my $startXMLTV = $startDate->strftime ('%Y%m%d%H%M%S %z');
my $stopXMLTV = $stopDate->strftime ('%Y%m%d%H%M%S %z');
# Program XML
$xml .= "<programme start=\"" . printDate(${startDate}) . "\" ";
$xml .= "stop=\"" . printDate(${stopDate}) . "\" channel=\"" . $channel_id . "\">\n";
$xml .= " <title lang=\"en\">" . xmltr($title) . "</title>\n" if $title;
$xml .= " <sub-title lang=\"en\">" . xmltr($subtitle) . "</sub-title>\n" if $subtitle;
$xml .= " <desc lang=\"en\">" . xmltr($desc) . "</desc>\n" if $desc;
$xml .= " <date>" . xmltr($releaseDate) . "</date>\n" if $releaseDate;
$xml .= " <video><quality>HDTV</quality></video>\n" if $hd;
$xml .= " <rating system=\"MPAA\"><value>" . xmltr($rating) . "</value></rating>\n"
if $rating;
$xml .= " <star-rating><value>" . xmltr($star_rating) . "</value></star-rating>\n"
if $star_rating;
$xml .= "</programme>\n";
return $xml;
}
|