User:AW01545

1. strictly a preliminary version
2. attention Doug!

hir21.pl

#!/usr/bin/env perl

# Date: $Date: 2010-06-21 23:12:19 -0400 (Mon, 21 Jun 2010) $
# Author: $Author: renickle $
# Revision: $Revision: 8 $
# Id: $Id: hir21.pl 8 2010-06-22 03:12:19Z renickle $
#
# MythNetvision Grabber Script for hirtv (Hungarian News)
#
################################################################################

use strict;

$|=1;

use LWP::Simple;
use HTML::TreeBuilder;
use HTML::Entities;
use Data::Dumper;
use Getopt::Long;
use Time::Local;
use File::stat;
use DateTime;

my $site="HirTV";
my $baseurl=cleantext("http://www.hirtv.hu");
my $url=$baseurl . "/?tPath=/view/videoview/hirado&sp=Offer";
my $cleanurl=cleantext($url);
my $description="HirTV Hungarian News";
my $video_created="";

my $cache_file="/tmp/hirado.content";
my $cache_time=7200;
my $header = '<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"
xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd"
xmlns:content="http://purl.org/rss/1.0/modules/content/"
xmlns:cnettv="http://cnettv.com/mrss/"
xmlns:creativeCommons="http://backend.userland.com/creativeCommonsRssModule"
xmlns:media="http://search.yahoo.com/mrss/"
xmlns:atom="http://www.w3.org/2005/Atom"
xmlns:amp="http://www.adobe.com/amp/1.0"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:mythtv="http://www.mythtv.org/wiki/MythNetvision_Grabber_Script_Format">
';
my $footer = "</rss>\n";

my %dirurls;
my %dirdates;

my %options=();

my $opt_return=GetOptions(\%options,'T|Tree!','S|Search=s','v|version!','p|page=i');


if($options{"v"}) {

  print "HirTV|T\n";
  exit 0;

  print <<"_EOXML_";
<grabber>
  <name>Hir21</name>
  <command>hir21.pl</command>
  <author>ricknickle\@hotmail.com</author>
  <thumbnnail src="/usr/share/mythtv/mythnetvision/icons/news.png"/>
  <type>video</type>
  <description>Hirado 21 is the 9 o\'clock news hour on HirTV, the conservative television network in Hungary.</description>
  <version>2</version>
  <search>false</search>
  <tree>true</tree>
</grabber>
_EOXML_
  exit 0;
}

if($options{"T"}) {

  print $header;

  hirado_channel();

  print $footer;

  exit 0;
}

sub hirado_channel {
  my $content="";


  if( -e $cache_file) {
    my $ss=stat($cache_file);
    if(($ss->mtime) && (time() - $ss->mtime > $cache_time)) {
      unlink($cache_file);
    }
  }

  if(! -e $cache_file) {
    $content = get($url);
    open(OUT,">$cache_file");
    print OUT $content;
    close(OUT);
  } else {
    my $save_rs=$/;
    $/=undef;
    open(IN,"<$cache_file");
    $content=<IN>;
    close(IN);
    $/=$save_rs;
  }
      
  $content=~s/<br \/>/ /gm;
  unless ($content) {
    die "Could not retrieve $url";
  }

  my $tree = HTML::TreeBuilder->new;
  eval { $tree->parse($content); };
  if ($@) {
    die "$url parse failed, $@";
  }

  my @as = $tree->find_by_tag_name('a');

  foreach my $a (@as) {
    my $dir = $a->as_trimmed_text();
    # H 303 255   r   a   d 303 263       2   1   2   0   1   0  
    $dir=~s/H\303\255rad\303\263\s+21\s+\d+\s//;
    my $video_src="";
    my $video_date="";

    if($a->attr('href')=~/videoview_src=(\S+)\&/) {
      $video_src=$1;
    }
    if($a->attr('href')=~/videoview_date=(\d+)/) {
      $video_date=$1;
    }

    if($video_date=~/(\d\d\d\d)(\d\d)(\d\d)/) {

      my $dt=DateTime->new(year=>$1,month=>$2,day=>$3,
                 hour=>21,minute=>00,second=>00,
                 nanosecond=>500000000,time_zone=>'Europe/Budapest');

      $video_created=sprintf("%s, %02d %s %04d %02d:%02d:%02d GMT",
        $dt->day_abbr,$dt->day,$dt->month_abbr,$dt->year,
        $dt->hour,$dt->minute,$dt->second
        );
    } else {
      $video_created="Thu, 17 Dec 2009 22:00:00 GMT";
    }

    $video_src=~s/date/$video_date/;

    my $video_link=cleantext($baseurl.$video_src);

    if($dir=~/^\s*$/) {
      #http://www.hirtv.hu/?tPath=/view/videoview/hirado&amp;sp=Offer/?tPath=/view/videoview/hirado&sp=Video&videoview_src=/filmek/hirado21/hiradodate.wmv&videoview_date=20100612
      # http://www.hirtv.hu/filmek/hirado21/hirado20100616.wmv

      $dirdates{'mai hirek'}=$video_created;
      $dirurls{'mai hirek'} = $video_link;
    } else {
      $dirdates{$dir}=$video_created;
      $dirurls{$dir} = $video_link;
    }
                }
    #print STDERR Dumper(%dirurls);
    (keys(%dirurls)) or die "No urls found";

    #return \%dirurls;

    my @dirs=keys %dirurls;

    my $nresults=$#dirs+1;

    print "<channel>
  <title>$site</title>
  <link>$cleanurl</link>
  <description>$description</description>
  <numresults>$nresults</numresults>
  <returned>$nresults</returned>
  <startindex>1</startindex>
  <directory name=\"Hirado 21 News\" thumbnail=\"%SHAREDIR%/mythnetvision/icons/mythtv.png\">
";

    foreach my $dir (sort (keys %dirurls)) {
      print "
  <item>
    <title>$dir</title>
    <author>HirTV</author>
    <pubDate>$dirdates{$dir}</pubDate>
    <description>Nightly News (debug URL) $dirurls{$dir}</description>
    <link>$dirurls{$dir}</link>
    <player>/usr/bin/cvlc</player>
    <playerargs>-f %URL%</playerargs>
    <media:group>
      <media:content url=\"%URL%\"/>
      <media:thumbnail url=\"%SHAREDIR%/mythnetvision/icons/hirtv.png\"/>
    </media:group>
    <rating>>5.0</rating>
  </item>
";

    }
  print "  </directory>\n";
  print "</channel>\n";

}

sub cleantext {
        my $text = shift;

        ($text) or return;
        $text =~ s/\n/ /g;
        $text =~ s/^\s+|\s+$//g;
        $text = encode_entities($text);
        return $text;
}