[mythtv-users] tv_grab_au: ninemsn obfuscating data

[Michael Cowell]

Tj wrote:

>
> I think I just got past the look_down error.
>
> get_guide_page should look something like this.. i.e. the jz encoding 
> and the "<SCRIPT>" things should be done in this sub instead. yay!
>
> sub get_guide_page {
>  my $service = shift;
>  my $date = shift;
>  my $url = "$NMSN/guide/${date}_$service->{regionid}.asp?"
>    . "channel=$service->{name}" . MSID();
>  print "GET_GUIDE_PAGE($url)\n" if $debug;
>  my $page = get_page($url) or
>    print "Warning: Failed to get program listing for day $date\n";
>  if ( $page ) {
>    ++$count_guide;
>    $page =~ s/jz\('([^']+)'\);/jz($1)/eg;
>    $page =~ s/<SCRIPT src=\"dcr.js\"><\/SCRIPT><SCRIPT 
> Language=\"Javascript\">/""/eg;
>    $page =~ s/^<\/SCRIPT><NOSCRIPT>.*<\/NOSCRIPT>/""/eg;
>  }
>  return $page;
>
Here is a cleaner patch, with config that works. I think yours changes 
should work too.

Michael
-------------- next part --------------
*** tv_grab_au	Sat Aug 20 12:09:38 2005
--- tv_grab_au.new	Wed Nov  9 12:08:01 2005
***************
*** 218,223 ****
--- 218,224 ----
    for my $service (@{$conf->{services}}) {
  
      my $guidedata = get_guide_page($service, dmY($date6am)) or next;
+ 
      my $tree      = HTML::TreeBuilder->new_from_content($guidedata);
  
      for ($tree->look_down('_tag' => 'table', 'class' => 'tv')) {
***************
*** 257,262 ****
--- 258,266 ----
  	  my @link = @{ $e->extract_links() };
  	  die "too many links:\n" . $html if @link > 1;
  	  my $url = $NMSN . $link[0]->[0];
+           # NMSN people have some javascript to generate new links, with cu
+           # in them instead of closeup. This should fix that
+           $url =~ s/closeup/cu/;
  
  	  # --- check (pid, row, rowspan, title) against old cached data
  	  my $cache_id = "$date:$pid:$row:$rowspan:$title";
***************
*** 410,415 ****
--- 414,443 ----
    return $want;
  }
  
+ # --- wrapper for the deobfuscator
+ sub deobfuscate {
+   my ($input) = @_;
+   my $guidedata = $input;
+   # De-obfuscate
+   $guidedata =~ s/jz\('([^']+)'\);/jz($1)/eg;
+   # Also need to remove useless script headers
+   $guidedata =~ s/<SCRIPT src=\"dcr.js\"><\/SCRIPT><SCRIPT Language=\"Javascript\">/""/eg;
+   $guidedata =~ s/^<\/SCRIPT><NOSCRIPT>.*<\/NOSCRIPT>/""/eg;
+   return $guidedata;
+ }
+ 
+ # --- deobfuscator from jollygoodshow at hotmail.com contributed to 
+ #     mythuser list
+ sub jz {
+        my ($z) = @_;
+        my ($y);
+ 
+        $z =~ s/%(..)/chr(hex($1))/eg;
+        ($y = $z) =~ s/(.)/chr(ord($1) - 1)/eg;
+        $y =~ s/%(..)/chr(hex($1))/eg;
+        return $y;
+ }
+ 
  # --- get details from the closeup page for given show
  sub get_closeup_details {
  
***************
*** 577,582 ****
--- 605,611 ----
  	($page, $base) = with_progress
  	  ( "getting regionid and channels for service $service->{name}",
  	    sub { get_content_base("$TVTODAY?channel=$service->{name}") } );
+ 
  	$service->{region} = "Australia";
  	($service->{regionid})
  	  = $base =~ /_(\d+).asp/ or die "cannot find regionid";
***************
*** 691,696 ****
--- 720,726 ----
    my $url = shift;
    my $page = (get_content_base($url))[0];
    $page and $page =~ s/&nbsp;/ /g;
+   $page = deobfuscate($page);
    return $page;
  }