view release on metacpan or  search on metacpan

DotCom.pm  view on Meta::CPAN

use HTML::Entities;
use HTML::TreeBuilder;
use LWP::Simple;

require Exporter;

our @ISA = qw(Exporter);

# Items to export into callers namespace by default. Note: do not export
# names by default without a very good reason. Use EXPORT_OK instead.
# Do not simply export all your public functions/methods/constants.

# This allows declaration	use Chess::Games::DotCom ':all';
# If you do not need this, moving things directly into @EXPORT or @EXPORT_OK
# will save memory.
our %EXPORT_TAGS = ( 'all' => [ qw(
	
) ] );

our @EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } );

our @EXPORT = qw(
	game_of_day puzzle_of_day
);

our $VERSION = '1.2';

our $home = 'http://www.chessgames.com';
my  $tb   = HTML::TreeBuilder->new;

# Preloaded methods go here.

my $ua;

sub _init_ua
{
    require LWP;
    require LWP::UserAgent;
    require HTTP::Status;
    require HTTP::Date;
    $ua = new LWP::UserAgent;  # we create a global UserAgent object
    my $ver = $LWP::VERSION = $LWP::VERSION;  # avoid warning
    $ua->agent("Mozilla/5.001 (windows; U; NT4.0; en-us) Gecko/25250101");
    $ua->env_proxy;
}

  
sub _get
{
    my $url = shift;
    my $ret;

    _init_ua() unless $ua;
    if (@_ && $url !~ /^\w+:/) 
      {
	  # non-absolute redirect from &_trivial_http_get
	  my($host, $port, $path) = @_;
	  require URI;
	  $url = URI->new_abs($url, "http://$host:$port$path");
      }
    my $request = HTTP::Request->new
      (GET => $url,
       
      );
    my $response = $ua->request($request);
    return $response->is_success ? $response->content : undef;
}

sub pgn_url {

  my $gid = shift;

  "http://www.chessgames.com/perl/nph-chesspgndownload?gid=$gid"
}

sub game_of_day {

    my $outfile = shift || "game_of_day.pgn";

    # retrieve http://www.chessgames.com

    my $html = get $home;

    # parse the page

    $tb->parse($html);

    my $god; # god == Game of the Day

    # make it so that text nodes are changed into nodes with tags
    # just like any other HTML aspect.
    # then they can be searched with look_down
    $tb->objectify_text;

    # Find the place in the HTML where Game of the Day is
    my $G = $tb->look_down
      (
       '_tag' => '~text',
       text   => 'Game of the Day'
      );

    my $table = $G->look_up
      (
       '_tag' => 'table',
      );

    my @tr = $table->look_down('_tag' => 'tr');

    my $god_tr = $tr[1];

    my $a = $god_tr->look_down('_tag' => 'a');

    # lets get the URL of the game
    my $game_url  = $a->attr('href');
    my ($game_id) = $game_url =~ m/(\d+)/;

    # let's get the game, faking out the web spider filter in the process:
    my $pgn       = _get pgn_url $game_id;

    # let's save it to disk
    open F, ">$outfile" or die "error opening $outfile for writing: $!";