Created
March 27, 2009 11:24
-
-
Save sasezaki/86649 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package WWW::Hanako; | |
use 5.010000; | |
use strict; | |
use warnings; | |
use Carp; | |
use LWP::UserAgent; | |
use WWW::Mechanize; | |
use Web::Scraper; | |
use Data::Dumper; | |
our @ISA = qw(); | |
our $VERSION = '0.05'; | |
my $HANAKO_BASE_URI = 'http://kafun.taiki.go.jp/'; | |
sub new | |
{ | |
my $proto = shift; | |
my $class = ref($proto) || $proto; | |
my $self = { | |
area => $_{area} || 0, | |
mst => $_{mst} || 0, | |
mech => WWW::Mechanize->new(agent=>"Net-Hanako/$VERSION"), | |
debug => 0, | |
}; | |
%$self = (%$self, @_); | |
bless($self, $class); | |
return $self; | |
} | |
sub today | |
{ | |
my $self = shift; | |
my @ret; | |
my $path = sprintf("Hyou0.aspx?MstCode=%d&AreaCode=%02d", | |
$self->{'mst'}, $self->{'area'}); | |
my $uri = $HANAKO_BASE_URI . $path; | |
my $uri2 = $HANAKO_BASE_URI . "Hyou2.aspx"; | |
if($self->{debug}){ | |
print "uri: $uri\n"; | |
print "uri2: $uri2\n"; | |
} | |
# set cookie | |
$self->{mech}->get($uri); | |
# get cookie | |
$self->{mech}->get($uri2); | |
if(!$self->{mech}->success()){ | |
carp("error"); | |
return; | |
} | |
if($self->{mech}->status() != 200){ | |
carp("response code: " . $self->{mech}->status()); | |
return; | |
} | |
my $content = $self->{mech}->content(); | |
my $col = scraper { | |
process '//td[1]','hour' => 'TEXT'; | |
process '//td[2]', 'pollen' => 'TEXT'; | |
process '//td[3]', 'wd' => 'TEXT'; | |
process '//td[4]', 'ws' => 'TEXT'; | |
process '//td[5]', 'temp' => 'TEXT'; | |
process '//td[6]', 'prec' => 'TEXT'; | |
process '//td[7]', 'prec_bool' => 'TEXT'; | |
result 'prec_bool', 'prec', 'temp', 'ws', 'wd','pollen', 'hour'; | |
}; | |
my $scraper = scraper { | |
process '//table[@id="dgd1"]//tr[position()!=1 and position() !=2]', 'row[]' => $col; | |
}; | |
my $ret = $scraper->scrape($content, $uri2); | |
if(!$ret->{"row"}){ | |
carp("scrape error"); | |
return; | |
} | |
return @{$ret->{'row'}}; | |
} | |
sub now | |
{ | |
my $self = shift; | |
my @today = $self->today(); | |
my $ret = pop(@today); | |
return $ret; | |
} | |
1; | |
use Data::Dumper; | |
my $hanako = WWW::Hanako->new(area=>3, mst=>51300200); | |
print Dumper($hanako->today()); | |
__END__ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment