ドキュメントに同じid属性が複数あるという、なんともダイナミックなHTMLにもめげず作り上げたのが以下
#!/usr/bin/perl
use encoding 'utf-8';
use strict;
use warnings;
use Encode qw(from_to);
use URI;
use URI::Escape qw(uri_escape_utf8);
use Web::Scraper;
use YAML;
if ($^O eq 'MSWin32') {
binmode(STDERR, ':encoding(shift_jis)');
Encode::from_to($ARGV[0], 'cp932', 'utf-8');
}
my $talent = shift || '小島よしお';
my $talent_schedule = scraper {
process '//div[@class="find_bl"]/following-sibling::*[1]//td', day => 'TEXT';
process '//div[@class="find_bl"]/following-sibling::*[1]//td/div',
'schedule[]' => scraper {
process 'div', media => sub { my $m = $_->attr('class'); $m =~ s/^icon_//g; $m };
process '/div/a', url => '@href';
process '/div/a', title => 'TEXT';
process '/div/node()[1]', timespan => sub {
my $s = $_->string_value;
$s =~ s/ //;
$s =~ s/(^|[^\d])(\d):(\d\d)/0$2:$3/g;
my @span = split(/[^\d:]/, $s);
\@span;
};
};
result qw/day schedule/;
};
my $uri = URI->new('http://talent-schedule.jp/'.uri_escape_utf8($talent));
my $oppappi_schedule = $talent_schedule->scrape($uri);
warn Dump $oppappi_schedule;
ちょっと日付まわりで苦労してますが...小島よしおって、結構番組出てますねぇ。
でもそんなの関係ry)
