csv of akb48 members

akb_members.pl

#!/usr/bin/perl

#
# by Keiya Chinen

use strict;
use Web::Scraper;
use URI;
use Data::Dumper;
use utf8;
$| = 1;

my %fetched;
my $url = 'http://www.google.com/intl/ja/+/project48/';
my $urle = $url;
$urle =~ s/([^\w ])/'%'.unpack('H2', $1)/eg;
$urle =~ tr/ /+/;
my %res = scrapeuri($url);
foreach my $id (keys %res) {
        print $res{$id}{id}.','.
        $res{$id}{name}.','.
        $res{$id}{type}."\n";
}

sub scrapeuri {
        my $scraper = scraper {
                process "/html/body/div[5]/ul/li", 'id[]' => '@data-gplusid';
                process "/html/body/div[5]/ul/li/a", 'name[]' => '@data-g-label';
                process "/html/body/div[5]/ul/li/a", 'type[]' => '@data-g-event';
        };
        my $link = $_[0];
        my $uri = new URI($link);
        print "scraping: $link\n";
        my $res = $scraper->scrape($uri);
        my %hash;
        my $i = 0;
        foreach my $tmp (@{$res->{id}}) {
                $hash{$tmp}{name} = $res->{name}[$i];
                $hash{$tmp}{type} = $res->{type}[$i];
                $hash{$tmp}{id} = $res->{id}[$i];
                $i++;
        }
        return %hash;
}

sub url_encode {
        my $str = shift;
        return $str;
}