Created
November 19, 2011 22:47
-
-
Save sekia/1379481 to your computer and use it in GitHub Desktop.
Scrapes table of japanese traditional colors on colordic.org and dumps color name / RGB value mappings as YAML
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
#!/usr/bin/env perl | |
use 5.014; | |
use strict; | |
use warnings; | |
use Carp; | |
use Encode; | |
use Furl; | |
use Web::Scraper; | |
use YAML::Any; | |
my $dic_url = shift // 'http://www.colordic.org/w/'; | |
sub trim(_) { | |
shift =~ s/^\s+|\s+$//gr; | |
} | |
sub parse_html_color_code(_) { | |
my $code = shift; | |
unless ($code =~ /^#(?:[0-9a-f]{3}|[0-9a-f]{6})$/i) { | |
croak "Unknown format: $code"; | |
} | |
$code =~ s/^#//; | |
map { hex } do { | |
given (length $code) { | |
when (3) { map { $_ x 2 } split //, $code; } | |
when (6) { $code =~ /([0-9a-f]{2})/gi; } | |
} | |
}; | |
} | |
my $color_list_scraper = scraper { | |
process '.colortable td', 'colors[]' => scraper { | |
process 'a', 'href' => '@href', 'name_and_code' => '@title', | |
'reading' => scraper { process 'span', 'reading' => 'TEXT' }; | |
}; | |
}; | |
my $res = Furl->new->get($dic_url); | |
my $scraped = $color_list_scraper->scrape(decode_utf8 $res->content); | |
my %colors; | |
for my $color (@{ $scraped->{colors} }) { | |
my ($kanji_name, $html_code) = split /\s+/, trim $color->{name_and_code}; | |
my $reading = $color->{reading}{reading}; | |
$colors{$kanji_name, $reading} = [parse_html_color_code $html_code]; | |
} | |
say encode_utf8 Dump(\%colors); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment