Created
October 24, 2010 11:10
-
-
Save t-abe/643453 to your computer and use it in GitHub Desktop.
perl script to use weblio.jp's dictionary
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/perl | |
use strict; | |
use warnings; | |
use Web::Scraper; | |
use LWP::UserAgent; | |
use URI; | |
use URI::Escape; | |
use Encode; | |
use utf8; | |
binmode STDIN, ":utf8"; | |
binmode STDOUT, ":utf8"; | |
my $word = shift || die; | |
$word = decode utf8 => $word; | |
my $items = dictor($word); | |
if( !$items and ( $word =~ s/ies/y/ or $word =~ s/s$// ) ){ | |
dictor($word); | |
} | |
sub dictor { | |
my $word = shift; | |
my $uri = sprintf("http://ejje.weblio.jp/content/%s", uri_escape_utf8($word)); | |
#print $uri, "\n"; | |
#exit; | |
my $ua = LWP::UserAgent->new; | |
my $res = $ua->get($uri)->decoded_content || die; | |
# inherently | |
my $items = 0; | |
printf("*%s\n", $word); | |
while ( $res =~ m{<div class="?level(0|1|2)"?>((?:<div class=KnenjSub>.+?</div>)?.+?)</div>}g ) { | |
my $level = $1; | |
my $text = $2; | |
$text =~ s/<.*?>//g; | |
$text =~ s/[\r\n]//g; | |
print "\n" if $level == 0 and $items++ != 0; | |
print "\t" x ($level+1); | |
print $text, "\n"; | |
} | |
return $items; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment