Created
March 8, 2012 12:00
-
-
Save YuheiNakasaka/2000713 to your computer and use it in GitHub Desktop.
oppai
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
use strict; | |
use warnings; | |
use LWP::UserAgent; | |
use URI; | |
use JSON qw/decode_json/; | |
use Digest::MD5 qw/md5_hex/; | |
use Path::Class qw/dir file/; | |
use Encode; | |
use utf8; | |
my $appid = ''; | |
my $uri = URI->new('http://api.bing.net/json.aspx'); | |
my $ua = LWP::UserAgent->new; | |
my $dir = dir('./data'); | |
my $page_count = 0; | |
my $download_count = 0; | |
while(1){ | |
my $offset = $page_count*50; | |
$uri->query_form( | |
AppId =>$appid, | |
Version =>'2.2', | |
Markert =>'ja-JP', | |
Sources => 'image', | |
'Image.Count' =>50, | |
'Image.Offset' =>$offset, | |
Adult => 'off', | |
Query => 'おっぱい' | |
); | |
my $res = $ua->get($uri); | |
die $res->status_line if $res->is_error; | |
my $ref = decode_json($res->content); | |
last unless defined @{$ref->{SearchResponse}{Image}{Results}}; | |
for my $entry(@{$ref->{SearchResponse}{Image}{Results}}){ | |
next unless $entry->{MediaUrl} =~ /\.jpg$/; | |
$download_count++; | |
my $filename = md5_hex(encode_utf8($entry->{MediaUrl})).'.jpg'; | |
my $filepath = $dir->file($filename); | |
next if -f $filepath; | |
print encode_utf8("$download_count:Download...$entry->{MediaUrl}\n"); | |
$res = $ua->get($entry->{MediaUrl},':content_file'=> $filepath->stringify); | |
unless ($res->content_type =~ m/^image/){ | |
unlink $filepath; | |
} | |
} | |
$page_count++; | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment