Created
August 21, 2012 17:27
-
-
Save skaji/3417549 to your computer and use it in GitHub Desktop.
Image Download
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 strict; | |
use warnings; | |
use Encode qw{encode_utf8 decode_utf8}; | |
use utf8; | |
use LWP::UserAgent; | |
use HTTP::Request; | |
use Digest::MD5 qw/md5_hex/; | |
use Path::Class qw/dir file/; | |
use URI; | |
use JSON qw{decode_json}; | |
use AnyEvent; | |
use AnyEvent::HTTP; | |
use Term::ANSIColor; | |
my $query = @ARGV ? $ARGV[0] : 'AKB48'; | |
my $account_key = 'ACCOUNT KEY'; | |
my $url = URI->new('https://api.datamarket.azure.com/Bing/Search/Image'); | |
my $ua = LWP::UserAgent->new; | |
my $page_count = 0; | |
my $download_count = 0; | |
my $dir = dir("./data"); | |
my $interval = 50; | |
$dir->mkpath if ! -d $dir; | |
STDOUT->autoflush(1); | |
while (1) { | |
my $skip = $page_count * $interval; | |
$url->query_form( | |
'Query' => qq{'$query'}, | |
'$top' => $interval, | |
'$skip' => $skip, | |
'$format' => 'json', | |
); | |
my $req = HTTP::Request->new(GET => $url); | |
$req->authorization_basic('', $account_key); | |
my $res = $ua->request($req); | |
die $res->status_line if !$res->is_success; | |
my $json = decode_json $res->content; | |
last if !defined $json->{d}{results}; | |
my $cv = AnyEvent->condvar; | |
my $stopper = AnyEvent->timer( | |
after => 60, | |
cb => sub { $cv->send } | |
); | |
my $begin_download_count = $download_count; | |
for my $entry (@{ $json->{d}{results} }) { | |
my $media_url = $entry->{MediaUrl}; | |
next unless $media_url =~ /\.jpg$/; | |
my $filename = md5_hex(encode_utf8($media_url)) . '.jpg'; | |
my $filepath = $dir->file($filename); | |
next if -f $filepath; | |
$download_count++; | |
http_get_event($cv, $media_url, $filepath, $download_count); | |
} | |
$cv->recv if $download_count != $begin_download_count; | |
print colored("[$download_count done]\n", 'green'); | |
$page_count++; | |
} | |
sub http_get_event { | |
my ($cv, $media_url, $filepath, $download_count) = @_; | |
$cv->begin; | |
http_get($media_url, sub { | |
my ($body, $header) = @_; | |
if ($header->{Status} =~ /\A2/ | |
&& $header->{'content-type'} =~ m{\Aimage}) { | |
open my $fh, '>:raw', $filepath or die $!; | |
print {$fh} $body; | |
close $fh; | |
print "$download_count:finished $media_url\n"; | |
} | |
$cv->end; | |
}); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment