Created
October 8, 2010 21:45
-
-
Save ngs/617628 to your computer and use it in GitHub Desktop.
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 -w | |
use strict; | |
use warnings; | |
use FindBin; | |
use lib "$FindBin::Bin/lib"; | |
use Getopt::Compact; | |
use Erockr; | |
use URI::Escape; | |
use encoding "utf8"; | |
my $getopt = Getopt::Compact->new( | |
name => 'erockr.pl', | |
args => 'NAME', | |
version => '0.1', | |
modes => [], | |
struct => [ | |
[[qw|o out|], 'Directory to save photos.','=s'] | |
], | |
); | |
my $name; | |
unless($name=shift @ARGV) { | |
print STDERR $getopt->usage; | |
exit 1; | |
} | |
my $opts = $getopt->opts; | |
utf8::encode($name); | |
my $e = Erockr->new( | |
name => $name, | |
dir => ( $opts->{out} || $FindBin::Bin ) . "/dl/".$name | |
); | |
1 while($e->next); |
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
package Erockr; | |
use strict; | |
use warnings; | |
use URI; | |
use URI::Escape; | |
use Data::Dumper; | |
use Web::Scraper; | |
use File::Path qw/mkpath/; | |
use LWP::Simple; | |
use constant URL_FORMAT => 'http://erockr.com/archive/%s/%d/200/s'; | |
sub new { | |
my $class = shift; | |
my $self = bless { | |
page => 1, | |
@_ | |
}, $class; | |
mkpath $self->dir; | |
$self; | |
} | |
sub dir { $_[0]->{dir} } | |
sub name { $_[0]->{name} } | |
sub next { | |
my $self = shift; | |
my $url = sprintf(URL_FORMAT,uri_escape($self->name),$self->{page}++); | |
print $url,"\n"; | |
my $page = scraper { | |
process '#searchResultList a', 'results[]' => '@href', | |
process 'a[rel="next"]', next_page => '@href', | |
}; | |
my $res = $page->scrape( URI->new($url) ); | |
$self->get_image($_) foreach @{ $res->{results} }; | |
defined $res->{next_page} | |
} | |
sub get_image { | |
my $self = shift; | |
my $url = shift; | |
my $page = scraper { | |
process '#image img', 'src' => '@src', | |
}; | |
my $res = $page->scrape( URI->new($url) ); | |
$self->download($res->{src}); | |
} | |
sub download { | |
my $self = shift; | |
my $url = shift; | |
if( $url =~ m|.*/(.*)$|i ) { | |
my $file = $self->dir."/$1"; | |
print "$url -> $file\n"; | |
getstore($url,$file); | |
return 1; | |
} | |
0; | |
} | |
1; | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment