Created
December 29, 2009 18:43
-
-
Save xaicron/265482 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 Web::Scraper; | |
| use URI; | |
| use WWW::Mechanize; | |
| use File::Basename qw/basename/; | |
| my $user_id = shift || die "Usage: $0 user_id [last_page_num]"; | |
| my $last_page = shift; | |
| #=============================================================================== | |
| my $uri_base = 'http://drawr.net/'; | |
| my $pre_load = scraper { | |
| process '//*[@class="pbooku"]/a/span[2]', num => 'TEXT'; | |
| process '//*[@class="pstaru"]/a', id => [ '@href', sub { /[?&]id=(\d+)$/; $1 } ]; | |
| }; | |
| my $scraper = scraper { | |
| process '//*[@class="entryAreaImg"]', 'list[]' => scraper { | |
| process 'a', id => [ '@href', sub { /[?&]id=(\d+)$|#rid(\d+)$/; $1 || $2 } ]; | |
| process 'a>img', url => [ '@src', sub { "$_" } ]; | |
| }; | |
| }; | |
| my $mech = WWW::Mechanize->new(autocheck => 1); | |
| #=============================================================================== | |
| &main();exit; | |
| sub main { | |
| mkdir $user_id or die "$user_id $!" unless -d $user_id; | |
| chdir $user_id or die "$user_id $!"; | |
| get_images(); | |
| } | |
| sub get_images { | |
| my $pre_res = pre_load(); | |
| die "Unkown" unless $pre_res->{num} && $pre_res->{id}; | |
| my $id = $pre_res->{id}; | |
| $last_page ||= int($pre_res->{num} / 10) + ($pre_res->{num} % 10 ? 1 : 0); | |
| for my $page (1..$last_page) { | |
| print "process page $page\n"; | |
| my $url = sprintf '%suser.php?id=%d&page=%d', $uri_base, $id, $page; | |
| $mech->get($url); | |
| my $res = $scraper->scrape($mech->content, $mech->uri); | |
| for my $img (@{$res->{list}}) { | |
| save_file($img->{id}, $img->{url}); | |
| $mech->add_header(Referer => $url); | |
| } | |
| } | |
| } | |
| sub pre_load { | |
| $mech->get($uri_base . $user_id); | |
| return $pre_load->scrape($mech->content, $mech->uri); | |
| } | |
| sub save_file { | |
| my $id = shift; | |
| my $url = shift; | |
| my $file_name = sprintf '%s_%s', $id, basename $url; | |
| print "skip $file_name\n" and return if -f $file_name; | |
| print "Download $file_name\n"; | |
| $mech->get($url); | |
| open my $fh, '>:raw', $file_name or die $!; | |
| print $fh $mech->content; | |
| close $fh; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment