API tools faq
paste
Advertisement
moytrage

deviantart_downloader.pl

moytrage
Feb 28th, 2012
872
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Perl 5.85 KB | None | 0 0
raw download clone embed print report
  1. # A Downloader for DeviantArt.com galleries. Per author.
  2. # Either use: deviantart_downloader.pl authorname1 authorname2 authorname3 ...
  3. # Or put a list of authors into @authors variable down below like in example.
  4. # In case of problems see program's output (including download log in author's subdir).
  5. # You may send letters to user moytra at Google's gmail.com
  6.  
  7. our @authors = @ARGV ? @ARGV : qw(anry artgerm genzoman artgutierrez kerembeyit jenovah-art sandara yukiusagi1983 pierrerodriguez longai);
  8.  
  9. use strict;
  10. use warnings;
  11.  
  12. our $check_existing_image_integrity = 0; # If all existing images are rechecked for integrity
  13. our $check_downloaded_image_integrity = 0; # If to check integrity right after download
  14. our $auto_remove_corrupted = 1; # If true will automatically remove corrupted files and try redownload
  15. our $force_html_redownload = 0; # If to redownload html pages referring images every time
  16. our $download_images = 1; # If 0 images are not downloaded. Only pages...
  17. our $ignore_download_errors = 1; # If 1 if there's no file on server (happens), still proceed, don't die...
  18.  
  19. our $offset_limit = 9960; # To prevent infinitly downloading HTML pages in case of parsing errors, limit offset (max num of retrieved pages).
  20.  
  21. our $down_log = "down.log"; # Download log from wget.
  22. our $null_file = ":NUL"; # Put /dev/null on Unix.
  23.  
  24. sub mdir($) {
  25.     my $dir = shift;
  26.     mkdir "$dir" or die "Can't create dir [$dir]." unless -d "$dir";
  27. }
  28.  
  29. sub down($$$) {
  30.     my ($url, $file, $log) = @_;
  31.     print "[Download]";
  32.  
  33.     return (system ("wget -a $log \"$url\" -O $file") == 0);
  34. }
  35.  
  36. sub check_integrity($) {
  37.     my $fname = shift;
  38.     print "[IntegrityCheck]";
  39.     return system("identify -verbose -quiet -regard-warnings \"$fname\" 2>> $null_file 1>> $null_file") == 0;
  40. }
  41.  
  42. sub unique_merge_into($@) {
  43.     my ($fname, @links) = @_;
  44.  
  45.     my %all_links;
  46.  
  47.     if (-e "$fname") {
  48.         open my $flinks, "<$fname" or die "Can't read open [$fname].";
  49.         while (<$flinks>) {
  50.             next if /^\s*$/;
  51.             chomp;
  52.             $all_links{$_} = 1;
  53.         }
  54.         close $flinks;
  55.     }
  56.  
  57.     # Merge existing links with new ones. For history, if some images were removed.
  58.     $all_links{$_} = 1 for @links;
  59.  
  60.     {
  61.         open my $flinks, ">$fname" or die "Can't write open [$fname].";
  62.         print $flinks "$_\n" for sort keys %all_links;
  63.         close $flinks;
  64.     }
  65. }
  66.  
  67. print '*' x 40, "Start!", '*' x 40, "\n";
  68.  
  69. for my $author (@authors) {
  70.     print "-" x 40, "[$author]", "-" x 40, "\n";
  71.  
  72.     my $offset = 0;
  73.  
  74.     mdir("$author");
  75.     mdir("$author/pages");
  76.     mdir("$author/super");
  77.     mdir("$author/full");
  78.  
  79.     my $fetch_next_page = 1;
  80.     my @links;
  81.     my %all_found_images;
  82.  
  83.     PAGE_LOOP:
  84.     while ($fetch_next_page) {
  85.         # Each page equals 24 images
  86.  
  87.         die "Offset limit reached... Looks like infinite loop, something wrong with parsing HTML pages." if $offset >= $offset_limit;
  88.  
  89.         $fetch_next_page = 0;
  90.         my $url = "http://$author.deviantart.com/gallery/?offset=$offset";
  91.         my $fname = "$author/pages/offset_".sprintf("%04d", $offset).".html";
  92.  
  93.         print "[$fname]\n";
  94.  
  95.         my $html_existed_before = -e $fname;
  96.  
  97.         if (not -e $fname or $force_html_redownload) {
  98.             down($url, $fname, "$author/$down_log") or die "Can't download [$url] to [$fname].";
  99.         }
  100.        
  101.         open my $file, "<$fname" or die "Can't open for reading [$fname].";
  102.         my $text = do { local $/; <$file> };
  103.         close $file;
  104.  
  105.         unless ($text =~ /^\s*(<!DOCTYPE html>|<html>)/ and $text =~ /<\/html>\s*$/) {
  106.             if ($html_existed_before and $auto_remove_corrupted) {
  107.                 print "[!Corrupted!][Delete][Restart]\n";
  108.                 unlink($fname) or die "Can't delete [$fname].";
  109.                 redo PAGE_LOOP;
  110.             } else {
  111.                 die "Corrupted HTML page [$fname], please resolve manually.";
  112.             }
  113.         }
  114.  
  115.         print "[Parse]\n\n";
  116.  
  117.         $text =~ /id="gruze-main"/ or die "Can't find magic marker of main view in HTML. Maybe website has changed encoding...";
  118.         $text = substr($text, $-[0]);
  119.  
  120.         for my $full_link ($text =~ /<a class="thumb"[^>]*?>.*?<\/a>/g) {
  121.             $full_link =~ s/[\r\n]/ /g;
  122.             $full_link =~ /^(<a.*?>)/ or die "Can't extract first <a> tag from [$full_link].";
  123.             my $link = $1;
  124.             my %attrs = ($link =~ /(\w+)="(.*?)"/g);
  125.  
  126.             unless ($attrs{super_img}) {
  127.                 warn "Empty super_img in link [$link]. Usually always present at DeviantArt. Skipping...";
  128.                 next;
  129.             }
  130.  
  131.             my ($quality, $url) = exists $attrs{super_fullimg} ? ("f", $attrs{super_fullimg}) : ("s", $attrs{super_img});
  132.  
  133.             $attrs{href} =~ /^http:\/\/$author\.deviantart\.com\/art\/(.+)$/i or die "Can't parse [$attrs{href}].";
  134.             $1 =~ /^(.+?)-(\d+)$/ or die;
  135.             my $id_name = sprintf("${author}_%010d_${quality}_$1", $2);
  136.  
  137.  
  138.             # This is a guarantee of no inf loop. If no new images are found from the author, finish...
  139.             next if exists $all_found_images{$id_name};
  140.  
  141.             $all_found_images{$id_name} = $id_name;
  142.  
  143.             $url =~ /\.([a-z]+)$/ or die "Can't get file extension from url [$url].";
  144.             my $ftype = $1;
  145.             my $fname = "$author/".($quality eq "s" ? "super" : ($quality eq "f" ? "full" : die))."/$id_name.$ftype";
  146.  
  147.             print "\t[$fname]\n\t";
  148.  
  149.             if (-e $fname and $check_existing_image_integrity and not check_integrity($fname)) {
  150.                 print "[!Corrupted!]";
  151.                 if ($auto_remove_corrupted) {
  152.                     print "[Delete]";
  153.                     unlink($fname);
  154.                 } else {
  155.                     die "Auto-delete not allowed... Dying...";
  156.                 }
  157.             }
  158.  
  159.             if (not -e $fname and $download_images) {
  160.                 unless (down($url, $fname, "$author/$down_log")) {
  161.                     if ($ignore_download_errors) {
  162.                         print "[DownloadFailure][Skip]\n";
  163.                         next;
  164.                     } else {
  165.                         die "Can't download [$url].";
  166.                     }
  167.                 }
  168.  
  169.                 check_integrity($fname) or die "Corrupted image [$fname] after download! Please resolve..." if $check_downloaded_image_integrity;
  170.             }
  171.  
  172.             print "\n\n";
  173.             $fetch_next_page = 1;
  174.             push @links, $full_link;
  175.         }
  176.  
  177.         $offset += 24;
  178.     }
  179.  
  180.     unique_merge_into("$author/links.html", @links);
  181.     unique_merge_into("all_links.html", @links);
  182. }
  183.  
  184. print '*' x 40, "All Finished! :)", '*' x 40, "\n";
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!