-
-
Save henrik/812918 to your computer and use it in GitHub Desktop.
# Google Art Project fullsize image downloader. | |
# By Henrik Nyh <http://henrik.nyh.se> 2011-02-05 under the MIT license. | |
# Requires Ruby and ImageMagick. | |
# | |
# NOTE: | |
# I'm afraid this script no longer works! See the Gist comments. | |
# | |
# Usage e.g.: | |
# ruby google_art_project.rb http://www.googleartproject.com/museums/tate/portrait-of-william-style-of-langley-174 | |
# | |
# You can specify multiple URLs on the command line, separated by space. | |
# Or you can specify no URLs on the command line and instead list them at the end of this file, one on each line, | |
# with "__END__" before the list. | |
# | |
# On OS X, it sets "Downloaded from" metadata and reveals in Finder. | |
# | |
# Can reportedly run on Windows as well, with Ruby from http://www.ruby-lang.org/en/downloads/ | |
# and ImageMagick from http://www.imagemagick.org/script/binary-releases.php#windows | |
# Note that you may need to edit the TEMP_DIRECTORY/OUTPUT_DIRECTORY below. | |
require "open-uri" | |
require "fileutils" | |
require "rbconfig" | |
module Kernel | |
def windows? | |
Config::CONFIG['host_os'].match(/mswin|windows|mingw/i) | |
end | |
end | |
class GAPDownloader | |
# Set this to "jpg" or "tif". | |
# jpg is a lot smaller but destructively compressed. | |
OUTPUT_EXTENSION = "jpg" | |
if windows? | |
# Case-sensitive. Use forward slashes, or double-escape backslashes. | |
TEMP_DIRECTORY = "C:/WINDOWS/Temp" | |
OUTPUT_DIRECTORY = TEMP_DIRECTORY | |
else | |
TEMP_DIRECTORY = "/tmp" | |
OUTPUT_DIRECTORY = "#{ENV['HOME']}/Downloads" | |
FileUtils.mkdir_p OUTPUT_DIRECTORY | |
end | |
# You can lower this if you get ridiculously high-res images otherwise. | |
MAX_ZOOM_ALLOWED = 10 | |
class RuntimeError < StandardError; end | |
def initialize(url) | |
ensure_image_magick! | |
@url = url | |
verify_url! | |
end | |
def download | |
get_image_id | |
determine_zoom | |
get_tiles | |
stitch_tiles | |
trim | |
set_metadata | |
done | |
end | |
private | |
def ensure_image_magick! | |
if !windows? && `which montage`.empty? | |
error "You must have ImageMagick installed. Could not find 'montage' in your PATH." | |
end | |
end | |
def verify_url! | |
unless @url.to_s.match(%r{\Ahttp://www\.googleartproject\.com/}) | |
error "Please specify a Google Art Project URL." | |
end | |
end | |
def get_image_id | |
@html = open(@url).read | |
# Reportedly the data-thumbnail can change in the middle of a long download session, but | |
# the encodedInfospotId will not. So if we key local files by the InfospotId, we can | |
# check for them if download fails and we start over. Also makes for more human names. | |
# If I run into it myself, I may adapt the code to auto-resolve a changed data-thumbnail. | |
@thumb_id = @html[/data-thumbnail="(.+?)"/, 1] | |
@perma_id = @html[/data-encodedInfospotId="(.+?)"/, 1] | |
unless @thumb_id && @perma_id | |
error "Couldn't find an image at this URL, sorry!" | |
end | |
end | |
def determine_zoom | |
0.upto(MAX_ZOOM_ALLOWED) do |zoom| | |
open(tile_url(0, 0, zoom)) | |
@max_zoom = zoom | |
end | |
rescue OpenURI::HTTPError => e | |
raise unless e.message == "404 Not Found" | |
end | |
def get_tiles | |
@max_x = 999 | |
@max_y = 999 | |
0.upto(@max_y) do |y| | |
0.upto(@max_x) do |x| | |
url = tile_url(x, y, @max_zoom) | |
path = tile_path(x, y) | |
if File.exists?(path) | |
puts "Skipping #{url} (already downloaded)..." | |
next | |
end | |
begin | |
data = open(url) # Raises at 404. | |
puts "Getting #{url}..." | |
File.open(path, "wb") { |f| f.print data.read } | |
rescue OpenURI::HTTPError => e | |
raise unless e.message == "404 Not Found" | |
if y.zero? | |
# Found max x. Start on next row. | |
@max_x = x - 1 | |
break | |
else | |
# Found max y. We have all tiles, so bail. | |
@max_y = y - 1 | |
return | |
end | |
end | |
end | |
end | |
end | |
def stitch_tiles | |
# `montage` is ImageMagick. | |
# We first stitch together the tiles of each row, then stitch all rows. | |
# Stitching the full image all at once can get extremely inefficient for large images. | |
tiles_wide = @max_x + 1 | |
tiles_high = @max_y + 1 | |
puts "Stitching #{tiles_wide} x #{tiles_high} = #{tiles_wide*tiles_high} tiles..." | |
0.upto(@max_y) do |y| | |
tiles = (0..@max_x).map { |x| tile_path(x, y) }.join(' ') | |
`montage #{tiles} -geometry +0+0 -tile #{tiles_wide}x1 #{row_path(y)}` | |
end | |
tiles = (0..@max_y).map { |y| row_path(y) }.join(' ') | |
`montage #{tiles} -geometry +0+0 -tile 1x#{tiles_high} #{full_path}` | |
end | |
def trim | |
# Trim the black blocks that may appear on right and bottom. | |
# We first add a black border to ensure no other color is trimmed, as described on | |
# http://www.imagemagick.org/Usage/crop/#trim | |
`convert #{full_path} -bordercolor black -border 1x1 -trim #{full_path}` | |
end | |
def set_metadata | |
# 300 DPI instead of 72 DPI; more sane for printing. | |
`convert #{full_path} -density 300 #{full_path}` | |
if !windows? && !`which xattr`.empty? | |
# Set "Downloaded from" Finder metadata, like Safari does. | |
system('xattr', '-w', 'com.apple.metadata:kMDItemWhereFroms', @url, full_path) | |
end | |
end | |
def done | |
puts "Done: #{full_path}" | |
# Reveal in Finder if on OS X. | |
unless windows? | |
`which osascript && osascript -e 'tell app "Finder"' -e 'reveal POSIX file "#{full_path}"' -e 'activate' -e 'end'` | |
end | |
end | |
def error(message) | |
raise GAPDownloader::RuntimeError, "#{message} (#{@url})" | |
end | |
def tile_url(x, y, zoom) | |
# The subdomain can seemingly be anything from lh3 to lh6. | |
"http://lh5.ggpht.com/#{@thumb_id}=x#{x}-y#{y}-z#{zoom}" | |
end | |
def tile_path(x, y) | |
File.join(TEMP_DIRECTORY, "gap-#{@perma_id}-tile-#{x}-#{y}.jpg") | |
end | |
def row_path(y) | |
File.join(TEMP_DIRECTORY, "gap-#{@perma_id}-row-#{@max_zoom}-#{y}.#{OUTPUT_EXTENSION}") | |
end | |
def full_path | |
File.join(OUTPUT_DIRECTORY, "#{@perma_id}.#{OUTPUT_EXTENSION}") | |
end | |
end | |
if __FILE__ == $0 | |
urls = ARGV.any? ? ARGV : (defined?(DATA) ? DATA.read.strip.split("\n") : []) | |
puts "Error: No URLs given!" if urls.empty? | |
urls.each do |url| | |
begin | |
GAPDownloader.new(url).download | |
rescue GAPDownloader::RuntimeError => e | |
puts "Error: #{e.message}" | |
end | |
end | |
end |
Unfortunately all these "torrent" or "emule" images are small, nothing like "The bedroom" or "Starry Night" on Google Art Project. The quality that I got of these images is insane! I can print a wall mural with it and still it looks crisp and sharp. But I guess it depends on what you want to do with the images. If it's for computer screen wallpaper than it's fine, but definitely not suitable for high rez printing (well maybe for a post stamp size ;)
Flolan, did you get any decent sizes of these images from emule? Decent, I mean approx 5000px X 7000px?
I was definitely hoping to get at least 80 MP for a nice large sized print. However, it is true that only a handful of images are above about 20 MP. At this point, the torrent is basically dead, since there are no seeders, and I am downloading at 4kbs (8 mb of 3 gigs total). If anyone still has this torrent on their computer, it would be great if you could seed it.
My internet connection is on my weak computer, so I was waiting to download the high res that were bogging down my processor (Like Rembrant's The Prodigal Son). It would be great if someone could take the initiative to start another torrent with just the high res images to complete the other one. We could do our best to keep it going for a while (personally, my internet is intermittent).
PS - for absolute clarity, the current torrent is "google-art-public-domain.zip", with 928 images if I remember correctly.
Hi BillTheGoat
Please, send for me url about torrent and Uffizi website. i researching.
Thanks
Hi all, i see in file flash project add lines code:
// package hurlant
// package crypto
// package hash
// class HMAC
package com.hurlant.crypto.hash
{
import flash.utils.*;
public class HMAC extends Object
{
public function HMAC(arg1:com.hurlant.crypto.hash.IHash, arg2:uint=0)
{
super();
this.hash = arg1;
this.bits = arg2;
return;
}
public function getHashSize():uint
{
if (bits != 0)
{
return bits / 8;
}
return hash.getHashSize();
}
public function dispose():void
{
hash = null;
bits = 0;
return;
}
public function compute(arg1:flash.utils.ByteArray, arg2:flash.utils.ByteArray):flash.utils.ByteArray
{
var loc1:*=null;
var loc2:*=null;
var loc3:*=null;
var loc4:*=0;
var loc5:*=null;
var loc6:*=null;
if (arg1.length > hash.getInputSize())
{
loc1 = hash.hash(arg1);
}
else
{
loc1 = new flash.utils.ByteArray();
loc1.writeBytes(arg1);
}
while (loc1.length < hash.getInputSize())
{
loc1[loc1.length] = 0;
}
loc2 = new flash.utils.ByteArray();
loc3 = new flash.utils.ByteArray();
loc4 = 0;
while (loc4 < loc1.length)
{
loc2[loc4] = loc1[loc4] ^ 54;
loc3[loc4] = loc1[loc4] ^ 92;
++loc4;
}
loc2.position = loc1.length;
loc2.writeBytes(arg2);
loc5 = hash.hash(loc2);
loc3.position = loc1.length;
loc3.writeBytes(loc5);
loc6 = hash.hash(loc3);
if (bits > 0 && bits < 8 * loc6.length)
{
loc6.length = bits / 8;
}
return loc6;
}
public function toString():String
{
return "hmac-" + (bits > 0 ? bits + "-" : "") + hash.toString();
}
internal var bits:uint;
internal var hash:com.hurlant.crypto.hash.IHash;
}
}
// class IHash
package com.hurlant.crypto.hash
{
import flash.utils.*;
public interface IHash
{
function toString():String;
function getHashSize():uint;
function getInputSize():uint;
function hash(arg1:flash.utils.ByteArray):flash.utils.ByteArray;
}
}
// class SHA1
package com.hurlant.crypto.hash
{
public class SHA1 extends com.hurlant.crypto.hash.SHABase implements com.hurlant.crypto.hash.IHash
{
public function SHA1()
{
super();
return;
}
internal function ft(arg1:uint, arg2:uint, arg3:uint, arg4:uint):uint
{
if (arg1 < 20)
{
return arg2 & arg3 | !arg2 & arg4;
}
if (arg1 < 40)
{
return arg2 ^ arg3 ^ arg4;
}
if (arg1 < 60)
{
return arg2 & arg3 | arg2 & arg4 | arg3 & arg4;
}
return arg2 ^ arg3 ^ arg4;
}
internal function kt(arg1:uint):uint
{
return arg1 < 20 ? 1518500249 : arg1 < 40 ? 1859775393 : arg1 < 60 ? 2400959708 : 3395469782;
}
public override function toString():String
{
return "sha1";
}
public override function getHashSize():uint
{
return HASH_SIZE;
}
internal function rol(arg1:uint, arg2:uint):uint
{
return arg1 << arg2 | arg1 >>> 32 - arg2;
}
protected override function core(arg1:Array, arg2:uint):Array
{
var loc1:*=null;
var loc2:*=0;
var loc3:*=0;
var loc4:*=0;
var loc5:*=0;
var loc6:*=0;
var loc7:*=0;
var loc8:*=0;
var loc9:*=0;
var loc10:*=0;
var loc11:*=0;
var loc12:*=0;
var loc13:*=0;
var loc14:*=0;
arg1[arg2 >> 5] = arg1[arg2 >> 5] | 128 << 24 - arg2 % 32;
arg1[(arg2 + 64 >> 9 << 4) + 15] = arg2;
loc1 = [];
loc2 = 1732584193;
loc3 = 4023233417;
loc4 = 2562383102;
loc5 = 271733878;
loc6 = 3285377520;
loc7 = 0;
while (loc7 < arg1.length)
{
loc8 = loc2;
loc9 = loc3;
loc10 = loc4;
loc11 = loc5;
loc12 = loc6;
loc13 = 0;
while (loc13 < 80)
{
if (loc13 < 16)
{
loc1[loc13] = arg1[loc7 + loc13] || 0;
}
else
{
loc1[loc13] = rol(loc1[loc13 - 3] ^ loc1[loc13 - 8] ^ loc1[loc13 - 14] ^ loc1[loc13 - 16], 1);
}
loc14 = rol(loc2, 5) + ft(loc13, loc3, loc4, loc5) + loc6 + loc1[loc13] + kt(loc13);
loc6 = loc5;
loc5 = loc4;
loc4 = rol(loc3, 30);
loc3 = loc2;
loc2 = loc14;
++loc13;
}
loc2 = loc2 + loc8;
loc3 = loc3 + loc9;
loc4 = loc4 + loc10;
loc5 = loc5 + loc11;
loc6 = loc6 + loc12;
loc7 = loc7 + 16;
}
return [loc2, loc3, loc4, loc5, loc6];
}
public static const HASH_SIZE:int=20;
}
}
// class SHABase
package com.hurlant.crypto.hash
{
import flash.utils.*;
public class SHABase extends Object implements com.hurlant.crypto.hash.IHash
{
public function SHABase()
{
super();
return;
}
public function getHashSize():uint
{
return 0;
}
public function toString():String
{
return "sha";
}
public function getInputSize():uint
{
return 64;
}
public function hash(arg1:flash.utils.ByteArray):flash.utils.ByteArray
{
var loc1:*=0;
var loc2:*=null;
var loc3:*=0;
var loc4:*=null;
var loc5:*=0;
var loc6:*=null;
var loc7:*=null;
var loc8:*=0;
loc1 = arg1.length;
loc2 = arg1.endian;
arg1.endian = flash.utils.Endian.BIG_ENDIAN;
loc3 = loc1 * 8;
while (arg1.length % 4 != 0)
{
arg1[arg1.length] = 0;
}
arg1.position = 0;
loc4 = [];
loc5 = 0;
while (loc5 < arg1.length)
{
loc4.push(arg1.readUnsignedInt());
loc5 = loc5 + 4;
}
loc6 = core(loc4, loc3);
loc7 = new flash.utils.ByteArray();
loc8 = getHashSize() / 4;
loc5 = 0;
while (loc5 < loc8)
{
loc7.writeUnsignedInt(loc6[loc5]);
++loc5;
}
arg1.length = loc1;
arg1.endian = loc2;
return loc7;
}
protected function core(arg1:Array, arg2:uint):Array
{
return null;
}
}
}
It is not future proof, but it should be a bit faster than the torrent and has images at high resolution:
http://commons.wikimedia.org/wiki/Category:Google_Art_Project
Hi Parkjisun,
So what exactly your code does? How can I use it? Does it work on Google Art Project?
Actually Google has now a hmac hash appended to the URL. This HMAC is generated like this:
data: "[perma_id]=x[x pos]-y[y pos]-z[zoom level]-t[timestamp from xml]"
hash: hash_hmac('sha1', secret_key, data)
hash: hash.base64Encode.replace(/-/, '_')
hash: hash.substr(0, 27)
url: image_url + "-t" + hash
Well that's the easy part. To create the secret key they use an embedded google PNG logo and compute some stuff from some of its pixel colors. I'm personnally too busy/tired to rewrite the AS3 code in PHP/Ruby, but here it is in case someone's interested:
This function generates two bytearrays which are used after:
public static function initLogo(arg1:flash.utils.ByteArray, arg2:flash.utils.ByteArray):void
{
var loc2:*;
loc2 = 0;
var loc1:*;
loc1 = new GoogleLogo(); // returns bitmapdata of embedded google logo
var loc3:*;
loc3 = 1;
while (loc3 <= 6)
{
loc2 = loc1.bitmapData.getPixel(0, loc3);
arg1.writeByte(loc2 >> 16);
if (loc3 != 6)
{
arg1.writeByte(loc2 >> 8);
arg1.writeByte(loc2);
}
++loc3;
}
loc3 = 6;
while (loc3 <= 11)
{
loc2 = loc1.bitmapData.getPixel(0, loc3);
if (loc3 != 6)
{
arg2.writeByte(loc2 >> 16);
}
arg2.writeByte(loc2 >> 8);
if (loc3 != 11)
{
arg2.writeByte(loc2);
}
++loc3;
}
return;
}
This function takes the two byte arrays and make the secret key:
public function getLogChannel(arg1:flash.utils.ByteArray):void
{
var loc1:*;
loc1 = 8;
while (loc1 < 16)
{
arg1[(loc1 - 8)] = this.logChannelA[loc1] * 47 ^ this.logChannelB[loc1];
++loc1;
}
return;
}
The Google logo is here: http://i.kd2.org/i/34/6j9OHv5lP.google-logo.png
Actually I tried to rewrite this in PHP but I failed, I don't really use AS3, so ByteArray is a bit new for me, but maybe I'm missing some stuff.
hello,
i am new to osx and the terminal. anyway i installed ruby, imagemagick and xcode. i still got an error message using this script:
/System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:277:in open_http': 403 Forbidden (OpenURI::HTTPError) from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:616:in
buffer_open'
from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:164:in open_loop' from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:162:in
catch'
from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:162:in open_loop' from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:132:in
open_uri'
from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:518:in open' from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:30:in
open'
from google_art_project.rb:94:in determine_zoom' from google_art_project.rb:93:in
upto'
from google_art_project.rb:93:in determine_zoom' from google_art_project.rb:57:in
download'
from google_art_project.rb:206
from google_art_project.rb:204:in `each'
from google_art_project.rb:204
Can anyone help me please?
Thanks in advance
@Flapomat I'm afraid this script doesn't work any more due to changes on Google's side.
What a pity. Do you know any other possibility to get the pictures in high res?
Can sadly confirm, also got HTTP 403:
user@MACHINE: /Applications/GoogleArtProject.RB/gist812918-0f80614973e377e34f3355130b6b8ae678b418b8 $ ruby google_art_project.rb http://www.googleartproject.com/museums/tate/portrait-of-william-style-of-langley-174
/System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:277:in open_http': 403 Forbidden (OpenURI::HTTPError) from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:616:in
buffer_open'
from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:164:in open_loop' from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:162:in
catch'
from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:162:in open_loop' from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:132:in
open_uri'
from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:518:in open' from /System/Library/Frameworks/Ruby.framework/Versions/1.8/usr/lib/ruby/1.8/open-uri.rb:30:in
open'
from google_art_project.rb:94:in determine_zoom' from google_art_project.rb:93:in
upto'
from google_art_project.rb:93:in determine_zoom' from google_art_project.rb:57:in
download'
from google_art_project.rb:206
from google_art_project.rb:204:in `each'
from google_art_project.rb:204
hello, anyone can give some pictures who have downloaded from google project. i will be more thanks.and i really need it . many thanks
need help !!!
Hello, im running a Windows 7 64bit on Intel Core 2 Duo 4GB Ram Memory.
After installing Ruby and ImageMagick I run the command prompt and keep getting:
"Error: Could't find an image at this URL, sorry!"
Do you think you can help me over this?
Best Regards,
Paulo.
GAP website has changed again, and is now fully in JS.
NOWADAYS THIS SCRIPT DOES NOT WORK FOR ME. WHAT IS THE REASON?
I AM IN WINDOWS XP AND HERE IS THE ERROR MESSAGE: COULDN`T FIND AND IMAGE AT THIS URL SORRY
Again, this script no longer works. Emelyanenko Kirill mailed me about a script that is supposed to work, though: https://github.com/EmelyanenkoK/GAPDownloader Haven't tried it myself.
Hi henrik,
I try your code on Mac Lion and I get error urllib2.HTTPError: HTTP Error 403: Forbidden:
'''felixmatoMacBook-Pro:EmelyanenkoK-GAPDownloader-41f7003 felix$ python extractionGoogleArtProject_Unix.py
(http://www.googleartproject.com/collection/moma-the-museum-of-modern-art/artwork/the-starry-night-vincent-van-gogh/320268/)
BZ/7D6G3mWJ+JNvVDnZV/jcxS+E=
(http://lh6.ggpht.com/JFp6OJr9g8KABxRwCpABRdfc0Od2SQsguNwtn0qhvOkxkeFYZhQGrg=x0-y0-z4-tBZ_7D6G3mWJ_JNvVDnZV_jcxS_E)
Traceback (most recent call last):
File "extractionGoogleArtProject_Unix.py", line 290, in
telechargerOeuvre(i[0], i[1], i[2])
File "extractionGoogleArtProject_Unix.py", line 255, in telechargerOeuvre
telechargerTableau(urlImage, normaliserNomFichier(nomFichierImage), zoom)
File "extractionGoogleArtProject_Unix.py", line 215, in telechargerTableau
telechargerTousFragments(urlImage, xMax, yMax, zoom)
File "extractionGoogleArtProject_Unix.py", line 138, in telechargerTousFragments
telechargerFragment(urlImage, cheminFragment, x, y, zoom)
File "extractionGoogleArtProject_Unix.py", line 122, in telechargerFragment
contenuFragment = getContenuUrl(urlFragment, refererGoogleArtProject)
File "extractionGoogleArtProject_Unix.py", line 32, in getContenuUrl
return urllib2.urlopen(requete).read()
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 400, in open
response = meth(req, response)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 513, in http_response
'http', request, response, code, msg, hdrs)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 438, in error
return self._call_chain(_args)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 372, in _call_chain
result = func(_args)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 521, in http_error_default
raise HTTPError(req.get_full_url(), code, msg, hdrs, fp)
urllib2.HTTPError: HTTP Error 403: Forbidden
Hi henrik,
I try your code on Mac Lion and get error (urllib2.HTTPError: HTTP Error 403: Forbidden).
Detail:
felixmatoMacBook-Pro:EmelyanenkoK-GAPDownloader-41f7003 felix$ python extractionGoogleArtProject_Unix.py
(http://www.googleartproject.com/collection/moma-the-museum-of-modern-art/artwork/the-starry-night-vincent-van-gogh/320268/)
BZ/7D6G3mWJ+JNvVDnZV/jcxS+E=
(http://lh6.ggpht.com/JFp6OJr9g8KABxRwCpABRdfc0Od2SQsguNwtn0qhvOkxkeFYZhQGrg=x0-y0-z4-tBZ_7D6G3mWJ_JNvVDnZV_jcxS_E)
Traceback (most recent call last):
File "extractionGoogleArtProject_Unix.py", line 290, in
telechargerOeuvre(i[0], i[1], i[2])
File "extractionGoogleArtProject_Unix.py", line 255, in telechargerOeuvre
telechargerTableau(urlImage, normaliserNomFichier(nomFichierImage), zoom)
File "extractionGoogleArtProject_Unix.py", line 215, in telechargerTableau
telechargerTousFragments(urlImage, xMax, yMax, zoom)
File "extractionGoogleArtProject_Unix.py", line 138, in telechargerTousFragments
telechargerFragment(urlImage, cheminFragment, x, y, zoom)
File "extractionGoogleArtProject_Unix.py", line 122, in telechargerFragment
contenuFragment = getContenuUrl(urlFragment, refererGoogleArtProject)
File "extractionGoogleArtProject_Unix.py", line 32, in getContenuUrl
return urllib2.urlopen(requete).read()
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 126, in urlopen
return _opener.open(url, data, timeout)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 400, in open
response = meth(req, response)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 513, in http_response
'http', request, response, code, msg, hdrs)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 438, in error
return self._call_chain(_args)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 372, in _call_chain
result = func(_args)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/urllib2.py", line 521, in http_error_default
raise HTTPError(req.get_full_url(), code, msg, hdrs, fp)
urllib2.HTTPError: HTTP Error 403: Forbidden
Hi henrik, I try your new code on Mac Lion and get urllib2.HTTPError: HTTP Error 403: Forbidden.
Someone suggested this solution: http://www.student.tugraz.at/kollmitzer/gap_howto.html
or try gigafineart.heroku.com
gigafineart.heroku.com works, but does anybody know how they do it?
I'm kind of make it work, see a demo: https://www.dropbox.com/s/gih93ye4v1y6lsu/the_starry_night.jpg?dl=0
I am currently getting black canvases when downloading, and have seen comments of others getting the same
BillTheGoat, i don't understand. Please tell me more about uffizi. Thanks.
Henrik, but i see this link above
Exists: http://lh4.ggpht.com/lRLL2L2K767UgLi94FDOE7IRYj-tzfmdHjTb2PCE7AFT6iATF9uS8STnmy9GTw3i9Q5AuWg6XtQ=x0-y0-z0
is persist.
and if i change value at row 94: open(tile_url(0, 0, zoom)) from 0 -> 1 then script running but error at name tile.
Sorry if not properly, i am not a programmer.