#!/usr/bin/env python
# coding: utf-8

# # Getting higher resolution versions of photos from the State Library of South Australia online collection interface
# 
# The State Library of South Australia makes a fabulous [collection of out of copyright photographs](https://www.slsa.sa.gov.au/photographs) available online. However, while you can zoom in using their collection interface to examine the details of many of these images, the download option seems to provide copies at a much lower resolution. This limits their usefulness for many types of research.
# 
# This notebook simply takes the tiled versions of the images which are displayed in the collection interface and stitches them together to create higher resolution versions.
# 
# For example, the version of [this photograph of Clement Wragge](https://collections.slsa.sa.gov.au/resource/B+43122) provided by the 'Download' button is 1024 x 787 pixels. The version created by this notebook is 5785 × 4337 pixels. 
# 
# Note that images available for download from the SLSA's [digital collections](https://digital.collections.slsa.sa.gov.au/) seem to be at a much higher resolution so don't need any special tricks to use.

# ## Setting things up
# 
# Run these cells using **Shift+Enter** to get the code ready to use.

# In[67]:


import requests
from PIL import Image
from io import BytesIO
from slugify import slugify
import re
from IPython.display import display, HTML, FileLink


# In[68]:


def get_json(url):
    '''
    Get the JSON file that includes information about the zoom levels and tiles.
    '''
    json_url = '{}/{}'.format(url.rstrip('/'), 'tiles.json')
    response = requests.get(json_url)
    data = response.json()
    return data

def get_highest_level(data):
    '''
    Find the highest level of zoom -- ie the biggest version of the image -- in the JSON data.
    '''
    for level in data['levels']:
        if level['name'] == 'z0':
            highest_zoom = level
            break
    return highest_zoom

def download_image(url):
    '''
    Provide a url of a digitised photos, and get back the largest possible version for download.
    Gets information about available zoom levels and tiles, then stitches the tiles together.
    '''
    # Get data about levels
    data = get_json(url)
    # Get the highest zoom level
    level = get_highest_level(data)
    # Dimensions of the biggest image
    w = level['width']
    h = level['height']
    # Create an empty image to paste the tiles into
    img = Image.new('RGB', (w, h))
    # Loop through all the tiles
    for index, tile in enumerate(level['tiles']):
        # Get a tile and open as an image
        response = requests.get(tile['url'])
        tile_img = Image.open(BytesIO(response.content))
        # When we've got the first tile, grab the height and width
        if index == 0:
            tile_w, tile_h = tile_img.size
        # The tile data includes an x and y index value indicating the position of the tile
        # To calculate it's coordinates, just multiply the index by the width/height
        x = tile['x'] * tile_w
        y = tile['y'] * tile_h
        # Paste the tile into the big image using the x/y coords to define the top left corner
        img.paste(tile_img, box=(x, y))
        id = re.search(r'resource\/(.*)', url).group(1)
    # Create file name that includes the image ID info
    image_name = 'slsa-{}.jpg'.format(slugify(id))
    # Save and display the image
    img.save(image_name)
    display(FileLink(image_name))
    display(HTML('<img src="{}">'.format(image_name)))


# ## Supply the URL of the photo
# 
# Just paste the url of the photo you want to download between the quotes in the cell below and run the cell using **Shift+Enter**. Once it has been created, the final image will be displayed below with a link for easy download.

# In[69]:


download_image('https://collections.slsa.sa.gov.au/resource/B+43122')


# In[ ]: