Download Unsplash Collections

download_collections.py

import urllib2
import requests
import os 
import json
import sys

# Local Lib
from utils import progress, dirExists, unsplashURL, getCollectionPhotos

# Container
photos = []

# Counters
count = 0
i = 0

# Collections
collections = ["827807"]
collection_folder = True

# Select picture quality
q = ["raw", "full", "regular", "small", "thumb"]
quality = q[0]


if dirExists("photos") == False:
    os.mkdir("photos")

if len(collections) == 0:
    print("No collections available")
    os._exit(1)

for collection in collections:
    current_page = 1
    collection_counter = 0
    is_curated = len(collection) <= 3 and len(collection) > 0

    if is_curated:
        collection_url = unsplashURL("collections/curated/" + collection)
    else:
        collection_url = unsplashURL("collections/" + collection)

    res = requests.get(collection_url)
    col = res.json()
    
    total_photos = col["total_photos"]
   
    if collection_folder and dirExists("photos/" + col["title"]) == False:
        os.mkdir("photos/" + col["title"])
        
    while total_photos > collection_counter:
        response = requests.get( getCollectionPhotos(is_curated, collection, current_page) )
        print("Got: ", collection_counter, " items")

        data = response.json()

        count += len(data)
        collection_counter += len(data)
        current_page += 1

        for photo in data:
            id = photo["id"]
            download_url = photo["urls"]["raw"]

            photos.append({
                "id": id,
                "url": download_url,
                "collection": {
                    "id": collection,
                    "title": col["title"]
                }
            })


print("Preparing to download", len(photos), "photos")
for photo in photos:
    r = requests.get(photo["url"], allow_redirects=True)
    i+=1

    if collection_folder:
        path = "photos/" + photo["collection"]["title"] + "/" + photo["id"] + ".jpg"
    else:
        path = "photos/" + photo["id"] + ".jpg"

    open(path, "wb").write(r.content)

    progress(i, count, str(i) + " of " + str(count))

utils.py

import sys
import os
import threading
import requests
from Queue import Queue

def progress(count, total, status=''):
    bar_len = 60
    filled_len = int(round(bar_len * count / float(total)))

    percents = round(100.0 * count / float(total), 1)
    bar = '=' * filled_len + '-' * (bar_len - filled_len)

    sys.stdout.write('[%s] %s%s ...%s\r' % (bar, percents, '%', status))
    sys.stdout.flush()  # As suggested by Rom Ruben (see: http://stackoverflow.com/questions/3173320/text-progress-bar-in-the-console/27871113#comment50529068_27871113)


def dirExists(path):
    return os.path.isdir(path)

def unsplashURL(pathname, query=False):
    c_id = "4c29b3461e0cbb98c8f8cbb00fd13cffcfd7746f209b57097d1ffefa06fd352a"
    c_sec = "2b269ee625b6b60f35b1b7a01123bfcd7cc9201e2d8f5b568ced854a048fc569"

    if query:
        return "https://api.unsplash.com/" + pathname + "?client_id=" + c_id + "&client_secret=" + c_sec + "&" + query

    return "https://api.unsplash.com/" + pathname + "?client_id=" + c_id + "&client_secret=" + c_sec

  
def getCollectionPhotos (curated, collection, page = 1):
    if curated:
        return unsplashURL("collections/curated/" + collection + "/photos") + "&page=" + str(page)

    return unsplashURL("collections/" + collection + "/photos") + "&page=" + str(page)