Downloading Harvard ART API records

download_items.py

import requests
import json

with open('key.json') as keyfile:
	key_data = json.load(keyfile)

api_key = key_data['key']

#mediums_i_want = ["2028333","2028206","2028902","2035812","2028183","2035306"]
mediums_i_want = ["2028216"]

medium_ids_string = "|".join(mediums_i_want)
print(medium_ids_string)
url = "https://api.harvardartmuseums.org/object"

params = {
	'apikey' : api_key,
	'medium' : medium_ids_string,
	'size': 100
}
r = requests.get(url, params=params)

data = json.loads(r.text)

print(data['info'])

counter = 1
max_pages = 0

max_pages = data['info']['pages']


while counter <= max_pages:

	print("Doing page",counter)

	params = {
		'apikey' : api_key,
		'medium' : medium_ids_string,
		'size': 100,
		'page' : counter
	}	

	r = requests.get(url, params=params)

	data = json.loads(r.text)


	for rec in data['records']:

		# filename = str(rec['id']) + '.json'
		filename = f"{rec['id']}.json"

		json.dump(rec, open('records/'+filename,'w'),indent=2)
		print(filename)


	counter = counter + 1

find_date.py

import json
import glob

all_dates = []

for file in glob.glob('records/*.json'):

	with open(file) as jsonfile:

		data = json.load(jsonfile)


		if 'datebegin' in data:
			if data['datebegin'] != 0:

				all_dates.append(data['datebegin'])


print('we have',len(all_dates), 'total number of dates')

total_number_dates = len(all_dates)

total_date_value = 0


for date in all_dates:

	total_date_value = total_date_value + date

print('avg is:', total_date_value / total_number_dates)

key.json

{
	"key": "YOUR KEY HERE"
}