gistfile1.py

import requests, json, os, csv, argparse


parser = argparse.ArgumentParser()
parser.add_argument('--file', dest='file', metavar='FILE',
                    action='store')
args = parser.parse_args()

file = args.file
newfile = 'NAIDs - ' + args.file

offset = 0

with open(newfile, 'w') as log :
	writelog = csv.writer(log, delimiter= '\t', quoting=csv.QUOTE_ALL)
	writelog.writerow( ('variantControlNumber', 'fileSize', 'labelFlag', 'accessFilename', 'naId', 'title') )
	log.close()

with open(file, 'rb') as csvfile:
	csvreader = csv.reader(csvfile, delimiter=',')
	for row in csvreader:

		variant_control_number = (row)[0]
		file_size = (row)[1]
		label_flag = (row)[2]
		access_file_name = (row)[3]
		
		geturl = 'https://catalog.archives.gov/api/v1?resultFields=description.fileUnit.title,naId&resultTypes=fileUnit&description.fileUnit.variantControlNumberArray.variantControlNumber.number=' + variant_control_number
		
		y = requests.get(geturl)
		parsed = json.loads(y.text)
	
		try :
			NAID = parsed['opaResponse']['results']['result'][0]['naId']
			title = parsed['opaResponse']['results']['result'][0]['description']['fileUnit']['title']
		
		except KeyError :
			print 'No result found for ' + variant_control_number + '.'
			pass
		
		offset = offset + 1
		with open(newfile, 'a') as log :
			writelog = csv.writer(log, delimiter= '\t', quoting=csv.QUOTE_ALL)
			writelog.writerow( (variant_control_number, file_size, label_flag, access_file_name, NAID, title) )
			log.close()
		print '\nRow ' + str(offset) + ' logged: ' + variant_control_number + ', ' + NAID + ', "' + title + '"'