Get list of U.S. approved drugs from https://drugs.ncats.io

inxight-drugs.py

import requests

def get_additional_data(id):
    r = requests.get('https://drugs.ncats.io/api/v1/substances(%s)/@additional' % id)
    if 200 == r.status_code:
        return r.json()
    return None

# experiment with the filters at https://drugs.ncats.io
params = {
    'facet': ['Substance Form/Principal Form',
              'Development Status/US Approved Rx',
              'Development Status/US Approved OTC'],
    'skip': 0,
    'top': 100
}

print('UNII\tName\tYear\tConditions\tStatus\tSource')
total = 0
while True:
    r = requests.get('https://drugs.ncats.io/api/v1/substances/search', params)
    if 200 != r.status_code:
        print('%s returns status code %d!' % (r.url, r.status_code))
        break
    json = r.json()
    count = json['count']
    total = total + count
    #print('fetched %d/%d' % (total, json['total']))
    for r in json['content']:
        #print('...%s' % r['uuid'])
        data = get_additional_data(r['uuid'])
        if data != None:
            status = None
            year = None
            conds = []
            for d in data:
                if (d['name'] == 'Highest Development Event'
                    or (d['name'] == 'Earliest Approved Event' and status == None)):
                    status = d['value']
                elif d['name'] == 'Approval Year':
                    year = d['value']
                elif d['name'] == 'Conditions':
                    conds.append(d['value']['label'])
                    
            if status != None and not status['withdrawn']:
                print('%s\t%s\t%s\t%s\t%s\t%s' % (
                    r['approvalID'], r['_name'], year, ';'.join(conds), status['status'], status['sourceURL']))
        
    if count < json['top']:
        # we're done
        break
    params['skip'] = total

#print('%d records processed!' % total)