kleio.py

import re
import sys
import json
import urllib
import requests

headers = {
 "Host": "www.disease-ontology.org",
 "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.11; rv:51.0) Gecko/20100101 Firefox/51.0",
 "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
 "Accept-Language": "en-US,en;q=0.5", 
 "Referer": "http://www.disease-ontology.org/",
 "Connection": "keep-alive",
 "Upgrade-Insecure-Requests": "1",
 "Pragma": "no-cache",
 "Cache-Control": "no-cache"
}

argument =  "+".join(sys.argv[1].split())


url = "http://www.disease-ontology.org/search?q={}&adv_search=False&operator=AND&field-1=name&value-1=".format(argument)

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


text = r.text

#print text

s = re.search(r'<td class=\"tbl-doid\">([\w:]+)</td>', text)

g = s.group(1)

# DOID:0050741
#print g


url =  "http://www.disease-ontology.org/query_tree?_dc=1486652979836&search=True&node={}".format(urllib.quote(g))

r2 = requests.get(url, headers = headers)

data = r2.json()

#print json.dumps(data, indent=4)


'''
[
    {
        "text": "disease", 
        "expanded": true, 
        "children": [
            {
                "text": "disease by infectious agent", 
                "leaf": false, 
                "id": "DOID:0050117"
            }, 
            {
                "text": "disease of anatomical entity", 
                "leaf": false, 
                "id": "DOID:7"
            }, 
            {
                "text": "disease of cellular proliferation", 
                "leaf": false, 
                "id": "DOID:14566"
            }, 
            {
                "text": "disease of mental health", 
                "expanded": true, 
                "children": [

'''

for l1 in data:
	for l2 in l1['children']:
		if "children" in l2:
			print l2["text"]

Usage:

$ python kleio.py "alcohol dependence"
disease of mental health