import re
import requests
import pandas as pd
from time import sleep

query = """
SELECT
  ?researcher ?researcherLabel ?researcherDescription
  (SAMPLE(?github_) AS ?github)
WITH {
  SELECT DISTINCT ?researcher WHERE {
    ?researcher ( wdt:P108 | wdt:P463 | wdt:P1416 ) / wdt:P361* wd:Q23048689 . 
  } 
} AS %researchers
WHERE {
  INCLUDE %researchers
  ?researcher wdt:P2037 ?github_ .
  SERVICE wikibase:label { bd:serviceParam wikibase:language "en,da,de,es,fr,nl,no,ru,sv,zh" . } 
}
GROUP BY ?researcher ?researcherLabel ?researcherDescription 
"""
response = requests.get("https://query.wikidata.org/sparql",
                        params={'query': query, 'format': 'json'})
researchers = pd.json_normalize(response.json()['results']['bindings'])


URL = "https://api.github.com/users/"
followers = []
for github in researchers['github.value']:
    if not re.match('^[a-zA-Z0-9]+$', github):
        followers.append(0)
        continue
    url = URL + github
    print(url)
    try:
        response = requests.get(url,
                                headers={'Accept':'application/vnd.github.v3+json'})
        user_followers = response.json()['followers']     
    except:
        user_followers = 0
    followers.append(user_followers)
    print("{} {}".format(github, followers))
    sleep(5)


researchers['followers'] = followers
columns = ['followers', 'github.value', 'researcherLabel.value',
           'researcher.value']

print(researchers.sort_values(['followers'], ascending=False)[columns].to_html(index=False))