gh-parse.py

import unicodecsv as csv

import urllib
import sys
import json
import requests

users_url = "https://api.github.com/users/%s"

# Use the following query to export all the user logins
# SELECT
#   actor.login
# FROM `githubarchive.month.*`
# WHERE repo.name like 'spinnaker/%'
#   AND _TABLE_SUFFIX > '2020'
#   AND type IN ('ForkEvent', 'PushEvent', 'WatchEvent', 'IssuesEvent', 'PullRequestReviewCommentEvent', 'PullRequestEvent')
# GROUP BY actor.login
#
#Generate New Token Here:
#https://github.com/settings/tokens
token = "YOUR TOKEN GOES HERE"
user_list = []
with open('logins.csv') as csvfile:
    spamreader = csv.reader(csvfile)
    for cnt, row, in enumerate(spamreader):
        if cnt == 0:
            continue #Skip header row
        print(users_url % row[0])
        u = requests.get(users_url % row[0], auth=("imosquera", token)).json()
        try:
            c = u.get("company")
            if c is not None and len(c) >= 1 and c[0] == "@":
                c = c[1:]
            user_tuple = (u["login"], c)
        except:
            print("error parsing")
            print(u)
        user_list.append(user_tuple)
        print cnt

with open('names.csv', "w") as csvfile:
    w = csv.writer(csvfile, encoding='utf-8')
    fieldnames = ["login", "company"]
    w.writerow(fieldnames)
    w.writerows(user_list)