find contributors that are not members of an organization

find_nonmembers.py

#!/usr/bin/env python
from __future__ import print_function
import re
import json
import argparse
from collections import defaultdict

import requests

parser = argparse.ArgumentParser(
    description="find non-members of a GitHub org by contributions to repos")
parser.add_argument("--token", nargs="?", type=str, help="GitHub API token")
parser.add_argument("--org", nargs="?", type=str, default="kubernetes",
                    help="the GitHub org to find non-member contirbutions for")

def get_pagination(response):
  if "Link" not in response.headers:
    return None
  parts = response.headers["Link"].split(",")
  res = {}
  for part in parts:
    match = re.search('<(.*)>; rel="(.*)"', part)
    if match:
      res[match.group(2)] = match.group(1)
  return res

def get_all_paginated(url, token=None):
    res = []
    while True:
        headers = {"Accept": "application/vnd.github.v3+json"}
        if token is not None:
            headers["Authorization"] = "token "+token
        r = requests.get(url, headers=headers, params={"per_page": "100"})
        res.extend(r.json())
        pagination = get_pagination(r)
        if pagination is None or "next" not in pagination:
            break
        url = pagination["next"]
    return res

def get_members(org, token=None):
    url = "https://api.github.com/orgs/%s/members" % org
    return get_all_paginated(url, token)
    

def get_contributors(repo, token=None):
    url = "https://api.github.com/repos/%s/stats/contributors" % repo
    return get_all_paginated(url, token)

def get_repos(org, token=None):
    url = "https://api.github.com/orgs/%s/repos" % org
    return get_all_paginated(url, token)

def main(args):
    org = "kubernetes"
    members_json = get_members(org, args.token)
    members = set(m["login"] for m in members_json)
    repos_json = get_repos(org, args.token)
    repos = [r["full_name"] for r in repos_json] 
    # TODO: this is naive, we're just taking the "total" returned by GitHub
    non_member_contributions = defaultdict(int)
    for repo in repos:
        print("getting results for repo: %s ..." % repo)
        contributors = get_contributors(repo, args.token)
        for c in contributors:
            login = c["author"]["login"]
            if login not in members:
                non_member_contributions[login.encode("utf-8")] += int(c["total"])
    by_contributions = sorted(
        ((k, v) for k,v in non_member_contributions.iteritems()), key=lambda v: -v[1])
    print("Non-Member GitHub Logins sorted by total contributions in %s:" % args.org)
    for nm in by_contributions:
        print("@{: <25}|    {: >4} total contributions".format(*nm))


if __name__ == "__main__":
    args = parser.parse_args()
    main(args)

You should get the collaborators not the members in order to include outside collaborators who are still valid for assigning.