Viewing top contributors for public GitHub repositories

github_repo_contributors.py

import json

import pandas as pd
import requests


def get_github_repo_top_contributors(org_user_name, repo_name, top_n=50):
    """
    Gets the top n contributors data for the given GitHub repository - the
    repository should be specified via an organisational or user name and
    a repository name.

    :param org_user_name:   An organisational or username
    :type  org_user_name:   ``str``

    :param repo_name:       A repository name
    :type  repo_name:       ``str``

    :param top_n:           The size of the top contributors list - default
                            is ``50``
    :type  top_n:           ``int``

    :return:                The top n contributors data for the given GitHub
                            repository, as a dataframe
    :rtype:                 ``pd.DataFrame``
    """
    def process_response_json(res):
        return json.loads(res.text)

    url_template = (
        'https://api.github.com/repos/{org_user_name}/{repo_name}/contributors'
        '?q=contributions&per_page={per_page}&page={page_num}&order=desc'
    )

    hundred_per_page_reqs, last_req_size = divmod(top_n, 100)

    if hundred_per_page_reqs == 0:
        return pd.DataFrame(process_response_json(requests.get(
            url_template.format(org_user_name=org_user_name, repo_name=repo_name, per_page=last_req_size, page_num=1)
        )))

    req_urls = [
        url_template.format(org_user_name=org_user_name, repo_name=repo_name, per_page=100, page_num=page_num)
        for page_num in range(1, hundred_per_page_reqs + 1)
    ]

    if last_req_size > 0:
        req_urls += [
            url_template.format(org_user_name=org_user_name, repo_name=repo_name, per_page=last_req_size, page_num=(hundred_per_page_reqs + 1))
        ]

    data = pd.DataFrame()

    for req_url in req_urls:
        try:
            _data = pd.DataFrame(process_response_json(requests.get(req_url)))
        except ValueError as e:
            raise
        else:
            data = pd.concat([data, _data], axis=0, ignore_index=True)

    return data