Script to fetch all users who stared one repository

996.py

# -*- coding: utf-8 -*-

__author__ = 'deadblue'

import logging
logging.basicConfig(
    level=logging.INFO, datefmt='%H:%M:%S',
    format='[%(asctime)s] %(message)s'
)

import csv
import os
import sys

import requests

_GQL_TEMPLATE_ = '''
query {
  repository(owner:"996icu", name:"996.ICU") {
    stargazers(%s) {
      nodes {
        id
        login
        createdAt
        repositories(isFork:false) {
          totalCount
        }
      }
      pageInfo {
        hasNextPage
        endCursor
      }
    }   
  }
}
'''

_logger = logging.getLogger(__name__)


def _print_usage(prog):
    print('>> Script for fetching stargazers of [996.icu] repository <<')
    print('Usage:')
    print('    %s <Your-Github-Access-Token> [Output-File]' % prog)


def _query_stargazers(token, limit, after=None):
    # build GQL
    if after is None:
        cond = 'first:%d' % limit
    else:
        cond = 'first:%d, after:"%s"' % (
            limit, after
        )
    gql = _GQL_TEMPLATE_ % cond
    # query datas
    resp = requests.post('https://api.github.com/graphql', json={
        'query': gql
    }, headers={
        'Authorization': 'bearer %s' % token
    })
    result = resp.json()
    return result['data']['repository']['stargazers']


def _main(prog, token=None, outfile=None):
    # check arguments
    if token is None:
        _print_usage(prog)
        exit(1)
    if outfile is None:
        outfile = os.path.join(
            os.getcwd(), '996.csv'
        )
    # start fetching
    _logger.info('Start fetching...')
    with open(outfile, 'w') as fp:
        # create csv writer
        cw = csv.DictWriter(fp, fieldnames=['id', 'login', 'createAt', 'repoCount'])
        cw.writerow({
            'id': 'ID',
            'login': 'User Name',
            'createAt': 'Create Time',
            'repoCount': 'Non-Fork Repository'
        })
        # fetch data
        count, after = 0, None
        while True:
            # github only allow query no more than 100 datas per request
            data = _query_stargazers(token, 100, after)
            # append result to csv file
            for node in data['nodes']:
                count += 1
                cw.writerow({
                    'id': node['id'],
                    'login': node['login'],
                    'createAt': node['createdAt'],
                    'repoCount': node['repositories']['totalCount']
                })
            # flush per 100 lines
            fp.flush()
            # update cursor
            after = data['pageInfo']['endCursor']
            # break at end
            if not data['pageInfo']['hasNextPage']:
                break
            _logger.info('Fetch accounts => %d', count)
    _logger.info('Fetch done, total count: %d', count)


if __name__ == '__main__':
    _main(sys.argv[0], *sys.argv[1:])