Gets some PR info for specified repositories

github-prs.py

# based on https://stackoverflow.com/a/73978756/684253
import requests
from datetime import datetime
import csv

token = "<a personal token>"

def export_projects(base_urls, token, out_filename):
    final_dataset = []
    fmt = "%Y-%m-%dT%H:%M:%SZ"
    auth_header = 'Bearer ' + token

    repos = []
    for base_url in base_urls:
      page = 1

      url = (base_url + "/pulls?state=closed&per_page=100&page=%d" % page)
      res=requests.get(url,headers={"Authorization": auth_header})

      res_repos=res.json()
      while res.json() != []:
        page= page + 1
        url = (base_url + "/pulls?state=closed&per_page=100&page=%d" % page)
        res=requests.get(url,headers={"Authorization": auth_header})
        res_repos.extend(res.json())

      repos.extend(res_repos)

    print("Fetching PRs, Please Wait")
    for data in repos:
      result = {}
      created_at = datetime.strptime(data['created_at'], fmt)
      closed_at = datetime.strptime(data['closed_at'], fmt)

      result['hours_to_review'] = round((closed_at - created_at).total_seconds() / 3600, 2)
      #url_for_pr = (base_url + "/pulls/%d" % data['number'])
      url_for_pr = data['url']
      res=requests.get(url_for_pr,headers={"Authorization": auth_header})
      pr_data = res.json()
      result['commits'] = pr_data['commits']
      result['additions'] = pr_data['additions']
      result['deletions'] = pr_data['deletions']
      result['changed_files'] = pr_data['changed_files']
      result['comments'] = pr_data['comments']
      result['review_comments'] = pr_data['review_comments']
      result['user_name'] = pr_data['user']['login']
      result['pr_number'] = data['number']
      result['pr_url'] = data['url']
      result['created_at'] = data['created_at']
      result['closed_at'] = data['closed_at']
      result['count_requested_reviewers'] = len(pr_data['requested_reviewers'])
      final_dataset.append(result)

    print("Writing to csv, Please Wait")
    keys = final_dataset[0].keys()
    with open(out_filename, 'w', newline='') as output_file:
      dict_writer = csv.DictWriter(output_file, keys)
      dict_writer.writeheader()
      dict_writer.writerows(final_dataset)

    print(("************* DONE (%s) *****************" % out_filename))


base_urls = [
  "https://api.github.com/repos/<org>/<repo>"
]

export_projects(base_urls, token, 'output.csv')