contributors parser implimented

Author: PeeachPie

.gitignore

@@ -0,0 +1 @@
+__pycache__

contributors_parser.py

@@ -0,0 +1,86 @@
+import csv
+from time import sleep
+from typing import Generator
+from github import Github, Repository, GithubException
+
+EMPTY_FIELD = 'Empty field'
+TIMEDELTA = 0.05
+TIMEZONE = 'Europe/Moscow'
+FIELDNAMES = ('repository name', 'login', 'name', 'email', 'url', 'permissions', 'total_commits', 'id', 'node_id', 'type', 'bio', 'site_admin')
+
+
+def log_contributors_to_csv(info: dict, csv_name: str):
+    with open(csv_name, 'a', newline='') as file:
+        writer = csv.DictWriter(file, fieldnames=FIELDNAMES)
+        writer.writerow(info)
+
+def log_contributors_to_stdout(info: dict):
+    print(info)
+
+def log_repository_contributors(repository: Repository, csv_name: str):
+    contributors_stats = get_contributors_stats(repository)
+
+    nvl = lambda val: val or EMPTY_FIELD
+
+    for contributor_stat in contributors_stats.values():
+        contributor = contributor_stat["contributor_object"]
+        contributor_permissons = repository.get_collaborator_permission(contributor)
+
+        info_tmp = {
+            'repository name': repository.full_name,
+            'login': contributor.login,
+            'name': nvl(contributor.name),
+            'email': nvl(contributor_stat['email']),
+            'url': contributor.html_url,
+            'permissions': nvl(contributor_permissons),
+            'total_commits': contributor_stat['total_commits'],
+            'id': contributor.id,
+            'node_id': contributor.node_id,
+            'type': contributor.type,
+            'bio': nvl(contributor.bio),
+            'site_admin': contributor.site_admin,
+        }
+
+        log_contributors_to_csv(info_tmp, csv_name)
+        log_contributors_to_stdout(info_tmp)
+
+        sleep(TIMEDELTA)
+
+def get_contributors_stats(repository: Repository) -> dict:
+    contributors_stats = dict()
+    
+    for commit in repository.get_commits():
+        contributor = commit.author
+
+        if not contributor.login in contributors_stats:
+            contributors_stats[contributor.login] = {
+                'total_commits': 0,
+                'email': commit.commit.author.email,
+                'contributor_object': contributor
+            }
+
+        contributors_stats[contributor.login]['total_commits'] += 1
+
+        sleep(TIMEDELTA)
+
+    return contributors_stats
+
+def log_contributors(client: Github, working_repos: Generator, csv_name: str, fork_flag: bool):
+    with open(csv_name, 'w', newline='') as file:
+        writer = csv.writer(file)
+        writer.writerow(FIELDNAMES)
+
+    for repo in working_repos:
+        try:
+            print('=' * 20, repo.full_name, '=' * 20)
+            log_repository_contributors(repo, csv_name)
+
+            if fork_flag:
+                for forked_repo in repo.get_forks():
+                    print('=' * 20, "FORKED:", forked_repo.full_name, '=' * 20)
+                    log_repository_contributors(forked_repo, csv_name)
+                    sleep(TIMEDELTA)
+
+        except GithubException as e:
+            print(e)
+            exit(1)

git_logger.py

@@ -12,7 +12,7 @@ def login(token):
     except GithubException as err:
         print(f'Github: Connect: error {err.data}')
         print('Github: Connect: user could not be authenticated please try again.')
-        raise exit(1)
+        exit(1)
     else:
         return client
 

main.py

@@ -9,6 +9,7 @@
 import issues_parser
 import invites_parser
 import wikipars
+import contributors_parser
 
 def parse_args():
     parser = argparse.ArgumentParser()
@@ -17,6 +18,7 @@ def parse_args():
     parser.add_argument("-p", "--pull_requests", help="log pull requests", action="store_true")
     parser.add_argument("-i", "--issues", help="log issues", action="store_true")
     parser.add_argument("-w", "--wikis", help="log wikis", action="store_true")
+    parser.add_argument("--contributors", help="log contributors", action="store_true")
     parser.add_argument("--forks_include", help="logging data from forks", action="store_true")
     parser.add_argument("-e", "--export_google_sheets", help="export table to google sheets", action="store_true")
     parser.add_argument('-t', '--token', type=str, required=True, help='token github account')
@@ -62,7 +64,6 @@ def main():
     path_drepo = args.download_repos
     fork_flag = args.forks_include
     log_pr_comments = args.pr_comments
-    start, finish = None, None
 
     try:
         client = git_logger.login(token=token)
@@ -84,6 +85,8 @@ def main():
             invites_parser.log_invitations(client, working_repos, csv_name)
         if args.wikis:
             wikipars.wikiparser(client, repositories, path_drepo, csv_name)
+        if args.contributors:
+            contributors_parser.log_contributors(client, working_repos, csv_name, fork_flag)
         if args.export_google_sheets:
             export_sheets.write_data_to_table(csv_name, args.google_token, args.table_id, args.sheet_id)
 

pull_requests_parser.py

@@ -107,17 +107,15 @@ def log_repositories_pr(repository: Repository, csv_name, token, start, finish,
         }
 
         if log_comments:
-            comments = pull.get_comments()
-            if comments.totalCount > 0:
-                for comment in comments:
-                    info = info_tmp
-                    info['comment body'] = comment.body
-                    info['comment created at'] = comment.created_at
-                    info['comment author name'] = comment.user.name
-                    info['comment author login'] = comment.user.login
-                    info['comment author email'] = nvl(comment.user.email)
-                    log_pr_to_csv(info, csv_name)
-                    log_pr_to_stdout(info)
+            for comment in pull.get_comments():
+                info = info_tmp
+                info['comment body'] = comment.body
+                info['comment created at'] = comment.created_at
+                info['comment author name'] = comment.user.name
+                info['comment author login'] = comment.user.login
+                info['comment author email'] = nvl(comment.user.email)
+                log_pr_to_csv(info, csv_name)
+                log_pr_to_stdout(info)
         else:
             log_pr_to_csv(info_tmp, csv_name)
             log_pr_to_stdout(info_tmp)