How to retrieve Github Repository Data using Python

Does your organization have (way) too many github repositories, and you need an easy way to summarize and keep record of what each one is for reporting, dashboard, or auditing purposes? Here's a quick script to do that very thing using the Github API.

Functions:

1. get_repo_info(owner, repo):

   • Takes a GitHub repository owner's username (owner) and repository name (repo).
   • Sends a request to GitHub's API to get repository information.
   • Returns the repository's information as a JSON object if successful, or None if there is an error.

2. get_collaborators(collaborators_url):

   • Takes the URL to the list of collaborators for a repository.
   • Sends a request to fetch the list of collaborators.
   • Returns a list of collaborator usernames, or an empty list if an error occurs.

3. get_languages(languages_url):

   • Takes the URL to the repository's languages data.
   • Sends a request to retrieve the programming languages used in the repository.
   • Returns a list of languages, or an empty list if there is an error.

4. get_open_issues(owner, repo):

   • Takes the repository owner's username (owner) and repository name (repo).
   • Sends a request to retrieve the list of open issues in the repository.
   • Returns the open issues in JSON format, or prints an error message if there's a problem.

5. get_repo_data(repo_url):

   • Takes a repository URL, parses it to get the owner and repo values, and then calls the other functions to gather various information about the repository.
   • Compiles the repository information, including its name, owner, visibility, collaborators, languages, open issues, and last activity, and returns it in a structured format (a dictionary).

import json
import requests
from pymongo import MongoClient

# MongoDB setup (replace with your actual connection details)
client = MongoClient("mongodb://localhost:27017/")
db = client["github_repos"]  # Database name
collection = db["repos"]     # Collection name

def get_repo_info(owner, repo):
    url = f"https://api.github.com/repos/{owner}/{repo}"
    headers = {"Accept": "application/vnd.github+json"}
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.json()
    else:
        print(f"Error: {response.status_code}")
        return None

def get_collaborators(collaborators_url):
    response = requests.get(collaborators_url)
    if response.status_code == 200:
        return [collaborator["login"] for collaborator in response.json()]
    else:
        return []

def get_languages(languages_url):
    response = requests.get(languages_url)
    if response.status_code == 200:
        return list(response.json().keys())
    else:
        return []

def get_open_issues(owner, repo):
    url = f"https://api.github.com/repos/{owner}/{repo}/issues?state=open"
    headers = {"Accept": "application/vnd.github+json"}
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.json()
    else:
        print(f"Error: {response.status_code}")
        return []

def get_repo_data(repo_url):
    owner, repo = repo_url.split("/")[-2:]
    repo_info = get_repo_info(owner, repo)

    if repo_info:
        data = {
            "Github URL": repo_url,
            "Project name": repo_info["name"],
            "Project owner": repo_info["owner"]["login"],
            "List users with access": get_collaborators(repo_info["collaborators_url"].split("{")[0]),  # remove template part of URL
            "Programming languages used": get_languages(repo_info["languages_url"]),
            "Security/visibility level": repo_info["visibility"],
            "Summary": repo_info["description"],
            "Last maintained": repo_info["pushed_at"],
            "Last release": repo_info["default_branch"],
            "Open issues": get_open_issues(owner, repo),
        }

        # Insert the data into MongoDB
        collection.insert_one(data)
        print("Data inserted into MongoDB successfully.")

        return data
    else:
        return None

# Example usage
repo_url = "https://github.com/URL"
repo_data = get_repo_data(repo_url)

if repo_data:
    print(json.dumps(repo_data, indent=4))