Extract repository stargazers + full profile infos

extract-stargazers.js

#!/usr/bin/env python3
import os
import sys
import csv
import time
from datetime import datetime, timezone

import requests

GITHUB_API = "https://api.github.com"


def github_get(url, token=None):
    headers = {"Accept": "application/vnd.github.v3.star+json"}
    if token:
        headers["Authorization"] = f"token {token}"
    resp = requests.get(url, headers=headers)
    if resp.status_code == 403 and "X-RateLimit-Remaining" in resp.headers and resp.headers["X-RateLimit-Remaining"] == "0":
        reset = int(resp.headers.get("X-RateLimit-Reset", 0))
        wait_for = max(0, reset - int(time.time())) + 1
        print(f"Rate limit hit. Waiting {wait_for}s...")
        time.sleep(wait_for)
        return github_get(url, token)
    resp.raise_for_status()
    return resp.json()


def iter_stargazers(owner, repo, token=None):
    page = 1
    while True:
        url = f"{GITHUB_API}/repos/{owner}/{repo}/stargazers?per_page=100&page={page}"
        data = github_get(url, token)
        if not data:
            break
        for item in data:
            user = item.get("user") or {}
            yield user["login"], user['id'], item.get("starred_at")
        page += 1


def get_user_details(login, token=None):
    url = f"{GITHUB_API}/users/{login}"
    data = github_get(url, token)
    return {
        "name": data.get("name"),
        "email": data.get("email"),
        "company": data.get("company"),
        "location": data.get("location"),
        "bio": data.get("bio"),
        "twitter_username": data.get("twitter_username"),
        "blog": data.get("blog"),
        "followers": data.get("followers"),
        "following": data.get("following"),
        "public_repos": data.get("public_repos"),
        "public_gists": data.get("public_gists"),
    }


def main():
    if len(sys.argv) != 3:
        print("Usage: python get_stargazers_with_company_country.py owner repo")
        sys.exit(1)

    owner, repo = sys.argv[1], sys.argv[2]
    token = os.environ.get("GITHUB_TOKEN")
    now = datetime.now(timezone.utc).replace(
        microsecond=0).isoformat().replace("+00:00", "Z")

    outname = f"{owner}-{repo}-stargazers-details.csv"
    with open(outname, "w", newline="", encoding="utf-8") as f:
        writer = csv.DictWriter(f, fieldnames=["repository", "user_id", "login", "name", "email", "company", "location", "bio",
                                "twitter", "blog", "followers", "following", "public_repos", "public_gists", "starred_at", "scrapped_at", "updated_at"])
        writer.writeheader()

        for login, id, starred_at in iter_stargazers(owner, repo, token):
            try:
                details = get_user_details(login, token)
                writer.writerow({
                    "repository": f"{owner}/{repo}",
                    "user_id": id,
                    "login": login,
                    "name": details["name"],
                    "email": details["email"],
                    "company": details["company"],
                    "location": details["location"],
                    "bio": details["bio"],
                    "twitter": details["twitter_username"],
                    "blog": details["blog"],
                    "followers": details["followers"],
                    "following": details["following"],
                    "public_repos": details["public_repos"],
                    "public_gists": details["public_gists"],
                    "starred_at": starred_at,
                    "scrapped_at": now,
                    "updated_at": now,
                })
                print(f"✔ {login}")
                time.sleep(0.3)  # Be polite to GitHub API
            except Exception as e:
                print(f"Error fetching {login}: {e}")
                continue

    print(f"\nSaved stargazer details to {outname}")


if __name__ == "__main__":
    main()