Intersect Stargazers in a Venn Diagram

stargzers_venn.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install matplotlib matplotlib-venn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "import time\n",
    "\n",
    "def get_stargazers(repo_owner, repo_name):\n",
    "    \"\"\"Fetches the list of users who have starred the given GitHub repository.\"\"\"\n",
    "    results = []\n",
    "    page = 1\n",
    "    while True:\n",
    "        url = f\"https://api.github.com/repos/{repo_owner}/{repo_name}/stargazers?page={page}&per_page=100\"\n",
    "        response = requests.get(url)\n",
    "        if response.status_code == 200:\n",
    "            stargazers = response.json()\n",
    "            if not stargazers:\n",
    "                break  # Exit loop if no more stargazers\n",
    "            for user in stargazers:\n",
    "                results.append(user['login'])\n",
    "            page += 1  # Increment page number for next iteration\n",
    "            time.sleep(10)\n",
    "        else:\n",
    "            print(f\"Error: {response.status_code} for url: {url}\")\n",
    "            break  # Exit loop on error\n",
    "    return results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "name_one = (\"unum-cloud\", \"usearch\")\n",
    "name_two = (\"unum-cloud\", \"ucall\")\n",
    "name_three = (\"ashvardanian\", \"stringzilla\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "stars_one = get_stargazers(*name_one)\n",
    "len(stars_one)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "stars_two = get_stargazers(*name_two)\n",
    "len(stars_two)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "stars_three = get_stargazers(*name_three)\n",
    "len(stars_three)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from matplotlib import pyplot as plt\n",
    "from matplotlib_venn import venn3\n",
    "\n",
    "venn3([set(stars_one), set(stars_two), set(stars_three)], ['/'.join(name_one), '/'.join(name_two), '/'.join(name_three)])\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

Be ready, that the GitHub API has an aggressive rate-limiter for non-authorized applications and also limits pagination to 400 pages.
This means, addressing over 40K GitHub stars with this API is impossible. For authorization, use your custom developer token:

headers = {'Authorization': 'token your-long-token-here'}
response = requests.get(url, headers=headers)

Attached you can find some of the outputs.