Downloding github repositories

Downloading the Repositories.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "from tqdm import tqdm\n",
    "import pandas as pd\n",
    "from github import Github\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('../../api_keys/github.txt', \"r\") as f:\n",
    "    API_KEY = f.read()\n",
    "    \n",
    "git_client = Github(API_KEY)\n",
    "\n",
    "ext_set = set(['ipnyb', 'py'])\n",
    "REPO_DIR_PARENT = '../../data/package_popularity/numpy/clones/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "repo_df = pd.read_csv('../../data/package_popularity/numpy/repo_info.csv')\n",
    "repo_df = repo_df[repo_df['stargazers_count'] >= 100]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_relevant_files (full_name, git_client, ext_set):\n",
    "    repo = git_client.get_repo(full_name)\n",
    "    contents = repo.get_contents(\"\")\n",
    "    files = []\n",
    "    \n",
    "    while contents:\n",
    "        file_content = contents.pop(0)\n",
    "        if file_content.type == \"dir\":\n",
    "            contents.extend(repo.get_contents(file_content.path))\n",
    "        elif file_content.name.split('.')[-1] in ext_set:\n",
    "            files.append((file_content.name, file_content.download_url))\n",
    "            \n",
    "    return files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for name, full_name in tqdm(repo_df[['name', 'full_name']].values):\n",
    "    repo_dir = os.path.join(REPO_DIR_PARENT, '_'.join(full_name.split('/')))\n",
    "    if os.path.exists(repo_dir):\n",
    "        pass\n",
    "    else:\n",
    "        try:\n",
    "            os.mkdir(repo_dir)\n",
    "            files = get_relevant_files(full_name, git_client, ext_set)\n",
    "\n",
    "            for name, download_url in files:\n",
    "                r = requests.get(download_url, allow_redirects=True)\n",
    "                open(os.path.join(repo_dir, name), 'wb').write(r.content)\n",
    "        \n",
    "        except Exception as ex:\n",
    "            print('Exception', name, full_name, ex)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}