Scraping US Grad Hotline

scrape_gradhotline.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "following-pillow",
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "thermal-indicator",
   "metadata": {},
   "outputs": [],
   "source": [
    "url_string = \"https://university.graduateshotline.com/ubystate.html\"\n",
    "\n",
    "r = requests.get(url_string)\n",
    "html = r.text\n",
    "\n",
    "soup = BeautifulSoup(html, 'html.parser')\n",
    "links = soup.find_all(\"a\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ruled-style",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = []\n",
    "for link in links:\n",
    "    data.append([link.get_text(strip=True), link.get('href')])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "manufactured-clothing",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(data)\n",
    "df.columns = ['name', 'url']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "hungarian-appeal",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>url</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>graduateshotline</td>\n",
       "      <td>https://www.graduateshotline.com</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>GRE</td>\n",
       "      <td>https://www.graduateshotline.com/gre.html</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>GRE Verbal Practice</td>\n",
       "      <td>https://gre.graduateshotline.com</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>GRE Word list</td>\n",
       "      <td>https://www.graduateshotline.com/gre-word-list...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Besk Books for GRE</td>\n",
       "      <td>https://gre.graduateshotline.com/top-4-books-f...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  name                                                url\n",
       "0     graduateshotline                   https://www.graduateshotline.com\n",
       "1                  GRE          https://www.graduateshotline.com/gre.html\n",
       "2  GRE Verbal Practice                   https://gre.graduateshotline.com\n",
       "3        GRE Word list  https://www.graduateshotline.com/gre-word-list...\n",
       "4   Besk Books for GRE  https://gre.graduateshotline.com/top-4-books-f..."
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "tutorial-first",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.to_csv('us_grad_hotline.tsv', sep='\\t', index=False)"
   ]
  }
 ],
 "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": "3.9.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}