{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# First Github Scraper\n",
    "\n",
    "This notebook is a simplified version of the IRE tutorial “Web scraping with Python.” Consult [the original material](https://github.com/ireapps/teaching-guide-python-scraping) to learn more about how to write a web scraper."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "import bs4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "URL = 'http://www.dllr.state.md.us/employment/warn.shtml'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "warn_page = requests.get(URL)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "soup = bs4.BeautifulSoup(warn_page.text, 'html.parser')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "table = soup.find('table')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "rows = table.find_all('tr')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "import csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "HEADERS = [\n",
    "    'warn_date',\n",
    "    'naics_code',\n",
    "    'biz',\n",
    "    'address',\n",
    "    'wia_code',\n",
    "    'total_employees',\n",
    "    'effective_date',\n",
    "    'type_code'\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('warn-data.csv', 'w', newline='') as outfile:\n",
    "    writer = csv.writer(outfile)\n",
    "    writer.writerow(HEADERS)\n",
    "    for row in rows[1:]:\n",
    "        cells = row.find_all('td')\n",
    "        values = [c.text.strip() for c in cells]\n",
    "        writer.writerow(values)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}