{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import urllib\n",
    "from bs4 import BeautifulSoup\n",
    "\n",
    "\n",
    "class GetVacancyInfo():\n",
    "    \n",
    "    # this class allows you to get information about certain vacancy on HeadHunter by url or by its ID\n",
    "    \n",
    "    def __init__(self, get_by_id=False, vacancy_url=None, vacancy_id=None):\n",
    "        \n",
    "        if get_by_id == True:\n",
    "            \n",
    "            assert type(vacancy_id) == str or type(vacancy_id) == int,  \"Incorrect ID's format\"\n",
    "            self.vacancy_id = vacancy_id\n",
    "            self.URL = \"https://spb.hh.ru/vacancy/\"+str(vacancy_id)\n",
    "            \n",
    "        else:\n",
    "            self.URL = self.clear_url(vacancy_url)\n",
    "        \n",
    "        \n",
    "    def clear_url(self,given_url):\n",
    "        \n",
    "        assert (type(given_url) == str), \"Incorrect URL's format\"\n",
    "        \n",
    "        if given_url.find('?') != -1:\n",
    "            valid_url = given_url[:given_url.find('?')]\n",
    "        else: \n",
    "            valid_url = given_url\n",
    "            \n",
    "        return valid_url\n",
    "        \n",
    "    \n",
    "    def get_html(self,url):\n",
    "        response = urllib.urlopen(url)\n",
    "        return response.read()\n",
    "    \n",
    "    \n",
    "    def parse(self,html):\n",
    "        soup = BeautifulSoup(html,'lxml')\n",
    "        \n",
    "        description = soup.find('div', class_='b-vacancy-desc-wrapper').get_text()\n",
    "        key_skills = soup.find('div', class_ = 'l-paddings').get_text()\n",
    "\n",
    "        return (description,key_skills)\n",
    "\n",
    "    \n",
    "    def get_info(self):\n",
    "        html = self.get_html(self.URL)\n",
    "        \n",
    "        try:    \n",
    "            info = self.parse(html)\n",
    "            \n",
    "        except AttributeError:\n",
    "            print 'Unavalible vacancy'\n",
    "            return \n",
    "            \n",
    "            \n",
    "        return info\n",
    "    \n",
    "# TODO: fix key skills parsing "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Крупная западная фармацевтическая компания производит набор медицинских представителей на конкурсной основе\n",
      "\n",
      "\n",
      "Обязанности: \n",
      "\n",
      "- заниматься продвижением препаратов компании на территории Москвы и московской области;\n",
      "\n",
      "- 10-12 визитов в день, ведение коммерческих переговоров с лидерами ключевых мнений;\n",
      "\n",
      "- ведение презентаций.\n",
      "\n",
      "\n",
      "Требования:\n",
      "\n",
      "- высшее медицинское/фармацевтическое образование;\n",
      "\n",
      "- опыт работы приветствуется;\n",
      "\n",
      "- хорошие презентационные навыки;\n",
      "\n",
      "- опыт вождения автомобиля;\n",
      "\n",
      "- опыт работы на п/к.\n",
      "\n",
      "\n",
      "З/п 550-750$  + социальный пакет (мед.страховка, представительские расходы, компьютер, телефон, машина - иномарка)\n"
     ]
    }
   ],
   "source": [
    "VI = GetVacancyInfo(get_by_id=True, vacancy_id=18123)\n",
    "print VI.get_info()[0]"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}