yelp scraper

yelp scraper.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Load required packages\n",
    "from bs4 import BeautifulSoup\n",
    "import requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# Read in a web page\n",
    "response = requests.get(\"https://www.yelp.com/search?find_desc=Vegetarian+Food&find_loc=Washington%2C+DC&ns=1\")\n",
    "soup = BeautifulSoup(response.content, \"html.parser\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Business name :  HipCityVeg\n",
      "Address :  712 7th St NWWashington, DC 20001\n",
      "4.5 star rating\n",
      "\n",
      "\n",
      "Business name :  Shouk\n",
      "Address :  655 K St NWWashington, DC 20001\n",
      "4.5 star rating\n",
      "\n",
      "\n",
      "Business name :  Chaia\n",
      "Address :  3207 Grace St NWWashington, DC 20007\n",
      "4.5 star rating\n",
      "\n",
      "\n",
      "Business name :  NuVegan Café\n",
      "Address :  2928 Georgia Ave NWWashington, DC 20001\n",
      "4.5 star rating\n",
      "\n",
      "\n",
      "Business name :  Pow Pow\n",
      "Address :  1253 H St NEWashington, DC 20002\n",
      "4.0 star rating\n",
      "\n",
      "\n",
      "Business name :  Beefsteak\n",
      "Address :  4531 Wisconsin Ave NWWashington, DC 20016\n",
      "4.5 star rating\n",
      "\n",
      "\n",
      "Business name :  Evolve Vegan Restaurant\n",
      "Address :  341 Cedar St NWWashington, DC 20012\n",
      "4.0 star rating\n",
      "\n",
      "\n",
      "Business name :  Unconventional Diner\n",
      "Address :  1207 9th St NWWashington, DC 20001\n",
      "4.5 star rating\n",
      "\n",
      "\n",
      "Business name :  Sababa\n",
      "Address :  3311 Connecticut Ave NWWashington, DC 20008\n",
      "4.0 star rating\n",
      "\n",
      "\n",
      "Business name :  Fancy Radish\n",
      "Address :  600 H St NEWashington, DC 20002\n",
      "4.5 star rating\n",
      "\n",
      "\n"
     ]
    }
   ],
   "source": [
    "all_li=soup.findAll(\"li\",{\"class\":\"regular-search-result\"})\n",
    "for myli in all_li:\n",
    "    try:\n",
    "        bizname = myli.find(\"a\",{\"class\":\"biz-name\"})\n",
    "        print(\"Business name : \", bizname.text)\n",
    "    except:\n",
    "        print(\"Business name missing\")\n",
    "    try:\n",
    "        addr = myli.find('address').text.strip()\n",
    "        print(\"Address : \",addr)\n",
    "    except:\n",
    "        print(\"Business address missing\")\n",
    "\n",
    "    try:\n",
    "        stars = myli.find(\"div\",{\"class\":\"i-stars\"})\n",
    "        rating = stars.find('img', alt=True)\n",
    "        print(rating['alt'])\n",
    "    except:\n",
    "        print(\"Business rating missing\")\n",
    "       \n",
    "    print('\\n') # Leave a line between businesses \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}