clarity detailed precinct scraper attempt.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from pyquery import PyQuery as pq\n",
    "import requests\n",
    "\n",
    "import csv\n",
    "from collections import OrderedDict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "localurl = \"https://enr.electionsfl.org/BRO/1985/Precincts/21073/?view=detailed\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "html = requests.get(localurl).content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Parsing United States Senator\n"
     ]
    }
   ],
   "source": [
    "masterlist = []\n",
    "options = pq(pq(html)(\"select#raceSelect\"))(\"option\")\n",
    "for option in options:\n",
    "    if pq(option).attr(\"selected\"):    # if not a none value\n",
    "        racename = pq(option).text()\n",
    "        print(\"Parsing \" + racename)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "for racerow in pq(html)(\"div.Race.row\"):\n",
    "    precinctname = pq(racerow)(\"span.PrecinctName\").text().strip()\n",
    "    # print(precinctname)\n",
    "    table = pq(racerow)(\"table.DetailResults\")\n",
    "    headers = []\n",
    "    for th in pq(pq(pq(table)(\"tr\"))[0])(\"th\"):\n",
    "        headers.append(pq(th).text())\n",
    "    for row in pq(pq(table)(\"tr\"))[1:]:\n",
    "        line = OrderedDict()\n",
    "        line['racename'] = racename\n",
    "        line['precinctname'] = precinctname\n",
    "        for i, item in enumerate(headers):\n",
    "            stuff = pq(pq(pq(row)(\"td\"))[i]).text().strip().replace(\"\\r\\n\", \"\")\n",
    "            line[item] = stuff\n",
    "        masterlist.append(line)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "with open(\"masterlist.csv\", \"w\", newline=\"\") as f:\n",
    "    writer = csv.writer(f)\n",
    "    writer.writerow(list(line.keys()))\n",
    "    for row in masterlist:\n",
    "        writer.writerow(list(row.values()))"
   ]
  },
  {
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}