Automatically guessing Quizzarium answers from DuckDuckGo search results based on hints.

autoquizzarium.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "\n",
    "ddg_query_base = 'https://duckduckgo.com/html/?q='\n",
    "\n",
    "resp = requests.get(ddg_query_base + 'Who originally sang vocals for ACDC?')\n",
    "text = resp.text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "whitespace_regexp = re.compile('\\s+')\n",
    "\n",
    "def get_search_result(question):\n",
    "    resp = requests.get(ddg_query_base + question)\n",
    "    soup = BeautifulSoup(resp.text)\n",
    "    pageText = soup.findAll(text=True)\n",
    "    non_empty_texts = [t for t in pageText if whitespace_regexp.fullmatch(t) is None]\n",
    "    stripped_texts = [t.strip() for t in non_empty_texts]\n",
    "    return stripped_texts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "re.compile(r'(?:^|[^\\w])(\\w\\w\\w\\w \\w\\wa\\ws)(?:$|[^\\w])', re.UNICODE)"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def build_hint_regexp(hint):\n",
    "    hint = ' '.join([h.replace(' ', '').replace('_', '\\w') for h in hint.split('   ')])\n",
    "    hint = '(?:^|[^\\w])(' + hint + ')(?:$|[^\\w])'\n",
    "    return re.compile(hint)\n",
    "build_hint_regexp('_ _ _ _   _ _ a _ s')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['html class']\n",
      "['html class']\n",
      "['html class']\n",
      "['Dirt Cheap']\n",
      "['Dirt Cheap']\n",
      "['Dirt Cheap']\n",
      "['that music']\n",
      "['sold three']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['This video']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['like Brian']\n",
      "['coal miner']\n",
      "['Dirt Cheap']\n",
      "['Dirt Cheap']\n",
      "['Dave Evans', 'band needs']\n",
      "['Long sheet']\n",
      "['with scene']\n",
      "['from their']\n",
      "['know which']\n",
      "['that seems', 'that brian']\n",
      "['Hell after']\n",
      "['Dave Evans']\n",
      "['Mark Evans']\n",
      "['wave group']\n"
     ]
    }
   ],
   "source": [
    "hint_regexp = build_hint_regexp('_ _ _ _   _ _ _ _ _')\n",
    "for t in stripped_texts:\n",
    "    m = hint_regexp.findall(t)\n",
    "    if m:\n",
    "        print(m)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['html class']\n",
      "['html class']\n",
      "['html class']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Mark Evans']\n"
     ]
    }
   ],
   "source": [
    "hint_regexp = build_hint_regexp('_ _ _ _   _ _ a _ s')\n",
    "for t in stripped_texts:\n",
    "    m = hint_regexp.findall(t)\n",
    "    if m:\n",
    "        print(m)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Dave Evans']\n",
      "['Mark Evans']\n"
     ]
    }
   ],
   "source": [
    "hint_regexp = build_hint_regexp(' _ _ _ _   _ v a n s')\n",
    "for t in stripped_texts:\n",
    "    m = hint_regexp.findall(t)\n",
    "    if m:\n",
    "        print(m)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [],
   "source": [
    "def find_answer(search_result, hint):\n",
    "    hint_regexp = build_hint_regexp(hint)\n",
    "    for t in search_result:\n",
    "        m = hint_regexp.findall(t)\n",
    "        if m:\n",
    "            print(m)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['David Copperfield']\n",
      "['Joyce Frankenberg']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n",
      "['David Copperfield']\n"
     ]
    }
   ],
   "source": [
    "search_result = get_search_result('What eponymous Dickens character born with a caul over head')\n",
    "find_answer(search_result, '_ _ _ _ _   _ _ _ _ _ _ _ _ _ _ _')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['html class']\n",
      "['html class']\n",
      "['html class']\n",
      "['John Books']\n",
      "['1975 novel']\n",
      "['that would']\n",
      "['Five Movie']\n",
      "['many 1980s', 'Sure Thing']\n",
      "['2018 Oscar']\n",
      "['Know About']\n",
      "['tall today']\n",
      "['Were Never', 'Same After']\n",
      "['from these']\n",
      "['Feud shows']\n",
      "['Know About']\n"
     ]
    }
   ],
   "source": [
    "search_result = get_search_result('John Books was the final role of which actor')\n",
    "find_answer(search_result, '_ _ _ _   _ _ _ _ _')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Bluestones', 'Trilithons', 'DuckDuckGo']\n",
      "['Historical']\n",
      "['Historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n",
      "['historical', 'bluestones', 'trilithons']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['guaranteed']\n",
      "['bluestones', 'trilithons']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['conditions']\n",
      "['Bluestones']\n",
      "['guaranteed']\n",
      "['bluestones', 'trilithons']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['abprivivry']\n",
      "['collegiate']\n",
      "['coursehero']\n",
      "['translator']\n",
      "['Dictionary']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['deviantART']\n",
      "['scientific']\n",
      "['containing']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n",
      "['Trilithons']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n",
      "['Trilithons']\n",
      "['stonehenge']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n",
      "['biljoissac']\n",
      "['Wallpapers']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n",
      "['biljoissac']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n",
      "['triviaquiz']\n",
      "['Historical']\n",
      "['Bluestones']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['seatmerazu']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['cufamosist']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['historical']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge', 'monographs']\n",
      "['Stonehenge']\n",
      "['Bluestones']\n",
      "['everywhere']\n",
      "['monographs']\n",
      "['Bluestones']\n",
      "['appearance']\n",
      "['Bluestones']\n",
      "['appearance']\n",
      "['Fibreglass']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n",
      "['Bluestones']\n",
      "['Trilithons']\n",
      "['Stonehenge']\n"
     ]
    }
   ],
   "source": [
    "search_result = get_search_result('Where would you find Saracens Bluestones and Trilithons')\n",
    "find_answer(search_result, '_ _ _ _ _ _ _ _ _ _')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Stonehenge']\n",
      "['Stonehenge']\n",
      "['Stonehenge']\n",
      "['Stonehenge']\n",
      "['stonehenge']\n",
      "['Stonehenge']\n",
      "['Stonehenge']\n",
      "['Stonehenge']\n",
      "['Stonehenge']\n",
      "['Stonehenge']\n",
      "['Stonehenge']\n",
      "['Stonehenge']\n"
     ]
    }
   ],
   "source": [
    "search_result = get_search_result('Where would you find Saracens Bluestones and Trilithons')\n",
    "find_answer(search_result, '_ _ _ _ _ _ e n _ _')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "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": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}