{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using the Google Books REST API \n",
    "\n",
    "#### API documentation:\n",
    "\n",
    "https://developers.google.com/books/docs/v1/getting_started#REST\n",
    "\n",
    "https://developers.google.com/books/docs/v1/using#query-params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Querying the Google Books API with an ISBN and loading the response\n",
    "\n",
    "from urllib.request import urlopen\n",
    "import json\n",
    "\n",
    "url = 'https://www.googleapis.com/books/v1/volumes?q=isbn:162779073X'\n",
    "\n",
    "json_text = urlopen(url).read().decode('utf8')\n",
    "\n",
    "print(json_text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Parsing the JSON text data to create a JSON object\n",
    "\n",
    "json_object = json.loads(json_text)\n",
    "\n",
    "json_object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing the top-level keys in the JSON object\n",
    "\n",
    "for key in json_object:\n",
    "    print(key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing the list of 'items', which contains metadata for a single book \n",
    "\n",
    "json_object['items']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing keys included in the metadata entry for a single book\n",
    "\n",
    "for key in json_object['items'][0]:\n",
    "    print(key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing keys included in a single book's 'volumeInfo'\n",
    "\n",
    "for key in json_object['items'][0]['volumeInfo']:\n",
    "    print(key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Viewing the contents of 'volumeInfo' for a single book\n",
    "\n",
    "json_object['items'][0]['volumeInfo']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Assigning the contents of 'volumeInfo' to the variable 'volume_info'\n",
    "\n",
    "item = json_object['items'][0]\n",
    "\n",
    "volume_info = item['volumeInfo']\n",
    "\n",
    "volume_info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Accessing the contents of several metadata fields\n",
    "\n",
    "volume_info['title']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "volume_info['publisher']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "volume_info['publishedDate']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "volume_info['description']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Note that the 'authors' field is formatted as a list\n",
    "\n",
    "volume_info['authors']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Reformatting the 'authors' list as a pipe-separated string\n",
    "\n",
    "'|'.join(volume_info['authors'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Combining several fields to create an example 'row'\n",
    "\n",
    "title = volume_info['title']\n",
    "authors = '|'.join(volume_info['authors'])\n",
    "published_date = volume_info['publishedDate']\n",
    "publisher = volume_info['publisher']\n",
    "description = volume_info['description']\n",
    "\n",
    "row = [title, authors, published_date, publisher, description]\n",
    "\n",
    "row "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using str.format() to construct API query URLs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\"This is a very {} sentence.\".format('informative')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "adjectives = ['informative', 'short', 'true', 'beautiful', 'misleading']\n",
    "\n",
    "for adjective in adjectives:\n",
    "    sentence = \"This is a very {} sentence.\".format(adjective)\n",
    "    print(sentence)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "adverbs = ['very', 'fairly', 'definitively', 'kinda']\n",
    "\n",
    "adjectives = ['informative', 'short', 'true', 'beautiful', 'misleading']\n",
    "\n",
    "for adverb in adverbs:\n",
    "    for adjective in adjectives:\n",
    "        sentence = \"This is a {} {} sentence.\".format(adverb, adjective)\n",
    "        print(sentence)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Generating a list of API query URLs\n",
    "\n",
    "isbns = ['1-6277-9073-X', '0-8050-9205-6', '0-307-40802-7', '0-307-35419-9', '0-307-35428-8', '0-9779440-0-X']\n",
    "\n",
    "for isbn in isbns:\n",
    "    sanitized_isbn = isbn.replace('-', '')  # removing hyphens from each ISBN\n",
    "    url = 'https://www.googleapis.com/books/v1/volumes?q=isbn:{}'.format(sanitized_isbn)\n",
    "    print(url)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## *Assignment:*\n",
    "\n",
    "1. Choose an author and create a list of their books' ISBNs. (Hint: Use Wikipedia.)\n",
    "\n",
    "2. Query the Google Books API for each ISBN in the list.\n",
    "\n",
    "3. Extract several metadata fields and add them to a list of lists.\n",
    "\n",
    "4. Write the list of lists to a CSV file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Google Books Free Text Query"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from urllib.request import urlopen\n",
    "import json\n",
    "\n",
    "url = 'https://www.googleapis.com/books/v1/volumes?q=Glenn+Greenwald&maxResults=40'\n",
    "\n",
    "json_text = urlopen(url).read().decode('utf8')\n",
    "\n",
    "json_object = json.loads(json_text)\n",
    "\n",
    "json_object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(json_object['items'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for item in json_object['items']:\n",
    "    print(item['volumeInfo']['title'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for item in json_object['items']:\n",
    "    volume_info = item['volumeInfo']\n",
    "    print('|'.join(volume_info['authors']))  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for item in json_object['items']:\n",
    "    volume_info = item['volumeInfo']\n",
    "    try:\n",
    "        print('|'.join(volume_info['authors']))  \n",
    "    except:\n",
    "        print('** No Author **')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Google Books Author Query"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from urllib.request import urlopen\n",
    "import json\n",
    "\n",
    "url = 'https://www.googleapis.com/books/v1/volumes?q=inauthor:\"Glenn+Greenwald\"&maxResults=40'\n",
    "\n",
    "json_text = urlopen(url).read().decode('utf8')\n",
    "\n",
    "json_object = json.loads(json_text)\n",
    "\n",
    "json_object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for item in json_object['items']:\n",
    "    volume_info = item['volumeInfo']\n",
    "    print(volume_info['title'])\n",
    "    try:\n",
    "        print('|'.join(volume_info['authors']))\n",
    "    except:\n",
    "        print('')\n",
    "    print()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## *Assignment:*\n",
    "\n",
    "1. Create a list of authors.\n",
    "\n",
    "2. Query the Google Books API for each author in the list.\n",
    "\n",
    "3. Extract several metadata fields for each book and add them all to a single list of lists.\n",
    "\n",
    "4. Write the list of lists to a CSV file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}