{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Make a new `JournalCrawler` (soup)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can create a new `JournalCrawler` whose `crawl_type` is **\"soup\"**."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[32m[success]\u001b[0m local driver can be built.\n",
      "\u001b[31m[failure]\u001b[0m remote driver can't be built.\n",
      "DRIVER_TYPE: \u001b[32mlocal\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "import re\n",
    "import time\n",
    "import requests\n",
    "import urllib\n",
    "import pandas as pd\n",
    "from bs4 import BeautifulSoup\n",
    "from gummy.utils import whichJournal, canonicalize, get_driver, find_text, split_soup, split_soup_by_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_soup(url):\n",
    "    return BeautifulSoup(requests.get(url).content, \"html.parser\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_soup_driver(url):\n",
    "    with get_driver() as driver:\n",
    "        driver.get(url)\n",
    "        time.sleep(3)\n",
    "        html = driver.page_source.encode(\"utf-8\")\n",
    "    return BeautifulSoup(html, \"html.parser\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## create `get_contents_soup`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://www.google.com/\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DRIVER_TYPE: \u001b[32mlocal\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "soup = get_soup(url)\n",
    "soup_driver = get_soup_driver(url)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### `get_title_from_soup`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```py\n",
    "    def get_title_from_soup(self, soup):\n",
    "        title = find_text(soup=soup, name=\"h1\", class_=\"title\", strip=True)\n",
    "        return title\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'[NOT FOUND]'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "find_text(soup=soup, name=\"h1\", class_=\"title\", strip=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### `get_sections_from_soup`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```py\n",
    "def get_sections_from_soup(self, soup):\n",
    "    sections = soup.find_all(name=\"h2\", class_=\"section-title\")\n",
    "    return sections\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "soup.find_all(name=\"h2\", class_=\"section-title\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "soup_driver.find_all(name=\"h2\", class_=\"section-title\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### `get_sections_from_soup`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```py\n",
    "    def get_sections_from_soup(self, soup):\n",
    "        sections = soup.find_all(name=\"section\", attrs={\"type\" : \"other\"})\n",
    "        abst = soup.find(name=\"div\", class_=\"art-abstract\")\n",
    "        if abst is not None:\n",
    "            asbt_section = soup.new_tag(name=\"section\", attrs={\"type\" : \"other\"})\n",
    "            asbt_h2Tag = soup.new_tag(name=\"h2\")\n",
    "            asbt_h2Tag.string = \"0. Abstract\"\n",
    "            asbt_section.append(asbt_h2Tag)\n",
    "            asbt_section.append(abst)\n",
    "            sections.insert(0, asbt_section)\n",
    "        sections = [e for e in soup.find_all(name=\"section\") if e.get(\"aria-labelledby\") not in self.AvoidAriaLabel]\n",
    "        return sections\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}