Mission_to_Mars.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "83dcc10b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import Splinter and BeautifulSoup\n",
    "from splinter import Browser\n",
    "from bs4 import BeautifulSoup as soup\n",
    "from webdriver_manager.chrome import ChromeDriverManager\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9ad32857",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "====== WebDriver manager ======\n",
      "Could not get version for google-chrome with the command:  powershell \"$ErrorActionPreference='silentlycontinue' ; (Get-Item -Path \"$env:PROGRAMFILES\\Google\\Chrome\\Application\\chrome.exe\").VersionInfo.FileVersion ; if (-not $? -or $? -match $error) { (Get-Item -Path \"$env:PROGRAMFILES(x86)\\Google\\Chrome\\Application\\chrome.exe\").VersionInfo.FileVersion } if (-not $? -or $? -match $error) { (Get-Item -Path \"$env:LOCALAPPDATA\\Google\\Chrome\\Application\\chrome.exe\").VersionInfo.FileVersion } if (-not $? -or $? -match $error) { reg query \"HKCU\\SOFTWARE\\Google\\Chrome\\BLBeacon\" /v version } if (-not $? -or $? -match $error) { reg query \"HKLM\\SOFTWARE\\Wow6432Node\\Microsoft\\Windows\\CurrentVersion\\Uninstall\\Google Chrome\" /v version }\"\n",
      "Current google-chrome version is UNKNOWN\n",
      "Get LATEST chromedriver version for UNKNOWN google-chrome\n",
      "Trying to download new driver from https://chromedriver.storage.googleapis.com/99.0.4844.51/chromedriver_win32.zip\n",
      "Driver has been saved in cache [C:\\Users\\CFlynn3\\.wdm\\drivers\\chromedriver\\win32\\99.0.4844.51]\n"
     ]
    }
   ],
   "source": [
    "executable_path = {'executable_path': ChromeDriverManager().install()}\n",
    "browser = Browser('chrome', **executable_path, headless=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f9a5d847",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Visit the mars nasa news site\n",
    "# search for elements with a specific combination of tag (div) and attribute (list_text)\n",
    "# telling our browser to wait one second before searching for components\n",
    "url = 'https://redplanetscience.com'\n",
    "browser.visit(url)\n",
    "# Optional delay for loading the page\n",
    "browser.is_element_present_by_css('div.list_text', wait_time=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "70fda82d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# set up HTML parser\n",
    "\n",
    "# The . is used for selecting classes such as list_text,\n",
    "# so the code 'div.list_text' pinpoints the <div /> tag with the class of list_text\n",
    "\n",
    "html = browser.html\n",
    "news_soup = soup(html, 'html.parser')\n",
    "slide_elem = news_soup.select_one('div.list_text')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "4909e9a1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<div class=\"content_title\">NASA's New Mars Rover Will Use X-Rays to Hunt Fossils</div>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Begin scraping\n",
    "\n",
    "slide_elem.find('div', class_='content_title')\n",
    "\n",
    "# We chain .find onto our previously assigned variable, slide_elem. \n",
    "# When we do this, we're saying, \"This variable holds a ton of information, \n",
    "# so look inside of that information to find this specific data.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9bd8e34c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"NASA's New Mars Rover Will Use X-Rays to Hunt Fossils\""
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Use the parent element to find the first `a` tag and save it as `news_title`\n",
    "news_title = slide_elem.find('div', class_='content_title').get_text()\n",
    "news_title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "fe5ced6d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# There are two methods used to find tags and attributes with BeautifulSoup:\n",
    "\n",
    "    # .find() \n",
    "        # used when we want only the first class and attribute we've specified.\n",
    "        \n",
    "    # .find_all() \n",
    "        # used when we want to retrieve all of the tags and attributes.\n",
    "\n",
    "# For example, if we were to use .find_all() instead of .find() when pulling the summary, \n",
    "# we would retrieve all of the summaries on the page instead of just the first one."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "4eb28cb0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"PIXL, an instrument on the end of the Perseverance rover's arm, will search for chemical fingerprints left by ancient microbes.\""
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Use the parent element to find the paragraph text\n",
    "news_p = slide_elem.find('div', class_='article_teaser_body').get_text()\n",
    "news_p"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8bd7b82",
   "metadata": {},
   "source": [
    "# 10.3.4\n",
    "# use markdown to separate the article scraping from the image scraping.\n",
    "\n",
    "### Featured Images"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5d1c2dc5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Visit URL\n",
    "url = 'https://spaceimages-mars.com'\n",
    "browser.visit(url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "776349b4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Find and click the full image button\n",
    "full_image_elem = browser.find_by_tag('button')[1]\n",
    "full_image_elem.click()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "37ae21cf",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Parse the resulting html with soup\n",
    "html = browser.html\n",
    "img_soup = soup(html, 'html.parser')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "13cb9ad9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'image/featured/mars2.jpg'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Find the relative image url\n",
    "\n",
    "img_url_rel = img_soup.find('img', class_='fancybox-image').get('src')\n",
    "\n",
    "    # img tag is nested in HTML\n",
    "    # .get('src') pulls the link to the image\n",
    "\n",
    "img_url_rel"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "bb5438a6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://spaceimages-mars.com/image/featured/mars2.jpg'"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Use the base URL to create an absolute URL\n",
    "img_url = f'https://spaceimages-mars.com/{img_url_rel}'\n",
    "img_url"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "b25d41cf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Mars</th>\n",
       "      <th>Earth</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>description</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Mars - Earth Comparison</th>\n",
       "      <td>Mars</td>\n",
       "      <td>Earth</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Diameter:</th>\n",
       "      <td>6,779 km</td>\n",
       "      <td>12,742 km</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Mass:</th>\n",
       "      <td>6.39 × 10^23 kg</td>\n",
       "      <td>5.97 × 10^24 kg</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Moons:</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Distance from Sun:</th>\n",
       "      <td>227,943,824 km</td>\n",
       "      <td>149,598,262 km</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Length of Year:</th>\n",
       "      <td>687 Earth days</td>\n",
       "      <td>365.24 days</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Temperature:</th>\n",
       "      <td>-87 to -5 °C</td>\n",
       "      <td>-88 to 58°C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                    Mars            Earth\n",
       "description                                              \n",
       "Mars - Earth Comparison             Mars            Earth\n",
       "Diameter:                       6,779 km        12,742 km\n",
       "Mass:                    6.39 × 10^23 kg  5.97 × 10^24 kg\n",
       "Moons:                                 2                1\n",
       "Distance from Sun:        227,943,824 km   149,598,262 km\n",
       "Length of Year:           687 Earth days      365.24 days\n",
       "Temperature:                -87 to -5 °C      -88 to 58°C"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 10.3.5 SCRAPING TABLES\n",
    "# Instead of scraping each row, or the data in each <td />, \n",
    "# we're going to scrape the entire table with Pandas' .read_html() function.\n",
    "\n",
    "df = pd.read_html('https://galaxyfacts-mars.com')[0]\n",
    "df.columns=['description', 'Mars', 'Earth']\n",
    "df.set_index('description', inplace=True)\n",
    "\n",
    "    # The Pandas function read_html() specifically searches for and returns a list of tables found in the HTML.\n",
    "    # By using the .set_index() function, we're turning the Description column into the DataFrame's index.\n",
    "    \n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "1d93e58a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'<table border=\"1\" class=\"dataframe\">\\n  <thead>\\n    <tr style=\"text-align: right;\">\\n      <th></th>\\n      <th>Mars</th>\\n      <th>Earth</th>\\n    </tr>\\n    <tr>\\n      <th>description</th>\\n      <th></th>\\n      <th></th>\\n    </tr>\\n  </thead>\\n  <tbody>\\n    <tr>\\n      <th>Mars - Earth Comparison</th>\\n      <td>Mars</td>\\n      <td>Earth</td>\\n    </tr>\\n    <tr>\\n      <th>Diameter:</th>\\n      <td>6,779 km</td>\\n      <td>12,742 km</td>\\n    </tr>\\n    <tr>\\n      <th>Mass:</th>\\n      <td>6.39 × 10^23 kg</td>\\n      <td>5.97 × 10^24 kg</td>\\n    </tr>\\n    <tr>\\n      <th>Moons:</th>\\n      <td>2</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <th>Distance from Sun:</th>\\n      <td>227,943,824 km</td>\\n      <td>149,598,262 km</td>\\n    </tr>\\n    <tr>\\n      <th>Length of Year:</th>\\n      <td>687 Earth days</td>\\n      <td>365.24 days</td>\\n    </tr>\\n    <tr>\\n      <th>Temperature:</th>\\n      <td>-87 to -5 °C</td>\\n      <td>-88 to 58°C</td>\\n    </tr>\\n  </tbody>\\n</table>'"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Pandas also has a way to easily convert our DataFrame back \n",
    "# into HTML-ready code using the .to_html() function. \n",
    "\n",
    "df.to_html()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "63c16202",
   "metadata": {},
   "outputs": [],
   "source": [
    "browser.quit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1e182fac",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "PythonData",
   "language": "python",
   "name": "pythondata"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}