#!/usr/bin/env python

# coding: utf-8

# In[1]:

# Import Splinter and BeautifulSoup

from splinter import Browser

from bs4 import BeautifulSoup as soup

from webdriver_manager.chrome import ChromeDriverManager

import pandas as pd

# In[2]:

executable_path = {'executable_path':ChromeDriverManager().install()}

browser = Browser('chrome', **executable_path, headless=False)

# In[3]:

# Visit the mars nasa news site

url = 'https://redplanetscience.com'

browser.visit(url)

# Optional delay for loading the page

browser.is_element_present_by_css('div.list_text', wait_time=1)

# In[4]:

html = browser.html

news_soup = soup(html, 'html.parser')

slide_elem = news_soup.select_one('div.list_text')

# In[5]:

slide_elem.find('div',class_='content_title')

# In[6]:

# Use the parent element to find the first `a` tag and save it as `news_title`

news_title = slide_elem.find('div',class_='content_title').get_text()

news_title

# In[7]:

# Use the parent element to find the paragraph text

news_p = slide_elem.find('div',class_='article_teaser_body').get_text()

news_p

# #### Scraping Image

# ### Features Images

# In[8]:

# Visit URL

url = 'https://spaceimages-mars.com'

browser.visit(url)

# In[9]:

# Find and click the full image button

full_image_elem = browser.find_by_tag('button')[1]

full_image_elem.click()

# In[10]:

# Parse the resulting html with soup

html = browser.html

img_soup = soup(html, 'html.parser')

# In[11]:

# Find the relative image url

img_url_rel = img_soup.find('img', class_='fancybox-image').get('src')

img_url_rel

# In[12]:

# Use the base URL to create an absolute URL

img_url = f'https://spaceimages-mars.com/{img_url_rel}'

img_url

# ### Scrape Mars Data: Mars Facts

# In[13]:

# Visit URL

url = 'https://galaxyfacts-mars.com/'

browser.visit(url)

# In[14]:

df = pd.read_html('https://galaxyfacts-mars.com')[0]

df.columns=['description', 'Mars', 'Earth']

df.set_index('description', inplace=True)

df

# In[15]:

# Turn the DataFrame into HTML-ready code

df.to_html()

# In[16]:

# Add the code to end the automated browsing session

browser.quit()

# In[65]:

# Import Splinter, BeautifulSoup, and Pandas

from splinter import Browser

from bs4 import BeautifulSoup as soup

import pandas as pd

from webdriver_manager.chrome import ChromeDriverManager

# In[66]:

# Set the executable path and initialize Splinter

executable_path = {'executable_path': ChromeDriverManager().install()}

browser = Browser('chrome', **executable_path, headless=False)

# ### Visit the NASA Mars News Site

# In[19]:

# Visit the mars nasa news site

url = 'https://redplanetscience.com/'

browser.visit(url)

# Optional delay for loading the page

browser.is_element_present_by_css('div.list_text', wait_time=1)

# In[20]:

# Convert the browser html to a soup object and then quit the browser

html = browser.html

news_soup = soup(html, 'html.parser')

slide_elem = news_soup.select_one('div.list_text')

# In[21]:

slide_elem.find('div', class_='content_title')

# In[22]:

# Use the parent element to find the first a tag and save it as `news_title`

news_title = slide_elem.find('div', class_='content_title').get_text()

news_title

# In[23]:

# Use the parent element to find the paragraph text

news_p = slide_elem.find('div', class_='article_teaser_body').get_text()

news_p

# ### JPL Space Images Featured Image

# In[24]:

# Visit URL

url = 'https://spaceimages-mars.com'

browser.visit(url)

# In[25]:

# Find and click the full image button

full_image_elem = browser.find_by_tag('button')[1]

full_image_elem.click()

# In[26]:

# Parse the resulting html with soup

html = browser.html

img_soup = soup(html, 'html.parser')

img_soup

# In[27]:

# find the relative image url

img_url_rel = img_soup.find('img', class_='fancybox-image').get('src')

img_url_rel

# In[28]:

# Use the base url to create an absolute url

img_url = f'https://spaceimages-mars.com/{img_url_rel}'

img_url

# ### Mars Facts

# In[29]:

df = pd.read_html('https://galaxyfacts-mars.com')[0]

df.head()

# In[30]:

df.columns=['Description', 'Mars', 'Earth']

df.set_index('Description', inplace=True)

df

# In[31]:

df.to_html()

# # D1: Scrape High-Resolution Mars’ Hemisphere Images and Titles

# ### Hemispheres

# In[67]:

# 1. Use browser to visit the URL

url = "https://astrogeology.usgs.gov/search/results?q=hemisphere+enhanced&k1=target&v1=Mars"

browser.visit(url)

# In[68]:

# 2. Create a list to hold the images and titles.

hemisphere_image_urls = []

# 3. Write code to retrieve the image urls and titles for each hemisphere.

# Given there are 4 search results in the page, identify the variable representing the number of search results.

results = browser.find_by_css("h3")

# Create the loop through the search results.

for item in range(len(results)):

# Create an empty dictionary to hold image url and title data

hemisphere = {}

# Find element on each loop and click

browser.find_by_css("h3")[item].click()

# Find Image tag and Extract

sample_element = browser.find_link_by_text("Sample").first

hemisphere['img_url'] = sample_element['href']

# Retrieve Hemisphere title

hemisphere['title'] = browser.find_by_css("h2.title").text

# Append Hemisphere data to List

hemisphere_image_urls.append(hemisphere)

# Navigate the page back

browser.back

# In[69]:

# 4. Print the list that holds the dictionary of each image url and title.

hemisphere_image_urls

# In[35]:

# 5. Quit the browser

browser.quit()

# In[ ]: