Mission to Mars

# Declare Dependencies 
                import requests
                import pandas as pd
                from splinter import Browser
                from bs4 import BeautifulSoup 
                as bs

                    # Choose the executable path to driverexecutable_path 
                    = {'executable_path': 
                    'chromedriver.exe'} browser 
                    = Browser('chrome', 
                    **executable_path, headless=False)

            # Visit NASA news url through splinter modulenews_url 
            = 'https://mars.nasa.gov/news
            'browser.visit(news_url)

# HTML object to create a Beautiful Soup objectnews_html 
                = browser.html
news_soup = bs(news_html,'lxml')

# Retrieve elements that contains the latest news title and news_paragraph
news_title = news_soup.find('div', class_='content_title').text
news_p = news_soup.find('div', class_='article_teaser_body').text

# Print scrapped data 
print(news_title)
print(news_p)

# Visit Mars Space Images through splinter module
jpl_url = 'https://www.jpl.nasa.gov/spaceimages/?search=&category=Mars'
browser.visit(jpl_url)

# HTML object to create a Beautiful Soup object
jpl_html = browser.html
jsoup = bs(jpl_html,'lxml')

# Retrieve background-image url from style tag and print img_link
img_link = jsoup.find('div', class_='carousel_container').article.footer.a['data-fancybox-href']
print(img_link)

# Retrive base url and concatenate website url with scrapped route
base_link = 'https://www.jpl.nasa.gov'
featured_image_url = base_link + img_link

# Print full link to featured image
print(featured_image_url)

# Visit Mars Weather Twitter through splinter module
weather_url = 'https://twitter.com/marswxreport?lang=en'
browser.visit(weather_url)

# HTML object to create a Beautiful Soup object
w_html = browser.html
wsoup = bs(w_html,'lxml')

tweets = wsoup.find_all('p', class_='TweetTextSize')
for tweet in tweets:
    weather_tweet = tweet.find('a').previousSibling
    if 'sol' and 'pressure' in weather_tweet:
        break
    else:
        continue
weather_tweet

#Replace new line with , and print data
mars_weather = weather_tweet.replace('\n',', ')
print(mars_weather)

# Visit Mars facts url 
fact_url = 'https://space-facts.com/mars/'

# Use Panda's 'read_html' to parse the url
fact_table = pd.read_html(fact_url)

# Find the Mars facts table
mars_fact_table = fact_table[0]
mars_fact_table

# Assign the columns Description and Value and use Description as index
mars_fact_table.columns = ['Description','Value']
mars_fact_table

# Generate HTML table from Mars facts dataframe
mars_fact_table_html = mars_fact_table.to_html (header=True, index=False, justify='center')

#Strip unwanted newlines to clean up the table and print
mars_fact_table_html = mars_fact_table_html.replace('\n', '')
print(mars_fact_table_html)

# Visit hemispheres website through splinter module 
hem_url = 'https://astrogeology.usgs.gov/search/results?q=hemisphere+enhanced&k1=target&v1=Mars'
browser.visit(hem_url)

# HTML object to create a Beautiful Soup object
hem_html = browser.html
hsoup = bs(hem_html,'lxml')

# # Retreive all items that contain mars hemispheres information
items = hsoup.find_all('div', class_='item')

# Create empty list for hemisphere urls 
hemisphere_image_urls = []

# Store the main_ul 
hemispheres_main_url = 'https://astrogeology.usgs.gov'

# Loop through the items
for i in items: 
    # Store title
    title = i.find('h3').text.strip(' Enhanced')
    
    # Store link that leads to full image website
    partial_img_url = i.find('a', class_='itemLink product-item')['href']
    
    # Visit the link that contains the full image website 
    browser.visit(hemispheres_main_url + partial_img_url)
    
    # HTML Object of individual hemisphere information website 
    partial_img_html = browser.html
    
    # Parse HTML with Beautiful Soup for every individual hemisphere information website 
    hsoup = bs(partial_img_html,'lxml')
    
    # Retrieve full image source 
    img_url = hemispheres_main_url + hsoup.find('img', class_='wide-image')['src']
    
    # Append the retreived information into a list of dictionaries 
    hemisphere_image_urls.append({"title" : title, "img_url" : img_url})

# Print hemisphere_image_urls
print(hemisphere_image_urls)