-
Notifications
You must be signed in to change notification settings - Fork 0
/
Mission_to_Mars_Challenge.py
303 lines (153 loc) · 4.9 KB
/
Mission_to_Mars_Challenge.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
#!/usr/bin/env python
# coding: utf-8
# In[12]:
# 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[13]:
# Set up Splinter
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]:
# div tag is our parent element that holds all of the elements within it.
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[7]:
# Use the parent element to find the first `a` tag and save it as `news_title`..using a get_text method searching within par
news_title = slide_elem.find('div', class_='content_title').get_text()
news_title
# In[8]:
# Use the parent element to find the paragraph text ---summary output
news_p = slide_elem.find('div', class_='article_teaser_body').get_text()
news_p
# ### Featured Images
# In[5]:
# Visit URL
url = 'https://spaceimages-mars.com'
browser.visit(url)
# In[6]:
# Find and click the full image button
full_image_elem = browser.find_by_tag('button')[1]
full_image_elem.click()
# In[8]:
# Parse the resulting html with soup
html = browser.html
img_soup = soup(html, 'html.parser')
img_soup
# In[6]:
# Find the relative image url -get srl pulls the link to the image
img_url_rel = img_soup.find('img', class_='fancybox-image').get('src')
img_url_rel
# In[7]:
# Use the base URL to create an absolute URL
img_url = f'https://spaceimages-mars.com/{img_url_rel}'
img_url
# ### Mars Facts
# In[9]:
df = pd.read_html('https://galaxyfacts-mars.com')[0]
df.head()
# In[10]:
df.columns=['description', 'Mars', 'Earth']
df.set_index('description', inplace=True)
df
# In[11]:
df.to_html()
# ### Challenge_starter_code
# In[1]:
# 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[ ]:
# 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[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]:
# 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[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
# ### JPL Space Images Featured Image
# 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')
img_soup
# 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
# ### Mars Facts
# In[13]:
df = pd.read_html('https://galaxyfacts-mars.com')[0]
df.head()
# In[14]:
df.columns=['Description', 'Mars', 'Earth']
df.set_index('Description', inplace=True)
df
# In[15]:
df.to_html()
# # D1: Scrape High-Resolution Mars’ Hemisphere Images and Titles
# ### Hemispheres
# In[14]:
# 1. Use browser to visit the URL
browser.visit('https://marshemispheres.com/')
# 2. Create a list to hold the images and titles.
hemispheres = []
# 3. Write code to retrieve the image urls and titles for each hemisphere.
for i in range(4):
hemisphere = {}
hemisphere['title'] = browser.find_by_css('a.itemLink h3')[i].text
browser.find_by_css('a.itemLink h3')[i].click()
hemisphere['url'] = browser.find_by_text("Sample")["href"]
browser.back()
hemispheres.append(hemisphere)
# In[25]:
# 4. Print the list that holds the dictionary of each image url and title.
hemispheres
# In[15]:
# 5. Quit the browser
browser.quit()
# # D2: Update the Web APP with Mars's Hemisphere Images and Titles
# In[ ]: