In [1]:

    

from requests_html import HTMLSession

session = HTMLSession()


    

In [3]:

    

resp = session.get('http://enter.lumenprize.com/people-choice-award-2018')

resp.ok


    

    
Out[3]:





True

In [13]:

    

people_urls = list(resp.html.find('.view-content', first=True).absolute_links)

len(people_urls)


    

    
Out[13]:





60

In [14]:

    

resp = session.get(people_urls[0])

resp.ok


    

    
Out[14]:





True

In [19]:

    

[x.text for x in resp.html.find('.percent')]


    

    
Out[19]:





['38%', '62%']

In [21]:

    

resp.html.find('.field-name-field-artist-name', first=True).text


    

    
Out[21]:





'Béatrice Lartigue, Lab212'

In [25]:

    

rows = []

for url in people_urls:
    resp = session.get(url)
    
    artist = resp.html.find('.field-name-field-artist-name', first=True).text
    up, down = [x.text for x in resp.html.find('.percent')]

    rows += [{
        'artist': artist,
        'url': url,
        'up': up,
        'down': down
    },]


    

In [27]:

    

import pandas as pd


    

In [28]:

    

df = pd.DataFrame(rows)


    

In [29]:

    

df.head()


    

    
Out[29]:







  

    

      

      
artist
      
down
      
up
      
url
    
  
  

    

      
0
      
Béatrice Lartigue, Lab212
      
62%
      
38%
      
http://enter.lumenprize.com/node/756
    
    

      
1
      
Scott Billings
      
49%
      
51%
      
http://enter.lumenprize.com/node/902
    
    

      
2
      
Clelio de Paula
      
30%
      
70%
      
http://enter.lumenprize.com/node/874
    
    

      
3
      
Synspecies (Elías Merino & Tadej Droljc)
      
75%
      
25%
      
http://enter.lumenprize.com/node/523
    
    

      
4
      
Ben Bogart
      
72%
      
28%
      
http://enter.lumenprize.com/node/694
    
  

In [ ]: