In [4]:

    

from bs4 import BeautifulSoup as bs
import requests


    

In [5]:

    

url = 'http://apps.who.int/gho/data/view.ebola-sitrep.ebola-summary-latest?lang=en'


    

In [6]:

    

r = requests.get(url)
data = r.text
soup = bs(data)


    

    




/home/simonwoerpel/Websites/scraping/who-ebola/venv/lib/python3.5/site-packages/bs4/__init__.py:166: UserWarning: No parser was explicitly specified, so I'm using the best available HTML parser for this system ("lxml"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.

To get rid of this warning, change this:

 BeautifulSoup([your markup])

to this:

 BeautifulSoup([your markup], "lxml")

  markup_type=markup_type))

In [26]:

    

ul = soup.findAll('ul', {'class': 'list_dash'})[0]


    

In [30]:

    

lis = ul.findAll('li')


    

In [31]:

    

len(lis)


    

    
Out[31]:





283

In [32]:

    

lis[0]


    

    
Out[32]:





<li><a class="link_internal" href="view.ebola-sitrep.ebola-summary-20160120?lang=en">Data published on 20 January 2016</a></li>

In [49]:

    

url_prefix = 'http://apps.who.int/gho/data/'
from datetime import datetime
d_format = '%d %B %Y'


    

In [50]:

    

with open('files.csv', 'w') as f:
    for li in lis:
        d = li.a.text.lstrip('Data published on ')
        date = datetime.strptime(d, d_format).date().isoformat()
        url = li.a.attrs['href']
        f.writelines('{},{}{}\n'.format(date, url_prefix, url))


    

In [38]:

    

li


    

    
Out[38]:





<li><a class="link_internal" href="view.ebola-sitrep.ebola-summary-20141112?lang=en">Data published on 12 November 2014</a></li>

In [39]:

    

li.a.url


    

In [40]:

    

li.a


    

    
Out[40]:





<a class="link_internal" href="view.ebola-sitrep.ebola-summary-20141112?lang=en">Data published on 12 November 2014</a>

In [44]:

    

li.a.attrs['href']


    

    
Out[44]:





'view.ebola-sitrep.ebola-summary-20141112?lang=en'

In [ ]: