rewrite chapter on web scraping

[damian0604]

xpath checker eruit voorbeelden kloppen niet meer

eventueel ook regexp eruit?

misschien css selector erin?

[damian0604]

sudo pip3 install cssselect

In [1]: import requests

In [2]: from lxml.html import fromstring

In [3]: response = requests.get('https://www.nu.nl/buitenland/5176460/britse-regering-zet-23-russische-diplomaten-vergiftiging-skripal.html')

In [4]: tree = fromstring(response.text)

In [5]: tree.xpath('//h1/text()')
Out[5]: 
['\n            Britse regering zet 23 Russische diplomaten uit om vergiftiging Skripal\n            ',
 '\n        ']

# of 

In [9]: e = tree.cssselect('.fluid')[0]

In [10]: e.text
Out[10]: '\n            Britse regering zet 23 Russische diplomaten uit om vergiftiging Skripal\n            '

[damian0604]

links:

# coding: utf-8

# In[8]:

import requests
from lxml.html import fromstring
tree = fromstring(requests.get('http://www.sueddeutsche.de/news?search=corporate+social+responsibility&sort=date&all%5B%5D=dep&all%5B%5D=typ&all%5B%5D=sys&all%5B%5D=time').text)
title = tree.xpath('//*[@class="entrylist__title"]/text()')
print(title)

# In[ ]:

overline = tree.xpath('//*[@class="entrylist__overtitle"]/text()')
print()

# In[10]:

links= tree.xpath('//a[@class="entrylist__link"]')

# In[11]:

l1 = links[0]

# In[14]:

echtelinks = [l.attrib["href"] for l in links]

# In[15]:

echtelinks