iteratecnn

In [23]: for i in html_content.iterchildren():
  ....: print i
  ....:
<Element head at 0x7f43a5737db8>
<Element body at 0x7f43a5737e10>
 
In [24]: news_stories = html_content.xpath('//h3[@data-analytics]/a/span/text()')
 
In [25]: news_links = html_content.xpath('//h3[@data-analytics]/a/@href')
 
In [26]: news_links
Out[26]:
['/2016/07/25/politics/democratic-convention-dnc-emails-russia/index.html',
 '/2016/07/25/us/fort-myers-nightclub-shooting/index.html',
 '/2016/07/24/world/ansbach-germany-blast/index.html',
 '/2016/07/25/europe/germany-attacks-asylum-seekers-refugees/index.html',
 '/2016/07/25/world/protests-boy-killed-bangladesh/index.html',
 '/2016/06/15/politics/muslim-ban-maps-donald-trump/index.html',
 '/2016/07/24/world/qandeel-baloch-death-father-azeem/index.html',
 '/2016/07/24/aviation/tripadvisor-world-favorite-airlines/index.html',
 '/2016/07/25/africa/koffi-olomide-dancer-kenya/index.html']
 
In [27]: news_stories
Out[27]:
['FBI launches investigation into suspected Russian email hack',
 "Two dead, 14 injured at Florida 'Swimsuit Glow Party'",
 'Suicide bomber was slated to be deported',
 'German public questions refugee policy',
 'Brutal killing of boy, 10, sparks protests',
 "Mapped: Trump's Muslim travel ban ",
 "Father of slain social star: 'I want revenge'",
 "World's most-loved airline is...",
 'Pop star apologizes for kicking dancer ']