If you're specifically looking at news articles, go for the Python library Newspaper: http://newspaper.readthedocs.io/en/latest/

Auto-detection of languages, and will automatically give you things like the following:

>>> article.parse()

>>> article.authors [u'Leigh Ann Caldwell', 'John Honway']

>>> article.text u'Washington (CNN) -- Not everyone subscribes to a New Year's resolution...'

>>> article.top_image u'http://someCDN.com/blah/blah/blah/file.png'

>>> article.movies [u'http://youtube.com/path/to/link.com', ...]