In [1]:

    

import sys
sys.path.insert(0, '..')
import ttk


    

In [2]:

    

from ttk.corpus import load_headline_corpus

corpus = load_headline_corpus()


    

In [3]:

    

len(corpus.sents(dates=['2017-06-13']))


    

    
Out[3]:





2906

In [4]:

    

for cat in corpus.categories():
    print (cat)


    

    




Russia Today
Economist
BBC
NPR
CNN
Fox News
Huffington Post
Reuters
Wall Street Journal
ABC News
Slate
The New Yorker
CBS News
Al Jazeera
Business Insider
Breitbart
Associated Press
The Independent
CNBC
The Guardian
Evening Standard
New York Times
Boston Globe
Weekly Standard
The Atlantic
Washington Post

In [ ]: