import newspaper
cnn_paper = newspaper.build('http://cnn.com', memoize_articles=False)
for article in cnn_paper.articles:
print article.url
The code above works sometime and other times it doesn't. I'm working on a virtualenv however all the required libraries are also installed in the system.
Traceback (most recent call last):
File "/Users/Shapath/Developer/Python/Newspaper/Newspaper/Parser/newspaperparser.py", line 1, in <module>
import newspaper
File "/Users/Shapath/Developer/Python/Newspaper/lib/python2.7/site-packages/newspaper/__init__.py", line 10, in <module>
from .article import Article, ArticleException
File "/Users/Shapath/Developer/Python/Newspaper/lib/python2.7/site-packages/newspaper/article.py", line 16, in <module>
from . import images
File "/Users/Shapath/Developer/Python/Newspaper/lib/python2.7/site-packages/newspaper/images.py", line 20, in <module>
from . import urls
File "/Users/Shapath/Developer/Python/Newspaper/lib/python2.7/site-packages/newspaper/urls.py", line 17, in <module>
from .packages.tldextract import tldextract
File "/Users/Shapath/Developer/Python/Newspaper/lib/python2.7/site-packages/newspaper/packages/tldextract/__init__.py", line 1, in <module>
from .tldextract import extract, TLDExtract
File "/Users/Shapath/Developer/Python/Newspaper/lib/python2.7/site-packages/newspaper/packages/tldextract/tldextract.py", line 37, in <module>
import pkg_resources
File "/Users/Shapath/Developer/Python/Newspaper/lib/python2.7/site-packages/pkg_resources.py", line 76, in <module>
import parser
File "/Users/Shapath/Developer/Python/Newspaper/Newspaper/Parser/parser.py", line 4, in <module>
cnn_paper = newspaper.build('http://cnn.com')