scraping 2018 nieman predictions

##libraries

import urllib2
from bs4 import BeautifulSoup
import csv


import sys
reload(sys)
sys.setdefaultencoding('utf8')

## getting the url we want to scrape

nieman_page = 'http://www.niemanlab.org/2017/12/the-rise-of-skeptical-reading/'

## querying the page and returning the html to the variable page

page = urllib2.urlopen(nieman_page).read()

## parsing html using BeautifulSoup and storing html in variable soup

soup = BeautifulSoup(page, 'html.parser')

## writes to csv 

file = csv.writer(open("Predictions.csv", "w"))
file.writerow(["Headline", "Blurb", "Byline", "Text"])


## prints headline

for headline in soup.findAll(attrs={'class' : 'simple-headline'}):
	headline = headline.text

## prints blurb    
    
for blurb in soup.findAll(attrs={'class' : 'simple-post-deck'}):
	blurb = blurb.text
    
## prints byline    
    
for author in soup.findAll(attrs={'class' : 'predix-byline'}):
	author = author.text
    
## prints text + author bio    
    
for prediction in soup.findAll(attrs={'class' : 'predix-storybody'}):
	prediction = prediction.text
	
	file.writerow([headline, blurb, author, prediction])