news_scraper_rev1.py

# -*- coding: utf-8 -*-
"""
Created on Sun Aug 14 20:37:16 2016

@author: Manash
"""
from bs4 import BeautifulSoup
import urllib2
import unicodedata
from datetime import datetime

# baseurl
news_paper_url = "http://en.prothom-alo.com/archive"
baseurl = 'http://en.prothom-alo.com/'

# request
prothom_alo_request = urllib2.urlopen(news_paper_url)

# Creating soup
prothomalo_soup = BeautifulSoup(prothom_alo_request, 'lxml')

# Getting all news links 
news_links = [baseurl + link['href'] for link in prothomalo_soup.find('div', {'class' : 'list list_square mb20'}).findAll('a')]

# selecting first news
first_news = news_links[0]

print first_news

# Request of the first news
news_request = urllib2.urlopen(first_news)

# soup
first_news_soup = BeautifulSoup(news_request)

# getting news
news_text = first_news_soup.find(itemprop="articleBody").get_text()
news_update = first_news_soup.find(itemprop="datePublished").get_text()

time = datetime.strptime(news_update[:5], "%H:%M")
convtime = time.strftime("%I:%M %p")

print convtime

print news_update[:5]

print unicodedata.normalize('NFKD',  news_text).encode('ascii','ignore')