dhakatribunelinkfetcher.py

from bs4 import BeautifulSoup
import urllib2

# Scraping Info (visiting a link with tags)
"""
title: h2 .entry-title with link

"""

news_link = 'http://www.dhakatribune.com/tags/Garments'
urllib2_header = [('User-agent', 'Mozilla/5.0')]

if __name__ == '__main__':
    request = urllib2.Request(news_link)
    request.add_header('User-agent', 'Mozilla/5.0')
    response = urllib2.urlopen(request)

    soup = BeautifulSoup(response, 'lxml')
    # print soup.prettify()
    news_title = soup.findAll('h2', {"class": "entry-title"})

    for title in news_title:
        s = BeautifulSoup(str(title), 'lxml')
        # Gets title
        print s.a.string
        # Gets link
        print s.a['href']

    # print news_title