flipKart Scraper

flipKart.py

import bs4
import re
import urllib2
import sys

item = sys.argv[1:]
item = '+'.join(item)
link = 'http://www.flipkart.com/search/a/all?query={0}&vertical=all&dd=0&autosuggest[as]=off&autosuggest[as-submittype]=entered&autosuggest[as-grouprank]=0&autosuggest[as-overallrank]=0&autosuggest[orig-query]=&autosuggest[as-shown]=off&Search=%C2%A0&otracker=start&_r=YSWdYULYzr4VBYklfpZRbw--&_l=pMHn9vNCOBi05LKC_PwHFQ--&ref=a2c6fadc-2e24-4412-be6a-ce02c9707310&selmitem=All+Categories'.format(item)
response = urllib2.urlopen(link)
thePage = response.read()
soup = bs4.BeautifulSoup(thePage)
firstBlockSoup = soup.find('div', attrs={'class': 'size1of4 fk-medium-atom unit'})
if not firstBlockSoup: print "Item Not Found"
else:
    titleSoup = firstBlockSoup.find('a', attrs={'class': 'title tpadding5 fk-anchor-link'})
    priceSoup = firstBlockSoup.find('span', attrs={'class': 'price'})
    detailSoup = firstBlockSoup.find('ul', attrs={'class': 'fk-extra-details'})
    DetailAvailable = False
    ValueTable = {'title': '', 'price':0, 'details': 'No Details Available'}
    if len(list(detailSoup.children)) > 1: DetailAvailable = True 
    if DetailAvailable:
        st = u''
        for detail in detailSoup.findAll('span', attrs={'class': 'itm'}):
            st += detail.string + u'\n'
        ValueTable['details'] = st
    ValueTable['title'] = titleSoup.attrs['title']
    ValueTable['price'] = int(re.findall('\d+', priceSoup.string)[0])
    print ValueTable