Subversion Repositories SmartDukaan

import urllib2

from BeautifulSoup import BeautifulSoup, NavigableString

import re

import sys

invalid_tags = ['b', 'i', 'u']

bestSellers = []

def strip_tags(html, invalid_tags):

    soup = BeautifulSoup(html,convertEntities=BeautifulSoup.HTML_ENTITIES)

    for tag in soup.findAll(True):

        if tag.name in invalid_tags:

            s = ""

            for c in tag.contents:

                if not isinstance(c, NavigableString):

                    c = strip_tags(unicode(c), invalid_tags)

                s += unicode(c)

            tag.replaceWith(s)

    return soup

class AmazonScraper:

    def __init__(self):

        self.count_trials = 0

    def read(self, url):

        request = urllib2.Request(url)

        request.add_header('User-Agent', 'Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.218 Safari/535.1')

        opener = urllib2.build_opener()

        response_data = ""

        try:

            response_data = opener.open(request).read()

            print "Fetched response from flipkart for %s" %(url)

        except urllib2.HTTPError as e:

            print 'ERROR: ', e

            print 'Retrying'

            self.count_trials += 1

            if self.count_trials < 3:

                return self.read(url)

        self.response_data=response_data

    def createData(self):

        self.soup = strip_tags(self.response_data,invalid_tags)

        self.response_data =None

        return self.scrape(self.soup)

    def scrape(self,soup):

        sellerData = soup.findAll("div" , {"class" : "a-row a-spacing-mini olpOffer"})

        for data in sellerData:

            print "sellerData****"

            price = data.find('span', attrs={'class' : re.compile('.*olpOfferPrice*')}).find('span').text

            print "Unit cost= ",float(price.replace("Rs.","").replace(",",""))

            unitCost = float(price.replace("Rs.","").replace(",",""))

            shippingCost = data.find('p', attrs={'class' : re.compile('.*olpShippingInfo*')}).find('span').text

            if "FREE" in shippingCost:

                print "shippingCost=0"

                shippingCost = 0

            else:

                print "shippingCost= ",float(shippingCost.replace("+Rs.","").replace("Delivery",""))

                shippingCost = float(shippingCost.replace("+Rs.","").replace("Delivery",""))

            sellerColumn =  data.find('p', attrs={'class' : re.compile('.*olpSellerName*')})

            print "Seller info ",sellerColumn

            ratingColumn = data.find('p', attrs={'class' : 'a-spacing-small'}).find('a').contents[0]

            print "Rating info ",ratingColumn

            print "***********************"

            return unitCost+shippingCost

    def getBestSellers(self,soup):

        global bestSellers

        bestSellerData = soup.findAll("div" , {"class" : "zg_itemImmersion"})

        for data in bestSellerData:

            temp = {}

            rankVal = data.find('span', attrs={'class' : 'zg_rankNumber'}).text

            print "Rank = ",rankVal.lstrip()

            productUrl = data.find('a')['href']

            print "Product URL = ",productUrl.lstrip().replace("\n","")

            productUrl = productUrl.replace("http://www.amazon.in/","").lstrip()

            ind = productUrl.rindex("/dp/")

            productName = productUrl[0:productUrl.rindex("/dp/")]

            print "Product Name = ",productName

            asin = productUrl[ind+4: productUrl.rindex("/ref=")]

            print "Asin = ",asin

            print "**********************"

            temp['Rank'] = rankVal.lstrip().replace(".","")

            temp['Url'] = productUrl.lstrip().replace("\n","")

            temp['Product Name'] = productUrl[0:productUrl.rindex("/dp/")]

            temp['Asin'] = productUrl[ind+4: productUrl.rindex("/ref=")]

            bestSellers.append(temp)

if __name__ == '__main__':

    scraper = AmazonScraper()

    scraper.read('http://www.amazon.in/gp/offer-listing/B001D0ROGO/ref=olp_sort_ps')

    print scraper.createData()