Subversion Repositories SmartDukaan

from BeautifulSoup import BeautifulSoup, NavigableString

import re

import sys

import  datetime

import grequests

import re

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 AmazonAsyncScraper:

    def __init__(self):

        self.count_trials = 0

    def read(self, urls, findStore):

        returnMap = {}

        print datetime.datetime.now()

        header = {'User-Agent':'Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.218 Safari/535.1',

                  'Accept-Charset' : 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',

                  'Accept-Encoding':'gzip,deflate,sdch'

                  }

        rs = (grequests.get(u, headers=header) for u in urls)

        for x in grequests.map(rs):

            soup = strip_tags(x.text,invalid_tags)

            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)

            x.close()

            sellerCount=0

            info = []

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

            dataLength = len(sellerData)

            for data in sellerData:

                tempMap={}

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

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

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

                if "FREE" in shippingCost:

                    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*')})

                store=""

                storeUrl=""

                if findStore:

                    storeUrl = sellerColumn.find('a')['href']

                    temp =  sellerColumn.find('a')

                    store = temp.text

                    if len(store)==0:

                        dom_in = storeUrl.find("www.amazon.in")

                        if dom_in ==-1:

                            storeUrl="http://amazon.in"+storeUrl

                        if storeUrl[storeUrl.rfind('/')+1:]=='AF6E3O0VE0X4D':

                            store = 'Saholic'

                    if len(store)!=0:

                        tempMap['isStoreFront']='True'

                    else:

                        tempMap['isStoreFront']='False'

                    tempMap['storeUrl'] =storeUrl

                asinind = x.url.index("offer-listing")

                refind = x.url.index("/ref=olp_sort_ps")

                asin = x.url[asinind+14:refind].strip()

                sellerCount+=1

                if sellerCount==1:

                    tempMap['sellerName'] = store.strip()

                    tempMap['sellerPrice'] = unitCost+shippingCost

                if sellerCount==2:

                    tempMap['sellerName'] = store.strip()

                    tempMap['sellerPrice'] = unitCost+shippingCost

                if sellerCount==3:

                    tempMap['sellerName'] = store.strip()

                    tempMap['sellerPrice'] = unitCost+shippingCost

                info.append(tempMap) 

                if sellerCount==3 or sellerCount==dataLength:

                    returnMap[asin] = info 

                    break

        if findStore:

            return self.findStoreFront(returnMap)

        else:

            return returnMap

    def findStoreFront(self,returnMap):

        storeFront={}

        for arr in returnMap.itervalues():

            for dic in arr:

                if dic['isStoreFront']!='True':

                    storeFront[dic.get('storeUrl')] =''

        rs = (grequests.get(u,stream=False) for u in storeFront.keys())

        for x in grequests.map(rs):

            soup = strip_tags(x.text,invalid_tags)

            x.close

            #print x.url.rfind('&me=')

            #print x.url[x.url.rfind('&me='):].rfind('&')

            mId= x.url[x.url.rfind('&me=')+4:x.url[x.url.rfind('&me='):].rfind('&')+x.url.rfind('&me=')]

            sellerName = soup.title.string

            #print mId

            try:

                ind = sellerName.index("@ Amazon.in")

                sellerName = sellerName[0:ind].strip()

            except:

                try:

                    ind = sellerName.split(":")

                    sellerName = ind[1].strip()

                except:

                    sellerName =""

            #storeFront[re.compile('*'+mId+'.*')] = sellerName

            #print mId

            #print sellerName

            myRe = re.compile('.*'+mId+'.*')

            for key in storeFront:

                if myRe.match(key):

                    #print "Match found ",key

                    storeFront[key] = sellerName.strip()

            #storeFront.get(re.compile('.*'+mId+'.*'))

        for arr in returnMap.itervalues():

            #print "arr is ",arr

            for dic in arr:

                #print "dic ",dic

                if dic['isStoreFront']!='True':

                    dic['sellerName'] =storeFront.get(dic.get('storeUrl'))

                    dic['isStoreFront']='True'

        print "********"

        return returnMap

#        rs = (grequests.get(u,stream=False) for u in urls)

#        for x in grequests.map(rs):

        #return soup.title.string

if __name__ == '__main__':

    urls=[]

    urls.append("http://amazon.in/gp/offer-listing/B007VZFZO8/ref=olp_sort_ps")

#    asin = []

#    for a in amazonlisted:

#        asin.append(a.asin)

#        urls.append('http://www.amazon.in/gp/offer-listing/'+str(a.asin)+'/ref=olp_sort_ps')

#        if len(urls)==50:

#            break

    print urls

    scraper = AmazonAsyncScraper()

    'http://www.amazon.in/gp/offer-listing/B003SNIN9Q/ref=olp_sort_ps'

    print len(urls)

    x = scraper.read(urls,True)

    print x

    print "##################"

#    fetched = x.items()

#    print list(set(asin) - set(fetched))

#    for a,i in x.iteritems():

#        print a

#        for data in i:

#            print data

#        print "*********"

    #print scraper.createData()

    print datetime.datetime.now()