Subversion Repositories SmartDukaan

Rev

Rev 15212 | Rev 15265 | Go to most recent revision | Details | Compare with Previous | Last modification | View Log | RSS feed

Rev Author Line No. Line
13829 kshitij.so 1 
from BeautifulSoup import BeautifulSoup, NavigableString
14744 kshitij.so 2 
from dtr.utils.utils import fetchResponseUsingProxy
13829 kshitij.so 3 
import re
4 
import sys
5 
 
6 
invalid_tags = ['b', 'i', 'u']
7 
bestSellers = []
8 
 
9 
def strip_tags(html, invalid_tags):
10 
    soup = BeautifulSoup(html,convertEntities=BeautifulSoup.HTML_ENTITIES)
11 
 
12 
    for tag in soup.findAll(True):
13 
        if tag.name in invalid_tags:
14 
            s = ""
15 
 
16 
            for c in tag.contents:
17 
                if not isinstance(c, NavigableString):
18 
                    c = strip_tags(unicode(c), invalid_tags)
19 
                s += unicode(c)
20 
 
21 
            tag.replaceWith(s)
22 
 
23 
    return soup
24 
 
25 
class AmazonScraper:
15212 kshitij.so 26 
    def __init__(self, livePricing=None):
13829 kshitij.so 27 
        self.count_trials = 0
15212 kshitij.so 28 
        self.livePricing = livePricing
13829 kshitij.so 29 
 
30 
    def read(self, url):
31 
        response_data = ""
32 
        try:
15212 kshitij.so 33 
            response_data = fetchResponseUsingProxy(url,livePricing=self.livePricing)
14744 kshitij.so 34 
        except Exception as e:
13829 kshitij.so 35 
            print 'ERROR: ', e
36 
            print 'Retrying'
37 
            self.count_trials += 1
38 
 
15155 kshitij.so 39 
            if self.count_trials < 5:
13829 kshitij.so 40 
                return self.read(url)
41 
 
42 
        self.response_data=response_data
15153 kshitij.so 43 
        if "Server Busy" in self.response_data:
44 
            print "Server busy...Ahhhhh"
45 
            self.count_trials += 1
46 
            return self.read(url)
13829 kshitij.so 47 
        return self.createData()
48 
 
49 
    def createData(self):
50 
        self.soup = strip_tags(self.response_data,invalid_tags)
51 
        self.response_data =None
52 
        return self.scrape(self.soup)
53 
 
54 
 
55 
    def scrape(self,soup):
56 
        sellerData = soup.findAll("div" , {"class" : "a-row a-spacing-mini olpOffer"})
57 
        for data in sellerData:
58 
            print "sellerData****"
59 
            price = data.find('span', attrs={'class' : re.compile('.*olpOfferPrice*')}).find('span').text
60 
            print "Unit cost= ",float(price.replace("Rs.","").replace(",",""))
61 
            unitCost = float(price.replace("Rs.","").replace(",",""))
62 
            shippingCost = data.find('p', attrs={'class' : re.compile('.*olpShippingInfo*')}).find('span').text
63 
            if "FREE" in shippingCost:
64 
                print "shippingCost=0"
65 
                shippingCost = 0
66 
            else:
67 
                try:
68 
                    print "shippingCost= ",float(shippingCost.replace("+Rs.","").replace("Delivery","").replace(",",""))
69 
                    shippingCost = float(shippingCost.replace("+Rs.","").replace("Delivery","").replace(",",""))
70 
                except:
71 
                    shippingCost = 0.0
72 
            try:
73 
                return (unitCost + shippingCost)
74 
            except:
75 
                return  unitCost
76 
 
77 
 
78 
if __name__ == '__main__':
15212 kshitij.so 79 
    scraper = AmazonScraper(True)
15153 kshitij.so 80 
    print scraper.read('http://www.amazon.in/gp/offer-listing/B00UFPHX8M')
13829 kshitij.so 81