Subversion Repositories SmartDukaan

Rev

Rev 17246 | Details | Compare with Previous | Last modification | View Log | RSS feed

Rev Author Line No. Line
14307 kshitij.so 1 
import urllib2
2 
from BeautifulSoup import BeautifulSoup, NavigableString
3 
import re
14759 kshitij.so 4 
from dtr.utils.utils import fetchResponseUsingProxy
14307 kshitij.so 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:
15210 kshitij.so 26 
    def __init__(self,livePricing=None):
14307 kshitij.so 27 
        self.count_trials = 0
15211 kshitij.so 28 
        self.livePricing = livePricing
14307 kshitij.so 29 
 
30 
    def read(self, url):
31 
        response_data = ""
32 
        try:
15211 kshitij.so 33 
            response_data = fetchResponseUsingProxy(url, livePricing=self.livePricing)
14759 kshitij.so 34 
        except Exception as e:
14307 kshitij.so 35 
            print 'ERROR: ', e
36 
            print 'Retrying'
37 
            self.count_trials += 1
38 
 
15156 kshitij.so 39 
            if self.count_trials < 5:
14307 kshitij.so 40 
                return self.read(url)
41 
 
42 
        self.response_data=response_data
15154 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)
14307 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 
        try:
57 
            sellerData = soup.find("span" , {"id" : "priceblock_dealprice"})
58 
            dealPrice = float(sellerData.text.replace("Rs.","").replace(",",""))
17246 kshitij.so 59 
            print dealPrice
14307 kshitij.so 60 
        except:
61 
            dealPrice = 0.0
62 
        try:
17246 kshitij.so 63 
            dealStatus = soup.find('span',{'id':re.compile('dealStatusAvailability_*')})
14307 kshitij.so 64 
            dealStatus = float(dealStatus.text.replace("%","").replace(",",""))
65 
        except:
66 
            dealStatus = 100
67 
 
17246 kshitij.so 68 
 
17247 kshitij.so 69 
        if dealStatus < 100 and dealPrice > 0:
14307 kshitij.so 70 
            return dealPrice
71 
        else:
72 
            return 0.0
73 
 
74 
if __name__ == '__main__':
15211 kshitij.so 75 
    scraper = AmazonScraper(True)
17246 kshitij.so 76 
    print scraper.read('http://www.amazon.in/dp/B015CSIA38/ref=gbdp_vlo_61287013_B015CSIA38?_encoding=UTF8&smid=A2WBY8FP973J47')
14307 kshitij.so 77