Subversion Repositories SmartDukaan

from BeautifulSoup import BeautifulSoup
import re
from sys import exit
from dtr.utils.utils import fetchResponseUsingProxy

headers = { 
           'User-agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11',
            'Accept' : 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',      
            'Accept-Language' : 'en-US,en;q=0.8',                     
            'Accept-Charset' : 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
            'Cookie':'T=TI141257426738726661427143281839817329423126740566618323641725716448; __sonar=7237334677420142002; __gads=ID=c8b82101a0e4f451:T=1412574724:S=ALNI_MbPMbEOZj2nAGjM54z8ZHFMqwTOTQ; FK-CMP-DATA=; SN=2.VI11FB3FB6ED9D4693A796AB8C965B3417.SI802C325AC43444858830E870C4FD3324.VS141257426735693951472.1412576209; VID=2.VI11FB3FB6ED9D4693A796AB8C965B3417.1412576209.VS141257426735693951472; NSID=2.SI802C325AC43444858830E870C4FD3324.1412576209.VI11FB3FB6ED9D4693A796AB8C965B3417; __utma=19769839.709301254.1412574234.1412574234.1412574234.1; __utmb=19769839.23.10.1412574234; __utmc=19769839; __utmz=19769839.1412574234.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); s_cc=true; gpv_pn=SellerListing%3AMobile%3AMicromax%20Canvas%20Fire%20A093; gpv_pn_t=no%20value; s_sq=%5B%5BB%5D%5D; s_ppv=36',
            'Host':'www.flipkart.com',
            'Accept-Encoding' : 'gzip,deflate,sdch'
        }

class FlipkartScraper:
    def __init__(self):
        self.count_trials = 0
        self.redirectCount = 0
    
    def read(self, url):
        try:
            """quick fix,need to add it conf""" 
            
            response_data = fetchResponseUsingProxy(url, headers)
            
        except Exception 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
        return self.createSoup(url)
    
#    def scrapeRedirectedPage(self,soup,redirect_url):
#        print soup
#        print redirect_url
#        t = soup.find("div" , {"class" : "seller-table fk-user-select-none line"})
#        print t
#        table_rows = t.findAll("tr" , {"class" : re.compile('t-row.*')})
#        print table_rows
#        for x in table_rows:
#            print x
#    
    def createSoup(self, url):
        print "Creating soup from flipkart data for %s" %(url)
        page=self.response_data.decode("utf-8")
        self.soup = BeautifulSoup(page,convertEntities=BeautifulSoup.HTML_ENTITIES)
        page = None
        self.response_data = None
        print "Soup created from flipkart data for %s" %(url)
        return self.scrape(self.soup,url)
    
    def scrape(self,soup,url):
        print "Inside json creator for %s" %(url)
        info = []
        buyBoxInfo = []
        oddSeller = soup.findAll("div" , {"class" : "line seller-item odd "})
        for data in oddSeller:
            temp={}
            price = data.find('span', attrs={'class' : re.compile('pxs-final-price.*')}).string.strip('Rs.').strip()
            temp['sellingPrice']=float(price)
            for metrics in data.find("div",{"class":"fk-text-right"}):
                try:
                    metric = metrics.findAll('input', {'type': 'submit'})
                except AttributeError:
                    continue
                try:
                    inputTags = metric[0]['data-lst-buytrend']
                except TypeError:
                    continue
                dataMetrics = metric[0]['data-listing-metrics']
                dataMetric = dataMetrics.split(';')
                temp['sellingPriceMetric'] = float(dataMetric[1])
                try:
                    temp['shippingFee'] = float(dataMetric[2])
                except:
                    temp['shippingFee'] = 0.0
                try:
                    buyTrend = inputTags[0:str(inputTags).index('NWSR')].replace('_','')
                except ValueError:
                    buyTrend = inputTags[0:str(inputTags).index('WSR')].replace('_','')
                temp['buyTrend']=buyTrend.strip()
                temp['sellingPrice'] = temp['sellingPrice'] + temp['shippingFee']
                if temp['buyTrend'] in  ('PrefNCheap','PrefCheap'):
                    buyBoxInfo.append(temp)
                info.append(temp)
        evenSeller = soup.findAll("div" , {"class" : "line seller-item even "})
        for data in evenSeller:
            temp={}
            price = data.find('span', attrs={'class' : re.compile('pxs-final-price.*')}).string.strip('Rs.')
            temp['sellingPrice']=float(price)
            for metrics in data.find("div",{"class":"fk-text-right"}):
                try:
                    metric = metrics.findAll('input', {'type': 'submit'})
                except AttributeError:
                    continue
                try:
                    inputTags = metric[0]['data-lst-buytrend']
                except TypeError:
                    continue
                dataMetrics = metric[0]['data-listing-metrics']
                dataMetric = dataMetrics.split(';')
                temp['sellingPriceMetric'] = float(dataMetric[1])
                try:
                    temp['shippingFee'] = float(dataMetric[2])
                except:
                    temp['shippingFee'] = 0.0
                try:
                    buyTrend = inputTags[0:str(inputTags).index('NWSR')].replace('_','')
                except ValueError:
                    buyTrend = inputTags[0:str(inputTags).index('WSR')].replace('_','')
                temp['buyTrend']=buyTrend.strip()
                temp['sellingPrice'] = temp['sellingPrice'] + temp['shippingFee']
                if temp['buyTrend'] in  ('PrefNCheap','PrefCheap'):
                    buyBoxInfo.append(temp)  
                info.append(temp)
        print info
        print "==========="
        print buyBoxInfo
        print "Returning Json response from flipkart for %s" %(url)
        return info, buyBoxInfo

if __name__ == '__main__':
    scraper = FlipkartScraper()
    x, z = scraper.read('http://www.flipkart.com/ps/MOBDUZSYZCA7HDYW')
    for y in x:
        print y
    print "==========="
    for t in z:
        print t