Subversion Repositories SmartDukaan

'''
Created on 14-May-2010

@author: gaurav
'''


from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from scrapy.http import Request

from demo.items import DemoItem
from scrapy.contrib.spidermiddleware import referer
from scrapy.http.headers import Headers
from scrapy.http.request.form import FormRequest
from scrapy.log import msg
from scrapy.http.response import Response
#from datastore.DataAccessor import add_new_phone

from datastore import DataAccessor
from datastore.DataAccessor import DataHelper

class univercell_price(BaseSpider):
    
    def __init__(self):
       self.domain_name = "univercellphones"
       da = DataHelper()
       for pitem in da.get_all_univervendors():
            self.start_urls.append(pitem.v_site.strip())
    
    def start_requests(self):
        listreq = []
        for url1 in self.start_urls:
            request = Request(url = url1, callback=self.parse)
            request.headers.setdefault("Referer", "www.google.com/search")
            listreq.append(request)
        return listreq
       
    def parse(self, response):
        da = DataHelper()
        vatplustax = 0
        hxs = HtmlXPathSelector(response)
        #sites = hxs.select('//div[@id="productsDiv"]/table/tbody/tr[2]/td/div/table/tbody/tr/td/table/tbody')
        #sites = hxs.select('//div[@id="productsDiv"]/table/tr[2]//tr')
        sites = hxs.select('//td[@class="gray-border"]')
        items = []
        for site in sites:
            item = {}
            #tmp = site.select('.//tr[2]/td/a/text()')
            item['title'] = site.select('.//tr[2]/td/a/text()')[0].extract()
            #psite = site.select(".//a[3][@href]/@href")[0].extract()
            item['price'] =site.select('.//tr[3]/th/label/text()')[0].extract()
            items.append(item)
        da = DataHelper()
              
        for i in items:
            str1 = str(i['title']).strip() 
            print str1
            amnt = i['price'].replace(",","")
            amnt = amnt.replace("Rs", "")
            amnt = amnt.replace("/", "")
            amnt = amnt.replace("-", "")
            amnt = amnt.strip() 
            vatplustax = 4*int(amnt)/100
            pr = int(amnt) + vatplustax 
            #print pr
            da.add_new_univerphone(str1,amnt,pr) 
            
        #lt = len(da.get_all_phones())  
        #print "length" + str(lt)
        #for ph in da.get_all_phones():
         #   print ph
            
        #f = open('/home/gaurav/twopassscrapy/pricelinks.txt', 'w')
        #for i in items:
            #f.write(i['title'])
            #f.write("\n")
            #f.write(i['link'])
            #f.write("\n")
        #f.close()    
        
SPIDER = univercell_price()