Subversion Repositories SmartDukaan

'''
Created on 17-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 import DataAccessor
from datastore.DataAccessor import DataHelper
import urllib
from xml.dom import INDEX_SIZE_ERR


class indiaplaza_extra(BaseSpider):
    
    def __init__(self):
       self.domain_name = "indiaplazaextrainfo"
       da = DataHelper()
       for pitem in da.get_all_ipbasic():
            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):
        hxs = HtmlXPathSelector(response)
        #sites = hxs.select('//td[@class="gray-border"]')
        #msg(response.url)
        #print(len(sites))
        name = hxs.select('.//div[@class="finDetHdr"]/h1/text()')[0].extract()
        price = hxs.select('.//div[@class="priceArea"]/span[1]/text()')[0].extract()
        try:
            ship_price = hxs.select('.//div[@class="priceArea"]/div[@class="row"][2]/text()')[0].extract()
        except IndexError:
            ship_price = hxs.select('.//div[@class="priceArea"]/div[@class="row"][2]/span/text()')[0].extract()
        try:
            guarantee_info = hxs.select('.//div[@class="priceArea"]/div[@class="row"][3]/text()')[0].extract()
        except IndexError:
            guarantee_info = hxs.select('.//div[@class="priceArea"]/div[@class="row"][4]/text()')[0].extract()
        ship_info = hxs.select('.//div[@class="priceArea"]/div[@class="row"][1]/text()')[0].extract() 
        
        urllib.unquote(name)
        urllib.unquote(price)
        urllib.unquote(ship_price)
        urllib.unquote(guarantee_info)
        urllib.unquote(ship_info)
        if ship_price == "Free shipping" :
            ship_price = "0"
        else :
            ship_price = ship_price.replace("Rs.","")
                
        price = price.replace("Rs.","")
        
        name = name.strip()
        price = price.strip()
        ship_price = ship_price.strip()
        guarantee_info = guarantee_info.strip()
        ship_info = ship_info.strip()
        
        shown_pr = int(price)
        final_pr = shown_pr + int(ship_price)
        print name
        print shown_pr
        print final_pr
        print guarantee_info
        print ship_info
        da = DataHelper()
        da.add_ipextra(name,shown_pr,final_pr,guarantee_info,ship_info)
    '''
        for site in sites:
            item = {}
            #tmp = site.select('.//tr[2]/td/a/text()')
            item['name'] = response.select('.//div[@class="finDetHdr"]/h1/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)
        
              
        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()
            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 = indiaplaza_extra()