Subversion Repositories SmartDukaan

'''
Created on 06-Jun-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 *
from datastore.DataCodeAccessor import *

from html2text import *
from babel.messages.pofile import unescape
import urllib

class babuchak1(BaseSpider):
    
    def __init__(self):
        initialize_table()
        #BABUCHAK_DOMAINNAME = "babuchak"   
        BABUCHAK_DOMAINNAME = get_code_word("BABUCHAK_DOMAINNAME")
        self.domain_name = BABUCHAK_DOMAINNAME 
        #BABUCHAK_URL = "http://www.shopping.babuchak.com/visitourstores.php?view=productListPage&category=108"
        BABUCHAK_URL = get_code_word("BABUCHAK_URL")
        self.start_urls.append(BABUCHAK_URL)
    

    def start_requests(self):
        #adding entry for the supplier i.e its name and site
        #BABUCHAK_HOMEPAGE = "http://www.shopping.babuchak.com"
        BABUCHAK_HOMEPAGE = get_code_word("BABUCHAK_HOMEPAGE")
        da = DataHelper()
        da.add_supplier(self.domain_name, BABUCHAK_HOMEPAGE)
        listreq = []
        
        #for each request a referer has to be set
        #BABUCHAK_REFERER = "www.google.com/search"
        BABUCHAK_REFERER = get_code_word("BABUCHAK_REFERER")
        for url1 in self.start_urls:
            request = Request(url = str(url1), callback=self.parse)
            request.headers.setdefault("Referer", BABUCHAK_REFERER)
            listreq.append(request)
        return listreq
        
    def parse(self, response):
        #url1 needed to get complete urls
        da = DataHelper()
        #BABUCHAK_URL1 = "http://www.shopping.babuchak.com/visitourstores.php"
        BABUCHAK_URL1 = get_code_word("BABUCHAK_URL1")
        hxs = HtmlXPathSelector(response)
        #BABUCHAK_XPATH1 = '//td[@class="mod-category-header"]'
        BABUCHAK_XPATH1 = get_code_word("BABUCHAK_XPATH1")
        info = hxs.select(BABUCHAK_XPATH1)
        for i in info:
            #BABUCHAK_XPATH2 = './/text()'
            BABUCHAK_XPATH2 = get_code_word("BABUCHAK_XPATH2")
            #BABUCHAK_XPATH3 = './/a/@href' 
            BABUCHAK_XPATH3 = get_code_word("BABUCHAK_XPATH3")
            no_pages = i.select(BABUCHAK_XPATH2)[2].extract()
            #print i.select(BABUCHAK_XPATH2)[1].extract() + "  "
            url = i.select(BABUCHAK_XPATH3)[0].extract()
            url = BABUCHAK_URL1 + url
            no_pages = urllib.unquote(no_pages)
            no_pages = no_pages.strip()
            no_pages = no_pages[1:len(no_pages)-1]
            no_pages = int(no_pages)
            #print url + " "
            #print no_pages
            da.add_babuchakurl(url, no_pages)
           
SPIDER = babuchak1()