Subversion Repositories SmartDukaan

Rev

Rev 154 | Rev 240 | Go to most recent revision | Show entire file | Ignore whitespace | Details | Blame | Last modification | View Log | RSS feed

Rev 154 Rev 170
Line 35... Line 35...
35 
            request.headers.setdefault("Referer", "www.google.com/search")
 35 
            request.headers.setdefault("Referer", "www.google.com/search")
36 
            listreq.append(request)
 36 
            listreq.append(request)
37 
        return listreq
 37 
        return listreq
38
38
39 
    def parse(self, response):
 39 
    def parse(self, response):
- 
 
 40 
        da = DataHelper()
40 
        vatplustax = 0
 41 
        vatplustax = 0
41 
        hxs = HtmlXPathSelector(response)
 42 
        hxs = HtmlXPathSelector(response)
42 
        #sites = hxs.select('//div[@id="productsDiv"]/table/tbody/tr[2]/td/div/table/tbody/tr/td/table/tbody')
 43 
        #sites = hxs.select('//div[@id="productsDiv"]/table/tbody/tr[2]/td/div/table/tbody/tr/td/table/tbody')
43 
        #sites = hxs.select('//div[@id="productsDiv"]/table/tr[2]//tr')
 44 
        #sites = hxs.select('//div[@id="productsDiv"]/table/tr[2]//tr')
44 
        sites = hxs.select('//td[@class="gray-border"]')
 45 
        sites = hxs.select('//td[@class="gray-border"]')
45 
        msg(response.url)
 - 
 
46 
        print(len(sites))
 - 
 
47 
        items = []
 46 
        items = []
48 
        for site in sites:
 47 
        for site in sites:
49 
            item = {}
 48 
            item = {}
50 
            #tmp = site.select('.//tr[2]/td/a/text()')
 49 
            #tmp = site.select('.//tr[2]/td/a/text()')
51 
            item['title'] = site.select('.//tr[2]/td/a/text()')[0].extract()
 50 
            item['title'] = site.select('.//tr[2]/td/a/text()')[0].extract()
52 
            #psite = site.select(".//a[3][@href]/@href")[0].extract()
 51 
            #psite = site.select(".//a[3][@href]/@href")[0].extract()
53 
            item['price'] =site.select('.//tr[3]/th/label/text()')[0].extract()
 52 
            item['price'] =site.select('.//tr[3]/th/label/text()')[0].extract()
54 
            items.append(item)
 53 
            items.append(item)
55 
        da = DataHelper()
54 
        da = DataHelper()
- 
 
 55
56 
        for i in items:
 56 
        for i in items:
57 
            str1 = str(i['title']).strip()
57 
            str1 = str(i['title']).strip()
58 
            print str1
 58 
            print str1
59 
            amnt = i['price'].replace(",","")
 59 
            amnt = i['price'].replace(",","")
60 
            amnt = amnt.replace("Rs", "")
 60 
            amnt = amnt.replace("Rs", "")
61 
            amnt = amnt.replace("/", "")
 61 
            amnt = amnt.replace("/", "")
62 
            amnt = amnt.replace("-", "")
 62 
            amnt = amnt.replace("-", "")
63 
            amnt = amnt.strip()
 63 
            amnt = amnt.strip()
- 
 
 64 
            vatplustax = 4*int(amnt)/100
64 
            pr = int(amnt) + vatplustax
65 
            pr = int(amnt) + vatplustax
65 
            #print pr
 66 
            #print pr
66 
            da.add_new_univerphone(str1,amnt,pr)
67 
            da.add_new_univerphone(str1,amnt,pr)
67
68
68 
        #lt = len(da.get_all_phones())
69 
        #lt = len(da.get_all_phones())