| 158 |
ashish |
1 |
'''
|
|
|
2 |
Created on 16-May-2010
|
|
|
3 |
|
|
|
4 |
@author: gaurav
|
|
|
5 |
'''
|
|
|
6 |
|
|
|
7 |
|
|
|
8 |
from scrapy.spider import BaseSpider
|
|
|
9 |
from scrapy.selector import HtmlXPathSelector
|
|
|
10 |
from scrapy.http import Request
|
|
|
11 |
|
|
|
12 |
from demo.items import DemoItem
|
|
|
13 |
from scrapy.contrib.spidermiddleware import referer
|
|
|
14 |
from scrapy.http.headers import Headers
|
|
|
15 |
from scrapy.http.request.form import FormRequest
|
|
|
16 |
from scrapy.log import msg
|
|
|
17 |
from scrapy.http.response import Response
|
|
|
18 |
|
|
|
19 |
from datastore import DataAccessor
|
|
|
20 |
from datastore.DataAccessor import DataHelper
|
|
|
21 |
|
|
|
22 |
|
|
|
23 |
class indiaplaza_spider(BaseSpider):
|
|
|
24 |
|
|
|
25 |
def __init__(self):
|
|
|
26 |
self.domain_name = "indiaplaza"
|
|
|
27 |
ct = 18
|
|
|
28 |
no = 1
|
|
|
29 |
while(no<=ct):
|
|
|
30 |
str1 = "http://www.indiaplaza.in/mobile-phones-Mobiles-1.htm?PageNo="+str(no)
|
|
|
31 |
self.start_urls.append(str1)
|
|
|
32 |
no=no+1
|
|
|
33 |
|
|
|
34 |
def start_requests(self):
|
|
|
35 |
listreq = []
|
|
|
36 |
for url1 in self.start_urls:
|
|
|
37 |
request = Request(url = str(url1), callback=self.parse,dont_filter=True,)
|
|
|
38 |
request.headers.setdefault("Referer", "http://www.indiaplaza.in")
|
|
|
39 |
listreq.append(request)
|
|
|
40 |
return listreq
|
|
|
41 |
|
|
|
42 |
def parse(self, response):
|
|
|
43 |
str1 = "http://www.indiaplaza.in"
|
|
|
44 |
hxs = HtmlXPathSelector(response)
|
|
|
45 |
phone_info = hxs.select('//tr/td/table[@id="browsesku"]')
|
|
|
46 |
items = []
|
|
|
47 |
#msg(len(phone_info))
|
|
|
48 |
#msg(response.body)
|
|
|
49 |
for i in phone_info:
|
|
|
50 |
item = {}
|
|
|
51 |
item['title'] = i.select('.//div[@class="skuimg"]/a/@title')[0].extract()
|
|
|
52 |
item['url'] = i.select('.//div[@class="skuimg"]/a/@href')[0].extract()
|
|
|
53 |
|
|
|
54 |
|
|
|
55 |
items.append(item)
|
|
|
56 |
|
|
|
57 |
f = open('/home/gaurav/Desktop/indiaplaza_info.txt', 'a')
|
|
|
58 |
da = DataHelper()
|
|
|
59 |
for item in items:
|
|
|
60 |
str2 = str1 + str(item['url'])
|
|
|
61 |
#amnt = item['price'].replace(",","")
|
|
|
62 |
#amnt = amnt.replace("Rs.", "")
|
|
|
63 |
#amnt = amnt.strip()
|
|
|
64 |
|
|
|
65 |
#pr = int(amnt) + vatplustax
|
|
|
66 |
da.add_ipbasic(item['title'],str2)
|
|
|
67 |
print item['title']
|
|
|
68 |
#print str(item['title'])
|
|
|
69 |
print str(item['title']).strip()
|
|
|
70 |
#print str2
|
|
|
71 |
f.write(str(item['title']).strip())
|
|
|
72 |
f.write("\n")
|
|
|
73 |
f.write(str2.strip())
|
|
|
74 |
f.write("\n\n")
|
|
|
75 |
f.close()
|
|
|
76 |
SPIDER = indiaplaza_spider()
|