| 5639 |
amar.kumar |
1 |
from BeautifulSoup import BeautifulSoup
|
|
|
2 |
from BaseScraper import BaseScraper
|
|
|
3 |
from Utils import removePriceFormatting
|
|
|
4 |
|
|
|
5 |
class SulekhaScraper(BaseScraper):
|
|
|
6 |
|
|
|
7 |
pageCount = 11
|
|
|
8 |
productCountPerScraping = 24
|
|
|
9 |
currentPage=1;
|
|
|
10 |
|
|
|
11 |
def __init__(self):
|
|
|
12 |
BaseScraper.__init__(self)
|
|
|
13 |
self.url = None
|
|
|
14 |
self.id = None
|
|
|
15 |
#self.currentPage = 1
|
|
|
16 |
|
|
|
17 |
def setUrl(self, url):
|
|
|
18 |
self.url = url
|
|
|
19 |
|
|
|
20 |
def scrape(self):
|
|
|
21 |
html = BaseScraper.read(self, self.url)
|
|
|
22 |
self.soup = BeautifulSoup(html)
|
|
|
23 |
self.phones = None
|
|
|
24 |
#self.setPageCount()
|
|
|
25 |
|
|
|
26 |
def getPhones(self):
|
|
|
27 |
phones = []
|
|
|
28 |
allPhoneUl = self.soup.find('ul', id="MMobBrandOffersListCont")
|
|
|
29 |
try:
|
|
|
30 |
for li in allPhoneUl.findAll('li'):
|
|
|
31 |
anchorDiv = li.find('div', {'class': 'dealtit'})
|
|
|
32 |
anchor = anchorDiv.find('a')
|
|
|
33 |
name = anchor.string.strip()
|
|
|
34 |
price = li.find('span',{'class': 'deals-our-price'}).contents[1].strip()
|
|
|
35 |
product_url = anchor['href'].strip()
|
|
|
36 |
in_stock = 1
|
|
|
37 |
|
|
|
38 |
try:
|
|
|
39 |
if price is None:
|
|
|
40 |
continue
|
|
|
41 |
else:
|
|
|
42 |
phones.append({
|
|
|
43 |
'name': str(name),
|
|
|
44 |
'price': removePriceFormatting(price),
|
|
|
45 |
'source': 'sulekha',
|
|
|
46 |
'product_url': str(product_url),
|
|
|
47 |
'in_stock': in_stock
|
|
|
48 |
})
|
|
|
49 |
|
|
|
50 |
except UnboundLocalError as e:
|
|
|
51 |
print e, name
|
|
|
52 |
print li
|
|
|
53 |
|
|
|
54 |
except Exception as e:
|
|
|
55 |
print e
|
|
|
56 |
|
|
|
57 |
self.phones = phones
|
|
|
58 |
return phones
|
|
|
59 |
|
|
|
60 |
def setPageCount(self):
|
|
|
61 |
self.currentPage = self.currentPage + 1
|
|
|
62 |
|
|
|
63 |
def getNextUrl(self):
|
|
|
64 |
if SulekhaScraper.currentPage < SulekhaScraper.pageCount:
|
|
|
65 |
SulekhaScraper.currentPage += 1
|
|
|
66 |
return 'http://mobiles.sulekha.com/common/common.aspx?type=mobileofferslist&makeId=0&modelId=0&pageNo=%s' % SulekhaScraper.currentPage
|
|
|
67 |
else:
|
|
|
68 |
return None
|
|
|
69 |
|
|
|
70 |
def getDataFromProductPage(self, url):
|
|
|
71 |
html = BaseScraper.read(self, url)
|
|
|
72 |
soup = BeautifulSoup(html)
|
|
|
73 |
name = soup.find('h1', {'class': 'product-title'})('a')[0].contents[0].string.strip()
|
|
|
74 |
price = soup.find('span',{'itemprop': 'price'}).string.strip()
|
|
|
75 |
in_stock = 1
|
|
|
76 |
|
|
|
77 |
data = {
|
|
|
78 |
"product_url": str(url),
|
|
|
79 |
"source": "sulekha",
|
|
|
80 |
"price": price,
|
|
|
81 |
"in_stock": 1,
|
|
|
82 |
"name": name
|
|
|
83 |
}
|
|
|
84 |
return data
|
|
|
85 |
|
|
|
86 |
if __name__ == '__main__':
|
|
|
87 |
s = SulekhaScraper()
|
|
|
88 |
|
|
|
89 |
data = s.getDataFromProductPage('http://deals.sulekha.com/blackberry-curve-9360-white-17561')
|
|
|
90 |
print data
|