Subversion Repositories SmartDukaan

Rev

Rev 4203 | Rev 5401 | Go to most recent revision | Details | Compare with Previous | Last modification | View Log | RSS feed

Rev Author Line No. Line
4039 varun.gupt 1 
'''
2 
Created on 07-Sep-2011
3 
 
4 
@author: Varun Gupta
5 
'''
6 
from BeautifulSoup import BeautifulSoup
7 
from BaseScraper import BaseScraper
4198 varun.gupt 8 
from Utils import removePriceFormatting
4039 varun.gupt 9 
 
10 
class HS18Scraper(BaseScraper):
11 
 
12 
    def __init__(self):
13 
        self.url = None
14 
        self.id = None
15 
 
16 
    def setUrl(self, url):
17 
        self.url = url
18 
 
19 
    def scrape(self):
20 
        html = BaseScraper.read(self, self.url)
21 
        self.soup = BeautifulSoup(html)
22 
 
23 
    def getPhones(self):
24 
        product_prices = []
25 
 
5291 varun.gupt 26 
        for div in self.soup.findAll('div', {'class': 'product_div'}):
27 
 
28 
            anchor = div.find('p', {'class': 'product_title'})('a')[0]
4039 varun.gupt 29 
            name = str(anchor['title'].strip())
30 
 
5291 varun.gupt 31 
            if name.endswith(' Mobile Phone'):
32 
                name = name.replace(' Mobile Phone', '')
4039 varun.gupt 33 
 
34 
            url = str(anchor['href'].strip())
4198 varun.gupt 35 
            price = removePriceFormatting(str(div.findAll('span', {'class': 'product_new_price'})[0].string.strip()))
4039 varun.gupt 36 
 
37 
            try:
4198 varun.gupt 38 
                product_prices.append({
39 
                        'name': name,
40 
                        'price': price,
41 
                        'source': 'homeshop18',
42 
                        'in_stock': 1,
43 
                        'product_url': url
44 
                    })
4039 varun.gupt 45 
 
46 
            except UnicodeEncodeError as e:
47 
                print 'Unicode Error', e, name
48 
                name_ascii = "".join([char if ord(char) < 128 else " " for char in name])
49 
                print name_ascii
4198 varun.gupt 50 
                product_prices.append({
51 
                        "name": str(name_ascii),
52 
                        "price": str(price),
53 
                        'source': 'homeshop18',
54 
                        "in_stock": 1,
55 
                        "product_url": str(url)
56 
                    })
4039 varun.gupt 57 
 
58 
        return product_prices
59 
 
60 
    def getNextUrl(self):
4198 varun.gupt 61 
        pagination_links = self.soup.find('div', {'class': 'pagination'}).findAll('span')
4039 varun.gupt 62 
 
4198 varun.gupt 63 
        try:
64 
            if pagination_links[-1]['class'].strip() == 'disabled_pagination':
65 
                return None
66 
            else:
67 
                return pagination_links[-1]('a')[0]['href'].strip()
68 
        except KeyError:
69 
            print pagination_links
4039 varun.gupt 70 
 
4199 varun.gupt 71 
    def getDataFromProductPage(self, url):
72 
        html = BaseScraper.read(self, url)
73 
        soup = BeautifulSoup(html)
4203 varun.gupt 74 
        name = soup.find('h1', {'id': 'productLayoutForm:pbiName'}).string.replace('Mobile Phone', '').strip()
75 
        price = removePriceFormatting(soup.find('span',{'id': 'productLayoutForm:OurPrice'}).string)
4199 varun.gupt 76 
 
77 
        data = {
78 
            "product_url": str(url),
4203 varun.gupt 79 
            "source": "homeshop18",
4199 varun.gupt 80 
            "price": price,
4203 varun.gupt 81 
            "in_stock": 1,
4199 varun.gupt 82 
            "name": name
83 
        }
84 
        return data
85 
 
86 
 
4039 varun.gupt 87 
if __name__ == '__main__':
88 
    scraper = HS18Scraper()
5291 varun.gupt 89 
#    print scraper.getDataFromProductPage('http://www.homeshop18.com/samsung-galaxy-note-n7000-mobile-phone/mobiles-accessories/gsm-handsets/product:16601211/cid:3027/')
90 
    scraper.setUrl('http://www.homeshop18.com/gsm-mobiles/categoryid:3027/search:*/start:112/')
91 
    scraper.scrape()
92 
    products = scraper.getPhones()
93 
    print products
94 
    print scraper.getNextUrl()