Subversion Repositories SmartDukaan

Rev

Rev 5291 | 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
5401 varun.gupt 9 
from SoupSelect import select
4039 varun.gupt 10 
 
11 
class HS18Scraper(BaseScraper):
12 
 
13 
    def __init__(self):
14 
        self.url = None
15 
        self.id = None
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 
 
24 
    def getPhones(self):
25 
        product_prices = []
26 
 
5401 varun.gupt 27 
        for div in select(self.soup, "div.product_div"):#self.soup.findAll('div', {'class': 'product_div'}):
5291 varun.gupt 28 
 
29 
            anchor = div.find('p', {'class': 'product_title'})('a')[0]
4039 varun.gupt 30 
            name = str(anchor['title'].strip())
31 
 
5291 varun.gupt 32 
            if name.endswith(' Mobile Phone'):
33 
                name = name.replace(' Mobile Phone', '')
4039 varun.gupt 34 
 
35 
            url = str(anchor['href'].strip())
4198 varun.gupt 36 
            price = removePriceFormatting(str(div.findAll('span', {'class': 'product_new_price'})[0].string.strip()))
4039 varun.gupt 37 
 
38 
            try:
4198 varun.gupt 39 
                product_prices.append({
40 
                        'name': name,
41 
                        'price': price,
42 
                        'source': 'homeshop18',
43 
                        'in_stock': 1,
44 
                        'product_url': url
45 
                    })
4039 varun.gupt 46 
 
47 
            except UnicodeEncodeError as e:
48 
                print 'Unicode Error', e, name
49 
                name_ascii = "".join([char if ord(char) < 128 else " " for char in name])
50 
                print name_ascii
4198 varun.gupt 51 
                product_prices.append({
52 
                        "name": str(name_ascii),
53 
                        "price": str(price),
54 
                        'source': 'homeshop18',
55 
                        "in_stock": 1,
56 
                        "product_url": str(url)
57 
                    })
4039 varun.gupt 58 
 
59 
        return product_prices
60 
 
61 
    def getNextUrl(self):
4198 varun.gupt 62 
        pagination_links = self.soup.find('div', {'class': 'pagination'}).findAll('span')
4039 varun.gupt 63 
 
4198 varun.gupt 64 
        try:
65 
            if pagination_links[-1]['class'].strip() == 'disabled_pagination':
66 
                return None
67 
            else:
68 
                return pagination_links[-1]('a')[0]['href'].strip()
69 
        except KeyError:
70 
            print pagination_links
4039 varun.gupt 71 
 
4199 varun.gupt 72 
    def getDataFromProductPage(self, url):
73 
        html = BaseScraper.read(self, url)
74 
        soup = BeautifulSoup(html)
4203 varun.gupt 75 
        name = soup.find('h1', {'id': 'productLayoutForm:pbiName'}).string.replace('Mobile Phone', '').strip()
76 
        price = removePriceFormatting(soup.find('span',{'id': 'productLayoutForm:OurPrice'}).string)
4199 varun.gupt 77 
 
78 
        data = {
79 
            "product_url": str(url),
4203 varun.gupt 80 
            "source": "homeshop18",
4199 varun.gupt 81 
            "price": price,
4203 varun.gupt 82 
            "in_stock": 1,
4199 varun.gupt 83 
            "name": name
84 
        }
85 
        return data
86 
 
87 
 
4039 varun.gupt 88 
if __name__ == '__main__':
89 
    scraper = HS18Scraper()
5291 varun.gupt 90 
#    print scraper.getDataFromProductPage('http://www.homeshop18.com/samsung-galaxy-note-n7000-mobile-phone/mobiles-accessories/gsm-handsets/product:16601211/cid:3027/')
5401 varun.gupt 91 
    scraper.setUrl('http://www.homeshop18.com/mobiles/category:14569/')
5291 varun.gupt 92 
    scraper.scrape()
93 
    products = scraper.getPhones()
94 
    print products
95 
    print scraper.getNextUrl()