Subversion Repositories SmartDukaan

'''

Created on 24-Aug-2011

@author: Varun Gupta

'''

from BeautifulSoup import BeautifulSoup

from BaseScraper import BaseScraper

from Utils import removePriceFormatting

class InfibeamScraper(BaseScraper):

    def __init__(self):

        self.url = None

        self.id = None

    def setUrl(self, url):

        self.url = url

    def scrape(self):

        html = BaseScraper.read(self, self.url)

        self.soup = BeautifulSoup(html)

    def getPhones(self):

        phone_prices = []

        for li in self.soup.findAll('ul', {'class': 'srch_result portrait'})[0]('li'):

            name = li.findAll('span', {'class': 'title'})[0].string

            try:

                price = li.findAll('div', {'class': 'price'})[0].findAll('span', {'class': 'normal'})[0].string

            except IndexError:

                price = removePriceFormatting(li.findAll('span', {'class': 'price'})[0].contents[-1].strip())

            url = li.findAll('a')[0]['href']

            try:

                phone_prices.append({

                        'name': str(name), 

                        'price': str(price),

                        'source': 'infibeam', 

                        'in_stock': 1, 

                        'product_url': str(url)

                    })

            except UnicodeEncodeError as e:

                print 'Unicode Error', e, name

                name_ascii = "".join([char if ord(char) < 128 else " " for char in name])

                print name_ascii

                phone_prices.append({

                        "name": str(name_ascii), 

                        "price": str(price),

                        'source': 'infibeam', 

                        "in_stock": 1, 

                        "product_url": str(url)

                    })

        return phone_prices

    def getNextUrl(self):

        b = self.soup.findAll('div', {'class': 'resultsSummary'})[0].findAll('b')

        current_max = int(b[0].string.split('-')[1])

        total_products = int(b[1].string)

        return 'http://www.infibeam.com/Mobiles/search?page=%d' % (1 + current_max / 20) if current_max < total_products else None

    def getDataFromProductPage(self, url):

        html = BaseScraper.read(self, url)

        soup = BeautifulSoup(html)

        name = soup.find('div', {'id': 'ib_details'}).find('h1', {'class': "fn"}).find('span', {'class': "item"}).string.strip()

        price = removePriceFormatting(soup.find('div',{'id': 'priceDiv'}).find('span', {'class': 'infiPrice amount price'}).string)

        in_stock = soup.find('div', {'id': 'colors'}).find('span', {'class':"status"}).string.strip()

        data = {

            "product_url": str(url), 

            "source": "infibeam", 

            "price": price, 

            "in_stock": 1 if in_stock == 'In Stock.' else 0, 

            "name": name

        }

        return data

if __name__ == '__main__':

    s = InfibeamScraper()

    print s.getDataFromProductPage('http://www.infibeam.com/Mobiles/i-HTC-EVO-3D-Android-Smartphone/P-E-M-HTC-EVO-3D.html?id=Black')

#    s.setUrl('http://www.infibeam.com/Mobiles/search?page=17')

#    s.scrape()

#    products = s.getPhones()

#    print products