def parse_sales_rank(cls, b, **kwargs):
if not isinstance(b, bs3_BeautifulSoup):
b = bs3_BeautifulSoup(b)
t = b.find('li', attrs={'id': re.compile('SalesRank')})
sales_rank_re = re.compile('(\d[\d,]+) in ([\w\ ]+)')
tt = sales_rank_re.findall(t.text)
return {'sales_rank': int(re.compile('\D').sub('', tt[0][0])),
'sales_rank_category': tt[0][1].strip(' ')}
def parse_sales_sub_rank(cls, b, **kwargs):
if not isinstance(b, bs3_BeautifulSoup):
b = bs3_BeautifulSoup(b)
t = b.find('li', attrs={'id': re.compile('SalesRank')})
tt = t.findAll('li', 'zg_hrsr_item')
sales_sub_rank = list()
for tti in tt:
d = dict()
d['sales_rank'] = int(re.compile('\D').sub('', tti.find('span', 'zg_hrsr_rank').text))
ttt = tti.find('span', 'zg_hrsr_ladder')
ttt = ttt.text.split(' ')[1]
d['sales_rank_category'] = ttt.split('>')
sales_sub_rank.append(d)
return sales_sub_rank
def parse_product_title(cls, b, **kwargs):
if not isinstance(b, bs3_BeautifulSoup):
b = bs3_BeautifulSoup(b)
return b.find('span', attrs={'id': 'productTitle'}).text
def parse_avg_rating(cls, b, **kwargs):
if not isinstance(b, bs3_BeautifulSoup):
b = bs3_BeautifulSoup(b)
t = b.find('span', 'reviewCountTextLinkedHistogram')
return float(re.compile('[\d\.]+').findall(t['title'])[0])