def parse_a_page(url):
bags = BagSet()
try:
response = urllib2.urlopen(url)
html_source = response.read()
soup = BeautifulSoup(html_source)
divs = soup.findAll('div', attrs={'class': 'details'})
except:
print '[ERROR][read source code]', sys.exc_info()
return bags
for div in divs:
div_str = str(div)
div_str = div_str.replace('\n', '')
div_str = re.sub('\s+', ' ', div_str)
try:
bags.add( Bag(div_str) )
except:
print '[ERROR][create bag obj]', sys.exc_info()
return bags
return bags
for div in divs:
div_str = str(div)
div_str = div_str.replace('\n', '')
div_str = re.sub('\s+', ' ', div_str)
try:
bags.add( Bag(div_str) )
except:
print '[ERROR][create bag obj]', sys.exc_info()
return bags
if __name__ == '__main__':
last_bags = BagSet()
new_bags = BagSet()
fout = open("nm_sale_handbags.dat", "a")
while True:
cur_time = strftime("%Y-%m-%d %H:%M:%S", gmtime())
cur_bags = parse_a_page(URL_NM_SALE_BAG)
for b in cur_bags.bags:
if not last_bags.exist(b):
new_bags.add(b)
if len(new_bags.bags) > 0:
print cur_time, 'Send email!'
# Set up the email here
send_email( str(new_bags) )
print >> fout, new_bags
else: