2-1 作业
2016-08-09 本文已影响0人
ooocoo
def get_page_within(pages):
for page_num in range(1,pages+1):
wb_data = requests.get('http://bj.xiaozhu.com/search-duanzufang-p{}-0/'.format(page_num))
soup = BeautifulSoup(wb_data.text,'lxml')
titles = soup.select('span.result_title')
prices = soup.select('span.result_price > i')
for title, price in zip(titles,prices):
data = {
'title':title.get_text(),
'price':int(price.get_text())
}
bnb_info.insert_one(data)
print('Done')