这个是抓取信息的
from bs4 import BeautifulSoupimport requestsurl = 'https://list.tmall.com/search_product.htm?q=%CB%AE%BA%F8+%C9%D5%CB%AE&type=p&vmarket=&spm=875.7931836%2FA.a2227oh.d100&from=mallfp..pc_1_searchbutton'response = requests.get(url) #解析网页soup = BeautifulSoup(response.text,'lxml') #.text将解析到的网页可读storenames = soup.select('#J_ItemList > div > div > p.productTitle > a') #选择出商店的信息prices = soup.select('#J_ItemList > div > div > p.productPrice > em') #选择出价格的信息sales = soup.select('#J_ItemList > div > div > p.productStatus > span > em') #选择出销售额的信息for storename, price, sale in zip(storenames,prices,sales): storename = storename.get_text().strip() #用get_text()方法筛选出标签中的文本信息，由于筛选结果有换行符\n所以用strip()将换行符去掉 price = price.get_text() sale = sale.get_text() print('商店名:%-40s价格:%-40s销售额:%s'%(storename,price,sale)) #使打印出来的信息规范 print('----------------------------------------------------------------------------------------------')from bs4 import BeautifulSoupimport 
