Python爬虫实现抓取京东店铺信息及下载图片功能示例

from bs4 import BeautifulSoup
import requests
url = '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 BeautifulSoup
import requests
import urllib.request
url = '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)
soup = BeautifulSoup(response.text, 'lxml')
imgs = soup.select('#J_ItemList > div > div > div.productImg-wrap > a > img')
a = 1
for i in imgs:
  if(i.get('src')==None):
    break
  img = 'http:'+i.get('src') #这里废了好长的时间，原来网站必须要有http：的
  #print(img)
  urllib.request.urlretrieve(img,'%s.jpg'%a, None,)
  a = a+1

theString = 'saaaay yes no yaaaass'
print theString.strip('say')

theString = 'saaaay yes no yaaaass'
print theString.strip('say')
print theString.strip('say ') #say后面有空格
print theString.lstrip('say')
print theString.rstrip('say')