第四周作业

#豆瓣cookie模拟登录，热门精选

import requests

import time

from lxml import etree

headers = {

  'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.87 Safari/537.36'

  'cookie':'###################################'

}

urls = ['https://www.douban.com/interest/1/1/?p={}'.format(str(i)) for i in range(1,10)]

for url in urls:

  res = requests.get(url,headers=headers)

  html = etree.HTML(res.text)

  infos = html.xpath('//div[@id="statuses"]/div[1]/div')

  for info in infos:

    name = info.xpath('div/div/div[1]/div[2]/a/text()')

    context = info.xpath('div/div/div[2]/div[1]/div/p/text()')

    print (name,context)

  time.sleep(2)