from bs4 import BeautifulSoup
import requests
import time
import pymongo
#创建数据库
client = pymongo.MongoClient('localhost', 27017) #激活客户端
douban = client['douban']
url_list = douban['url_list']
item_list = douban['item_info']
start_url = ['https://movie.douban.com/top250?start={}&filter='.format(str(i)) for i in range(0, 250, 25)]
urlone = 'https://movie.douban.com/top250?start=0&filter='
#获取某页各电影的信息(影名,链接,评分,评论数,一句话影评)
def get_index_url(url):
wb_data = requests.get(url)
soup = BeautifulSoup(wb_data.text, 'lxml')
titles = soup.select('div.hd > a > span.title')
links = soup.select('div > div.info > div.hd > a ')
scores = sou