爬虫爬取豆瓣top250并保存到mongoDB数据库中

import requests
from lxml import etree
import pymongo
import time

class DouBan:
    def getUrl(self,url,):
        try:
            for page in range(10):
                url = 'https://movie.douban.com/top250?start=' + str(page * 25) + '&filter='
                r = requests.get(url)
                r.raise_for_status()
                r.encoding = r.apparent_encoding
                re = etree.HTML(r.text)
                title = re.xpath('//div[@class="hd"]/a/span[@class="title"][1]//text()')
                href = re.xpath('//div[@class="hd"]/a/@href')
                for i in range(len(title)):
                    data1.insert_one({'影名': title[i], '链接': href[i]})
                    time.sleep(0.1)
        except Exception as e:
            print(e)

if __name__ == '__main__':
    # MongoDB的连接
    client = pymongo.MongoClient('localhost', 27017)
    data = client['douban']
    data1 = data['db']
    url = 'https://movie.douban.com/top250'
    douban = DouBan()
    douban.getUrl(url)