爬取豆瓣电影信息保存到Excel

 from bs4 import BeautifulSoup
 import requests
 import html.parser
 from openpyxl import Workbook,load_workbook
 import os
 class DouBan(object):

     def __init__(self):
         self.url = 'https://movie.douban.com/'
         self.header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'}

     def openUrl(self, url):
         response = requests.get(url,headers=self.header)
         return response

     def getUrl(self):
         response = self.openUrl(self.url)
         douban_html = response.text
         # print(douban_html)
         soup = BeautifulSoup(douban_html,'html.parser')
         hrefs = soup.select("li.poster > a")
         return hrefs
         # for href in hrefs:
         #     print(href['href']
     def getMsg(self):
         hrefs = self.getUrl()
         for num,href in enumerate(hrefs):
             msg_list = []
             print(href['href'])
             response = self.openUrl(href['href'])
             html_mover = response.text
             soup = BeautifulSoup(html_mover,'html.parser')
             all_info = soup.select('div#content')
             # print(all_info)
             title = all_info[0].select('h1')[0].text.replace('\n','')
             msg_list.append(title)
             # print(title)
             info = all_info[0].select('#info')[0].text
             msg_list.append(info)
             # print(info)
             describe = all_info[0].select('div#link-report span')[0].text.replace(' ','')
             msg_list.append(describe)
             # print(describe)
             # return title,info,describe
             for col in range(3):
                 self.saveMsg(num+1, col+1,  msg_list[col])

     def saveMsg(self, row_, column_,msg):
         # msg = self.getMsg()
         # a = os.path.exists('//move_msg.xlsx')
         # if a=False:
         #     os.mkdir('move_msg.xlsx')

         wb = load_workbook('move_msg.xlsx')
         sheet = wb.active
         sheet.cell(row=row_, column=column_).value = msg
         wb.save('move_msg.xlsx')

 if __name__ == "__main__":
     db = DouBan()
     db.getMsg()