import requests
import re
import openpyxl
for page in range(80):
  try:

      params = (

          ('start', str(page * 20)),
          ('limit', '20'),
          ('status', 'P'),
          ('sort', 'new_score'),
          ('comments_only', '1'),
          ('ck', 'qN8_'),
      )

      r = requests.get('https://movie.douban.com/subject/32493124/comments', headers=headers, params=params, cookies=cookies)

      yonghumingchengs = re.findall('', r.json()['html'], re.S)
      youyongshus = re.findall('(.*?)', r.json()['html'], re.S)
      pinglunshijians = re.findall('', r.json()['html'], re.S)
      pingluns = re.findall('(.*?)', r.json()['html'], re.S)



      for i in range(20):
          a = a + 1
          sheet.append([yonghumingchengs[i], youyongshus[i], pinglunshijians[i].split()[0].split("-")[-1],
                        pinglunshijians[i].split()[1].split(":")[0], pingluns[i]])
      print(f"已爬取完第{page}页数据,存入{i + 1}条数据....")
  except:
      wb.save("全部.xlsx")
      print(f"共爬取{page}页数据，存入{a}条数据....")
      ~~~

import pandas as pd
df = pd.read_excel('全部.xlsx',names=['用户名称','点赞数','评论日期','评论时间','评论内容'])
df.head()

df.drop_duplicates()

df.info()