Python获取豆瓣《狼殿下》200条热门短评写入excel

# 200条之后的评论需要登录才能查看，后续研究
# index需要修改

import urllib.request
import re
import pandas as pd

headers = {'User-Agent',
           'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36'}

df = pd.DataFrame({'comment_time': [0],
                   'user_name': [0],
                   'user_id': [0],
                   'star': [0],
                   'title': [0],
                   'comments': [0]})

for j in range(11):
    start_page = str(j * 20)
    url = "https://movie.douban.com/subject/26743567/comments?start=%s" %(start_page)  # 确定要爬取的入口链接 
    
    print(j, url)
    
    opener = urllib.request.build_opener()
    opener.addheaders = [headers]
    data = opener.open(url).read().decode('utf8')
    
    # 获取评论时间
    comment_time_pattern = re.compile('<span class