Crawling Douban Movie Code

import json

import requests
from bs4 import BeautifulSoup
import openpyxl
wb=openpyxl.Workbook()
#创建工作薄
sheet=wb.active
#获取工作薄的活动表
sheet.title='movies'
#工作表重命名

sheet['A1'] ='电影名'     #加表头，给A1单元格赋值
sheet['B1'] ='评分'   #加表头，给B1单元格赋值
sheet['C1'] ='播放链接'   #加表头，给C1单元格赋值
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.106 Safari/537.36'}
url = 'https://movie.douban.com/j/search_subjects?'
if True:
    # 封装参数
    params = {
        'type': 'movie',
        'tag': '热门',
        'page_limit': '50',
        'page_start': '0',
    }
    # 发送请求，并把响应内容赋值到变量res里面
    res = requests.get(url, headers=headers, params=params)
    res_text = res.text
    # 确认这个response对象状态正确
    print(res.status_code)
    # 如果响应成功，继续
    if int(res.status_code) == 200:
        movies = json.loads(res_text)
        print(movies)
        # 定位数据
        subjects = movies['subjects']

    for movie in subjects:
        title = movie['title']
        rate = movie['rate']
        url = str(movie['url'])
        sheet.append([title, rate, url])
    # for i in subjects:
    #     print()
wb.save('movie.xlsx')