import requests
from lxml import html
import pandas as pd

def spider(isbn):
    url = 'https://movie.douban.com/cinema/later/{}/'.format(isbn)
    headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36"}

    html_data = requests.get(url, headers=headers).text
    selector = html.fromstring(html_data)

    div_list = selector.xpath('//div[@id="showing-soon"]/div')
    print('有{}部电影即将上映'.format(len(div_list)))

    movie_info_list = []
    for div in div_list:
        # 获取电影名字
        movie_names = div.xpath('div[@class="intro"]/h3/a/text()')[0]
        # print(movie_names)
        # 获取电影上映日期
        movie_days = div.xpath('div/ul/li/text()')[0]
        # print(movie_days)
        # 获取电影类型
        movie_types = div.xpath('div/ul/li/text()')[1]
        # print(movie_types)
        # 获取电影出版国家
        movie_countries = div.xpath('div/ul/li/text()')[2]
        # print(movie_countries)
        # 获取电影想看的人数
        movie_numbers = div.xpath('div/ul/li/span/text()')[0]
        movie_numbers = movie_numbers.replace('人想看', '')
        # print(movie_numbers)
        # 获取电影的封面图片
        movie_photos = div.xpath('a/img/@src')
        # print(movie_photos)

        movie_info_list.append(
            {"movie_name": movie_names,
             "movie_days": movie_days,
             "movie_types": movie_types,
             "movie_countries": movie_countries,
             "movie_numbers": movie_numbers,
             "movie_photos": movie_photos}
        )

    print('############################################')
    print('##################排序前####################')
    print('############################################')
    print(movie_info_list)

    print('############################################')
    print('##################具体如下###################')
    print('############################################')

    for movies in movie_info_list:
        print(movies)

    print('############################################')
    print('##################排序后####################')
    print('############################################')

    movie_info_list.sort(key=lambda x: int(x['movie_numbers']), reverse=True)    # 定义匿名函数使列表按'movie_numbers'的方式排序
    print(movie_info_list)    

    print('############################################')
    print('##################具体如下###################')
    print('############################################')

    for movies in movie_info_list:
        print(movies)
    
    # 将爬取到的数据存进本地csv文件里 
    df = pd.DataFrame(movie_info_list)    # 转化成dataframe格式
    df.to_csv('豆瓣电影信息.csv')    # 存储成csv

    # 批量图片下载
    for movies in movie_info_list:
        movie_link = movies['movie_photos'][0]    # 记得加[0]，不然会报错
        # print(movie_link)
        res = requests.get(movie_link)
        if res.status_code == 200:
            with open('../image/{}.jpg'.format(movies['movie_name']), 'wb') as f:
                f.write(res.content)

isbn = input('请输入要搜索的城市名（中英文均可），例如：沈阳或shenyang')
spider(isbn)

请输入要搜索的城市名（中英文表示），例如：shenyang沈阳
有25部电影即将上映
############################################
##################排序前####################
############################################
[{'movie_name': '爱在零纬度', 'movie_days': '10月29日', 'movie_types': '爱情 / 家庭', 'movie_countries': '中国大陆', 'movie_numbers': '188', 'movie_photos': ['https://img1.doubanio.com/view/photo/s_ratio_poster/public/p2572231307.jpg']}...]
############################################
##################具体如下###################
############################################
{'movie_name': '爱在零纬度', 'movie_days': '10月29日', 'movie_types': '爱情 / 家庭', 'movie_countries': '中国大陆', 'movie_numbers': '188', 'movie_photos': ['https://img1.doubanio.com/view/photo/s_ratio_poster/public/p2572231307.jpg']}
{'movie_name': '小巷管家', 'movie_days': '10月29日', 'movie_types': '剧情', 'movie_countries': '中国大陆', 'movie_numbers': '122', 'movie_photos': ['https://img3.doubanio.com/view/photo/s_ratio_poster/public/p2572339805.jpg']}
...}
############################################
##################排序后####################
############################################
[{'movie_name': '天气之子', 'movie_days': '11月01日', 'movie_types': '爱情 / 动画 / 奇幻', 'movie_countries': '日本', 'movie_numbers': '67442', 'movie_photos': ['https://img3.doubanio.com/view/photo/s_ratio_poster/public/p2570055890.jpg']},
...]
############################################
##################具体如下###################
############################################
{'movie_name': '天气之子', 'movie_days': '11月01日', 'movie_types': '爱情 / 动画 / 奇幻', 'movie_countries': '日本', 'movie_numbers': '67442', 'movie_photos': ['https://img3.doubanio.com/view/photo/s_ratio_poster/public/p2570055890.jpg']}
{'movie_name': '终结者：黑暗命运', 'movie_days': '11月01日', 'movie_types': '动作 / 科幻 / 冒险', 'movie_countries': '美国', 'movie_numbers': '21889', 'movie_photos': ['https://img9.doubanio.com/view/photo/s_ratio_poster/public/p2571762536.jpg']},
...}

保存到本地csv文件，效果如下：

豆瓣电影信息.csv.png

批量下载图片到本地，效果如下：

图片保存到本地.png