爬豆瓣---正在热播

金灰

于 2024-08-06 07:30:00 发布

阅读量91

点赞数 4

分类专栏： # 爬虫文章标签：网络 python

本文链接：https://blog.csdn.net/2303_80857229/article/details/140936678

版权

爬虫专栏收录该内容

47 篇文章 1 订阅

订阅专栏

免责声明:本文仅做分享...!

import requests
from lxml import etree


def douban():
    # 自己看着伪装吧....
    headers = {
        'cookie': 'bid=RwDQeYLHA1I; ll="118225"; _pk_id.100001.4cf6=0dffc70094368c73.1722857141.; _pk_ses.100001.4cf6=1; ap_v=0,6.0; __utma=30149280.1944585126.1722857142.1722857142.1722857142.1; __utmb=30149280.0.10.1722857142; __utmc=30149280; __utmz=30149280.1722857142.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); __utma=223695111.886919447.1722857142.1722857142.1722857142.1; __utmb=223695111.0.10.1722857142; __utmc=223695111; __utmz=223695111.1722857142.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); __yadk_uid=3pNZpd4N3s1lkWAjKSqyanVloqxTQj5i; _vwo_uuid_v2=D4DF9A94C1DD66CD378F6079E3EB24505|40f351d032498a834c47c3f4b75f102b',
        'priority': 'u=0, i',
        'sec-ch-ua': '"Not)A;Brand";v="99", "Microsoft Edge";v="127", "Chromium";v="127"',
        'sec-ch-ua-mobile': '?0',
        'sec-ch-ua-platform': '"Windows"',
        'sec-fetch-dest': 'document',
        'sec-fetch-mode': 'navigate',
        'sec-fetch-site': 'none',
        'sec-fetch-user': '?1',
        'upgrade-insecure-requests': '1',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36'
    }
    # 输入你所在的市区进行查询正在热播的:
    city = input("请输入你所在的市区(英文小写就行):")
    url = f'https://movie.douban.com/cinema/nowplaying/{city}/'
    url_content = requests.get(url, headers=headers)
    url_content.encoding = 'utf-8'
    # print(url_content.text)
    data = url_content.text
    return data


def deal_with(datas):
    tree = etree.HTML(datas)
    # print(tree)
    # divs = tree.xpath('//ul[@class="lists"]/li/')
    # 正在热播的电影:
    lis_now = tree.xpath('//div[@id="nowplaying"]//ul[@class="lists"]/li')
    for li in lis_now:
        # 名称
        title = li.xpath('./@data-title')
        # print(title)
        # 时长
        times = li.xpath('./@data-duration')
        # 产地
        area = li.xpath('./@data-region')
        # 导演
        director = li.xpath('./@data-director')
        # 演员s
        actors = li.xpath('./@data-actors')
        # status = li.xpath('./@data-category')
        # status2 = li.xpath('./@data-enough')
        # 评分
        score = li.xpath('./@data-score')
        # 一键去
        lianJie = li.xpath('./ul/li/a/@href')[0]
        print(f'电影名称:{title} , 时长:{times} , 产地:{area} , 评分:{score} , 导演:{director} , 演员:{actors} , 详情:{lianJie}')

# 即将上映的自己写...


if __name__ == '__main__':
    datas = douban()
    deal_with(datas)