小学期Python 豆瓣即将上映

# !/usr/bin/python3
# -*- coding: utf-8 -*-
# @Time    : 2020/6/30 18:42
# @Author  : FancyKing
# @FileName: dou_ban.py
# @Software: PyCharm

import requests
from fake_headers import Headers
from fake_useragent import UserAgent
from lxml import html


def gen_headers():
    fake_useragent = UserAgent(use_cache_server=True, cache=True, verify_ssl=False)
    # fake_useragent.update()
    fake_headers = Headers(headers=False).generate()
    fake_headers['User-Agent'] = fake_useragent.random
    # print(fake_headers)
    return fake_headers


def dou_ban_show(film_list_sorted):
    print('There are {} film(s) will on.'.format(len(film_list_sorted)))
    for foo in film_list_sorted:
        print('影片名称： {}'.format(foo['film_name']))
        print('\t上映日期： {}'.format(foo['film_date']))
        print('\t影片类型： {}'.format(foo['film_prop']))
        print('\t出版地区： {}'.format(foo['film_bel']))
        print('\t喜爱人数： {}'.format(foo['film_fav']))


def dou_ban_curler(uri):
    curler = requests.Session()
    site_data = curler.get(url=uri, headers=gen_headers()).text
    site_data.encode('utf-8')
    parser_data = html.fromstring(site_data)
    film_list_origin = parser_data.xpath('//div[@class="intro"]')
    film_list_sort = []
    for foo in film_list_origin:
        film_name = foo.xpath('h3/a/text()')[0]
        film_date = foo.xpath('ul/li[1]/text()')[0]
        film_prop = foo.xpath('ul/li[2]/text()')[0]
        film_bel = foo.xpath('ul/li[3]/text()')[0]
        film_fav = foo.xpath('ul/li[4]/span/text()')[0].replace('人想看', '')
        film_list_sort.append({
            'film_name': film_name,
            'film_date': film_date,
            'film_prop': film_prop,
            'film_bel': film_bel,
            'film_fav': film_fav
        })
    film_list_sort.sort(key=lambda x: float(x['film_fav']), reverse=True)
    return film_list_sort


# https://files.catbox.moe/wnsgeb.png
if __name__ == '__main__':
    douban_latest_uri = 'https://movie.douban.com/cinema/later/beijing/'
    film_list = dou_ban_curler(douban_latest_uri)
    while len(film_list) <= 0:
        dou_ban_curler(douban_latest_uri)
    dou_ban_show(film_list)