import hashlib
import random
import time
import uuid
from fake_useragent import UserAgent
import requests
from re import findall
from time import sleep
from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait


def get_html(url):
    '''

    :param url:要爬取的地址
    :return:返回html
    '''
    headers = {"User-Agent": UserAgent().chrome,
               "Cookie": "__mta=207860269.1704201302145.1704213737093.1704213880564.33;"
                         "uuid_n_v=v1;"
                         "uuid=EAC4EE70A97011EE9D005D48E25AAA2026CA184696BC4B3C99668D0A2CABF221;"
                         "_lxsdk_cuid=18cca502bf1c8-0ab73a0cab1c77-26001951-144000-18cca502bf1c8;"
                         "_csrf=393580308f4d1dbe8c7c22df65a716f6d3b2e6ebf5d081d15383e0c5f4abf77d;"
                         "Hm_lvt_703e94591e87be68cc8da0da7cbd0be2=1704201301,1704207964,1704208473;"
                         "_lx_utm=utm_source%3Dbing%26utm_medium%3Dorganic;"
                         "_lxsdk=EAC4EE70A97011EE9D005D48E25AAA2026CA184696BC4B3C99668D0A2CABF221;"
                         "Hm_lpvt_703e94591e87be68cc8da0da7cbd0be2=1704213881;"
                         "_lxsdk_s=18cca9eeac1-26b-1be-ff4%7C%7C81"
                }  # cookie避开验证码
    print(url)
    resp = requests.get(url, headers=headers, timeout=5)
    sleep(5)
    if resp.status_code == 200:
        resp.encoding = 'utf-8'
        return resp.text
    else:
        return None

def get_html_more(url):
    '''

    :param url:获取详情页网址
    :return: 返回html
    '''
    driver = webdriver.Chrome()
    driver.get(url)
    uid = uuid.uuid4()  # 随机uid
    ts = time.time() * 1000  # 时间戳
    key = 'A013F70DB97834C0A5492378BD76C53A'  # 固定
    ua = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'  # 固定
    index = 1000 * random.random() + 1
    enstr = f'method=GET&timeStamp={ts}&User-Agent={ua}&index={index}&channelId=40009&sVersion=2&key={key}'
    signkey = hashlib.md5(enstr.encode(encoding='UTF-8')).hexdigest()
    # https://www.maoyan.com/ajax/films/1320283?timeStamp={}&index={}&signKey={}&channelId=40011&sVersion=1&webdriver=false
    url_1 = url + f'?timeStamp{ts}&index={index}&signKey={signkey}&channelId=40011&sVersion=1&webdriver=false'
    WebDriverWait(driver, 10)
    # driver.get(url_1)
    #WebDriverWait(driver, 10)
    #driver.get(url)
    return driver.page_source

def parse_list(html):
    '''

    :param html: 传递进来一个有电影列表的html
    :return:返回一个电影列表的url
    '''
    a_list = findall(r'<div class="channel-detail movie-item-title".+>\s+<a href="(/films/\d+)"', html)
    list_url = ['http://www.maoyan.com{}'.format(url) for url in a_list]
    return list_url

def pares_index(html):
    '''

    :param html:传递捡来一个有电影信息的html
    :return: 已经提取好的电影信息
    '''
    name = findall(r'<h1 class="name">(.+)</h1>', html)  # 电影名称
    type = findall(r'<a class="text-link".*?>(.*?)</a>', html)  # 电影类型
    country = findall(r'class="ellipsis">(\s*)(\S+)', html)[1][1]  # 上映国家
    filmtime = findall( r'<li class="ellipsis">(\s*)(\S+)(\s*)', html)[2][1]  # 上映时间
    actors_a = findall(r'<div class="name">\s*(.*?)\s*</div>', html)
    actors = format_data(actors_a)  # 演员名单
    # dirctor =
    return {"name": name, "type": type, "country": country, "filmtime": filmtime, "actors": actors}

def format_data(actors):
    actor_set = set()
    for actor in actors:
        actor_set.add(actor.strip())
    return actor_set

def main():
    num = int(input("请输入要获取多少页："))
    for page in range(num):
        url = 'https://maoyan.com/films?showType=3&offset={}'.format(page * 30)
        list_html = get_html(url)
        list_url = parse_list(list_html)
        for url in list_url:
            info_html = get_html_more(url)
            movie = pares_index(info_html)
            print(movie)

if __name__ == '__main__':
    main()