import csv
from re import findall
from time import sleep
import requests
from fake_useragent import UserAgent
import openpyxl



def get_html(url):
    '''

    :param url:要爬取的地址
    :return:返回html
    '''
    headers = {"User-Agent": UserAgent().chrome}
    print(url)
    resp = requests.get(url, headers=headers)
    sleep(2)
    if resp.status_code == 200:
        resp.encoding = 'utf-8'
        return resp.text
    else:
        return None

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'"name":"(.*?)"', html)  # 电影名称
    # filmtime = findall(r'"premiereDate":"(.*?)"', html)  # 上映时间
    # avgPrice = findall(r'"avgPrice":"(.*?)"', html)  # 平均票价
    # avgSalesCount = findall(r'"avgSalesCount":(\d+)', html)  # 场均人次
    # salesInWan = findall(r'"salesInWan":"(.*?)"', html)  # 总票价
    # return {"name": name, "filmtime": filmtime, "avgPrice": avgPrice, "avgSalesCount": avgSalesCount, "salesInWan": salesInWan}
    movieCode = findall(r'"movieCode":"(.*?)"', html)  # 电影编号
    return movieCode


def pares_index_detail(list_html_detail):
    '''

    :param list_html_detail: 获取详情页
    :return: 返回所要数据
    '''
    name = findall(r'<div class="movie-info-content"><div class="movie-name">(.*?)</div>', list_html_detail)  # 电影名称
    wedPrice_test = findall( r'<div class="data-name">首周票房</div><div class="data-value">(\d+\.\d+|\d+)<span class="data-unit">(.*?)</span>',
                       list_html_detail)  # 首周票房
    wedPrice_num = [a for a, _ in wedPrice_test]
    wedPrice_dan = [a for _, a in wedPrice_test]
    wedPrice = wedPrice_num + wedPrice_dan
    dayPrice_test = findall(r'<div class="data-name">首日票房</div><div class="data-value">(\d+\.\d+|\d+)<span class="data-unit">(.*?)</span>',
                       list_html_detail)  # 首日票房
    dayPrice_num = [a for a, _ in dayPrice_test]
    dayPrice_dan = [a for _, a in dayPrice_test]
    dayPrice = dayPrice_num + dayPrice_dan
    score = findall(r'<div class="data-name">豆瓣评分</div><div class="data-value">(.*?)</div>',
                       list_html_detail)  # 豆瓣评分
    direct = findall(r'<p class="name">(.*?)</p><p class="desc">导演</p>',
                       list_html_detail)  # 导演
    actors_a = findall(r'<p class="name">(.*?)</p><p class="desc">(.*?)</p>',
                       list_html_detail)  # 演员名单
    actors = format_data(actors_a)
    return {"name": name, "wedPrice": wedPrice, "dayPrice": dayPrice, "score": score, "direct": direct, "actors": actors}

def format_data(actors):
    actor_list = []
    for actor in actors:
        if actor[1] != "导演":
            actor_list.append(actor[0])
        # actor_list = [actors[0] for actor_a in actor if actor[1] != '导演']
    return actor_list

def xlsx_data(data):
    # 打开一个工作簿
    workbook = openpyxl.load_workbook("filmsdata_1_1.xlsx")

    # 获取活动的工作表
    worksheet = workbook.active

    # 定义数据
    data = [
        [','.join(data['name'][:]), ','.join(data['wedPrice'][:]), ','.join(data['dayPrice'][:]), ','.join(data['score'][:]), ','.join(data['direct'][:]), ','.join(data['actors'][:])]
    ]

    for row in data:
        worksheet.append(row)

    # for i in range(len(data['name'])):
    #     data_1 = [data['name'][i], data['filmtime'][i], data['avgPrice'][i], data['avgSalesCount'][i], data['salesInWan'][i]]
    # # return {"name": name, "filmtime": filmtime, "avgPrice": avgPrice, "avgSalesCount": avgSalesCount, "salesInWan": salesInWan}
    #     worksheet.append(data_1)
    #
    # # 保存工作簿为xlsx文件
    workbook.save("filmsdata_1_1.xlsx")

def main():
    num = int(input("请输入要获取多少年："))
    for page in range(num):
        year = 2022 - page
        url = 'https://zgdypf.zgdypw.cn/getYearData?year={}'.format(year)
        list_html = get_html(url)
        movie = pares_index(list_html)
        # xlsx_data(movie)
        print(movie)
        for i in range(len(movie)):
            url = f'https://zgdypf.zgdypw.cn/movie/detail/' + movie[i] + f'?from=movie&tab=1&secondTab={year}'
            list_html_detail = get_html(url)
            detail = pares_index_detail(list_html_detail)
            xlsx_data(detail)

if __name__ == '__main__':
    main()