# Encoding: utf-8
# Author: furongbing
# Date: 2021-11-19 20:54
# Project name: FrbPythonFiles
# IDE: PyCharm
# File name: Mtime
import requests
import pandas as pd
from threading import Thread
import time
import json
 
# 模塊說(shuō)明：
"""
從時(shí)光網(wǎng)上按年代獲取指定年份電影的數(shù)據(jù)
"""
# 更新日志：
"""
1、2021-11-19：
    a、完成初版
"""
# 待修改：
"""
"""
# 請(qǐng)求頭數(shù)據(jù)
headers = {"Accept": "application/json, text/plain, */*",
           "Accept-Encoding": "gzip, deflate",
           'Accept-Language': 'zh-CN,zh;q=0.9',
           'Connection': 'keep-alive',
           'Content-Type': 'application/x-www-form-urlencoded',
           'Cookie': '_tt_=FB8A3FAD4704D42543B7EC121C2565AA; __utma=196937584.1082595229.1637326918.1637326918.1637326918.1; __utmz=196937584.1637326918.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); Hm_lvt_07aa95427da600fc217b1133c1e84e5b=1637241042,1637326637,1637374129; Hm_lpvt_07aa95427da600fc217b1133c1e84e5b=1637374170',
           'Host': 'front-gateway.mtime.com',
           'Origin': 'http://film.mtime.com',
           'Referer': 'http://film.mtime.com/',
           'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36'
           }
pagesize = 20  # todo 獲取的每頁(yè)數(shù)據(jù)條數(shù)，一般建議成默認(rèn)的20就可以了，設(shè)置的太大，每頁(yè)包含的數(shù)據(jù)量就大，某一條電影數(shù)據(jù)出錯(cuò)會(huì)導(dǎo)致其它數(shù)據(jù)也被拋棄。
data = []
error = []
 
 
def get_data(p_year=1987):  # 按照年份獲取當(dāng)年度所有的電影數(shù)據(jù)
    url = 'http://front-gateway.mtime.com/mtime-search/search/unionSearch2'  # 請(qǐng)求的url
    params = {'year': p_year, 'pageSize': pagesize, 'pageIndex': 1, 'searchType': 0}  # 請(qǐng)求的表單數(shù)據(jù)
    # 獲取當(dāng)年度所有的電影的數(shù)量，繼而計(jì)算要獲取多少頁(yè)
    try:
        r = requests.get(url=url, params=params, headers=headers, timeout=10)
        r.encoding = r.apparent_encoding
        all_data = json.loads(r.text)
        moviesCount = all_data['data']['moviesCount']
        pages = round(moviesCount / pagesize)
    except Exception:
        moviesCount = 1000
        pages = round(moviesCount / pagesize)
 
    # 定義變量
    來(lái)源 = '時(shí)光網(wǎng)'
    年代 = p_year
    ID, 中文名, 英文名, 類型, 形式, 海報(bào)url, 評(píng)分, 導(dǎo)演, 主演, 詳情, 可播放, 國(guó)家地區(qū), 上映日期, 片長(zhǎng), 票房, 觀看日期 = [''] * 16
 
    for page in range(pages):  # todo 一共要獲取多少頁(yè)
        if page % 10 == 0:  # 每10頁(yè)輸出一次進(jìn)度
            print(f'已完成 {100 * page / pages:.2f}%')
        pageindex = page + 1
        params = {'year': p_year, 'pageSize': pagesize, 'pageIndex': pageindex, 'searchType': 0}  # 請(qǐng)求的表單數(shù)據(jù)
        try:  # 獲取指定頁(yè)的電影數(shù)據(jù)
            r = requests.get(url=url, params=params, headers=headers, timeout=10)
            r.encoding = r.apparent_encoding
            all_data = json.loads(r.text)
            movies = all_data['data']['movies']
            # 獲取電影具體信息
            for movie in movies:
                ID = movie['movieId']
                中文名 = movie['name']
                英文名 = movie['nameEn']
                類型 = movie['movieType']
                形式 = movie['movieContentType']
                海報(bào)url = movie['img']
                其它譯名 = movie['titleOthersCn']
                評(píng)分 = movie['rating']
                導(dǎo)演 = movie['directors']
                主演 = movie['actors']
                詳情 = movie['href']
                可播放 = movie['canPlay']
                國(guó)家地區(qū) = movie['locationName']
                上映日期 = movie['realTime']
                片長(zhǎng) = movie['length']
                info = [來(lái)源, 年代, ID, 中文名, 英文名, 類型, 形式, 海報(bào)url, 其它譯名, 評(píng)分, 導(dǎo)演, 主演, 詳情, 可播放, 國(guó)家地區(qū), 上映日期, 片長(zhǎng), 票房, 觀看日期]
                data.append(info)
        except Exception as err:
            er_year, er_pagesize, er_pageindex, er_msg = p_year, pagesize, pageindex, err
            error.append([er_year, er_pagesize, er_pageindex, er_msg])
            print(f"出錯(cuò)啦，出錯(cuò)年份：{p_year}，pagesize：{pagesize}，page：{pageindex}，出錯(cuò)原因：{er_msg}")
            continue
 
 
if __name__ == '__main__':
    begin = time.perf_counter()
    threads = []
    for year in range(2020, 2021):  # todo 此處可以自定義要獲取的年份
        t = Thread(target=get_data, args=(year,))
        threads.append(t)
        t.start()
    for t in threads:
        t.join()
 
    with open('error.txt', 'w', encoding='utf-8') as f:
        f.write(str(error))
 
    data.insert(0, ['來(lái)源', '年代', 'ID', '中文名', '英文名', '類型', '形式', '海報(bào)url', '其它譯名', '評(píng)分', '導(dǎo)演', '主演', '詳情', '可播放', '國(guó)家地區(qū)', '上映日期', '片長(zhǎng)', '票房', '觀看日期'])
    df = pd.DataFrame(data)
    df.to_excel(excel_writer=r'film.xlsx', sheet_name='sheet1', index=None, header=False)  # todo film.xlsx為最后保存的文件名
 
    end = time.perf_counter()
    runtime = end - begin
    print(f'運(yùn)行時(shí)長(zhǎng)：{runtime:.3f}秒。')