抓取电视剧+网络剧的信息：电视剧+网络剧实时热度和实时播放量数据！！！

分析：

代码部分：

import requests,time
from pandas import DataFrame
from my_fake_useragent import UserAgent

def get_headers():
    ua = UserAgent().random()
    headers = {
        'Connection':'close',
        'Referer':'猫眼热度',
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.67 Safari/537.36 Edg/87.0.664.47',
    }#这是想使用动态User-Agent的，但是在持久化储存的时候，使用动态的User-Agent会报错，所以就不用了
    return headers

def get_requests():
        
    params = {
        
        'seriesType':'',
        'platformType':'',
        'showDate':'2',
        'dateType':'0',
        'rankType':'0',
    }
    session = requests.Session()#处理cookie
    session.get(url='猫眼热度',headers=get_headers())
    my_url = '猫眼热度ajax请求'
    response = session.get(url=my_url,headers=get_headers(),params=params)
    response.encoding = 'utf-8'
    data_list = response.json()['dataList']
    
    dateTime = data_list['updateInfo']['updateTimestamp']
    dateTime = time.strftime("%Y-%m-%d %H:%M",time.localtime(dateTime/1000))
    print('抓取数据数据',dateTime,'
')
    
    
    name_list = []
    platfor_list = []
    releaseInfo_list = []
    heat_list = []
    play_list = []#把抓取到的数据放在列表里面
    
    for dic in data_list['list']:
        name = dic['seriesInfo']['name']
        platfor = dic['seriesInfo']['platformDesc']
        releaseInfo = dic['seriesInfo']['releaseInfo']
        heat = dic['currHeatDesc']
        try:
            play = dic['playCountSplitUnit']['num']#这部分是数据的解析提取
        except:
            play = None
            
        
        print(name,platfor,releaseInfo,'{}万热度 '.format(heat),'{}万播放量'.format(play),'
')
        name_list.append(name)
        platfor_list.append(platfor)
        releaseInfo_list.append(releaseInfo)
        heat_list.append(heat)
        play_list.append(play)
        
    return dateTime,name_list,platfor_list,releaseInfo_list,heat_list,play_list
    
def ptable_to_csv():#数据的持久化储存
    
    dic = {
        
        '时间':get_requests()[0],
        '剧名':get_requests()[1],
        '平台':get_requests()[2],
        '上线时间':get_requests()[3],
        '热度(万)':get_requests()[4],
        '平台播放量(万)':get_requests()[5],
    }
    data = DataFrame(data=dic)
    data.to_csv('video_data.csv',encoding='utf-8-sig',mode='a',header=None)
    
def main():
    
    while True:
        ptable_to_csv()
        time.sleep(30)#循环，实验效果，这里设置是30秒抓一次（可以设置30分钟等）
        
main()

ok，下面是抓取效果：