import requests
from bs4 import BeautifulSoup
from pprint import pprint
import re


def joke(page):

    url = 'http://xx/?m=vod-index-pg-'+str(page)+'.html'

    header = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
    }
    response = requests.get(url, headers=header)

    html = response.text

    soup = BeautifulSoup(html, 'lxml')

    articles = soup.find_all("table")[1]

    artices = articles.find_all("tr", {"class": {"row"}})

    for item in artices:

        title = item.a.get_text().strip()
        url = item.a['href']
        diqu = item.select('tr td:nth-of-type(2)')[0].get_text().strip()
        lleibie = item.select('tr td:nth-of-type(3)')[0].get_text().strip()
        addtime = item.select('tr td:nth-of-type(4)')[0].get_text().strip()
        #print(title,url,diqu,lleibie,addtime)
        urla = 'http://caiji.kuyun98.com/'+url
        responsea = requests.get(urla, headers=header)
        htmla = responsea.text
        soupa = BeautifulSoup(htmla, 'lxml')
        table = soupa.select('table')[1]
        img = table.select('img')[0].get('src')  # 缩略图
        tableb = table.find('table')
        yanyuan = tableb.select('tr')[1].get_text()  # 演员
        daoyan = tableb.select('tr')[2].get_text()  # 影片导演
        shanying = tableb.select('tr')[8].get_text()  # 上映时间
        des = tableb.select('tr')[9].get_text()  # 影片简介
        vide = table.select('table tr table')[1:]
        for i in range(0, len(vide)):
          videtr = vide[i].select('a')
        for item in range(0, len(videtr)):
           result = ' '.join(videtr[item])
        info =re.findall('http://[^\s]*.*', result)
        pprint(info)
            
if __name__ == "__main__":

    for page in range(1, 2):
        joke(page)