import requests
import parsel
from tqdm import tqdm
import csv
import time

header = {
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
}


def get_vidio(pageurl):
    # pageurl = "https://www.kirinjewelry2006.com/video/products-detail-967094"
    response = requests.get(url=pageurl, headers=header)
    if response.status_code == 200:
        res_text = response.text
        select = parsel.Selector(res_text)
        vidio_name = select.xpath('//*[@id="v620a34694dad7"]//h1/text()').get().split("-")[-1]
        # print(vidio_name)
        vidio_url = select.xpath('//*[@id="v620a34694dad7"]//img/@video-src').get()
        vidio_res = requests.get(url=vidio_url,headers=header).content
        
        with open('vidio\\{}.mp4'.format(vidio_name), 'wb') as file:
            file.write(vidio_res)
        print("{}视频已保存".format(vidio_name))

        with open('vidio.csv', encoding="utf-8", mode='a', newline="") as f:
            csv_writer = csv.writer(f)
            csv_writer.writerow([vidio_name,])
        time.sleep(5)
    else:
        print("无法获取视频")

for page in tqdm(range(2,87)):
    print("正在爬取第{}页".format(page))
    url = "https://www.kirinjewelry2006.com/products-list-{}".format(page)
    response = requests.get(url=url,headers=header).text
    select = parsel.Selector(response)

    lis = select.xpath('//*[@id="v6204665765bf2"]/div/div[2]/div[2]//div[1]/ul/li')
    for li in lis:
        href = li.xpath('div/a/@href').get()
        pageurl = "https://www.kirinjewelry2006.com" + href
        # print(pageurl)
        try:
            get_vidio(pageurl)
        except:
            continue