from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import requests
#设置无界面模式
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
  
class VideoCrawl(object):
  video_box=[]#收集video真正的url
  def __init__(self,url):
    self.driver=webdriver.Chrome(executable_path=r"C:\Program Files\python\Lib\site-packages\selenium\webdriver\chrome\chromedriver.exe",options=chrome_options)#设置无界面模式
    self.driver.get(url)
  
  #程序运行完毕，析构函数关闭selenium
  def __del__(self):
    print("爬取结束。。。。。",len(VideoCrawl.video_box),VideoCrawl.video_box)
    self.driver.close()
  
  def run(self):
    self.get_detail_info()
  #获取列表页所有详情页的url
  def get_detail_info(self):
    detail_info = self.driver.find_elements_by_xpath('//a[@class="video-wrap statpid"]')
    detail_url=[]
    for i in detail_info:
      detail_url.append(i.get_attribute('href'))#获取视频页url
    video_playtime_list=self.driver.find_elements_by_xpath('//span[@class="video-duration"]')
    video_playtime_list=[i.text for i in video_playtime_list]
    for res in zip(detail_url,video_playtime_list):
      playtime=res[1].split(":")[0]
      # print("playtime--------",playtime)
      if int(res[1].split(":")[0])<=5:#播放时间小于5分钟的要
        # print(res[0],"解析的url",playtime)
        self.parse_video(res[0],res[1])
      else:
        pass
  #解析详情页
  def parse_video(self,url,t):
    self.driver.get(url)
    videoobj = self.driver.find_elements_by_xpath('//video')
    video_url=videoobj[0].get_attribute('src')
    title=self.driver.find_elements_by_xpath('//h1[@class="video-title"]')[0].text
    print('video_url--------',video_url,title,t)
    #保存video到本地
    self.save_video(video_url,title,t)
    #类变量统计video_url
    VideoCrawl.video_box.append(video_url)
  #保存,请求video_url，二进制保存为mp4
  def save_video(self,url,title,t):
    filename="video"+title+"-"+t.replace(":","")+".mp4"
    video=requests.get(url).content
    with open(filename,"wb") as file:
      file.write(video)
    print(f"{filename}写入文件完毕")
  
if __name__ == '__main__':
  crawl=VideoCrawl('https://v.huya.com/cat/7')
  crawl.run()