python爬虫实现各视频网站vip付费电影下载

使用解析网站解析视频播放地址：http://jx.618g.com/
爬取解析网站，获得视屏片段
cmd命令合成很多ts文件为完整的MP4视屏文件：copy /b *ts movie.mp4
可在cmd窗口下运行，需到文件目录下，也可使用bat文件运行
为提高下载速度，使用进程池的方式下载

import requests
from multiprocessing import Pool
from fake_useragent import UserAgent
import os

# 单线程方式
# def download():
#     headers = {
#         ‘User-Agent‘: UserAgent().chrome
#     }
#     i=0
#     while True:
#         base_url = ‘https://youku.cdn7-okzy.com/20191203/16033_b28cd947/1000k/hls/0d2d28c500600%04d.ts‘ % i
#         response = requests.get(base_url, headers=headers)
#         # print(response.status_code)
#         if response.status_code == 404:
#             print(‘下载完成‘)
#             break
#         else:
#             with open(‘./video/{}‘.format(base_url[-10:]), ‘wb‘)as f:
#                 f.write(response.content)
#             i+=1
#
#
# if __name__ == ‘__main__‘:
#     download()


# 使用进程池方式下载（更快，cpu占用更多）
def download(i,n):
    headers = {
        ‘User-Agent‘: UserAgent().chrome
    }
    base_url = ‘https://youku.cdn7-okzy.com/20191203/16033_b28cd947/1000k/hls/0d2d28c500600%04d.ts‘ % i
    response = requests.get(base_url, headers=headers)
    with open(‘./video/{}‘.format(base_url[-10:]), ‘wb‘)as f:
        f.write(response.content)
    if i % 10 == 0:
        print(‘\r下载进度：‘+str((i/n)*100)[:4]+‘%‘, end=‘‘)


if __name__ == ‘__main__‘:
    n = 2200
    po = Pool(5) # 创建一个进程池，可以包含5个子进程
    for i in range(0, n):
        po.apply_async(download, args=(i,n))  # 将全部进程全部加到进程队列中去
    po.close()

    print(‘\r开始下载.....‘, end=‘‘)
    po.join()