python小白学习记录 多线程爬取ts片段

 

 

from lxml import etree
import requests
from urllib import request
import time
import os
from queue import Queue
import threading
import re
from multiprocessing import pool
from urllib import request
import ffmpeg
def download(urls):
    for index in range(0,1342):
        n = index
        if(index<=999):
            n = str(n).zfill(3)
        else:
            n = str(n)
        # print(n)
        url = "https://zy.512wx.com/20171106/vM1OOVna/1200kb/hls/ppvod1983%s.ts" %n
        print("url",url)
        urls.put(url)
class Consumer(threading.Thread):
    def __init__(self,urls,*args,**kwargs):
        super(Consumer, self).__init__(*args,**kwargs)
        self.urls = urls
        self.queueLock = threading.Lock()
    def run(self):
        while True:
            if self.urls.empty():
                break
            else:
                self.queueLock.acquire()
                file = self.urls.get()
                self.queueLock.release()
                name = file.split('/')[-1]
                print("name",name)
                if os.access("./video/{}".format(name), os.F_OK):
                    pass
                else:
                    with open("./video/{}".format(name), "wb") as fp:
                        resp = requests.get(file,verify = False)
                        fp.write(resp.content)
                print(threading.current_thread(),name + "下载完成")

def get_ts(urls):
    with open("./video/kuiba.ts","wb") as fp:
        for index in range(0, len(urls)):
            resp =  requests.get(urls[index])
            fp.write(resp.content)
            print(str(index)+"下载完成")
def main():
    urls = Queue(2000)
    download(urls)
    # with open("./video/kuiba.ts", "wb") as fp:
    #     while not urls.empty():
    #         file = urls.get()
    #         name = file.split('/')[-1]
    #         if os.access("./video/{}".format(name), os.F_OK):
    #             with open("./video/{}".format(name), "rb") as f:
    #                 fp.write(f.read())
    #         else:
    #             pass
    #         print(name + "下载完成")

    # for index in range(0,16):
    #     x = Consumer(urls)
    #     x.start()
if __name__ == '__main__':
    # main()
    cmd = "ffmpeg" + " -i " + "./video/kuiba.ts" + " -c copy " + "F:\pycharm\kuiba.mp4"
    os.system(cmd)
    print("done")

ts 转 mp4 

命令 copy /b 原文件名 新文件名 

================================

由于ts被加密了 所以以上ts均无法打开

在m3u8文件中，有说明是采用的aes-128加密技术，并且在f12中得到了key.key密钥，

但是在网上的aes程序虽然给的样例跑通了，

但是把爬取到的加密ts文件读取解密保存时一直报错

在网上找了一个解密软件，把key和ts文件放在同一文件下，

由于免费只能解密并合并三个ts片段

但成功了，并且解密的ts文件是可以播放的