爬取带key的ts视频网站

朋友在某网站学习，每次都要打开网页，想保存在本地播放，却没有下载方式。于是找我试试能不能下载下来。
1.分析一下网页，打开，按下F12，获取相关信息。
2.视频信息一般保存在m3u8文件中，因此直接搜索查找。

3.观察m3u8文件发现，ts文件为aes-128加密，key的获取方法就是直接从url获取。
4.从文件中提取出来url信息后，获取key值，将key转换为十六进制，尝试解密，发现成功。那么此种方法可行，只需要将m3u8中的ts链接获取，根据秘钥一个一个解密就可以了。
5.ts文件爬取完成后，在dos窗口使用命令行直接将文件合并就可以了。
copy /b *.ts videos.mp4

6.完整代码

# -*- coding: utf-8 -*-
"""
Time    : 2021-04-02 13:53
Name    : 茅十八
File    : spider_shipin.py
Topic   : 爬取中国会计网视频
"""
import requests
import re
import json
import base64
from Crypto.Cipher import AES


class Kuai_ji(object):
    def __init__(self):
        self.header = {
            'Host': 'elearning.chinaacc.com',
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:87.0) Gecko/20100101 Firefox/87.0',
            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
            'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
            'Accept-Encoding': 'gzip, deflate, br',
            'Referer': 'https://member.chinaacc.com/',
            'Connection': 'keep-alive',
            'Cookie': 'hd_uid=CjsAJWBj98UjEPREAzzTAg==; clct_nuID=16171642301299115; bdp_uuid=25a70cc998-1ceae87102-e8be58078c; zg_did=%7B%22did%22%3A%20%22178867fdea4119-0154b88d38575c-4c3f237d-144000-178867fdea523d%22%7D; zg_9b4551cf447148b0845f31f91e8a524d=%7B%22sid%22%3A%201618188966620%2C%22updated%22%3A%201618189325497%2C%22info%22%3A%201617860882274%2C%22superProperty%22%3A%20%22%7B%7D%22%2C%22platform%22%3A%20%22%7B%7D%22%2C%22utm%22%3A%20%22%7B%7D%22%2C%22referrerDomain%22%3A%20%22%22%2C%22cuid%22%3A%20%2282819233%22%7D; Hm_lvt_f1ca44b62370e4b7dc11d5937e51c2d6=1617929078,1617929186,1617955478,1618188971; _pk_id.member.chinaacc.com.e1fb=1cf2a9176d4ec1af.1617348690.1.1617348690.1617348690.; lastloginuser=m7677_41968; SelCourse=a|; _pk_id.www.chinaacc.com.e1fb=0be54a9159621948.1617929192.3.1618189311.1618189311.; _pk_ref.www.chinaacc.com.e1fb=%5B%22%22%2C%22%22%2C1618189311%2C%22https%3A%2F%2Fwww.chinaacc.com%2F%22%5D; _pk_id.www.chinaacc.com.eab1=2f935fa43caa4d22.1617929210.3.1618189325.1618189317.; _pk_ref.www.chinaacc.com.eab1=%5B%22%22%2C%22%22%2C1618189317%2C%22https%3A%2F%2Fwww.chinaacc.com%2F%22%5D; zg_ffaecff2118841b9866c8c549ea3c5a9=%7B%22sid%22%3A%201617958599807%2C%22updated%22%3A%201617960522067%2C%22info%22%3A%201617929338497%2C%22superProperty%22%3A%20%22%7B%7D%22%2C%22platform%22%3A%20%22%7B%7D%22%2C%22utm%22%3A%20%22%7B%7D%22%2C%22referrerDomain%22%3A%20%22elearning.chinaacc.com%22%7D; trackerSdkVisitor_isNew=true; trackerSdkData={%22uid%22:%2281263452%22%2C%22platform_source%22:%22web%22%2C%22time%22:1618189325622%2C%22bdp_uuid%22:%2225a70cc998-1ceae87102-e8be58078c%22}; BIGipServermember.chinaacc.com=654392074.20480.0000; clientID=qJQvIBoumlK4DmXSbdByMvqZukMzCNGRuQHxZQDNXpBN8dzrqLDzUr99QJXCu3mladZpXkW9DwNR%0D%0A0gFt_OGTGbltFnm7o8c3MtWmo7jdFDY%0D%0A; client_ucToken=9F7D029DA3ADB8A8F60EBDE0D85B0312-6bab3e37de618bbc456b1a315b7ddfb1-01; Hm_lpvt_f1ca44b62370e4b7dc11d5937e51c2d6=1618189326; sid=e27f6440-c9bd-4a64-af08-1bcb7733c338; cdeluid=81263452; username=m7677_41968; JSESSIONID=5701254F6527C1F5E24B334186D48BE2; _pk_ses.www.chinaacc.com.e1fb=*; _pk_ses.www.chinaacc.com.eab1=*',
            'Upgrade-Insecure-Requests': '1',
            'Cache-Control': 'max-age=0',
        }

        self.url = "https://www.chinaacc.com/demo/h5/2/198/cware-39252/video-901.html"
        self.m3u8_url = self.getm3u8()

    def getm3u8(self):
        rous = requests.get(self.url, headers=self.header)
        data = re.findall(r"JSON.parse\('(.*)'\)", rous.text)[0].replace('\\', '')
        json_data = json.loads(data).get('videoPath')
        m3u8_url = 'https:' + json_data
        return m3u8_url

    def get_data(self):
        print(self.m3u8_url)
        data = requests.get(self.m3u8_url).text
        aes_url = re.findall(r'#EXT-X-KEY:METHOD=AES-128,URI="(.*)"', data)[0]
        keys = requests.get(aes_url).text
        key = base64.b64decode(keys)
        iv = '00000000000000000000000000000000'
        iv = bytes.fromhex(iv)
        ts_datas = re.findall(r'(/ssec.chinaacc.com/.*)\n', data)
        i = 0
        for ts_data in ts_datas:
            ts_url = 'http:/' + ts_data
            print(ts_url)
            ts_rous = requests.get(ts_url)
            file_path = str(i) + ".ts"
            to_file_path = 'videos\\' + str(i) + '.ts'
            with open(file_path, 'wb') as f:
                f.write(ts_rous.content)
            with open(file_path, 'rb') as f:
                cryptor = AES.new(key, AES.MODE_CBC, iv)  # 创建实例
                plain_data = cryptor.decrypt(f.read())  # 放入需要解密的东西
                with open(to_file_path, 'wb') as w:
                    w.write(plain_data)
            i += 1


def main():
    kuai_ji = Kuai_ji()
    kuai_ji.get_data()


if __name__ == '__main__':
    main()