首先找一个视频网站,分析网站:
找到这个iframe的src:
过去看看:
点击观看就发现了多了些东西:
具体分析下:
简单猜测下这个key.key一定是解密的
现在视频服务器地址列表有了,解密的密码有了。可以直接爬视频下来了:
import os
import requests
import re
import time
#视频视频地址
pathUrl = 'https://video.dious.cc/20200617/fYdT3OVu/1000kb/hls/index.m3u8'
#整个文件夹装
dir = "./dpcq/"
if not os.path.exists(dir):
os.makedirs(dir)
def getVideo():
headers = {
"user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36",
}
res = requests.get(pathUrl, headers=headers)
res.encoding = res.apparent_encoding
#拿取视频的全部路径列表
urlList = re.findall(r'\n(.*\.ts)', res.text)
print(len(urlList))
count = 0
for item in urlList:
#慢慢拿取,假装人为,一共395个文件,没加sleep,我只拿取了170个,加了全拿下来了
time.sleep(6)
count += 1
res2 = requests.get(item, stream=True, headers=headers)
res2.encoding = res2.apparent_encoding
print(res2.status_code)
with open(dir + 'demo{}.mp4'.format(str(count)), "wb") as mp4:
#边拿边从内存写到硬盘里
for chunk in res2.iter_content(chunk_size=1024 * 1024):
if chunk:
mp4.write(chunk)
if __name__ == '__main__':
getVideo()
给爷下来!!
但是。。放不起:
加个解密就完事了:
import os
from Crypto.Cipher import AES
from Crypto.Util.Padding import pad
# 之前key.key文件里的数字 '722c55ff989ded9a'
cryptorObj = AES.new(bytes('722c55ff989ded9a'.encode()), AES.MODE_CBC, bytes('722c55ff989ded9a'.encode()))
dir = './dpcq/'
if __name__ == "__main__":
w = open('./video.mp4', "wb")
files = os.listdir(dir)
# 这里我是demoXXX.MP4命名的, os.listdir读取时随机的,sort排个序
files.sort(key=lambda x: int(x.split('demo')[1][:-4]))
print(files)
for item in files:
fileObj = open(dir + '{}'.format(item), 'rb')
fc = fileObj.read()
# 最开始没加这个判断会报错 Data must be padded to 16 byte boundary in CBC mode 网上查了下解决方法:
if fc and (len(fc) % 16) != 0:
# EXT-X-KEY:METHOD=AES-128的加密方式,对应加密的key大小16byte,对应AES.MODE_CBC,
# 如果视频大小不是16的倍数,解密时出现:ValueError(“Data must be padded to %d byte boundary in CBC mode” % self.block_size)
fc = pad(fc, 16) # 按16的倍数补齐长度
w.write(cryptorObj.decrypt(fc))
over