使用工具Python 3.7.0

requests库

re库

base64库

分析过程

确定视频资源下载地址

由于之前没有这方面的项目经历，在网上查找资料后，这篇文章给了我灵感(原来西瓜视频上的Url是经过Base64加密的)，那么是如何确定西瓜视频上的Url是经过Base64加密的呢？这个字符串仅有64个字符(A~Z a~z + / )以及后缀=组成

将目标字符串解密后再将解密字符串加密回去与原来的值做比较如果相同就是Base64

import requests

import re

from base64 import b64decode, b64encode

url = 'https://www.ixigua.com/i6704446868685849092'

headers = {

'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.106 Safari/537.36'

}

resp =requests.get(url=url, headers=headers)

ex = '''"main_url":"(.*?)"'''

def doCheck(source):

if bytes(source, encoding='utf-8') == b64encode(b64decode(source)):

return True

return False

if doCheck(re.findall(ex, resp.text)[0]):

print('该Url是Base64加密!!!')

else:

print('该Url不是Base64加密!!!')

下载测试

import requests

import re

from base64 import b64decode, b64encode

headers = {

'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.106 Safari/537.36'

}

url = 'https://www.ixigua.com/i6704446868685849092'

resp =requests.get(url=url, headers=headers)

ex = '''"main_url":"(.*?)"'''

def doCheck(source):

if bytes(source, encoding='utf-8') == b64encode(b64decode(source)):

return True

return False

def getVideoUrl(source):

return b64decode(source).decode('utf-8')

source =re.findall(ex, resp.text)[0]

if doCheck(source):

resp = requests.get(url=getVideoUrl(source), headers=headers)

with open('./Video.mp4', 'wb') as fp:

fp.write(resp.content)

else:

print('该Url不是Base64加密!!!')

运行结果

​