python下载好看视频的短视频

前言

1.改代码只是为了练习爬虫而写的，非恶意代码，如有侵权，会及时删除；
2.该网站的视频本身是可以下载的，使用代码目的只是为了方便下载视频。

1 获取视频地址的加密信息

# mp4地址是加密在源代码里面的
def get_encode(self):
    resp = requests.get(url=self.url, headers=self.headers)
    resp.close()
    obj = re.compile('"encrptedVideoMeta":"(.*?)"')
    enc_text = obj.search(resp.text, re.S).group(1)
    return enc_text

2 解密

# 两次解密，先base64解密，然后在用位运算解密
def get_decode(self, text):
      dec_text = base64.b64decode(text.encode()).decode()
      t = 'guanghui456'
      n = ''
      for i in range(len(dec_text)):
          o = ord(dec_text[i])
          s = ord(t[i % len(t)])
          n += chr(o ^ s)
      dct = json.loads(n)
      self.name = dct['title']
      self.mp4_url = dct['clarityUrl'][-1]['url']

3 下载视频

    def downLoad(self):
        if not os.path.isdir('video'):
            os.mkdir('video')
        resp = requests.get(url=self.mp4_url, headers=self.headers)
        resp.close()
        with open('video/%s.mp4' % self.name, mode='wb') as f:
            f.write(resp.content)
        print('%s下载完成' % self.name)

4 完整代码

"""
好看视频的短视频的播放地址在源代码里面，但是加密了，所以需要对加密内容进行解密
需要进行两次解密，1是base64解密，2是位运算解密
"""
import requests
import base64
import json
import re
import os


class Application:
    def __init__(self, url):
        self.url = url
        self.headers = {
            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36 Edg/133.0.0.0'
        }

    def get_encode(self):
        resp = requests.get(url=self.url, headers=self.headers)
        resp.close()
        obj = re.compile('"encrptedVideoMeta":"(.*?)"')
        enc_text = obj.search(resp.text, re.S).group(1)
        return enc_text

    def get_decode(self, text):
        dec_text = base64.b64decode(text.encode()).decode()
        t = 'guanghui456'
        n = ''
        for i in range(len(dec_text)):
            o = ord(dec_text[i])
            s = ord(t[i % len(t)])
            n += chr(o ^ s)
        dct = json.loads(n)
        self.name = dct['title']
        self.mp4_url = dct['clarityUrl'][-1]['url']
        # print(self.mp4_url)

    def downLoad(self):
        if not os.path.isdir('video'):
            os.mkdir('video')
        resp = requests.get(url=self.mp4_url, headers=self.headers)
        resp.close()
        with open('video/%s.mp4' % self.name, mode='wb') as f:
            f.write(resp.content)
        print('%s下载完成' % self.name)

    def main(self):
        text_ = self.get_encode()
        self.get_decode(text_)
        self.downLoad()


if __name__ == '__main__':
    main_url = input('输入https://haokan.baidu.com/v?vid=*************&tab=recommend：').strip()
    app = Application(main_url)
    app.main()