Python爬虫破解登陆哔哩哔哩的方法

写在前面

作为一名找不到工作的爬虫菜鸡人士来说，登陆这一块肯定是个比较大的难题。
 从今天开始准备一点点对大型网站进行逐个登陆破解。加深自己爬虫水平。

环境搭建

• Python 3.7.7环境，Mac电脑测试
• Python内置库
• 第三方库：rsa、urllib、requests

PC端登陆

全部代码：

'''PC登录哔哩哔哩'''
class Bilibili_For_PC():
  def __init__(self, **kwargs):
    for key, value in kwargs.items(): setattr(self, key, value)
    self.session = requests.Session()
    self.__initialize()
  '''登录函数'''
  def login(self, username, password, crack_captcha_func=None, **kwargs):
    # 若参数中给入代理,则设置
    self.session.proxies.update(kwargs.get('proxies', {}))
    # 是否需要验证码
    is_need_captcha = False
    while True:
      # 需要验证码
      if is_need_captcha:
        captcha_img = self.session.get(self.captcha_url, headers=self.captcha_headers).content
        data = {'image': base64.b64encode(captcha_img).decode('utf-8')}
        captcha = self.session.post(self.crack_captcha_url, json=data).json()['message']
      # 获得key值
      appkey = '1d8b6e7d45233436'
      data = {
            'appkey': appkey,
            'sign': self.__calcSign('appkey={}'.format(appkey))
          }
      response = self.session.post(self.getkey_url, data=data)
      response_json = response.json()
      key_hash = response_json['data']['hash']
      pub_key = rsa.PublicKey.load_pkcs1_openssl_pem(response_json['data']['key'].encode('utf-8'))
      # 模拟登录
      if is_need_captcha:
        data = "access_key=&actionKey=appkey&appkey={}&build=6040500&captcha={}&challenge=&channel=bili&cookies=&device=pc&password={}&permission=ALL&seccode=&subid=1&ts={}&username={}&validate=" \
            .format(appkey, captcha, urllib.parse.quote_plus(base64.b64encode(rsa.encrypt('{}{}'.format(key_hash, password).encode(), pub_key))), int(time.time()), urllib.parse.quote_plus(username))
      else:
        data = "access_key=&actionKey=appkey&appkey={}&build=6040500&captcha=&challenge=&channel=bili&cookies=&device=pc&password={}&permission=ALL&seccode=&subid=1&ts={}&username={}&validate=" \
            .format(appkey, urllib.parse.quote_plus(base64.b64encode(rsa.encrypt('{}{}'.format(key_hash, password).encode(), pub_key))), int(time.time()), urllib.parse.quote_plus(username))
      data = "{}&sign={}".format(data, self.__calcSign(data))
      response = self.session.post(self.login_url, data=data, headers=self.login_headers)
      response_json = response.json()
      # 不需要验证码, 登录成功
      if response_json['code'] == 0 and response_json['data']['status'] == 0:
        for cookie in response_json['data']['cookie_info']['cookies']:
          self.session.cookies.set(cookie['name'], cookie['value'], domain='.bilibili')
        print('[INFO]: Account -> %s, login successfully' % username)
        infos_return = {'username': username}
        infos_return.update(response_json)
        return infos_return, self.session
      # 需要识别验证码
      elif response_json['code'] == -105:
        is_need_captcha = True
      # 账号密码错误
      elif response_json['code'] == -629:
        raise RuntimeError('Account -> %s, fail to login, username or password error' % username)
      # 其他错误
      else:
        raise RuntimeError(response_json.get('message'))
  '''计算sign值'''
  def __calcSign(self, param, salt="560c52ccd288fed045859ed18bffd973"):
    sign = hashlib.md5('{}{}'.format(param, salt).encode('utf-8'))
    return sign.hexdigest()
  '''初始化'''
  def __initialize(self):
   # 登陆请求头
    self.login_headers = {'Content-type': 'application/x-www-form-urlencoded'}
    # 破解验证码请求头
    self.captcha_headers = {'Host': 'passport.bilibili.com'}
    # 获取key密钥URL
    self.getkey_url = 'https://passport.bilibili.com/api/oauth2/getKey'
    # 获取登陆URL
    self.login_url = 'https://passport.bilibili.com/api/v3/oauth2/login'
    # 获取验证码URL
    self.captcha_url = 'https://passport.bilibili.com/captcha'
    # 破解网站来自: https://github.com/Hsury/Bilibili-Toolkit
    # 破解验证码URL
    self.crack_captcha_url = 'https://bili.dev:2233/captcha'
    # 请求头都得加这个
    self.session.headers.update({'User-Agent': "Mozilla/5.0 BiliDroid/5.51.1 ([e-mail])"})

移动端登陆

移动端与PC端类似，网址URL差异以及请求头差异。在此不过多介绍。
 全部代码：

'''移动端登录B站'''
class Bilibili_For_Mobile():
  def __init__(self, **kwargs):
    for key, value in kwargs.items(): setattr(self, key, value)
    self.session = requests.Session()
    self.__initialize()
  '''登录函数'''
  def login(self, username, password, crack_captcha_func=None, **kwargs):
    self.session.proxies.update(kwargs.get('proxies', {}))
    # 是否需要验证码
    is_need_captcha = False
    while True:
      # 需要验证码
      if is_need_captcha:
        captcha_img = self.session.get(self.captcha_url, headers=self.captcha_headers).content
        data = {'image': base64.b64encode(captcha_img).decode('utf-8')}
        captcha = self.session.post(self.crack_captcha_url, json=data).json()['message']
      # 获得key值
      appkey = 'bca7e84c2d947ac6'
      data = {
            'appkey': appkey,
            'sign': self.__calcSign('appkey={}'.format(appkey))
          }
      response = self.session.post(self.getkey_url, data=data)
      response_json = response.json()
      key_hash = response_json['data']['hash']
      pub_key = rsa.PublicKey.load_pkcs1_openssl_pem(response_json['data']['key'].encode('utf-8'))
      # 模拟登录
      if is_need_captcha:
        data = "access_key=&actionKey=appkey&appkey={}&build=6040500&captcha={}&challenge=&channel=bili&cookies=&device=phone&mobi_app=android&password={}&permission=ALL&platform=android&seccode=&subid=1&ts={}&username={}&validate=" \
            .format(appkey, captcha, urllib.parse.quote_plus(base64.b64encode(rsa.encrypt('{}{}'.format(key_hash, password).encode(), pub_key))), int(time.time()), urllib.parse.quote_plus(username))
      else:
        data = "access_key=&actionKey=appkey&appkey={}&build=6040500&captcha=&challenge=&channel=bili&cookies=&device=phone&mobi_app=android&password={}&permission=ALL&platform=android&seccode=&subid=1&ts={}&username={}&validate=" \
            .format(appkey, urllib.parse.quote_plus(base64.b64encode(rsa.encrypt('{}{}'.format(key_hash, password).encode(), pub_key))), int(time.time()), urllib.parse.quote_plus(username))
      data = "{}&sign={}".format(data, self.__calcSign(data))
      response = self.session.post(self.login_url, data=data, headers=self.login_headers)
      response_json = response.json()
      # 不需要验证码, 登录成功
      if response_json['code'] == 0 and response_json['data']['status'] == 0:
        for cookie in response_json['data']['cookie_info']['cookies']:
          self.session.cookies.set(cookie['name'], cookie['value'], domain='.bilibili')
        print('[INFO]: Account -> %s, login successfully' % username)
        infos_return = {'username': username}
        infos_return.update(response_json)
        return infos_return, self.session
      # 需要识别验证码
      elif response_json['code'] == -105:
        is_need_captcha = True
      # 账号密码错误
      elif response_json['code'] == -629:
        raise RuntimeError('Account -> %s, fail to login, username or password error' % username)
      # 其他错误
      else:
        raise RuntimeError(response_json.get('message'))
  '''计算sign值'''
  def __calcSign(self, param, salt="60698ba2f68e01ce44738920a0ffe768"):
    sign = hashlib.md5('{}{}'.format(param, salt).encode('utf-8'))
    return sign.hexdigest()
  '''初始化'''
  def __initialize(self):
    self.login_headers = {
                'Content-type': 'application/x-www-form-urlencoded'
              }
    self.captcha_headers = {
                'Host': 'passport.bilibili.com'
              }
    self.getkey_url = 'https://passport.bilibili.com/api/oauth2/getKey'
    self.login_url = 'https://passport.bilibili.com/api/v3/oauth2/login'
    self.captcha_url = 'https://passport.bilibili.com/captcha'
    # 破解网站来自: https://github.com/Hsury/Bilibili-Toolkit
    self.crack_captcha_url = 'https://bili.dev:2233/captcha'
    self.session.headers.update({'User-Agent': "Mozilla/5.0 BiliDroid/5.51.1 ([e-mail])"})

到此这篇关于Python爬虫破解登陆哔哩哔哩的方法的文章就介绍到这了,更多相关Python爬虫破解登陆内容请搜索三水点靠木以前的文章或继续浏览下面的相关文章希望大家以后多多支持三水点靠木！