寫在前面

作為一名找不到工作的爬蟲菜雞人士來說，登陸這一塊肯定是個比較大的難題。 從今天開始準備一點點對大型網(wǎng)站進行逐個登陸破解。加深自己爬蟲水平。

環(huán)境搭建

PC端登陸

全部代碼：

’’’PC登錄嗶哩嗶哩’’’class Bilibili_For_PC(): def __init__(self, **kwargs): for key, value in kwargs.items(): setattr(self, key, value) self.session = requests.Session() self.__initialize() ’’’登錄函數(shù)’’’ def login(self, username, password, crack_captcha_func=None, **kwargs): # 若參數(shù)中給入代理,則設(shè)置 self.session.proxies.update(kwargs.get(’proxies’, {})) # 是否需要驗證碼 is_need_captcha = False while True: # 需要驗證碼 if is_need_captcha:captcha_img = self.session.get(self.captcha_url, headers=self.captcha_headers).contentdata = {’image’: base64.b64encode(captcha_img).decode(’utf-8’)}captcha = self.session.post(self.crack_captcha_url, json=data).json()[’message’] # 獲得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’)) # 模擬登錄 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() # 不需要驗證碼, 登錄成功 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 # 需要識別驗證碼 elif response_json[’code’] == -105:is_need_captcha = True # 賬號密碼錯誤 elif response_json[’code’] == -629:raise RuntimeError(’Account -> %s, fail to login, username or password error’ % username) # 其他錯誤 else:raise RuntimeError(response_json.get(’message’)) ’’’計算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): # 登陸請求頭 self.login_headers = {’Content-type’: ’application/x-www-form-urlencoded’} # 破解驗證碼請求頭 self.captcha_headers = {’Host’: ’passport.bilibili.com’} # 獲取key密鑰URL self.getkey_url = ’https://passport.bilibili.com/api/oauth2/getKey’ # 獲取登陸URL self.login_url = ’https://passport.bilibili.com/api/v3/oauth2/login’ # 獲取驗證碼URL self.captcha_url = ’https://passport.bilibili.com/captcha’ # 破解網(wǎng)站來自: https://github.com/Hsury/Bilibili-Toolkit # 破解驗證碼URL self.crack_captcha_url = ’https://bili.dev:2233/captcha’ # 請求頭都得加這個 self.session.headers.update({’User-Agent’: 'Mozilla/5.0 BiliDroid/5.51.1 (bbcallen@gmail.com)'})

移動端登陸

移動端與PC端類似，網(wǎng)址URL差異以及請求頭差異。在此不過多介紹。 全部代碼：

’’’移動端登錄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() ’’’登錄函數(shù)’’’ def login(self, username, password, crack_captcha_func=None, **kwargs): self.session.proxies.update(kwargs.get(’proxies’, {})) # 是否需要驗證碼 is_need_captcha = False while True: # 需要驗證碼 if is_need_captcha:captcha_img = self.session.get(self.captcha_url, headers=self.captcha_headers).contentdata = {’image’: base64.b64encode(captcha_img).decode(’utf-8’)}captcha = self.session.post(self.crack_captcha_url, json=data).json()[’message’] # 獲得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’)) # 模擬登錄 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() # 不需要驗證碼, 登錄成功 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 # 需要識別驗證碼 elif response_json[’code’] == -105:is_need_captcha = True # 賬號密碼錯誤 elif response_json[’code’] == -629:raise RuntimeError(’Account -> %s, fail to login, username or password error’ % username) # 其他錯誤 else:raise RuntimeError(response_json.get(’message’)) ’’’計算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’ # 破解網(wǎng)站來自: 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 (bbcallen@gmail.com)'})

到此這篇關(guān)于Python爬蟲破解登陸嗶哩嗶哩的方法的文章就介紹到這了,更多相關(guān)Python爬蟲破解登陸內(nèi)容請搜索好吧啦網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持好吧啦網(wǎng)！