python - Twitch Bot URL 恶意软件/病毒检测 PYTHON

Question

我正在研究 Python 中的 Twitch Bot 模块，其中 Bot 不断监视某人消息中的 URL，并将确定该 URL 是否是恶意的。恶意软件功能已经运行，并且已经针对 Python 中设置的字符串进行了测试。

这是从字符串创建 URL 数组的好代码：

好代码：

regex = r"(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’]))"

def Find(string):   
    # findall() has been used  
    # with valid conditions for urls in string 
    regex = r"(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’]))"
    url = re.findall(regex,string)       
    return [x[0] for x in url]
    
# Driver Code 
string = 'Hey guys I think you really need to check www.youtube.com and www.discovery.com out'

indicators = Find(string)

def malware(bot, user):
    for site in indicators:
        params = {'apikey': api_key, 'resource': site}
        response = requests.get(url, params=params)
        response_json = json.loads(response.content)

        if response_json['positives'] <= 0:
            bot.send_message(f"The URL {site} has been determined to be: NOT MALICIOUS AND SAFE")

        elif 1 >= response_json['positives'] >= 3:
            bot.send_message(f"The URL {site} has been determined to be: POSSIBLY MALICIOUS")

        elif response_json['positives'] >= 4:
            bot.send_message(f"The URL {site} has been determined to be: DEFINITELY MALICIOUS")

        else:
            bot.send_message(f"The URL {site} cannot be determined to be safe or not: PROCEED WITH CAUTION!!!!")

        time.sleep(5)

不幸的是，当我尝试进一步开发此代码以持续监控消息时，它要么不起作用，要么将包括 URL 在内的原始消息拉到恶意软件函数中并且函数中断。

谁能给我一些关于如何使这个糟糕的代码工作的想法？

我需要有关“检查”功能的帮助

错误代码：

def Find2(message):   
    regex = r"(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’]))"
    url = re.findall(regex,message)       
    return [x[0] for x in url]

LINKS = ("www.yes.com", "www.google.com")

regex = r"(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’]))"

def Check(bot, user, message):
    if any([site in message for site in LINKS]):
        indicators = Find2(message)
        malware(bot, user, indicators)
        return False

    return True

def malware(bot, user, message):
    for site in message:
        params = {'apikey': api_key, 'resource': site}
        response = requests.get(url, params=params)
        response_json = json.loads(response.content)
        bot.send_message(f"I detected the URL {site} before I broke")

        if response_json['positives'] <= 0:
            bot.send_message(f"The URL {site} has been determined to be: NOT MALICIOUS AND SAFE")

        elif 1 >= response_json['positives'] >= 3:
            bot.send_message(f"The URL {site} has been determined to be: POSSIBLY MALICIOUS")

        elif response_json['positives'] >= 4:
            bot.send_message(f"The URL {site} has been determined to be: DEFINITELY MALICIOUS")

        else:
            bot.send_message(f"The URL {site} cannot be determined to be safe or not: PROCEED WITH CAUTION!!!!")

        time.sleep(5)

标签： pythonbotsmalwaretwitchvirus