python+tesseract 训练和破解验证码

 

tesseract 训练验证码

https://www.cnblogs.com/jnhs/p/11320413.html

 

训练的话，照着上面的做吧，最好名字一样，我改名了一直不行。

 

下载验证码

#下载验证码
def downloadImg():
    for i in range(1, 100):

        headers = {
            # 用户代理
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'
        }
        file_name = "C:\\Users\\Desktop\\notebook\\notebook\\captch\\" + str(i) + "_captch.png"
        print(file_name)
        # 获取图片内容
        response = requests.get("https://yoururl/captcha.png", headers=headers)
        # 写入图片
        with open(file_name, 'wb') as fp:
            for data in response.iter_content(128):
                fp.write(data)

将图片黑白化（