ddddocr识别验证码

from ddddocr import DdddOcr
import requests
from urllib.parse import urlparse
import urllib3

# 禁用 SSL 警告
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

class CaptchaRecognizer:
    def __init__(self):
        # 初始化 ddddocr
        self.ocr = DdddOcr(show_ad=False)

    def is_url(self, path):
        """检查是否是URL"""
        try:
            result = urlparse(path)
            return all([result.scheme, result.netloc])
        except:
            return False

    def get_image_content(self, path, timeout=10):
        """获取图片内容，支持本地文件和网络URL"""
        try:
            if self.is_url(path):
                # 下载网络图片
                response = requests.get(
                    path,
                    headers={
                        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
                    },
                    verify=False,
                    timeout=timeout
                )
                if response.status_code == 200:
                    return response.content
                raise Exception(f"下载图片失败: HTTP {response.status_code}")
            else:
                # 读取本地文件
                with open(path, 'rb') as f:
                    return f.read()
        except Exception as e:
            print(f"获取图片失败: {str(e)}")
            return None

    def recognize(self, image_path, timeout=10):
        """识别验证码图片
       
        Args:
            image_path: 图片文件路径或URL
            timeout: 网络请求超时时间(秒)
           
        Returns:
            str: 识别结果，失败返回None
        """
        try:
            # 获取图片内容
            image_bytes = self.get_image_content(image_path, timeout)
            if not image_bytes:
                return None
               
            # 识别验证码
            result = self.ocr.classification(image_bytes)
            return result
           
        except Exception as e:
            print(f"识别失败: {str(e)}")
            return None

def recognize_captcha(image_path, timeout=10):
    """便捷函数，直接识别验证码
   
    Args:
        image_path: 图片文件路径或URL
        timeout: 网络请求超时时间(秒)
       
    Returns:
        str: 识别结果，失败返回None
    """
    recognizer = CaptchaRecognizer()
    return recognizer.recognize(image_path, timeout)

# 使用示例
if __name__ == "__main__":
    # 方式1：使用便捷函数
    result = recognize_captcha("http://**.*.*/captcha.jpg")
    print(f"识别结果1: {result}")
   
    # 方式2：使用类
    recognizer = CaptchaRecognizer()
    result = recognizer.recognize("http://*.*.*.*/captcha.jpg")
    print(f"识别结果2: {result}")