醋醋百科网

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import base64
import os
from PIL import Image
import pytesseract
import cv2
import numpy as np

# 指定 tesseract 可执行文件的路径
pytesseract.pytesseract.tesseract_cmd = r'D:\Program Files\Tesseract-OCR\tesseract.exe'

def preprocess_image(image_path):
    """
    优化预处理：增加降噪和形态学处理
    """
    image = Image.open(image_path)
    image_cv = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
    
    # 转为灰度并高斯模糊降噪
    gray = cv2.cvtColor(image_cv, cv2.COLOR_BGR2GRAY)
    gray = cv2.GaussianBlur(gray, (3, 3), 0)
    
    # 自适应阈值处理
    binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
                                   cv2.THRESH_BINARY_INV, 21, 4)
    
    # 形态学闭运算连接字符
    kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
    closed = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel)
    
    # 中值滤波去噪
    processed_image = cv2.medianBlur(closed, 3)
    
    return Image.fromarray(processed_image)

def recognize_captcha(image_path):
    processed_image = preprocess_image(image_path)
    
    # 调试：保存预处理后的图片
    debug_path = "processed_debug.png"
    processed_image.save(debug_path)
    print(f"预处理后的图片已保存至：{os.path.abspath(debug_path)}")
    
    # 调整Tesseract参数（尝试不同PSM模式）
    custom_config = r'--oem 3 --psm 8 -c tessedit_char_whitelist=ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789'
    captcha_text = pytesseract.image_to_string(processed_image, config=custom_config)
    
    return captcha_text.strip()

def download_captcha():
    driver = webdriver.Chrome()
    try:
        driver.get("系统地址")
        img_element = WebDriverWait(driver, 10).until(
            EC.presence_of_element_located((By.XPATH, "img[contains(@src, 'data:image/jpg; base64')]"))
        )
        src_data = img_element.get_attribute("src")
        _, base64_str = src_data.split(",", 1)
        image_data = base64.b64decode(base64_str)
        save_path = "captcha.png"
        with open(save_path, "wb") as f:
            f.write(image_data)
        return save_path
    finally:
        driver.quit()  # 确保关闭浏览器

if __name__ == "__main__":
    image_path = download_captcha()
    if image_path:
        captcha_text = recognize_captcha(image_path)
        print(f"识别结果: {captcha_text}")   给此脚本添加个标题 用于发布