python识别图标并点击功能实现

import time
import pyautogui
import pyscreeze
import cv2
# 屏幕缩放系数 mac缩放是2 windows一般是1
screenScale=1
#事先读取按钮截图
target= cv2.imread(r"./image/ssk.png",cv2.IMREAD_GRAYSCALE)
# 先截图
screenshot=pyscreeze.screenshot('my_screenshot.png')
# 读取图片 灰色会快
temp = cv2.imread(r'my_screenshot.png',cv2.IMREAD_GRAYSCALE)
theight, twidth = target.shape[:2]
tempheight, tempwidth = temp.shape[:2]
print("目标图宽高："+str(twidth)+"-"+str(theight))
print("模板图宽高："+str(tempwidth)+"-"+str(tempheight))
# 先缩放屏幕截图 INTER_LINEAR INTER_AREA
scaleTemp=cv2.resize(temp, (int(tempwidth / screenScale), int(tempheight / screenScale)))
stempheight, stempwidth = scaleTemp.shape[:2]
print("缩放后模板图宽高："+str(stempwidth)+"-"+str(stempheight))
# 匹配图片
res = cv2.matchTemplate(scaleTemp, target, cv2.TM_CCOEFF_NORMED)
mn_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
if(max_val>=0.9):
    # 计算出中心点
    top_left = max_loc
    bottom_right = (top_left[0] + twidth, top_left[1] + theight)
    tagHalfW=int(twidth/2)
    tagHalfH=int(theight/2)
    tagCenterX=top_left[0]+tagHalfW
    tagCenterY=top_left[1]+tagHalfH
    #左键点击屏幕上的这个位置
    pyautogui.click(tagCenterX,tagCenterY,button='left') # 点击
else:
    print ("没找到")

import cv2
import numpy as np
import pyautogui
import time
class ImageClicker:
    def __init__(self, target_image_path, retry_count=3, retry_interval=1, match_threshold=0.75):
        self.target_image_path = target_image_path
        self.retry_count = retry_count
        self.retry_interval = retry_interval
        self.match_threshold = match_threshold
        # 加载目标图片
        self.target_image = cv2.imread(self.target_image_path)
        # 提取目标图片的 SIFT 特征
        self.sift = cv2.SIFT_create()
        self.kp1, self.des1 = self.sift.detectAndCompute(self.target_image, None)
    def click_image(self):
        for i in range(self.retry_count):
            try:
                # 获取浏览器窗口截图
                screenshot = pyautogui.screenshot()
                screenshot = cv2.cvtColor(np.array(screenshot), cv2.COLOR_RGB2BGR)
                # 提取截图的 SIFT 特征
                kp2, des2 = self.sift.detectAndCompute(screenshot, None)
                # 进行特征匹配
                bf = cv2.BFMatcher()
                matches = bf.knnMatch(self.des1, des2, k=2)
                # 使用 Lowe's Ratio Test 筛选匹配结果
                good = []
                for m, n in matches:
                    if m.distance < self.match_threshold * n.distance:  # 使用 match_threshold 阈值
                        good.append([m])
                # 计算目标元素的位置
                if len(good) > 0:
                    src_pts = np.float32([self.kp1[m[0].queryIdx].pt for m in good]).reshape(-1, 1, 2)
                    dst_pts = np.float32([kp2[m[0].trainIdx].pt for m in good]).reshape(-1, 1, 2)
                    M, mask = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)
                    h, w = self.target_image.shape[:2]
                    pts = np.float32([[0, 0], [0, h - 1], [w - 1, h - 1], [w - 1, 0]]).reshape(-1, 1, 2)
                    dst = cv2.perspectiveTransform(pts, M)
                    # 计算点击坐标
                    x = int((dst[0][0][0] + dst[2][0][0]) / 2)  # 计算水平方向的中间位置
                    y = int((dst[0][0][1] + dst[2][0][1]) / 2)  # 计算垂直方向的中间位置
                    # 点击目标元素
                    pyautogui.click(x, y)
                    return True  # 点击成功
            except Exception as e:
                print(f"点击失败：{e}")
                time.sleep(self.retry_interval)
        return False  # 点击失败
# 使用示例
image_clicker = ImageClicker('4.png', retry_count=5,
                             retry_interval=2,
                             match_threshold=0.8)  # 设置 match_threshold 为 0.8
if image_clicker.click_image():
    print("点击成功！")
else:
    print("点击失败！")

image_clicker = ImageClicker('4.png', retry_count=5, retry_interval=2, match_threshold=0.8)
if image_clicker.click_image():
    print("点击成功！")
else:
    print("点击失败！")