Бот делает скрины и ищет то что вы указали (фото/скрин) при подключении к любому окну(игры/видео) нужно найти Объект (А-фото/скрин) и нажать кнопку (С-фото/скрин) Если объект (А-фото/скрин) не был найден нужно нажать на кнопку (B-фото/скрин) чтобы продолжить поиски ---> не реализовано

Main

import cv2 as cv
import numpy as np
import os
from time import time
from windowcapture import WindowCapture
from vision import Vision

os.chdir(os.path.dirname(os.path.abspath(__file__)))
wincap = WindowCapture('Название окна игры/видео/браузера')
vision_limestone = Vision('Сюда фото.jpg')
loop_time = time()
while(True):
    screenshot = wincap.get_screenshot()
    points = vision_limestone.find(screenshot, 0.8, 'rectangles')
    print('FPS{}'.format(1 / (time() - loop_time)))
    loop_time = time()
    if cv.waitKey(1) == ord('q'): # The end (**Выключить на кнопку Q**)
        cv.destroyAllWindows()
        break
print('Done.')

vision

import cv2 as cv
import numpy as np


class Vision:

    needle_img = None
    needle_w = 0
    needle_h = 0
    method = None
    
    def __init__(self, needle_img_path, method=cv.TM_CCOEFF_NORMED):
        self.needle_img = cv.imread(needle_img_path, cv.IMREAD_UNCHANGED)

        self.needle_w = self.needle_img.shape[1]
        self.needle_h = self.needle_img.shape[0]

        self.method = method

    def find(self, haystack_img, threshold=0.5, debug_mode=None):
        result = cv.matchTemplate(haystack_img, self.needle_img, self.method)
        locations = np.where(result >= threshold)
        locations = list(zip(*locations[::-1]))
        rectangles = []
        for loc in locations:
            rect = [int(loc[0]), int(loc[1]), self.needle_w, self.needle_h]
            rectangles.append(rect)
            rectangles.append(rect)
        rectangles, weights = cv.groupRectangles(rectangles, groupThreshold=1, eps=0.5)

        points = []
        if len(rectangles):

            line_color = (0, 255, 0)
            line_type = cv.LINE_4
            marker_color = (255, 0, 255)
            marker_type = cv.MARKER_CROSS

            for (x, y, w, h) in rectangles:

                center_x = x + int(w/2)
                center_y = y + int(h/2)
                points.append((center_x, center_y))

                if debug_mode == 'rectangles':
                    top_left = (x, y)
                    bottom_right = (x + w, y + h)
                    cv.rectangle(haystack_img, top_left, bottom_right, color=line_color, 
                                lineType=line_type, thickness=2)
                elif debug_mode == 'points':
                    cv.drawMarker(haystack_img, (center_x, center_y), 
                                color=marker_color, markerType=marker_type, 
                                markerSize=40, thickness=2)

        if debug_mode:
            cv.imshow('Matches', haystack_img)
            cv.waitKey()
            cv.imwrite('result_click_point.jpg', haystack_img)

        return points

WindowCapture

import numpy as np
import win32gui, win32ui, win32con


class WindowCapture:

    w = 0
    h = 0
    hwnd = None
    cropped_x = 0
    cropped_y = 0
    offset_x = 0
    offset_y = 0

    def __init__(self, window_name=None):
        if window_name is None:
            self.hwnd = win32gui.GetDesktopWindow()
        else:
            self.hwnd = win32gui.FindWindow(None, window_name)
            if not self.hwnd:
                raise Exception('Window not found: {}'.format(window_name))

        window_rect = win32gui.GetWindowRect(self.hwnd)
        self.w = window_rect[2] - window_rect[0]
        self.h = window_rect[3] - window_rect[1]

        border_pixels = 8
        titlebar_pixels = 30
        self.w = self.w - (border_pixels * 2)
        self.h = self.h - titlebar_pixels - border_pixels
        self.cropped_x = border_pixels
        self.cropped_y = titlebar_pixels

        self.offset_x = window_rect[0] + self.cropped_x
        self.offset_y = window_rect[1] + self.cropped_y

    def get_screenshot(self):

        wDC = win32gui.GetWindowDC(self.hwnd)
        dcObj = win32ui.CreateDCFromHandle(wDC)
        cDC = dcObj.CreateCompatibleDC()
        dataBitMap = win32ui.CreateBitmap()
        dataBitMap.CreateCompatibleBitmap(dcObj, self.w, self.h)
        cDC.SelectObject(dataBitMap)
        cDC.BitBlt((0, 0), (self.w, self.h), dcObj, (self.cropped_x, self.cropped_y), win32con.SRCCOPY)

        signedIntsArray = dataBitMap.GetBitmapBits(True)
        img = np.fromstring(signedIntsArray, dtype='uint8')
        img.shape = (self.h, self.w, 4)

        dcObj.DeleteDC()
        cDC.DeleteDC()
        win32gui.ReleaseDC(self.hwnd, wDC)
        win32gui.DeleteObject(dataBitMap.GetHandle())

        img = img[...,:3]

        img = np.ascontiguousarray(img)

        return img

    @staticmethod
    def list_window_names():
        def winEnumHandler(hwnd, ctx):
            if win32gui.IsWindowVisible(hwnd):
                print(hex(hwnd), win32gui.GetWindowText(hwnd))
        win32gui.EnumWindows(winEnumHandler, None)

    def get_screen_position(self, pos):
        return (pos[0] + self.offset_x, pos[1] + self.offset_y)

Заранее благодарю тебя!