Use Baidu AIP to obtain the text in the specified area of the screen

Go straight to the code

Press... After running F7 Is the first coordinate ,F8 Is the second coordinate . Can get F7 and F8 Previous information

import pyautogui
from pynput.keyboard import Listener
from PIL import ImageGrab
from aip import AipOcr


#  Baidu identification characters 
class FanYi(object):

    #  Used to store coordinates 
    coordinate = []
    #  For storing data 
    data = []

    def __init__(self, file, APP_ID, API_KEY, SECRET_KEY, num=0):
        self.num = num
        self.file = file
        self.client = AipOcr(APP_ID, API_KEY, SECRET_KEY)
        if num != 0:
            print(" Get the number of columns as "+str(num)+" Table for , Move the mouse to the first coordinate and press F7 Start .")
        else:
            pass

    #  Baidu character recognition 
    def Ocr_baidu(self):
        with open(self.file, 'rb') as f:
            image = f.read()
            text = self.client.basicAccurate(image)
        words_result=text['words_result']
        if self.num == 0:
            for i in range(len(words_result)):
                print(words_result[i]['words'])
        else:
            for i in range(len(words_result)):
                data_in = words_result[i]['words']
                self.data.append(data_in)
            j = 1
            str_data = ''
            for i in self.data:
                if j < self.num:
                    str_data = str_data+i+"\t"
                    j += 1
                else:
                    j = 1
                    str_data = str_data+i+"\n"
            self.data.clear()
            print(str_data)
        print("##################### Move the mouse to the first coordinate position and press F7########################")


    #  Execute screenshot 
    def make_screenshot(self, x1, y1, x2, y2):
        bbox = (x1, y1, x2, y2)
        im = ImageGrab.grab(bbox)
        im.save(self.file)

    def on_press(self, key):
        pass

    #  Get screenshot location 
    def on_release(self, key):
        print(str(key))
        if str(key) == "Key.f7":
            x1,y1 = pyautogui.position()
            print(" The first coordinate is :"+str(x1), str(y1)+", Move the mouse to the second coordinate position and press F8 Start getting information ")
            self.coordinate.append(x1)
            self.coordinate.append(y1)
        elif str(key) == "Key.f8":
            if len(self.coordinate) == 2:
                x2,y2 = pyautogui.position()
                print(" The second coordinate is :"+str(x2), str(y2))
                self.coordinate.append(x2)
                self.coordinate.append(y2)
                print(self.coordinate)
                if self.coordinate[0] < self.coordinate[2] and self.coordinate[1] < self.coordinate[3]:
                    self.make_screenshot(self.coordinate[0],self.coordinate[1],self.coordinate[2],self.coordinate[3])
                    print(" Picture obtained successfully ")
                    self.Ocr_baidu()
                    self.coordinate.clear()

                elif self.coordinate[0] > self.coordinate[2] and self.coordinate[1] < self.coordinate[3]:
                    self.make_screenshot(self.coordinate[2],self.coordinate[1],self.coordinate[0],self.coordinate[3])
                    print(" Picture obtained successfully ")
                    self.Ocr_baidu()
                    self.coordinate.clear()

                elif self.coordinate[0] > self.coordinate[2] and self.coordinate[1] > self.coordinate[3]:
                    self.make_screenshot(self.coordinate[2],self.coordinate[3],self.coordinate[0],self.coordinate[1])
                    print(" Picture obtained successfully ")
                    self.Ocr_baidu()
                    self.coordinate.clear()

                elif self.coordinate[0] < self.coordinate[2] and self.coordinate[1] > self.coordinate[3]:
                    self.make_screenshot(self.coordinate[0],self.coordinate[3],self.coordinate[2],self.coordinate[1])
                    print(" Picture obtained successfully ")
                    self.Ocr_baidu()
                    self.coordinate.clear()

                else:
                    print(" Please press f7 Get the first coordinate again ")
                    self.coordinate.clear()
            else:
                print(" Please press f7 Get the first coordinate again ")
                self.coordinate.clear()
        else:
            print(" Move the mouse to the first coordinate position and press F7")

    #  Monitor the keyboard f7 and f8 Button 
    def start_listen(self):
        with Listener(on_press=None, on_release=self.on_release) as listener:
            listener.join()




# num=int( Number of table columns ) Default equal to 0
set_num = input(" If it is a table, please enter the number of columns in the table , If it's not a carriage return skip ")
if set_num == '':
    set_num = str(0)
FanYi = FanYi(file='find_cor_img.jpg',
              APP_ID='baiduaip In order to get ',
              API_KEY='9zA7FyHZCpkdkicY6NBG3aZ17',
              SECRET_KEY='WD9n2SDPhqIe5W9WRY0nN8MLCvQU8ROU3',
              num=int(set_num)
              )
FanYi.start_listen()