python实现截图识别文字(已打包成exe程序)_python截图提取文字

# 导入必要的模块
from datetime import datetime  # 用于获取当前日期和时间
from tkinter import *  # 用于创建 GUI 界面
import pyautogui  # 用于屏幕截图
from PIL import ImageGrab  # 用于处理图像数据
import os  # 用于文件和目录操作
import pytesseract  # 用于文字识别
import pyperclip  # 用于剪贴板操作
 
# 设置 Tesseract OCR 的路径和配置
tesseract_exe = r'.\Tesseract-OCR\tesseract.exe'
tessdata_dir = r'.\Tesseract-OCR\tessdata'
pytesseract.pytesseract.tesseract_cmd = tesseract_exe
tessdata_dir_config = '--tessdata-dir "{}"'.format(tessdata_dir)
 
# 创建一个名为 ScreenCaptureApp 的类
class ScreenCaptureApp:
    def __init__(self, root):
        # 初始化应用程序的根窗口
        self.root = root
        self.root.attributes('-fullscreen', True)  # 设置窗口全屏
        self.root.attributes('-alpha', 0.1)  # 设置窗口透明度
        self.root.title("Area capture")  # 设置窗口标题
 
        # 获取屏幕的宽度和高度
        self.screen_width, self.screen_height = pyautogui.size()
 
        # 创建一个 Canvas 控件用于显示截图区域
        self.canvas = Canvas(self.root, cursor="cross")
        self.canvas.pack(fill=BOTH, expand=YES)
 
        # 绑定鼠标事件处理函数
        self.canvas.bind("<ButtonPress-1>", self.on_press)
        self.canvas.bind("<B1-Motion>", self.on_drag)
        self.canvas.bind("<ButtonRelease-1>", self.on_release)
 
        # 初始化一些坐标和变量
        self.start_x = None
        self.start_y = None
        self.end_x = None
        self.end_y = None
        self.rect = None
        self.mask_rect = None
        self.image_path = None
 
        # 更新窗口大小
        self.update_window_size()
 
    # 更新窗口大小
    def update_window_size(self):
        screen_width = self.root.winfo_screenwidth()
        screen_height = self.root.winfo_screenheight()
        self.root.geometry("%dx%d" % (screen_width, screen_height))
 
    # 鼠标按下事件处理函数
    def on_press(self, event):
        self.start_x = self.canvas.canvasx(event.x)
        self.start_y = self.canvas.canvasy(event.y)
        if self.rect:
            self.canvas.delete(self.rect)
        if self.mask_rect:
            self.canvas.delete(self.mask_rect)
        self.rect = self.canvas.create_rectangle(self.start_x, self.start_y, self.start_x, self.start_y, outline="blue", fill="blue",
                                                 stipple='gray25', width=3)
 
    # 鼠标拖动事件处理函数
    def on_drag(self, event):
        cur_x = self.canvas.canvasx(event.x)
        cur_y = self.canvas.canvasy(event.y)
        self.canvas.coords(self.rect, self.start_x, self.start_y, cur_x, cur_y)
        self.update_mask(cur_x, cur_y)
 
    # 鼠标释放事件处理函数
    def on_release(self, event):
        self.end_x = self.canvas.canvasx(event.x)
        self.end_y = self.canvas.canvasy(event.y)
        # 计算截图区域的坐标
        if self.start_x < self.end_x and self.start_y < self.end_y:
            left = self.start_x
            top = self.start_y
            right = self.end_x
            bottom = self.end_y
        # ... (其他情况的计算省略)
 
        # 使用 ImageGrab.grab 截取屏幕图像
        screenshot = ImageGrab.grab(bbox=(left, top, right, bottom))
 
        # 获取当前脚本的目录和当前日期时间
        script_directory = os.path.dirname(os.path.abspath(__file__))
        current_datetime = datetime.now().strftime("%Y-%m-%d-%H%M%S")
 
        # 构建图像文件名
        file_name = f"xzlScreenshot-{current_datetime}.png"
        self.image_path = os.path.join(script_directory, "image/" + file_name)
 
        # 保存截图到文件
        screenshot.save(self.image_path)
 
        # 配置 Tesseract OCR 参数
        custom_config = r'--oem 3 --psm 6 -c preserve_interword_spaces=1'
 
        # 使用 pytesseract 进行文字识别
        text = pytesseract.image_to_string(screenshot, lang='+'.join(['eng', 'chi_sim']), config=f'--tessdata-dir "{tessdata_dir}" {custom_config}')
 
        # 将识别结果复制到剪贴板
        pyperclip.copy(text)
 
        # 读取配置文件并检查是否需要自动删除截图
        with open('config.txt', 'r', encoding="utf-8") as file:
            content = file.read()
        key_value_pairs = content.strip().split('\n')
        for i in range(0, len(key_value_pairs)):
            key = key_value_pairs[i].split('=')
            value = key[1]
            if str(key[0]) == "autoDeleteImg":
                auto_delete_img_value = value
                break
        if int(auto_delete_img_value) == int(1):
            if self.image_path:
                os.remove(self.image_path)
 
        # 关闭应用程序窗口
        self.root.destroy()
 
    # 更新遮罩效果
    def update_mask(self, cur_x, cur_y):
        if self.mask_rect:
            self.canvas.delete(self.mask_rect)
        self.mask_rect = self.canvas.create_rectangle(0, 0, self.root.winfo_screenwidth(), self.root.winfo_screenheight(), fill="black", )
        self.canvas.tag_lower(self.mask_rect)
        self.canvas.coords(self.mask_rect, self.start_x, self.start_y, cur_x, cur_y)
 
# 主函数，创建应用程序对象并运行
def main():
    root = Tk()
    app = ScreenCaptureApp(root)
    root.mainloop()
 
# 检查脚本是否作为主程序运行
if __name__ == "__main__":
    main()