用paddleocr识别微信聊天的内容，调用文心一言API进行回复

# -*- coding: UTF-8 -*- import sys import time import pyautogui import pyperclip from paddleocr import PaddleOCR, draw_ocr from PIL import Image import re import requests import json API_KEY = "<>" SECRET_KEY = "<>" URL = "https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/chat/aquilachat_7b?access_token=" language = 'ch' img_path = 'screenshot_region.png' result_img = 'screenshot_region_out.png' ocr = PaddleOCR(use_angle_cls=True, use_gpu=False,lang=language) def sendwx(target, msg, delay_time=2): """ 实现原理：1、通过打开微信的快捷键ctrl+alt+w,打开微信窗口 2、通过搜索快捷键ctrl+f,打开搜索窗口 3、通过ctrl+v快捷键实现输入功能 4、通过ctrl+enter快捷键实现搜索or发送功能 :param target: 发送目标 :param msg: 需要发送的消息 :param delay_time: 延迟时间 默认2秒 :return:无返回值 """ try: # 清空剪切板并将目标写入到剪切板 pyperclip.copy("") pyperclip.copy(target) # 打开微信窗口 # pyautogui.hotkey("ctrl", "alt", "w") # time.sleep(delay_time) # 使用快捷键ctrl+f定位到微信搜索栏 pyautogui.hotkey("ctrl", "f") time.sleep(delay_time) # 使用快捷键ctrl+v将目标粘贴到微信搜索栏，微信将自动搜索 pyautogui.hotkey("ctrl", "v") time.sleep(delay_time) # 按回车键打开搜索出的目标 pyautogui.press("enter") time.sleep(delay_time) # 清空剪切板并将未点检信息写入到剪切板 pyperclip.copy("") pyperclip.copy(msg) # 使用快捷键ctrl+v将信息粘贴到微信输入框，按回车发送消息 pyautogui.hotkey("ctrl", "v") time.sleep(delay_time) pyautogui.press("enter") # log im = pyautogui.screenshot() im.save('screenshot.png') except Exception as ex: print("发送微信消息出现异常: " + str(ex)) sys.exit(0) def cutscreen(name): pyperclip.copy(name) pyautogui.hotkey("ctrl", "f") time.sleep(50) pyautogui.hotkey("ctrl", "v") pyautogui.press("enter") time.sleep(50) # 清空剪切板并将未点检信息写入到剪切板 pyperclip.copy("") screenshot = pyautogui.screenshot(region=(259, 64, 703, 637)) # 如果你想将截图保存为文件 screenshot.save('screenshot_region.png') def ocrImg(): # need to run only once to download and load model into memory result = ocr.ocr(img_path, cls=True) worlds = "" for line in result: worlds = worlds + str(line[-1][0]) # 显示结果# image = Image.open(img_path).convert('RGB') boxes = [line[0] for line in result] txts = [line[1][0] for line in result] scores = [line[1][1] for line in result] im_show = draw_ocr(image, boxes, txts, scores) im_show = Image.fromarray(im_show) im_show.save(result_img) return worlds def yiyananswer(question): url = URL + get_access_token() payload = json.dumps({ "messages": [ { "role": "user", "content": question }, ] }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) dict_obj = json.loads(response.text) return dict_obj['result'] def get_access_token(): """ 使用 AK，SK 生成鉴权签名（Access Token） :return: access_token，或是None(如果错误) """ url = "https://aip.baidubce.com/oauth/2.0/token" params = {"grant_type": "client_credentials", "client_id": API_KEY, "client_secret": SECRET_KEY} return str(requests.post(url, params=params).json().get("access_token")) if __name__ == '__main__': names=["微信名1","微信名2"] while True: for name in names: cutscreen(name) #会 识别最后一个提问后的文字发送到API text = ocrImg(language, img_path, result_img) matches = re.findall(r'提问(.*?)(?=\n|$)', text, re.DOTALL) results = [match.split()[-1].strip() for match in matches] if results: last_poem = results[0] input_string = yiyananswer(last_poem) if input_string != "": sendwx(name, input_string + "\n来源一言", 2) time.sleep(50) else: time.sleep(50) time.sleep(50)