Python利用PaddleOCR制作個搜題小工具

pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple

pip install "paddleocr>=2.0.1" # 推薦使用2.0.1+版本

from paddleocr import PaddleOCR, draw_ocr

# Paddleocr目前支持中英文、英文、法語、德語、韓語、日語，可以通過修改lang參數進行切換
# 參數依次為`ch`, `en`, `french`, `german`, `korean`, `japan`。
ocr = PaddleOCR(use_angle_cls=True, lang="ch")  # need to run only once to download and load model into memory
# 選擇你要識別的圖片路徑
img_path = '11.jpg'
result = ocr.ocr(img_path, cls=True)
for line in result:
    print(line)

# 顯示結果
from PIL import Image

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, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

Android Debug Bridge version 1.0.41
Version 31.0.3-7562133

import os
from PIL import Image

# 截圖
def pull_screenshot():
    os.system('adb shell screencap -p /sdcard/screenshot.png')
    os.system('adb pull /sdcard/screenshot.png .')

img = Image.open("./screenshot.png")
# 切割問題區域
# (起始點的橫坐標，起始點的縱坐標，寬度，高度）
question  = img.crop((10, 400, 1060, 1000))
# 保存問題區域
question.save("./question.png")

ocr = PaddleOCR(use_angle_cls=False, 
                        lang="ch", 
                        show_log=False
                        )  # need to run only once to download and load model into memory
img_path = 'question.png'
result = ocr.ocr(img_path, cls=False)

# 獲取題目文本
questionList = [line[1][0] for line in result]
text = ""
# 將數組轉換為字符串
for str in questionList :
    text += str
print(text)

import webbrowser
webbrowser.open('https://baidu.com/s?wd=' + urllib.parse.quote(question))

# -*- coding: utf-8 -*-

# @Author  : Pu Zhiwei
# @Time    : 2021-09-02 20:29

from PIL import Image
import os
import matplotlib.pyplot as plt
from paddleocr import PaddleOCR, draw_ocr
import pyperclip
import pyautogui
import time
import webbrowser
import urllib.parse


# 鼠標位置
currentMouseX, currentMouseY = 60, 282

# 截圖獲取當前題目
def pull_screenshot():
    os.system('adb shell screencap -p /sdcard/screenshot.png')
    os.system('adb pull /sdcard/screenshot.png .')

# 移動鼠標到搜索框搜索
def MoveMouseToSearch():
    # duration 參數，移動時間，即用時0.1秒移動到對應位置
    pyautogui.moveTo(currentMouseX, currentMouseY, duration=0.1)
    # 左鍵點擊
    pyautogui.click()
    pyautogui.click()
    # 模擬組合鍵，粘貼
    pyautogui.hotkey('ctrl', 'v')

# 擴充問題
def AddText(list, length, text):
    if length > 3:
        return text + list[3]
    else:
        return text
# 打開瀏覽器
def open_webbrowser(question):
    webbrowser.open('https://baidu.com/s?wd=' + urllib.parse.quote(question))


# 顯示所識別的題目
def ShowAllQuestionText(list):
    text = ""
    for str in list:
        text += str
    print(text)



if __name__ == "__main__":
    while True:
        print("\n\n請將鼠標放在Word的搜索框上，三秒後腳本將自動獲取Word搜索框位置！\n\n")
        # 延時三秒輸出鼠標位置
        time.sleep(3)
        # 獲取當前鼠標位置
        currentMouseX, currentMouseY = pyautogui.position()
        print('當前鼠標位置為: {0} , {1}'.format(currentMouseX, currentMouseY))
        start = input("按y鍵程序開始運行，按其他鍵重新獲取搜索框位置：")
        if start == 'y':
            break

    while True:
        t = time.perf_counter()
        pull_screenshot()
        img = Image.open("./screenshot.png")
        # 切割問題區域
        # (起始點的橫坐標，起始點的縱坐標，寬度，高度）
        question  = img.crop((10, 400, 1060, 1000))
        # 保存問題區域
        question.save("./question.png")


        # 加載 PaddleOCR
        # Paddleocr目前支持中英文、英文、法語、德語、韓語、日語，可以通過修改lang參數進行切換
        # 參數依次為`ch`, `en`, `french`, `german`, `korean`, `japan`。

        # 自定義模型地址
        # det_model_dir='./inference/ch_ppocr_server_v2.0_det_train', 
        #                rec_model_dir='./inference/ch_ppocr_server_v2.0_rec_pre',
        #                cls_model_dir='./inference/ch_ppocr_mobile_v2.0_cls_train',
        ocr = PaddleOCR(use_angle_cls=False, 
                        lang="ch", 
                        show_log=False
                        )  # need to run only once to download and load model into memory
        img_path = 'question.png'
        result = ocr.ocr(img_path, cls=False)

        questionList = [line[1][0] for line in result]
        length = len(questionList)
        text = ""
        if length < 1:
            text = questionList[0]
        elif length == 2:
            text = questionList[1]
        else:
            text = questionList[1] + questionList[2]

        print('\n\n')
        ShowAllQuestionText(questionList)
        # 將結果寫入剪切板
        pyperclip.copy(text)
        # 點擊搜索
        MoveMouseToSearch()
        
        # 計算時間
        print('\n\n')
        end_time3 = time.perf_counter()
        print('用時: {0}'.format(end_time3 - t))
        
        go = input('輸入回車繼續運行,輸入 e 打開瀏覽器搜索，輸入 a 增加題目長度，輸入 n 結束程序運行： ')
        if go == 'n':
            break
  
        if go == 'a':
            text = AddText(questionList, length, text)
            pyperclip.copy(text)
            # 點擊搜索
            MoveMouseToSearch()
            stop = input("輸入回車繼續")
        elif go == 'e':
            # 打開瀏覽器
            open_webbrowser(text)
            stop = input("輸入回車繼續")

        print('\n------------------------\n\n')