pip install pytesseract,PIL

import os
import re
from PIL import Image
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'D:\Program Files\Tesseract-OCR\tesseract.exe'
 
def sanitize_filename(name):
    """去除文件名中不允許的字符"""
    return re.sub(r'[<>:"/\\|?*]', '', name)
 
def rename_images_with_first_line_text(folder_path):
    # 獲取文件夾中所有的jpg圖片
    for filename in os.listdir(folder_path):
        if filename.lower().endswith(".jpg"):
            image_path = os.path.join(folder_path, filename)
            try:
                # 打開圖片并使用 pytesseract 識別第一行文字
                image = Image.open(image_path)
                text = pytesseract.image_to_string(image, lang="chi_sim")  # 識別簡體中文
                first_line = "".join(text.splitlines()[0:2]).strip()  # 僅取第一行和第二行文字并去除空格
 
                if first_line:
                    # 將文件名設(shè)為識別到的第一行文字
                    new_filename = f"{sanitize_filename(first_line)}.jpg"
                    new_path = os.path.join(folder_path, new_filename)
                    os.rename(image_path, new_path)
                    print(f"文件已重命名為: {new_filename}")
                else:
                    print(f"未檢測到文字，跳過文件: {filename}")
 
            except Exception as e:
                print(f"處理文件 {filename} 時出錯: {e}")
 
# 使用文件夾路徑調(diào)用函數(shù)
folder_path = "."  # 替換為存放JPG圖片的文件夾路徑
rename_images_with_first_line_text(folder_path)