Python进行图片信息提取并重命名

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):
    """去除文件名中不允许的字符"""
    return re.sub(r'[<>:"/\\|?*]', '', name)
 
def rename_images_with_first_line_text(folder_path):
    # 获取文件夹中所有的jpg图片
    for filename in os.listdir(folder_path):
        if filename.lower().endswith(".jpg"):
            image_path = os.path.join(folder_path, filename)
            try:
                # 打开图片并使用 pytesseract 识别第一行文字
                image = Image.open(image_path)
                text = pytesseract.image_to_string(image, lang="chi_sim")  # 识别简体中文
                first_line = "".join(text.splitlines()[0:2]).strip()  # 仅取第一行和第二行文字并去除空格
 
                if first_line:
                    # 将文件名设为识别到的第一行文字
                    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"文件已重命名为: {new_filename}")
                else:
                    print(f"未检测到文字，跳过文件: {filename}")
 
            except Exception as e:
                print(f"处理文件 {filename} 时出错: {e}")
 
# 使用文件夹路径调用函数
folder_path = "."  # 替换为存放JPG图片的文件夹路径
rename_images_with_first_line_text(folder_path)